From varnish-bugs at varnish-cache.org Wed Dec 1 07:46:44 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Wed, 01 Dec 2010 07:46:44 -0000 Subject: [Varnish] #485: Virtualhost logging for varnishncsa In-Reply-To: <043.fde65ce041c93ef9119ae5492b077e39@varnish-cache.org> References: <043.fde65ce041c93ef9119ae5492b077e39@varnish-cache.org> Message-ID: <052.67700e7b9cd97acce96ba94a69e1e5cb@varnish-cache.org> #485: Virtualhost logging for varnishncsa ---------------------------------------------------------+------------------ Reporter: rhalff | Owner: tfheen Type: enhancement | Status: reopened Priority: normal | Milestone: Component: varnishncsa | Version: trunk Severity: normal | Resolution: Keywords: varnishncsa, virtual hosts, apache, logging | ---------------------------------------------------------+------------------ Changes (by briceburg): * status: closed => reopened * resolution: fixed => Comment: I am unable to get virtualhost support working using the trunk with the -F parameter. Is it possible to see an example which outputs standard ncsa combined log w/ %v option (described above in 1st post)?: {{{ www.test.nl 111.222.333.44 - - [03/Apr/2009:11:41:57 +0200] "GET /favicon.ico HTTP/1.1" 404 209 "-" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; GTB5)" }}} My goal is to use AWStats to parse varnishncsa generated log file -- where varnish is serving multiple websites/hosts. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Wed Dec 1 09:58:20 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Wed, 01 Dec 2010 09:58:20 -0000 Subject: [Varnish] #825: varnish.spec dependency 'initscripts' not valid for SuSE/SLES Message-ID: <040.fc90388613640974d9c37e4c5d2c703f@varnish-cache.org> #825: varnish.spec dependency 'initscripts' not valid for SuSE/SLES --------------------------------+------------------------------------------- Reporter: pom | Type: defect Status: new | Priority: normal Milestone: After Varnish 2.1 | Component: build Version: 2.1.3 | Severity: minor Keywords: rpmbuild SUSE SLES | --------------------------------+------------------------------------------- Tested for varnish-2.1.3 There is no rpm called initscripts for SuSE/SLES. When building the package from tarball on SLES, I have to remove the initscripts dependency manually, otherwise rpmbuild is not possible. Test system: SLES 10.3 -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Wed Dec 1 10:00:14 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Wed, 01 Dec 2010 10:00:14 -0000 Subject: [Varnish] #825: varnish.spec dependency 'initscripts' not valid for SuSE/SLES In-Reply-To: <040.fc90388613640974d9c37e4c5d2c703f@varnish-cache.org> References: <040.fc90388613640974d9c37e4c5d2c703f@varnish-cache.org> Message-ID: <049.873a9be5fa09b758fa55fe5d351f5b71@varnish-cache.org> #825: varnish.spec dependency 'initscripts' not valid for SuSE/SLES --------------------------------+------------------------------------------- Reporter: pom | Type: defect Status: new | Priority: normal Milestone: After Varnish 2.1 | Component: build Version: 2.1.3 | Severity: minor Keywords: rpmbuild SUSE SLES | --------------------------------+------------------------------------------- Comment(by pom): Sorry, rpmbuild is indeed possible, but no install on SLES. ^^ -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Wed Dec 1 13:00:17 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Wed, 01 Dec 2010 13:00:17 -0000 Subject: [Varnish] #485: Virtualhost logging for varnishncsa In-Reply-To: <043.fde65ce041c93ef9119ae5492b077e39@varnish-cache.org> References: <043.fde65ce041c93ef9119ae5492b077e39@varnish-cache.org> Message-ID: <052.addf151e9ee684f09aa24d7a0682ae1d@varnish-cache.org> #485: Virtualhost logging for varnishncsa ---------------------------------------------------------+------------------ Reporter: rhalff | Owner: tfheen Type: enhancement | Status: closed Priority: normal | Milestone: Component: varnishncsa | Version: trunk Severity: normal | Resolution: fixed Keywords: varnishncsa, virtual hosts, apache, logging | ---------------------------------------------------------+------------------ Changes (by tfheen): * status: reopened => closed * resolution: => fixed Old description: > Hi, > > I've changed the varnishncsa sourcecode to support virtualhost logging. > > I know in the TODO of varnishncsa there is a future wish for "Log in > any format one wants", > but I can imagine that would need a total rewrite and takes some time. > > So in the meantime I have a request to add the virtualhost logging as > a commandline option. > > I've added a -v flag enabling virtualhost style logging > In this case the logformat looks like: > > $ varnishncsa -v > www.test.nl 111.222.333.44 - - [03/Apr/2009:11:41:57 +0200] "GET > /favicon.ico HTTP/1.1" 404 209 "-" "Mozilla/4.0 > (compatible; MSIE 7.0; Windows NT 5.1; GTB5)" > > Notice the 'www.test.nl' being logged. > > This is the equivalent of this kind apache logging: > > http://httpd.apache.org/docs/2.0/vhosts/mass.html#simple : > > LogFormat "%V %h %l %u %t \"%r\" %s %b" vcommon > > http://httpd.apache.org/docs/2.0/vhosts/mass.html#simple.rewrite : > > LogFormat "%{Host}i %h %l %u %t \"%r\" %s %b" vcommon > > So this adds the Host part to the normal kind of logging ncsa is doing. > > Taken that this is a very common way to log virtual hosts I would say > the -v option is not just some hack to suit my own needs, I think it > is usefull for others also. > > Without this I am not able to use awstats the way we used it when we > where not using varnish. > > Attached you will find the diff against the current trunk. > > Greetings, > Rob Halff New description: Hi, I've changed the varnishncsa sourcecode to support virtualhost logging. I know in the TODO of varnishncsa there is a future wish for "Log in any format one wants", but I can imagine that would need a total rewrite and takes some time. So in the meantime I have a request to add the virtualhost logging as a commandline option. I've added a -v flag enabling virtualhost style logging In this case the logformat looks like: $ varnishncsa -v www.test.nl 111.222.333.44 - - [03/Apr/2009:11:41:57 +0200] "GET /favicon.ico HTTP/1.1" 404 209 "-" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; GTB5)" Notice the 'www.test.nl' being logged. This is the equivalent of this kind apache logging: http://httpd.apache.org/docs/2.0/vhosts/mass.html#simple : LogFormat "%V %h %l %u %t \"%r\" %s %b" vcommon http://httpd.apache.org/docs/2.0/vhosts/mass.html#simple.rewrite : LogFormat "%{Host}i %h %l %u %t \"%r\" %s %b" vcommon So this adds the Host part to the normal kind of logging ncsa is doing. Taken that this is a very common way to log virtual hosts I would say the -v option is not just some hack to suit my own needs, I think it is usefull for others also. Without this I am not able to use awstats the way we used it when we where not using varnish. Attached you will find the diff against the current trunk. Greetings, Rob Halff -- Comment: You want %{Host}i, not %v. See http://www.varnish- cache.org/docs/trunk/reference/varnishncsa.html for supported switches. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Thu Dec 2 17:56:56 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Thu, 02 Dec 2010 17:56:56 -0000 Subject: [Varnish] #826: Double Content-Length header when using pass Message-ID: <043.c8b89edf1269302f4d7edffee13e03bc@varnish-cache.org> #826: Double Content-Length header when using pass --------------------+------------------------------------------------------- Reporter: kdajka | Type: defect Status: new | Priority: normal Milestone: | Component: regress Version: 2.1.4 | Severity: normal Keywords: | --------------------+------------------------------------------------------- Hi, After updating varnish from 2.1.2 to 2.1.4. I'm having problem with double Content-Length header. Here is my VCL: {{{ sub vcl_recv { if ( req.url == "/" ) { return (pass); } } }}} My backends are apache servers, which handle req.url == "/", they send 301 redirect, based on user-agent. Apache sends proper Content-Length header, and varnish doubles it adding same header with identical size. Some mobile clients can't deal with doubled headers. I managed to overcome problem with this VCL snippet: {{{ sub vcl_fetch { if (beresp.status == 301) { unset beresp.http.Content-Length; } } }}} -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Sun Dec 5 04:57:23 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Sun, 05 Dec 2010 04:57:23 -0000 Subject: [Varnish] #813: Varnish 503's w/ FetchError straight read_error: 11 In-Reply-To: <042.cd8906484102a2787785c6a4c8b2aa70@varnish-cache.org> References: <042.cd8906484102a2787785c6a4c8b2aa70@varnish-cache.org> Message-ID: <051.3f0dd4d59bd593fb11705432b48277f4@varnish-cache.org> #813: Varnish 503's w/ FetchError straight read_error: 11 ----------------------+----------------------------------------------------- Reporter: ntang | Owner: martin Type: defect | Status: new Priority: high | Milestone: Component: varnishd | Version: 2.1.2 Severity: major | Keywords: ----------------------+----------------------------------------------------- Comment(by thiagocsf): We were running 2.1.2, ran across this issue and upgraded to 2.1.4; the issue persists. Our issue is triggered with a POST, not a GET, but seems similar in nature. The double-up on Content-Length seems strange to me (response was encoded with gzip; going directly to the server works and 8041 is the correct compressed size) {{{ (...) 63 Backend c 96 [snip] [snip] 96 TxRequest b POST (...) 96 RxProtocol b HTTP/1.1 96 RxStatus b 200 96 RxResponse b OK 96 RxHeader b ETag: "cda288f5902fc7fce5ae6815e55c9ad2" 96 RxHeader b Last-Modified: Fri, 03 Dec 2010 11:37:31 GMT 96 RxHeader b Content-Length: 49995 96 RxHeader b Status: 200 OK 96 RxHeader b Content-Type: application/xml; charset=utf-8 96 RxHeader b Server: Apache 96 RxHeader b Content-Length: 8041 96 RxHeader b Date: Fri, 03 Dec 2010 11:37:31 GMT 96 RxHeader b Age: 0 96 RxHeader b Via: 1.1 varnish 96 RxHeader b Connection: Keep-Alive 96 RxHeader b Vary: Accept-Encoding 96 RxHeader b Content-Encoding: gzip 63 TTL c 1454655346 RFC 120 1291376251 0 0 0 0 63 VCL_call c fetch 63 VCL_return c pass 63 ObjProtocol c HTTP/1.1 63 ObjStatus c 200 63 ObjResponse c OK 63 ObjHeader c ETag: "cda288f5902fc7fce5ae6815e55c9ad2" 63 ObjHeader c Last-Modified: Fri, 03 Dec 2010 11:37:31 GMT 63 ObjHeader c Status: 200 OK 63 ObjHeader c Content-Type: application/xml; charset=utf-8 63 ObjHeader c Date: Fri, 03 Dec 2010 11:37:31 GMT 63 ObjHeader c Via: 1.1 varnish 63 ObjHeader c Vary: Accept-Encoding 63 ObjHeader c Content-Encoding: gzip 63 ObjHeader c Server: Apache 63 ObjHeader c Cache-Control: private, max-age=0 63 FetchError c straight read_error: 0 }}} -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Sun Dec 5 08:13:15 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Sun, 05 Dec 2010 08:13:15 -0000 Subject: [Varnish] #813: Varnish 503's w/ FetchError straight read_error: 11 In-Reply-To: <042.cd8906484102a2787785c6a4c8b2aa70@varnish-cache.org> References: <042.cd8906484102a2787785c6a4c8b2aa70@varnish-cache.org> Message-ID: <051.246ae5c7681df1308f2f44d2adbb85cc@varnish-cache.org> #813: Varnish 503's w/ FetchError straight read_error: 11 ----------------------+----------------------------------------------------- Reporter: ntang | Owner: martin Type: defect | Status: new Priority: high | Milestone: Component: varnishd | Version: 2.1.2 Severity: major | Keywords: ----------------------+----------------------------------------------------- Comment(by thiagocsf): I can confirm 2.1.5pre1 (http://varnish- cache.org/~tfheen/varnish-2.1.5pre1.tar.gz) solved this issue for us. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 6 04:40:17 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 06 Dec 2010 04:40:17 -0000 Subject: [Varnish] #782: expose sp->esis to vcl (patch attached) In-Reply-To: <045.38ab3dedb5c8bc37860e60bac6c20b23@varnish-cache.org> References: <045.38ab3dedb5c8bc37860e60bac6c20b23@varnish-cache.org> Message-ID: <054.6d1d718c2ed021d0b172a1d499b50ae5@varnish-cache.org> #782: expose sp->esis to vcl (patch attached) -------------------------+-------------------------------------------------- Reporter: askalski | Owner: kristian Type: enhancement | Status: new Priority: normal | Milestone: Component: build | Version: trunk Severity: normal | Keywords: esi -------------------------+-------------------------------------------------- Comment(by blakefrost): The original patch wasn't working for me because the modified files were being over written during the make install. I moved the changes to the source for the generated files. This patch should now apply cleanly and work as advertised. I would like to second askalski request for this patch to be incorporated. Exposing this variable allows for the important distinction between the initial request and esi requests. This is handy if you'd like to modify one or the other but not both. A pattern I follow is to return all dynamically generated content in the first response and esi blocks to fill in with static/shared/cached content. In order to enable cacheing for the esi parts cookies must be cleared prior to the esi request but not before the initial request. This is where req.esis comes in which makes it trivial to do so. I've include the vcl_recv and vcl_feth implementation I use to accomplish the above. {{{ sub vcl_recv { if (req.esis > 0) { unset req.http.cookie; } } sub vcl_fetch { if (beresp.http.Content-Type ~ "text/html") { esi; } } }}} -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 6 13:14:31 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 06 Dec 2010 13:14:31 -0000 Subject: [Varnish] #826: Double Content-Length header when using pass In-Reply-To: <043.c8b89edf1269302f4d7edffee13e03bc@varnish-cache.org> References: <043.c8b89edf1269302f4d7edffee13e03bc@varnish-cache.org> Message-ID: <052.9ad41010efffd006d22a96250c94e87f@varnish-cache.org> #826: Double Content-Length header when using pass ---------------------+------------------------------------------------------ Reporter: kdajka | Owner: martin Type: defect | Status: new Priority: normal | Milestone: Component: regress | Version: 2.1.4 Severity: normal | Keywords: ---------------------+------------------------------------------------------ Changes (by martin): * owner: => martin -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 6 13:20:42 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 06 Dec 2010 13:20:42 -0000 Subject: [Varnish] #824: Saintmode: repeated failure causes varnish to go into 503 mode In-Reply-To: <045.8fa19d1123839c8ac2f07e73e3e9f542@varnish-cache.org> References: <045.8fa19d1123839c8ac2f07e73e3e9f542@varnish-cache.org> Message-ID: <054.3798a96f00e080ae308f4eb697cd2660@varnish-cache.org> #824: Saintmode: repeated failure causes varnish to go into 503 mode ----------------------+----------------------------------------------------- Reporter: grosser2 | Owner: kristian Type: defect | Status: new Priority: normal | Milestone: Component: varnishd | Version: trunk Severity: normal | Keywords: ----------------------+----------------------------------------------------- Changes (by kristian): * owner: => kristian * component: build => varnishd Comment: When you say repeated requests, are those identical requests or requests to different pages giving 500-errors? And how precise is that "5+/-" number? Are you really on trunk, or some other version? It sounds like you are filling the saintmode list - there is a threshold (which you can set with saintmode_threshold, defaults to 10 objects). When you've added more objects to the saintmode list than the threshold specifies, the entire backend will be considered sick - even if healthprobes indicate that everything is OK. It sounds like this is what you are hitting. It's not really recommended to use saint mode for 30 minutes. And you should throw in a restart at the end. Typical lengths for saint mode is 20-30 seconds, not minutes, so you're well outside the norm. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 6 13:21:17 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 06 Dec 2010 13:21:17 -0000 Subject: [Varnish] #822: Repository URLs are wrong on the wiki page UsingSvnSvk In-Reply-To: <047.5ff850794de151226124161e23165988@varnish-cache.org> References: <047.5ff850794de151226124161e23165988@varnish-cache.org> Message-ID: <056.b27c8aabafa704ee07fd4624d2a5b30f@varnish-cache.org> #822: Repository URLs are wrong on the wiki page UsingSvnSvk ---------------------------+------------------------------------------------ Reporter: bonetruck2 | Owner: tfheen Type: documentation | Status: new Priority: low | Milestone: Component: website | Version: trunk Severity: minor | Keywords: ---------------------------+------------------------------------------------ Changes (by tfheen): * owner: => tfheen -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 6 15:15:02 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 06 Dec 2010 15:15:02 -0000 Subject: [Varnish] #824: Saintmode: repeated failure causes varnish to go into 503 mode In-Reply-To: <045.8fa19d1123839c8ac2f07e73e3e9f542@varnish-cache.org> References: <045.8fa19d1123839c8ac2f07e73e3e9f542@varnish-cache.org> Message-ID: <054.609f640985dd76acf1abdabdd5723cac@varnish-cache.org> #824: Saintmode: repeated failure causes varnish to go into 503 mode ----------------------+----------------------------------------------------- Reporter: grosser2 | Owner: kristian Type: defect | Status: new Priority: normal | Milestone: Component: varnishd | Version: trunk Severity: normal | Keywords: ----------------------+----------------------------------------------------- Comment(by grosser2): Repeated request to the same page that gives 500 errors. Were not on trunk but 2.1.4. The restart sounds good. If our servers go down we want varnish to serve the cached page for a long time, so users do not get an error page on cached+high traffic pages like home. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 6 15:23:25 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 06 Dec 2010 15:23:25 -0000 Subject: [Varnish] #824: Saintmode: repeated failure causes varnish to go into 503 mode In-Reply-To: <045.8fa19d1123839c8ac2f07e73e3e9f542@varnish-cache.org> References: <045.8fa19d1123839c8ac2f07e73e3e9f542@varnish-cache.org> Message-ID: <054.75e69acef850815428bdab5251a534a6@varnish-cache.org> #824: Saintmode: repeated failure causes varnish to go into 503 mode ----------------------+----------------------------------------------------- Reporter: grosser2 | Owner: kristian Type: defect | Status: new Priority: normal | Milestone: Component: varnishd | Version: trunk Severity: normal | Keywords: ----------------------+----------------------------------------------------- Comment(by kristian): Can you please supply varnishlog output from when this is happening? Preferably accompanied with the actual request. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Tue Dec 7 01:38:23 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Tue, 07 Dec 2010 01:38:23 -0000 Subject: [Varnish] #827: varnish child died in object_cmp Message-ID: <043.3b98080c99e4f9f35543ee1216c618e7@varnish-cache.org> #827: varnish child died in object_cmp ----------------------+----------------------------------------------------- Reporter: dmyaho | Owner: phk Type: defect | Status: new Priority: high | Milestone: Varnish 2.1 release Component: varnishd | Version: 2.1.3 Severity: major | Keywords: Assert error ----------------------+----------------------------------------------------- Varnish 2.1.3 Linux web-1 2.6.18-194.11.1.el5PAE #1 SMP Tue Jul 27 06:02:35 EDT 2010 i686 i686 i386 GNU/Linux The child process died once every ~5 days. Could someone please take a look? Please let me know if you need further information. Thanks! The messages below is from our /var/log/messages file: Dec 6 18:30:52 web-1 /d/varnish[22365]: Child (7262) died signal=6 Dec 6 18:30:52 web-1 /d/varnish[22365]: Child (7262) Panic message: Assert error in object_cmp(), cache_expire.c line 380:#012 Condition(((aa))->magic == (0x4d301302)) not true.#012thread = (cache- worker)#012ident = Linux,2.6.18-194.11.1.el5PAE,i686,-smalloc,-hcritbit,epoll#012Backtrace:#012 0x806cb5c: pan_ic+cc#012 0x80612a6: object_cmp+56#012 0x769510: /usr/local/lib/libvarnish.so.1(binheap_delete+0x2e0) [0x769510]#012 0x806156e: EXP_NukeOne+13e#012 0x8085b46: STV_alloc+f6#012 0x8063871: FetchBody+5b1#012 0x8059f77: cnt_fetch+737#012 0x805b92a: CNT_Session+44a#012 0x806f5df: wrk_do_cnt_sess+ef#012 0x806e661: wrk_thread_real+341#012sp = 0xaf937004 {#012 fd = 21, id = 21, xid = 893998447,#012 client = 74.7.178.42:64276,#012 step = STP_FETCH,#012 handling = deliver,#012 err_code = 200, err_reason = (null),#012 restarts = 0, esis = 0#012 ws = 0xaf93704c { #012 id = "sess",#012 {s,f,r,e} = {0xaf9377dc,+772,(nil),+16384},#012 },#012 http[req] = {#012 ws = 0xaf93704c[sess]#012 "GET",#012 "/index.php?title=MediaWiki:Monobook.css&usemsgcache=yes&ctype=text%2Fcss&smaxage=18000&action=raw&maxage=18000",#012 "HTTP/1.1",#012 "Accept: */*",#012 "Referer: http://www.mywebsite.org/index.php/page",#012 "Accept-Language: en- US",#012 "User-Agent: Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; MDDR; Zune 4.0; .NET4.0C; .NET4.0E)",#012 "Host: www.mywebsite.org",#012 "Connection: Keep-Alive",#012 "Cookie: __utma=221264669.1516477775.1286286826.1286286826.1286286826.1; __utmz=221264669.1286286826.1.1.utmcsr=google.com|utmccn=(referral)|utmcmd=referral|utmcct=/",#012 "X-Forwarded-For: 74.7.178.42",#012 "Accept-Encoding: gzip",#012 },#012 worker = 0xb7f8b194 {#012 ws = 0xb7f8b2ac { #012 id = "wrk",#012 {s,f,r,e} = {0xb7f85150,+1472,(nil),+16384},#012 },#012 http[bereq] = {#012 ws = 0xb7f8b2ac[wrk]#012 Dec 6 18:30:52 web-1 /d/varnish[22365]: child (17885) Started -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Wed Dec 8 22:50:33 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Wed, 08 Dec 2010 22:50:33 -0000 Subject: [Varnish] #828: varnishstat sms_nbytes is huge Message-ID: <046.4eae888ca7c0382d43ece73f0d4cb54a@varnish-cache.org> #828: varnishstat sms_nbytes is huge -------------------------+-------------------------------------------------- Reporter: delimiter | Owner: phk Type: defect | Status: new Priority: normal | Milestone: Component: varnishstat | Version: 2.1.0 Severity: normal | Keywords: varnishstat sms_nbytes -------------------------+-------------------------------------------------- $ varnishstat -1 | grep sms_ sms_nreq 42474 0.02 SMS allocator requests sms_nobj 0 . SMS outstanding allocations sms_nbytes 18446744073709551128 . SMS outstanding bytes sms_balloc 20610360 . SMS bytes allocated sms_bfree 20610360 . SMS bytes freed (END) 18446744073709551128 = 16 petabytes. How can this be correct? -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Thu Dec 9 08:43:31 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Thu, 09 Dec 2010 08:43:31 -0000 Subject: [Varnish] #829: Varnishstat does not return fields in specified order Message-ID: <041.56b7b056ffab1a37386ebe8f2d76baa3@varnish-cache.org> #829: Varnishstat does not return fields in specified order -------------------------+-------------------------------------------------- Reporter: wido | Owner: phk Type: enhancement | Status: new Priority: normal | Milestone: Component: varnishstat | Version: 2.1.4 Severity: normal | Keywords: -------------------------+-------------------------------------------------- When specifying a list of fields with varnishstat, the fields are returned in alphabetical order, not in the order you specified them. {{{ root at cache01:~# varnishstat -1 -f uptime,n_object,cache_miss cache_miss 669 0.00 Cache misses n_object 0 . N struct object uptime 652776 1.00 Client uptime root at cache01:~# }}} Is there any specific reason for this? Seems to me that the fields should be returned in the order I specified them in. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Thu Dec 9 08:54:59 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Thu, 09 Dec 2010 08:54:59 -0000 Subject: [Varnish] #830: Init script doesn't allow you to set DAEMON_OPTS for varnishlog Message-ID: <041.0ef4db3d1a46a6fc440b20be57e03e2b@varnish-cache.org> #830: Init script doesn't allow you to set DAEMON_OPTS for varnishlog -------------------------+-------------------------------------------------- Reporter: wido | Owner: phk Type: enhancement | Status: new Priority: normal | Milestone: Component: varnishlog | Version: 2.1.4 Severity: normal | Keywords: init,ubuntu,debian -------------------------+-------------------------------------------------- The current init script of varnishlog doesn't allow you to specify other DAEMON_OPTS, they are hardcoded into the script. {{{ ... ... test -x $DAEMON || exit 0 DAEMON_OPTS="-a -w ${LOGFILE} -D -P $PIDFILE" start_varnishlog() { ... ... }}} It would be nice if you could set those in /etc/default/varnishlog (Ubuntu / Debian). This way you could specify the output file and what you would like to log to the file. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Thu Dec 9 08:57:18 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Thu, 09 Dec 2010 08:57:18 -0000 Subject: [Varnish] #831: Init script doesn't allow you to set DAEMON_OPTS for varnishncsa Message-ID: <041.7843c50b5ad30c900a44261949fc2998@varnish-cache.org> #831: Init script doesn't allow you to set DAEMON_OPTS for varnishncsa -------------------+-------------------------------------------------------- Reporter: wido | Type: enhancement Status: new | Priority: normal Milestone: | Component: varnishncsa Version: 2.1.4 | Severity: normal Keywords: | -------------------+-------------------------------------------------------- It's almost the same as #830, but this one is for varnishncsa on Ubuntu/Debian. {{{ ... ... test -x $DAEMON || exit 0 DAEMON_OPTS="-a -c -w ${LOGFILE} -D -P $PIDFILE" start_varnishncsa() { ... ... }}} Some people (like me) would like to pipe the output of varnishncsa to for example 'logger' (So the contents go to syslog) or to another file with some other options. (Keeping in mind that in trunk you can specify the format). -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Sat Dec 11 18:25:54 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Sat, 11 Dec 2010 18:25:54 -0000 Subject: [Varnish] #832: Error resolving IPv6 literal w/o port Message-ID: <039.e921458af12652c361ffca82e19b5360@varnish-cache.org> #832: Error resolving IPv6 literal w/o port ----------------------+----------------------------------------------------- Reporter: bz | Owner: phk Type: defect | Status: new Priority: low | Milestone: Component: varnishd | Version: trunk Severity: normal | Keywords: IPv6 getaddrinfo ----------------------+----------------------------------------------------- There is a problem in Emit_Sockaddr() handling IPv6 literals without a port (see tests below). Currently we only use the host extracted in VSS_parse() for getaddrinfo() if we also got a port, which is fine for IPv4 literals but not for IPv6 as those still have the surrounding '[' ']' in that case. As a solution prefer whatever host or port parts VSS_parse() returns over the initial string. Tests without patch: ---------------- # sh -c 'varnishd -V; echo; for addr in 192.0.2.1 192.0.2.1:80 "[2001:db8::1]" "[2001:db8::1]:80"; do echo "==> Testing address ${addr}"; varnishd -b ${addr} -C -n /tmp > /dev/null; echo; echo; done' varnishd (varnish-2.1.4 SVN ) Copyright (c) 2006-2009 Linpro AS / Verdens Gang AS ==> Testing address 192.0.2.1 ==> Testing address 192.0.2.1:80 ==> Testing address [2001:db8::1] Message from VCC-compiler: Backend host '"[2001:db8::1]"' could not be resolved to an IP address: hostname nor servname provided, or not known (Sorry if that error message is gibberish.) (input Line 2 Pos 13) .host = "[2001:db8::1]"; ------------###############- In backend specification starting at: (input Line 1 Pos 1) backend default { #######---------- Running VCC-compiler failed, exit 1 ==> Testing address [2001:db8::1]:80 Applying the attached patch and re-running: ---------------------------------- # sh -c 'varnishd -V; echo; for addr in 192.0.2.1 192.0.2.1:80 "[2001:db8::1]" "[2001:db8::1]:80"; do echo "==> Testing address ${addr}"; varnishd -b ${addr} -C -n /tmp > /dev/null; echo; echo; done' varnishd (varnish-2.1.4 SVN ) Copyright (c) 2006-2009 Linpro AS / Verdens Gang AS ==> Testing address 192.0.2.1 ==> Testing address 192.0.2.1:80 ==> Testing address [2001:db8::1] ==> Testing address [2001:db8::1]:80 -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Sat Dec 11 18:32:10 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Sat, 11 Dec 2010 18:32:10 -0000 Subject: [Varnish] #832: Error resolving IPv6 literal w/o port In-Reply-To: <039.e921458af12652c361ffca82e19b5360@varnish-cache.org> References: <039.e921458af12652c361ffca82e19b5360@varnish-cache.org> Message-ID: <048.66179be7e2bef88fdc5f3dbac111743b@varnish-cache.org> #832: Error resolving IPv6 literal w/o port ----------------------+----------------------------------------------------- Reporter: bz | Owner: phk Type: defect | Status: new Priority: low | Milestone: Component: varnishd | Version: trunk Severity: normal | Keywords: IPv6 getaddrinfo ----------------------+----------------------------------------------------- Comment(by bz): The description in the patch should say "IPv6 literals". -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 13 08:04:41 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 13 Dec 2010 08:04:41 -0000 Subject: [Varnish] #774: Panic message: Assert error in STV_alloc() In-Reply-To: <046.ecc2f4bc4f7ae0ce88547b074a00b027@varnish-cache.org> References: <046.ecc2f4bc4f7ae0ce88547b074a00b027@varnish-cache.org> Message-ID: <055.10ff975e7f2ff89c72f6d7231b49404d@varnish-cache.org> #774: Panic message: Assert error in STV_alloc() -----------------------+---------------------------------------------------- Reporter: wittwerch | Owner: kristian Type: defect | Status: assigned Priority: low | Milestone: Component: varnishd | Version: 2.0 Severity: normal | Keywords: -----------------------+---------------------------------------------------- Changes (by kristian): * status: new => assigned Old description: > We encountered a crash on our varnish server. > > Sep 7 14:01:50 myserver varnishd[26296]: Child (26297) Panic message: > Assert error in STV_alloc(), stevedore.c line 71: Condition((st) != > NULL) not true. thread = (cache-worker) Backtrace: 0x41ba68: > /usr/sbin/varnishd [0x41ba68] 0x43121d: > /usr/sbin/varnishd(STV_alloc+0x9d) [0x43121d] 0x4154e2: > /usr/sbin/varnishd(Fetch+0x6b2) [0x4154e2] 0x410154: /usr/sbin/varnishd > [0x410154] 0x411379: /usr/sbin/varnishd(CNT_Session+0x389) [0x411379] > 0x41d9e2: /usr/sbin/varnishd [0x41d9e2] 0x41cf4f: /usr/sbin/varnishd > [0x41cf4f] 0x372f806617: /lib64/libpthread.so.0 [0x372f806617] > 0x372f0d3c2d: /lib64/libc.so.6(clone+0x6d) [0x372f0d3c2d] sp = > 0x2aaaedfa2008 { fd = 37, id = 37, xid = 1793847417, client = > 84.253.6.190:44291, step = STP_FETCH, handling = discard, restarts > = 0, esis = 0 ws = 0x2aaaedfa2080 { id = "sess", {s,f,r,e} = > {0x2aaaedfa2820,+391,(nil),+16384}, }, http[req] = { ws = > 0x2aaaedfa2080[sess] "GET", "/mammut-extern/TokoPST/DSC.zip", > "HTTP/1.1", > > There was no port open on tcp/80 anymore, so the automatically restart > did not work. New description: We encountered a crash on our varnish server. Sep 7 14:01:50 myserver varnishd[26296]: Child (26297) Panic message: Assert error in STV_alloc(), stevedore.c line 71: Condition((st) != NULL) not true. thread = (cache-worker) Backtrace: 0x41ba68: /usr/sbin/varnishd [0x41ba68] 0x43121d: /usr/sbin/varnishd(STV_alloc+0x9d) [0x43121d] 0x4154e2: /usr/sbin/varnishd(Fetch+0x6b2) [0x4154e2] 0x410154: /usr/sbin/varnishd [0x410154] 0x411379: /usr/sbin/varnishd(CNT_Session+0x389) [0x411379] 0x41d9e2: /usr/sbin/varnishd [0x41d9e2] 0x41cf4f: /usr/sbin/varnishd [0x41cf4f] 0x372f806617: /lib64/libpthread.so.0 [0x372f806617] 0x372f0d3c2d: /lib64/libc.so.6(clone+0x6d) [0x372f0d3c2d] sp = 0x2aaaedfa2008 { fd = 37, id = 37, xid = 1793847417, client = 84.253.6.190:44291, step = STP_FETCH, handling = discard, restarts = 0, esis = 0 ws = 0x2aaaedfa2080 { id = "sess", {s,f,r,e} = {0x2aaaedfa2820,+391,(nil),+16384}, }, http[req] = { ws = 0x2aaaedfa2080[sess] "GET", "/mammut-extern/TokoPST/DSC.zip", "HTTP/1.1", There was no port open on tcp/80 anymore, so the automatically restart did not work. -- Comment: David: What parameters are you using to start up? Your log confirms running out of space (ie: LRU). We've seen this in the past on servers with multiple -s arguments where one is tiny. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 13 08:11:45 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 13 Dec 2010 08:11:45 -0000 Subject: [Varnish] #794: varnishsizes : Say what sizes it show in desc / manpage In-Reply-To: <044.7f4426446242b5edf8778fed4e31dbf3@varnish-cache.org> References: <044.7f4426446242b5edf8778fed4e31dbf3@varnish-cache.org> Message-ID: <053.55c2d1590154ce66f346261631ffd334@varnish-cache.org> #794: varnishsizes : Say what sizes it show in desc / manpage ---------------------------+------------------------------------------------ Reporter: mandark | Owner: kristian Type: documentation | Status: closed Priority: low | Milestone: Varnish 2.1 release Component: documentation | Version: trunk Severity: trivial | Resolution: fixed Keywords: varnishsizes | ---------------------------+------------------------------------------------ Changes (by kristian): * status: new => closed * resolution: => fixed Comment: (In [5643]) Varnishsizes.rst: Mention that scale is in bytes Fixes #794 -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 13 08:14:32 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 13 Dec 2010 08:14:32 -0000 Subject: [Varnish] #824: Saintmode: repeated failure causes varnish to go into 503 mode In-Reply-To: <045.8fa19d1123839c8ac2f07e73e3e9f542@varnish-cache.org> References: <045.8fa19d1123839c8ac2f07e73e3e9f542@varnish-cache.org> Message-ID: <054.b890332ed2cead6d11e4cf7f99029a7f@varnish-cache.org> #824: Saintmode: repeated failure causes varnish to go into 503 mode ----------------------+----------------------------------------------------- Reporter: grosser2 | Owner: kristian Type: defect | Status: new Priority: low | Milestone: Component: varnishd | Version: trunk Severity: normal | Keywords: ----------------------+----------------------------------------------------- Changes (by kristian): * priority: normal => low Comment: Any further update on this issue from your end? Not much I can do without varnishlog-output and the request-data... -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 13 08:26:22 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 13 Dec 2010 08:26:22 -0000 Subject: [Varnish] #833: Panic message: Assert error in VRT_int_string() Message-ID: <044.59103fb3a1a0b5a0e4c1e9aa1e0ede0c@varnish-cache.org> #833: Panic message: Assert error in VRT_int_string() ----------------------+----------------------------------------------------- Reporter: mandark | Owner: phk Type: defect | Status: new Priority: normal | Milestone: Component: varnishd | Version: 2.1.2 Severity: critical | Keywords: panic, assert error, VRT_int_string ----------------------+----------------------------------------------------- Hi ! Just got a varnish Panic, with varnish version varnish-2.1.2 SVN b8c9904 Can't find any open / closed ticket about this so I post here my syslog dump, hope that help or it's already fixed ! Dec 13 08:59:33 cache2 varnishd[19431]: Child (19434) died signal=6 Dec 13 08:59:33 cache2 varnishd[19431]: Child (19434) Panic message: Assert error in VRT_int_string(), cache_vrt.c line 829: #012 Condition((p = WS_Alloc(sp->http->ws, size)) != 0) not true. #012errno = 104 (Connection reset by peer) #012thread = (cache-worker) #012ident = Linux,2.6.32-5-amd64,x86_64,-sfile,-hcritbit,epoll #012Assert error in VRT_int_string(), cache_vrt.c line 829: #012 Condition((p = WS_Alloc(sp->http->ws, size)) != 0) not true. #012errno = 104 (Connection reset by peer) #012thread = (cache-worker) #012ident = Linux,2.6.32-5-amd64,x86_64,-sfile,-hcritbit,epoll #012Backtrace: #012 Backtrace: #012 0x4244b8: /usr/sbin/varnishd() [0x4244b8] #012 0x42bd45: /usr/sbin/varnishd(VRT_int_string+0xc5) [0x42bd45] #012 0x7fd3bf0f38a4: ./vcl.4aqDu9P8.so(+0x68a4) [0x7fd3bf0f38a4] #012 0x428e46: /usr/sbin/varnishd(VCL_error_method+0x46) [0x428e46] #012 0x414693: /usr/sbin/varnishd() [0x414693] #012 0x414fc5: /usr/sbin/varnishd(CNT_Session+0x235) [0x414fc5] #012 0x4268f8: /usr/sbin/varnishd() [0x4268f8] #012 0x425bd3: /usr/sbin/varnishd() [0x425bd3] #012 0x7feceb11c8ba: /lib/libpthread.so.0(+0x68ba) [0x7feceb11c8ba] #012 0x7fecea9ea01d: /lib/libc.so.6(clone+0x6d) [0x7fecea9ea01d] #012sp = 0x7fcfdd1df008 { #012 fd = 34, id = 34, xid = 2640976544, #012 client = x.x.x.x:48645, #012 step = STP_ERROR, #012 handling = deliver, #012 err_code = 503, err_reason = (null), #012 restarts = 4, esis = 0 #012 ws = 0x7fcfdd1df078 { overflow #012 id = "sess", #012 {s,f,r,e} = {0x7fcfdd1dfc90,+65536,(nil),+65536}, #012 }, #012 http[req] = { #012 ws = 0x7fcfdd1df078[sess] #012 "GET", #012 "/masturbation-pour-une-fille-forum11-32864.html", #012 "HTTP/1.0", #012 "Host: www.actuados.com", #012 "User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 1.1.4322; InfoPath.1; ZangoToolbar 4.8.2; .NET CLR 2.0.50727)", #012 "X-Forwarded-For: x.x.x.x", #012 "cookie: .ASPXANONYMOUS=2xNFVi3RywEkAAAAMWZjMDFmZTctYdExNS00YmUwLTlhYmItNDk2MGMxYjc1NzI50; 0da338be153a2a25ec682989327b6b8e=a9192a6caafc Dec 13 08:59:33 cache2 varnishd[19431]: Child cleanup complete Dec 13 08:59:33 cache2 varnishd[19431]: child (10347) Started Dec 13 08:59:33 cache2 varnishd[19431]: Pushing vcls failed: dlopen(./vcl.1P9zoqAU.so): ./vcl.1P9zoqAU.so: cannot open shared object file: No such file or directory Dec 13 08:59:33 cache2 varnishd[19431]: Stopping Child Dec 13 08:59:33 cache2 varnishd[19431]: Child (10347) said Dec 13 08:59:33 cache2 varnishd[19431]: Child (10347) said Child starts Dec 13 08:59:33 cache2 varnishd[19431]: Child (10347) said managed to mmap 107374182400 bytes of 107374182400 Dec 13 08:59:33 cache2 varnishd[19431]: Child (10347) said Child dies Dec 13 08:59:34 cache2 varnishd[19431]: Child (10347) died Dec 13 08:59:34 cache2 varnishd[19431]: Child cleanup complete Kind regards, Julien -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 13 08:30:40 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 13 Dec 2010 08:30:40 -0000 Subject: [Varnish] #833: Panic message: Assert error in VRT_int_string() In-Reply-To: <044.59103fb3a1a0b5a0e4c1e9aa1e0ede0c@varnish-cache.org> References: <044.59103fb3a1a0b5a0e4c1e9aa1e0ede0c@varnish-cache.org> Message-ID: <053.2f45190dcd30f1c4dd402bf74a80849d@varnish-cache.org> #833: Panic message: Assert error in VRT_int_string() ----------------------+----------------------------------------------------- Reporter: mandark | Owner: phk Type: defect | Status: new Priority: normal | Milestone: Component: varnishd | Version: 2.1.2 Severity: critical | Keywords: panic, assert error, VRT_int_string ----------------------+----------------------------------------------------- Comment(by mandark): Oops, sorry for the presentation ... I missed the Preview button ... Trying again : {{{ Dec 13 08:59:33 cache2 varnishd[19431]: Child (19434) died signal=6 Dec 13 08:59:33 cache2 varnishd[19431]: Child (19434) Panic message: Assert error in VRT_int_string(), cache_vrt.c line 829: #012 Condition((p = WS_Alloc(sp->http->ws, size)) != 0) not true. #012errno = 104 (Connection reset by peer) #012thread = (cache-worker) #012ident = Linux,2.6.32-5-amd64,x86_64,-sfile,-hcritbit,epoll #012Assert error in VRT_int_string(), cache_vrt.c line 829: #012 Condition((p = WS_Alloc(sp->http->ws, size)) != 0) not true. #012errno = 104 (Connection reset by peer) #012thread = (cache-worker) #012ident = Linux,2.6.32-5-amd64,x86_64,-sfile,-hcritbit,epoll #012Backtrace: #012 Backtrace: #012 0x4244b8: /usr/sbin/varnishd() [0x4244b8] #012 0x42bd45: /usr/sbin/varnishd(VRT_int_string+0xc5) [0x42bd45] #012 0x7fd3bf0f38a4: ./vcl.4aqDu9P8.so(+0x68a4) [0x7fd3bf0f38a4] #012 0x428e46: /usr/sbin/varnishd(VCL_error_method+0x46) [0x428e46] #012 0x414693: /usr/sbin/varnishd() [0x414693] #012 0x414fc5: /usr/sbin/varnishd(CNT_Session+0x235) [0x414fc5] #012 0x4268f8: /usr/sbin/varnishd() [0x4268f8] #012 0x425bd3: /usr/sbin/varnishd() [0x425bd3] #012 0x7feceb11c8ba: /lib/libpthread.so.0(+0x68ba) [0x7feceb11c8ba] #012 0x7fecea9ea01d: /lib/libc.so.6(clone+0x6d) [0x7fecea9ea01d] #012sp = 0x7fcfdd1df008 { #012 fd = 34, id = 34, xid = 2640976544, #012 client = 201.40.124.36:48645, #012 step = STP_ERROR, #012 handling = deliver, #012 err_code = 503, err_reason = (null), #012 restarts = 4, esis = 0 #012 ws = 0x7fcfdd1df078 { overflow #012 id = "sess", #012 {s,f,r,e} = {0x7fcfdd1dfc90,+65536,(nil),+65536}, #012 }, #012 http[req] = { #012 ws = 0x7fcfdd1df078[sess] #012 "GET", #012 "/masturbation-pour-une-fille-forum11-32864.html", #012 "HTTP/1.0", #012 "Host: www.actuados.com", #012 "User-Agent: Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 1.1.4322; InfoPath.1; ZangoToolbar 4.8.2; .NET CLR 2.0.50727)", #012 "X-Forwarded-For: 218.70.154.36", #012 "cookie: .ASPXANONYMOUS=2xNFVi3RywElAAAAMWZjMDFmZTdtYzExNS00YmUwLTlhYmItNDk2MGMwYjc1NzI50; 0da638be153a2a15ec682989427b6b8f=a5193a1caafc Dec 13 08:59:33 cache2 varnishd[19431]: Child cleanup complete Dec 13 08:59:33 cache2 varnishd[19431]: child (10347) Started Dec 13 08:59:33 cache2 varnishd[19431]: Pushing vcls failed: dlopen(./vcl.1P9zoqAU.so): ./vcl.1P9zoqAU.so: cannot open shared object file: No such file or directory Dec 13 08:59:33 cache2 varnishd[19431]: Stopping Child Dec 13 08:59:33 cache2 varnishd[19431]: Child (10347) said Dec 13 08:59:33 cache2 varnishd[19431]: Child (10347) said Child starts Dec 13 08:59:33 cache2 varnishd[19431]: Child (10347) said managed to mmap 107374182400 bytes of 107374182400 Dec 13 08:59:33 cache2 varnishd[19431]: Child (10347) said Child dies Dec 13 08:59:34 cache2 varnishd[19431]: Child (10347) died Dec 13 08:59:34 cache2 varnishd[19431]: Child cleanup complete }}} -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 13 08:32:20 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 13 Dec 2010 08:32:20 -0000 Subject: [Varnish] #833: Panic message: Assert error in VRT_int_string() In-Reply-To: <044.59103fb3a1a0b5a0e4c1e9aa1e0ede0c@varnish-cache.org> References: <044.59103fb3a1a0b5a0e4c1e9aa1e0ede0c@varnish-cache.org> Message-ID: <053.b10d9b1b905974f637bcb218ff6f813c@varnish-cache.org> #833: Panic message: Assert error in VRT_int_string() ----------------------+----------------------------------------------------- Reporter: mandark | Owner: kristian Type: defect | Status: assigned Priority: normal | Milestone: Component: varnishd | Version: 2.1.2 Severity: normal | Keywords: panic, assert error, VRT_int_string ----------------------+----------------------------------------------------- Changes (by kristian): * owner: phk => kristian * status: new => assigned * severity: critical => normal Comment: You are running out of session workspace. If you increase sess_workspace, this issue will go away. Before I close the ticket, I'd like to see the VCL to determine if this is a natural workspace exhaustion or triggered by something more sinister. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 13 10:17:31 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 13 Dec 2010 10:17:31 -0000 Subject: [Varnish] #824: Saintmode: repeated failure causes varnish to go into 503 mode In-Reply-To: <045.8fa19d1123839c8ac2f07e73e3e9f542@varnish-cache.org> References: <045.8fa19d1123839c8ac2f07e73e3e9f542@varnish-cache.org> Message-ID: <054.bacaf2077b90e69f4287b60fef125ed5@varnish-cache.org> #824: Saintmode: repeated failure causes varnish to go into 503 mode ----------------------+----------------------------------------------------- Reporter: grosser2 | Owner: kristian Type: defect | Status: new Priority: low | Milestone: Component: varnishd | Version: trunk Severity: normal | Keywords: ----------------------+----------------------------------------------------- Comment(by grosser2): im not able to reproduce the error in our staging environment, and im not willing to put the production system at risk, ill report back if it happens again, or if we decide to try saintmode again -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 13 10:21:52 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 13 Dec 2010 10:21:52 -0000 Subject: [Varnish] #824: Saintmode: repeated failure causes varnish to go into 503 mode In-Reply-To: <045.8fa19d1123839c8ac2f07e73e3e9f542@varnish-cache.org> References: <045.8fa19d1123839c8ac2f07e73e3e9f542@varnish-cache.org> Message-ID: <054.debf662c2c88990a441c7d66e1a0613b@varnish-cache.org> #824: Saintmode: repeated failure causes varnish to go into 503 mode ----------------------+----------------------------------------------------- Reporter: grosser2 | Owner: kristian Type: defect | Status: closed Priority: low | Milestone: Component: varnishd | Version: trunk Severity: normal | Resolution: worksforme Keywords: | ----------------------+----------------------------------------------------- Changes (by kristian): * status: new => closed * resolution: => worksforme Comment: Ok, I'll close the ticket as I can't reproduce and it seems like that it's just a misunderstanding of what saintmode does. Feel free to re-open if the problem reappears. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 13 12:28:08 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 13 Dec 2010 12:28:08 -0000 Subject: [Varnish] #813: Varnish 503's w/ FetchError straight read_error: 11 In-Reply-To: <042.cd8906484102a2787785c6a4c8b2aa70@varnish-cache.org> References: <042.cd8906484102a2787785c6a4c8b2aa70@varnish-cache.org> Message-ID: <051.4a82a5e4582535bedc3fbb7a45d7a998@varnish-cache.org> #813: Varnish 503's w/ FetchError straight read_error: 11 ----------------------+----------------------------------------------------- Reporter: ntang | Owner: martin Type: defect | Status: closed Priority: high | Milestone: Component: varnishd | Version: 2.1.2 Severity: major | Resolution: fixed Keywords: | ----------------------+----------------------------------------------------- Changes (by martin): * status: new => closed * resolution: => fixed Comment: I understand that this issue is fixed for you in 2.1.5pre1. Closing ticket. Regards, Martin Blix Grydeland -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 13 13:09:45 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 13 Dec 2010 13:09:45 -0000 Subject: [Varnish] #828: varnishstat sms_nbytes is huge In-Reply-To: <046.4eae888ca7c0382d43ece73f0d4cb54a@varnish-cache.org> References: <046.4eae888ca7c0382d43ece73f0d4cb54a@varnish-cache.org> Message-ID: <055.f6904d9810df44f0a7c7d313ac4f7add@varnish-cache.org> #828: varnishstat sms_nbytes is huge ------------------------------------+--------------------------------------- Reporter: delimiter | Owner: phk Type: defect | Status: closed Priority: normal | Milestone: Component: varnishstat | Version: 2.1.0 Severity: normal | Resolution: fixed Keywords: varnishstat sms_nbytes | ------------------------------------+--------------------------------------- Changes (by phk): * status: new => closed * resolution: => fixed Comment: This is an artifact of an unlocked counter, don't worry about it. I belive it is fixed in newer versions. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 13 13:11:31 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 13 Dec 2010 13:11:31 -0000 Subject: [Varnish] #829: Varnishstat does not return fields in specified order In-Reply-To: <041.56b7b056ffab1a37386ebe8f2d76baa3@varnish-cache.org> References: <041.56b7b056ffab1a37386ebe8f2d76baa3@varnish-cache.org> Message-ID: <050.55a62485c9c596e03f7bf8f8ffc4da2e@varnish-cache.org> #829: Varnishstat does not return fields in specified order -------------------------+-------------------------------------------------- Reporter: wido | Owner: martin Type: enhancement | Status: new Priority: normal | Milestone: Component: varnishstat | Version: 2.1.4 Severity: normal | Keywords: -------------------------+-------------------------------------------------- Changes (by martin): * owner: phk => martin -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 13 13:12:24 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 13 Dec 2010 13:12:24 -0000 Subject: [Varnish] #830: Init script doesn't allow you to set DAEMON_OPTS for varnishlog In-Reply-To: <041.0ef4db3d1a46a6fc440b20be57e03e2b@varnish-cache.org> References: <041.0ef4db3d1a46a6fc440b20be57e03e2b@varnish-cache.org> Message-ID: <050.5420396a0b06f2edab5c1ba23d3814a0@varnish-cache.org> #830: Init script doesn't allow you to set DAEMON_OPTS for varnishlog -------------------------+-------------------------------------------------- Reporter: wido | Owner: martin Type: enhancement | Status: new Priority: normal | Milestone: Component: varnishlog | Version: 2.1.4 Severity: normal | Keywords: init,ubuntu,debian -------------------------+-------------------------------------------------- Changes (by martin): * owner: phk => martin -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 13 13:12:29 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 13 Dec 2010 13:12:29 -0000 Subject: [Varnish] #831: Init script doesn't allow you to set DAEMON_OPTS for varnishncsa In-Reply-To: <041.7843c50b5ad30c900a44261949fc2998@varnish-cache.org> References: <041.7843c50b5ad30c900a44261949fc2998@varnish-cache.org> Message-ID: <050.7402b796684213d055fcb076c3501a25@varnish-cache.org> #831: Init script doesn't allow you to set DAEMON_OPTS for varnishncsa -------------------------+-------------------------------------------------- Reporter: wido | Owner: martin Type: enhancement | Status: new Priority: normal | Milestone: Component: varnishncsa | Version: 2.1.4 Severity: normal | Keywords: -------------------------+-------------------------------------------------- Changes (by martin): * owner: => martin -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 13 13:15:24 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 13 Dec 2010 13:15:24 -0000 Subject: [Varnish] #827: varnish child died in object_cmp In-Reply-To: <043.3b98080c99e4f9f35543ee1216c618e7@varnish-cache.org> References: <043.3b98080c99e4f9f35543ee1216c618e7@varnish-cache.org> Message-ID: <052.e4f48928f75a3c93fd6994a746d98142@varnish-cache.org> #827: varnish child died in object_cmp ----------------------+----------------------------------------------------- Reporter: dmyaho | Owner: phk Type: defect | Status: new Priority: high | Milestone: Varnish 2.1 release Component: varnishd | Version: 2.1.3 Severity: major | Keywords: Assert error ----------------------+----------------------------------------------------- Description changed by phk: Old description: > Varnish 2.1.3 > Linux web-1 2.6.18-194.11.1.el5PAE #1 SMP Tue Jul 27 06:02:35 EDT 2010 > i686 i686 i386 GNU/Linux > > The child process died once every ~5 days. Could someone please take a > look? Please let me know if you need further information. Thanks! > > The messages below is from our /var/log/messages file: > > Dec 6 18:30:52 web-1 /d/varnish[22365]: Child (7262) died signal=6 > Dec 6 18:30:52 web-1 /d/varnish[22365]: Child (7262) Panic message: > Assert error in object_cmp(), cache_expire.c line 380:#012 > Condition(((aa))->magic == (0x4d301302)) not true.#012thread = (cache- > worker)#012ident = > Linux,2.6.18-194.11.1.el5PAE,i686,-smalloc,-hcritbit,epoll#012Backtrace:#012 > 0x806cb5c: pan_ic+cc#012 0x80612a6: object_cmp+56#012 0x769510: > /usr/local/lib/libvarnish.so.1(binheap_delete+0x2e0) [0x769510]#012 > 0x806156e: EXP_NukeOne+13e#012 0x8085b46: STV_alloc+f6#012 0x8063871: > FetchBody+5b1#012 0x8059f77: cnt_fetch+737#012 0x805b92a: > CNT_Session+44a#012 0x806f5df: wrk_do_cnt_sess+ef#012 0x806e661: > wrk_thread_real+341#012sp = 0xaf937004 {#012 fd = 21, id = 21, xid = > 893998447,#012 client = 74.7.178.42:64276,#012 step = STP_FETCH,#012 > handling = deliver,#012 err_code = 200, err_reason = (null),#012 > restarts = 0, esis = 0#012 ws = 0xaf93704c { #012 id = "sess",#012 > {s,f,r,e} = {0xaf9377dc,+772,(nil),+16384},#012 },#012 http[req] = > {#012 ws = 0xaf93704c[sess]#012 "GET",#012 > "/index.php?title=MediaWiki:Monobook.css&usemsgcache=yes&ctype=text%2Fcss&smaxage=18000&action=raw&maxage=18000",#012 > "HTTP/1.1",#012 "Accept: */*",#012 "Referer: > http://www.mywebsite.org/index.php/page",#012 "Accept-Language: en- > US",#012 "User-Agent: Mozilla/4.0 (compatible; MSIE 8.0; Windows NT > 6.1; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR > 3.0.30729; Media Center PC 6.0; MDDR; Zune 4.0; .NET4.0C; .NET4.0E)",#012 > "Host: www.mywebsite.org",#012 "Connection: Keep-Alive",#012 > "Cookie: __utma=221264669.1516477775.1286286826.1286286826.1286286826.1; > __utmz=221264669.1286286826.1.1.utmcsr=google.com|utmccn=(referral)|utmcmd=referral|utmcct=/",#012 > "X-Forwarded-For: 74.7.178.42",#012 "Accept-Encoding: gzip",#012 > },#012 worker = 0xb7f8b194 {#012 ws = 0xb7f8b2ac { #012 id = > "wrk",#012 {s,f,r,e} = {0xb7f85150,+1472,(nil),+16384},#012 > },#012 http[bereq] = {#012 ws = 0xb7f8b2ac[wrk]#012 > Dec 6 18:30:52 web-1 /d/varnish[22365]: child (17885) Started New description: Varnish 2.1.3 Linux web-1 2.6.18-194.11.1.el5PAE #1 SMP Tue Jul 27 06:02:35 EDT 2010 i686 i686 i386 GNU/Linux The child process died once every ~5 days. Could someone please take a look? Please let me know if you need further information. Thanks! The messages below is from our /var/log/messages file: {{{ Dec 6 18:30:52 web-1 /d/varnish[22365]: Child (7262) died signal=6 Dec 6 18:30:52 web-1 /d/varnish[22365]: Child (7262) Panic message: Assert error in object_cmp(), cache_expire.c line 380: Condition(((aa))->magic == (0x4d301302)) not true. thread = (cache-worker) ident = Linux,2.6.18-194.11.1.el5PAE,i686,-smalloc,-hcritbit,epoll#012Backtrace: 0x806cb5c: pan_ic+cc 0x80612a6: object_cmp+56 0x769510: /usr/local/lib/libvarnish.so.1(binheap_delete+0x2e0) [0x769510] 0x806156e: EXP_NukeOne+13e 0x8085b46: STV_alloc+f6 0x8063871: FetchBody+5b1 0x8059f77: cnt_fetch+737 0x805b92a: CNT_Session+44a 0x806f5df: wrk_do_cnt_sess+ef 0x806e661: wrk_thread_real+341 sp = 0xaf937004 { fd = 21, id = 21, xid = 893998447,#012 client = 74.7.178.42:64276, step = STP_FETCH, handling = deliver, err_code = 200, err_reason = (null), restarts = 0, esis = 0 ws = 0xaf93704c { id = "sess", {s,f,r,e} = {0xaf9377dc,+772,(nil),+16384},#012 }, http[req] = { ws = 0xaf93704c[sess] "GET", "/index.php?title=MediaWiki:Monobook.css&usemsgcache=yes&ctype=text%2Fcss&smaxage=18000&action=raw&maxage=18000", "HTTP/1.1", "Accept: */*", "Referer: http://www.mywebsite.org/index.php/page", "Accept-Language: en-US", "User-Agent: Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; MDDR; Zune 4.0; .NET4.0C; .NET4.0E)", "Host: www.mywebsite.org", "Connection: Keep-Alive", "Cookie: __utma=221264669.1516477775.1286286826.1286286826.1286286826.1; __utmz=221264669.1286286826.1.1.utmcsr=google.com|utmccn=(referral)|utmcmd=referral|utmcct=/", "X-Forwarded-For: 74.7.178.42", "Accept-Encoding: gzip", }, worker = 0xb7f8b194 { ws = 0xb7f8b2ac { id = "wrk", {s,f,r,e} = {0xb7f85150,+1472,(nil),+16384}, }, http[bereq] = { ws = 0xb7f8b2ac[wrk] Dec 6 18:30:52 web-1 /d/varnish[22365]: child (17885) Started }}} -- -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 13 14:41:31 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 13 Dec 2010 14:41:31 -0000 Subject: [Varnish] #411: restart not available in vcl_deliver In-Reply-To: <043.41ab1c9ec6f0837bc7df7c634c3f382d@varnish-cache.org> References: <043.41ab1c9ec6f0837bc7df7c634c3f382d@varnish-cache.org> Message-ID: <052.f4d7730b60e7ff60f66cbde1ac51eb18@varnish-cache.org> #411: restart not available in vcl_deliver ----------------------+----------------------------------------------------- Reporter: hajile | Owner: martin Type: defect | Status: closed Priority: normal | Milestone: Component: varnishd | Version: trunk Severity: normal | Resolution: fixed Keywords: | ----------------------+----------------------------------------------------- Changes (by martin): * status: new => closed * resolution: => fixed Comment: (In [5644]) Implement restart in vcl_deliver(), and add test case for it. Fixes: #411 -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Tue Dec 14 10:02:02 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Tue, 14 Dec 2010 10:02:02 -0000 Subject: [Varnish] #826: Double Content-Length header when using pass In-Reply-To: <043.c8b89edf1269302f4d7edffee13e03bc@varnish-cache.org> References: <043.c8b89edf1269302f4d7edffee13e03bc@varnish-cache.org> Message-ID: <052.3ab40aa5318aa7b7335d61894e67bcff@varnish-cache.org> #826: Double Content-Length header when using pass ---------------------+------------------------------------------------------ Reporter: kdajka | Owner: martin Type: defect | Status: closed Priority: normal | Milestone: Component: regress | Version: 2.1.4 Severity: normal | Resolution: fixed Keywords: | ---------------------+------------------------------------------------------ Changes (by martin): * status: new => closed * resolution: => fixed Comment: This is a duplicate of #801, and was fixed by r5461 in trunk. This changeset was merged to the 2.1 branch in r5467, and will be in Varnish 2.1.5 when that is released. -- Ticket URL: Varnish The Varnish HTTP Accelerator From mark at g.foster.cc Tue Dec 14 06:37:07 2010 From: mark at g.foster.cc (Mark Foster) Date: Mon, 13 Dec 2010 22:37:07 -0800 Subject: [Varnish] #828: varnishstat sms_nbytes is huge In-Reply-To: <055.f6904d9810df44f0a7c7d313ac4f7add@varnish-cache.org> References: <046.4eae888ca7c0382d43ece73f0d4cb54a@varnish-cache.org> <055.f6904d9810df44f0a7c7d313ac4f7add@varnish-cache.org> Message-ID: Thanks for the explanation. In fact, the incorrect counter corrupts the varnish_allocated munin graph that we are using, so it's not so easy to ignore. This is a production setup and we need the graph to look right. Do you happen to know what version the fix is in? On Mon, Dec 13, 2010 at 5:09 AM, Varnish wrote: > #828: varnishstat sms_nbytes is huge > > ------------------------------------+--------------------------------------- > Reporter: delimiter | Owner: phk > Type: defect | Status: closed > Priority: normal | Milestone: > Component: varnishstat | Version: 2.1.0 > Severity: normal | Resolution: fixed > Keywords: varnishstat sms_nbytes | > > ------------------------------------+--------------------------------------- > Changes (by phk): > > * status: new => closed > * resolution: => fixed > > > Comment: > > This is an artifact of an unlocked counter, don't worry about it. > > I belive it is fixed in newer versions. > > -- > Ticket URL: > Varnish > The Varnish HTTP Accelerator > -------------- next part -------------- An HTML attachment was scrubbed... URL: From varnish-bugs at varnish-cache.org Tue Dec 14 16:27:29 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Tue, 14 Dec 2010 16:27:29 -0000 Subject: [Varnish] #834: Varnish sends health checks to backends after backend was removed with a config reload Message-ID: <043.6794df45fbdc17af537e779f3d75a268@varnish-cache.org> #834: Varnish sends health checks to backends after backend was removed with a config reload --------------------------------+------------------------------------------- Reporter: mkania | Type: defect Status: new | Priority: normal Milestone: | Component: build Version: 2.1.3 | Severity: normal Keywords: healthcheck reload | --------------------------------+------------------------------------------- I noticed this on a production cluster, where we were removing backends from the varnish config, and issued a config reload. Requests no longer go to the removed backends, but varnish is still sending health checks. 0 Backend_health - asset_demux_phx5 Still sick ------- 0 3 5 0.000000 0.251935 0 Backend_health - asset_demux_phx12 Still sick ------- 0 3 5 0.000000 0.261331 0 Backend_health - asset_demux_phx6 Still sick ------- 0 3 5 0.000000 0.267248 0 Backend_health - asset_demux_phx13 Still sick ------- 0 3 5 0.000000 0.267399 0 Backend_health - asset_demux_phx8 Still sick ------- 0 3 5 0.000000 0.259694 0 Backend_health - asset_demux_phx0 Still sick ------- 0 3 5 0.000000 0.267166 0 Backend_health - asset_demux_phx2 Still sick ------- 0 3 5 0.000000 0.274461 I've verified that all references have been removed from the config. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Tue Dec 14 20:04:03 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Tue, 14 Dec 2010 20:04:03 -0000 Subject: [Varnish] #834: Varnish sends health checks to backends after backend was removed with a config reload In-Reply-To: <043.6794df45fbdc17af537e779f3d75a268@varnish-cache.org> References: <043.6794df45fbdc17af537e779f3d75a268@varnish-cache.org> Message-ID: <052.d78d1a007bf94170a2134acf50a13cc2@varnish-cache.org> #834: Varnish sends health checks to backends after backend was removed with a config reload --------------------------------+------------------------------------------- Reporter: mkania | Type: defect Status: new | Priority: normal Milestone: | Component: build Version: 2.1.3 | Severity: normal Keywords: healthcheck reload | --------------------------------+------------------------------------------- Comment(by nav): Did you discard old config? -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Tue Dec 14 20:13:54 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Tue, 14 Dec 2010 20:13:54 -0000 Subject: [Varnish] #834: Varnish sends health checks to backends after backend was removed with a config reload In-Reply-To: <043.6794df45fbdc17af537e779f3d75a268@varnish-cache.org> References: <043.6794df45fbdc17af537e779f3d75a268@varnish-cache.org> Message-ID: <052.6f22a44386eacf1526c92cc0594fe486@varnish-cache.org> #834: Varnish sends health checks to backends after backend was removed with a config reload --------------------------------+------------------------------------------- Reporter: mkania | Type: defect Status: new | Priority: normal Milestone: | Component: build Version: 2.1.3 | Severity: normal Keywords: healthcheck reload | --------------------------------+------------------------------------------- Comment(by mkania): Yes. An automated process generates the varnish config and which backends need to be in rotation, which means the old config was overwritten. Once change is detected in the config a /etc/init.d/varnish reload will run. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Wed Dec 15 09:38:38 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Wed, 15 Dec 2010 09:38:38 -0000 Subject: [Varnish] #834: Varnish sends health checks to backends after backend was removed with a config reload In-Reply-To: <043.6794df45fbdc17af537e779f3d75a268@varnish-cache.org> References: <043.6794df45fbdc17af537e779f3d75a268@varnish-cache.org> Message-ID: <052.804ed8c625f7abfe53a7efea580613a7@varnish-cache.org> #834: Varnish sends health checks to backends after backend was removed with a config reload ----------------------+----------------------------------------------------- Reporter: mkania | Type: defect Status: closed | Priority: normal Milestone: | Component: build Version: 2.1.3 | Severity: normal Resolution: invalid | Keywords: healthcheck reload ----------------------+----------------------------------------------------- Changes (by kristian): * status: new => closed * resolution: => invalid Comment: Using load/use does not trigger 'discard'. The old configuration is present. This is not a bug - it's working as intended. Part of this logic has been drastically improved to avoid polling the same backend multiple times - but part of it has not. To stop the requests, you will have to use vcl.discard once the refcounter is down. Feel free to use the mail list for further discussion - there's certainly room for it, but as this isn't a bug, I'm closing it. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Wed Dec 15 13:43:15 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Wed, 15 Dec 2010 13:43:15 -0000 Subject: [Varnish] #835: Varnish stops receiving incoming connections, but the process is still up Message-ID: <043.0b306324d23af01d5f961c07ada4c811@varnish-cache.org> #835: Varnish stops receiving incoming connections, but the process is still up ----------------------+----------------------------------------------------- Reporter: blamer | Owner: phk Type: defect | Status: new Priority: high | Milestone: Varnish 2.1 release Component: varnishd | Version: 2.1.4 Severity: major | Keywords: broken pipe, freeze, crash ----------------------+----------------------------------------------------- '''System''': {{{ Linux myh0stz 2.6.26-2-sparc64-smp #1 SMP Fri Sep 17 02:49:30 UTC 2010 sparc64 GNU/Linux 32 Cores 8 GB RAM 1000 MBit Plently of disk space (> 100 gb free) Debian Sparc Varnish was compiled from 2.1.4 source }}} '''Symptom''': At random moments (the resources of the servers are free in those moments), varnishd does not allow connections. It's like nothing is opened on those sockets. It just freezes. I strace-d it (strace -p PID -f -t) (last 500 lines): {{{ [pid 18629] 18:18:12 clock_gettime(CLOCK_REALTIME, {1291997892, 856942092}) = 0 [pid 18629] 18:18:12 poll([{fd=14, events=POLLIN}], 1, 50 [pid 18618] 18:18:12 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:12 write(8, "R"..., 1) = 1 [pid 18619] 18:18:12 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:12 nanosleep({0, 100000000}, [pid 18619] 18:18:12 read(7, "R"..., 1) = 1 [pid 18619] 18:18:12 clock_gettime(CLOCK_REALTIME, {1291997892, 871675208}) = 0 [pid 18619] 18:18:12 epoll_wait(10, [pid 18629] 18:18:12 <... poll resumed> ) = 0 (Timeout) [pid 18629] 18:18:12 ioctl(14, 0x8004667e, 0xf19d43bc) = 0 [pid 18629] 18:18:12 write(4, "\355\235 \10"..., 4) = 4 [pid 18619] 18:18:12 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, u64=2428082451382272}}}, 100, -1) = 1 [pid 18629] 18:18:12 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25621, NULL [pid 18619] 18:18:12 read(3, "\355\235 \10"..., 400) = 4 [pid 18619] 18:18:12 epoll_ctl(10, EPOLL_CTL_MOD, 14, {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3986497544, u64=17121876577064321024}}) = 0 [pid 18619] 18:18:12 epoll_wait(10, [pid 18618] 18:18:12 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:12 write(8, "R"..., 1) = 1 [pid 18619] 18:18:12 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:12 nanosleep({0, 100000000}, [pid 18619] 18:18:12 read(7, "R"..., 1) = 1 [pid 18619] 18:18:12 clock_gettime(CLOCK_REALTIME, {1291997892, 972535516}) = 0 [pid 18619] 18:18:12 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 73349872}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 174123604}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18620] 18:18:13 <... poll resumed> ) = 0 (Timeout) [pid 18620] 18:18:13 clock_gettime(CLOCK_REALTIME, [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=3998392328, u64=17172964285337305088}}}, 100, -1) = 1 [pid 18620] 18:18:13 <... clock_gettime resumed> {1291997893, 195829832}) = 0 [pid 18619] 18:18:13 read(15, [pid 18620] 18:18:13 poll([{fd=5, events=POLLIN}], 1, 1000 [pid 18619] 18:18:13 <... read resumed> "GET /wp- content/themes/digisport/"..., 8191) = 589 [pid 18619] 18:18:13 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 [pid 18624] 18:18:13 <... futex resumed> ) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18624] 18:18:13 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b3842c) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 197972548}) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 198420916}) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 198734648}) = 0 [pid 18624] 18:18:13 writev(15, [{"HTTP/1.1"..., 8}, {" "..., 1}, {"404"..., 3}, {" "..., 1}, {"Not Found"..., 9}, {"\r\n"..., 2}, {"Server: Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"X-Pingback: http://www.digisport."..., 46}, {"\r\n"..., 2}, {"Expires: Wed, 11 Jan 1984 05:00:0"..., 38}, {"\r\n"..., 2}, {"Last-Modified: Fri, 10 Dec 2010 1"..., 44}, {"\r\n"..., 2}, {"Cache-Control: no-cache, must-rev"..., 51}, {"\r\n"..., 2}, {"Pragma: no-cache"..., 16}, {"\r\n"..., 2}, {"Vary: Accept-Encoding"..., 21}, {"\r\n"..., 2}, {"Content-Encoding: gzip"..., 22}, {"\r\n"..., 2}, {"Content-Type: text/html; charset="..., 38}, {"\r\n"..., 2}, {"Content-Length: 17208"..., 21}, {"\r\n"..., 2}, {"Date: Fri, 10 Dec 2010 16:18:13 G"..., 35}, {"\r\n"..., 2}, {"X-Varnish: 1052092382 1052083617"..., 32}, {"\r\n"..., 2}, {"Age: 1073"..., 9}, {"\r\n"..., 2}, ...], 38) = 17700 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 200894048}) = 0 [pid 18624] 18:18:13 poll([{fd=15, events=POLLIN}], 1, 50 [pid 18612] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18612] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 240571564}) = 0 [pid 18612] 18:18:13 nanosleep({1, 0}, [pid 18617] 18:18:13 <... nanosleep resumed> {1, 0}) = 0 [pid 18617] 18:18:13 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18617] 18:18:13 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4033866460) = 0 [pid 18617] 18:18:13 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18617] 18:18:13 nanosleep({1, 0}, [pid 18615] 18:18:13 <... nanosleep resumed> {1, 0}) = 0 [pid 18615] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 250373144}) = 0 [pid 18615] 18:18:13 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18615] 18:18:13 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4050643676) = 0 [pid 18615] 18:18:13 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18615] 18:18:13 nanosleep({1, 0}, [pid 18624] 18:18:13 <... poll resumed> ) = 0 (Timeout) [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b383bc) = 0 [pid 18624] 18:18:13 write(4, "\356R\240\10"..., 4 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, u64=2428082451382272}}}, 100, -1) = 1 [pid 18624] 18:18:13 <... write resumed> ) = 4 [pid 18619] 18:18:13 read(3, [pid 18624] 18:18:13 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25917, NULL [pid 18619] 18:18:13 <... read resumed> "\356R\240\10"..., 400) = 4 [pid 18619] 18:18:13 epoll_ctl(10, EPOLL_CTL_MOD, 15, {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3998392328, u64=17172964285337305088}}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 274913284}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 375723208}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18625] 18:18:13 <... read resumed> "1"..., 1) = 1 [pid 18625] 18:18:13 read(11, "0"..., 1) = 1 [pid 18625] 18:18:13 read(11, "6"..., 1) = 1 [pid 18625] 18:18:13 read(11, "f"..., 1) = 1 [pid 18625] 18:18:13 read(11, "\r"..., 1) = 1 [pid 18625] 18:18:13 read(11, "\n"..., 1) = 1 [pid 18625] 18:18:13 read(11, "http://www.digisport.ro/video\">Vi"..., 4207) = 4207 [pid 18625] 18:18:13 read(11, "\r"..., 1) = 1 [pid 18625] 18:18:13 read(11, "\n"..., 1) = 1 [pid 18625] 18:18:13 read(11, [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=3986497544, u64=17121876577064321024}}}, 100, -1) = 1 [pid 18619] 18:18:13 read(14, "GET /img/wp-content/uploads/2010/"..., 8191) = 703 [pid 18619] 18:18:13 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 [pid 18629] 18:18:13 <... futex resumed> ) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18629] 18:18:13 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18629] 18:18:13 ioctl(14, 0x8004667e, 0xf19d442c) = 0 [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 471524104}) = 0 [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 472037492}) = 0 [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 472340392}) = 0 [pid 18629] 18:18:13 writev(14, [{"HTTP/1.1"..., 8}, {" "..., 1}, {"200"..., 3}, {" "..., 1}, {"OK"..., 2}, {"\r\n"..., 2}, {"Server: Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"Content-Disposition: inline; file"..., 71}, {"\r\n"..., 2}, {"Last-Modified: Fri, 10 Dec 2010 1"..., 44}, {"\r\n"..., 2}, {"Content-Type: image/jpeg"..., 24}, {"\r\n"..., 2}, {"Content-Length: 34330"..., 21}, {"\r\n"..., 2}, {"Date: Fri, 10 Dec 2010 16:18:13 G"..., 35}, {"\r\n"..., 2}, {"X-Varnish: 1052092383 1052054539"..., 32}, {"\r\n"..., 2}, {"Age: 4457"..., 9}, {"\r\n"..., 2}, {"Via: 1.1 varnish"..., 16}, {"\r\n"..., 2}, {"Connection: keep-alive"..., 22}, {"\r\n"..., 2}, {"\r\n"..., 2}, {"\377\330\377\340\0\20JFIF\0\1\1\1\0\226\0\226\0\0\377\333\0C\0\10\6\6\7\6\5\10\7"..., 34330}], 28) = 34668 [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18629] 18:18:13 <... clock_gettime resumed> {1291997893, 475416560}) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1 [pid 18629] 18:18:13 poll([{fd=14, events=POLLIN}], 1, 50 [pid 18618] 18:18:13 <... write resumed> ) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 476985560}) = 0 [pid 18619] 18:18:13 epoll_wait(10, {{EPOLLIN, {u32=3998392328, u64=17172964285337305088}}}, 100, -1) = 1 [pid 18619] 18:18:13 read(15, "HEAD / HTTP/1.1\r\nX-Forwarded-For:"..., 8191) = 102 [pid 18619] 18:18:13 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 [pid 18624] 18:18:13 <... futex resumed> ) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18624] 18:18:13 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b3842c) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 495145448}) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 495574520}) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 495897344}) = 0 [pid 18624] 18:18:13 writev(15, [{"HTTP/1.1"..., 8}, {" "..., 1}, {"200"..., 3}, {" "..., 1}, {"OK"..., 2}, {"\r\n"..., 2}, {"Server: Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"Last-Modified: Tue, 03 Aug 2010 0"..., 44}, {"\r\n"..., 2}, {"ETag: \"40125-0-48ce652c74380\""..., 29}, {"\r\n"..., 2}, {"Vary: Accept-Encoding"..., 21}, {"\r\n"..., 2}, {"Content-Type: text/html"..., 23}, {"\r\n"..., 2}, {"Content-Length: 0"..., 17}, {"\r\n"..., 2}, {"Date: Fri, 10 Dec 2010 16:18:13 G"..., 35}, {"\r\n"..., 2}, {"X-Varnish: 1052092384 1052090630"..., 32}, {"\r\n"..., 2}, {"Age: 236"..., 8}, {"\r\n"..., 2}, {"Via: 1.1 varnish"..., 16}, {"\r\n"..., 2}, {"Connection: keep-alive"..., 22}, {"\r\n"..., 2}, {"\r\n"..., 2}], 29) = 313 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 497661528}) = 0 [pid 18624] 18:18:13 poll([{fd=15, events=POLLIN}], 1, 50 [pid 18629] 18:18:13 <... poll resumed> ) = 0 (Timeout) [pid 18629] 18:18:13 ioctl(14, 0x8004667e, 0xf19d43bc) = 0 [pid 18629] 18:18:13 write(4, "\355\235 \10"..., 4) = 4 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, u64=2428082451382272}}}, 100, -1) = 1 [pid 18629] 18:18:13 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25623, NULL [pid 18619] 18:18:13 read(3, "\355\235 \10"..., 400) = 4 [pid 18619] 18:18:13 epoll_ctl(10, EPOLL_CTL_MOD, 14, {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3986497544, u64=17121876577064321024}}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18624] 18:18:13 <... poll resumed> ) = 0 (Timeout) [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b383bc) = 0 [pid 18624] 18:18:13 write(4, "\356R\240\10"..., 4 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, u64=2428082451382272}}}, 100, -1) = 1 [pid 18624] 18:18:13 <... write resumed> ) = 4 [pid 18619] 18:18:13 read(3, [pid 18624] 18:18:13 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25919, NULL [pid 18619] 18:18:13 <... read resumed> "\356R\240\10"..., 400) = 4 [pid 18619] 18:18:13 epoll_ctl(10, EPOLL_CTL_MOD, 15, {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3998392328, u64=17172964285337305088}}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 577819076}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 678596784}) = 0 [pid 18619] 18:18:13 epoll_wait(10, {{EPOLLIN, {u32=3986497544, u64=17121876577064321024}}}, 100, -1) = 1 [pid 18619] 18:18:13 read(14, "GET /stiri HTTP/1.1\r\nUser-Agent: "..., 8191) = 773 [pid 18619] 18:18:13 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 [pid 18629] 18:18:13 <... futex resumed> ) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18629] 18:18:13 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18629] 18:18:13 ioctl(14, 0x8004667e, 0xf19d442c) = 0 [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 738793608}) = 0 [pid 18629] 18:18:13 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25625, NULL [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 779390960}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 880271512}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18620] 18:18:13 <... poll resumed> ) = 1 ([{fd=5, revents=POLLIN}]) [pid 18618] 18:18:13 write(8, "R"..., 1 [pid 18620] 18:18:13 clock_gettime(CLOCK_REALTIME, [pid 18618] 18:18:13 <... write resumed> ) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, [pid 18620] 18:18:13 <... clock_gettime resumed> {1291997893, 980448784}) = 0 [pid 18619] 18:18:13 <... read resumed> "R"..., 1) = 1 [pid 18620] 18:18:13 accept(5, [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, [pid 18620] 18:18:13 <... accept resumed> {sa_family=AF_INET, sin_port=htons(50619), sin_addr=inet_addr("81.196.12.36")}, [16]) = 17 [pid 18619] 18:18:13 <... clock_gettime resumed> {1291997893, 981728996}) = 0 [pid 18620] 18:18:13 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1} [pid 18619] 18:18:13 epoll_wait(10, [pid 18620] 18:18:13 <... futex resumed> ) = 1 [pid 18624] 18:18:13 <... futex resumed> ) = 0 [pid 18620] 18:18:13 poll([{fd=5, events=POLLIN}], 1, 1000 [pid 18624] 18:18:13 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18624] 18:18:13 ioctl(17, 0x8004667e, 0xf7b3842c) = 0 [pid 18624] 18:18:13 poll([{fd=17, events=POLLIN}], 1, 50) = 1 ([{fd=17, revents=POLLIN}]) [pid 18624] 18:18:13 read(17, "GET /wp-content/themes/digisport/"..., 8191) = 427 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 984534164}) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 984991888}) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 985292996}) = 0 [pid 18624] 18:18:13 writev(17, [{"HTTP/1.1"..., 8}, {" "..., 1}, {"200"..., 3}, {" "..., 1}, {"OK"..., 2}, {"\r\n"..., 2}, {"Server: Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"Last-Modified: Tue, 16 Feb 2010 0"..., 44}, {"\r\n"..., 2}, {"ETag: \"46853-65c-47fb4c59bb740\""..., 31}, {"\r\n"..., 2}, {"Content-Type: image/gif"..., 23}, {"\r\n"..., 2}, {"Content-Length: 1628"..., 20}, {"\r\n"..., 2}, {"Date: Fri, 10 Dec 2010 16:18:13 G"..., 35}, {"\r\n"..., 2}, {"X-Varnish: 1052092386 1052083384"..., 32}, {"\r\n"..., 2}, {"Age: 1100"..., 9}, {"\r\n"..., 2}, {"Via: 1.1 varnish"..., 16}, {"\r\n"..., 2}, {"Connection: keep-alive"..., 22}, {"\r\n"..., 2}, {"\r\n"..., 2}, {"GIF89a\34\0$\0\367\0\0\"\37\210w\344\363\235\237\314\36\271\336XZ\250\0\215\303\307\361"..., 1628}], 28) = 1924 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 987145288}) = 0 [pid 18624] 18:18:13 poll([{fd=17, events=POLLIN}], 1, 50) = 0 (Timeout) [pid 18624] 18:18:14 ioctl(17, 0x8004667e, 0xf7b383bc) = 0 [pid 18624] 18:18:14 write(4, "\367\244\200\10"..., 4 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, u64=2428082451382272}}}, 100, -1) = 1 [pid 18624] 18:18:14 <... write resumed> ) = 4 [pid 18619] 18:18:14 read(3, [pid 18624] 18:18:14 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25921, NULL [pid 18619] 18:18:14 <... read resumed> "\367\244\200\10"..., 400) = 4 [pid 18619] 18:18:14 epoll_ctl(10, EPOLL_CTL_ADD, 17, {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=4154753032, u64=17844528395396841472}}) = 0 [pid 18619] 18:18:14 epoll_wait(10, {{EPOLLIN, {u32=4154753032, u64=17844528395396841472}}}, 100, -1) = 1 [pid 18619] 18:18:14 read(17, "GET /stiri HTTP/1.1\r\nUser-Agent: "..., 8191) = 773 [pid 18619] 18:18:14 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 [pid 18629] 18:18:14 <... futex resumed> ) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18629] 18:18:14 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18629] 18:18:14 ioctl(17, 0x8004667e, 0xf19d442c) = 0 [pid 18629] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 47222624}) = 0 [pid 18629] 18:18:14 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25627, NULL [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 82163424}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 183055080}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18612] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18612] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 241243672}) = 0 [pid 18612] 18:18:14 nanosleep({1, 0}, [pid 18617] 18:18:14 <... nanosleep resumed> {1, 0}) = 0 [pid 18617] 18:18:14 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18617] 18:18:14 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4033866460) = 0 [pid 18617] 18:18:14 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18617] 18:18:14 nanosleep({1, 0}, [pid 18615] 18:18:14 <... nanosleep resumed> {1, 0}) = 0 [pid 18615] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 252058036}) = 0 [pid 18615] 18:18:14 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18615] 18:18:14 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4050643676) = 0 [pid 18615] 18:18:14 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18615] 18:18:14 nanosleep({1, 0}, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 283774800}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 384582084}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18620] 18:18:14 <... poll resumed> ) = 1 ([{fd=5, revents=POLLIN}]) [pid 18620] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 419035140}) = 0 [pid 18620] 18:18:14 accept(5, {sa_family=AF_INET, sin_port=htons(50630), sin_addr=inet_addr("81.196.12.36")}, [16]) = 18 [pid 18620] 18:18:14 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 [pid 18624] 18:18:14 <... futex resumed> ) = 0 [pid 18620] 18:18:14 poll([{fd=5, events=POLLIN}], 1, 1000 [pid 18624] 18:18:14 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18624] 18:18:14 ioctl(18, 0x8004667e, 0xf7b3842c) = 0 [pid 18624] 18:18:14 poll([{fd=18, events=POLLIN}], 1, 50) = 1 ([{fd=18, revents=POLLIN}]) [pid 18624] 18:18:14 read(18, "GET /stiri HTTP/1.1\r\nUser-Agent: "..., 8191) = 773 [pid 18624] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 421629696}) = 0 [pid 18624] 18:18:14 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25923, NULL [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 485429080}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 586203652}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 687050580}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 787847056}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 888672272}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 989458320}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 90264196}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18611] 18:18:15 <... poll resumed> ) = 1 ([{fd=6, revents=POLLIN}]) [pid 18611] 18:18:15 read(6, "ping\n"..., 8191) = 5 [pid 18611] 18:18:15 time(NULL) = 1291997895 [pid 18611] 18:18:15 writev(9, [{"200 19 \n"..., 13}, {"PONG 1291997895 1.0"..., 19}, {"\n"..., 1}], 3) = 33 [pid 18611] 18:18:15 poll([{fd=6, events=POLLIN}], 1, -1 [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 191048264}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18612] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18612] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 241947668}) = 0 [pid 18612] 18:18:15 nanosleep({1, 0}, [pid 18617] 18:18:15 <... nanosleep resumed> {1, 0}) = 0 [pid 18617] 18:18:15 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18617] 18:18:15 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4033866460) = 0 [pid 18617] 18:18:15 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18617] 18:18:15 nanosleep({1, 0}, [pid 18615] 18:18:15 <... nanosleep resumed> {1, 0}) = 0 [pid 18615] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 253632384}) = 0 [pid 18615] 18:18:15 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18615] 18:18:15 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4050643676) = 0 [pid 18615] 18:18:15 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18615] 18:18:15 nanosleep({1, 0}, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 291949320}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 392767872}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18620] 18:18:15 <... poll resumed> ) = 0 (Timeout) [pid 18620] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 423866840}) = 0 [pid 18620] 18:18:15 poll([{fd=5, events=POLLIN}], 1, 1000 [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 493554528}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 594343716}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 695131520}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 795928848}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 896786468}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 997543276}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18618] 18:18:16 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:16 write(8, "R"..., 1) = 1 [pid 18619] 18:18:16 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:16 nanosleep({0, 100000000}, [pid 18619] 18:18:16 read(7, "R"..., 1) = 1 [pid 18619] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, 98361332}) = 0 [pid 18619] 18:18:16 epoll_wait(10, [pid 18618] 18:18:16 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:16 write(8, "R"..., 1) = 1 [pid 18619] 18:18:16 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:16 nanosleep({0, 100000000}, [pid 18619] 18:18:16 read(7, "R"..., 1) = 1 [pid 18619] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, 199182492}) = 0 [pid 18619] 18:18:16 epoll_wait(10, [pid 18612] 18:18:16 <... nanosleep resumed> NULL) = 0 [pid 18612] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, 242623312}) = 0 [pid 18612] 18:18:16 nanosleep({1, 0}, [pid 18617] 18:18:16 <... nanosleep resumed> {1, 0}) = 0 [pid 18617] 18:18:16 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18617] 18:18:16 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4033866460) = 0 [pid 18617] 18:18:16 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18617] 18:18:16 nanosleep({1, 0}, [pid 18615] 18:18:16 <... nanosleep resumed> {1, 0}) = 0 [pid 18615] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, 255275216}) = 0 [pid 18615] 18:18:16 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18615] 18:18:16 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4050643676) = 0 [pid 18615] 18:18:16 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18615] 18:18:16 nanosleep({1, 0}, [pid 18618] 18:18:16 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:16 write(8, "R"..., 1) = 1 [pid 18619] 18:18:16 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:16 nanosleep({0, 100000000}, [pid 18619] 18:18:16 read(7, "R"..., 1) = 1 [pid 18619] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, 299975276}) = 0 [pid 18619] 18:18:16 epoll_wait(10, [pid 18620] 18:18:16 <... poll resumed> ) = 1 ([{fd=5, revents=POLLIN}]) [pid 18620] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, 315826092}) = 0 [pid 18620] 18:18:16 accept(5, {sa_family=AF_INET, sin_port=htons(42033), sin_addr=inet_addr("81.196.12.86")}, [16]) = 19 [pid 18620] 18:18:16 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 [pid 18629] 18:18:16 <... futex resumed> ) = 0 [pid 18620] 18:18:16 poll([{fd=5, events=POLLIN}], 1, 1000 [pid 18629] 18:18:16 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18629] 18:18:16 ioctl(19, 0x8004667e, 0xf19d442c) = 0 [pid 18629] 18:18:16 poll([{fd=19, events=POLLIN}], 1, 50) = 1 ([{fd=19, revents=POLLIN}]) [pid 18629] 18:18:16 read(19, "GET / HTTP/1.1\r\nHost: www.digispo"..., 8191) = 99 [pid 18629] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, 318403888}) = 0 [pid 18629] 18:18:16 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25629, NULL [pid 18611] 18:18:16 <... poll resumed> ) = 1 ([{fd=6, revents=POLLHUP}]) [pid 18611] 18:18:16 close(6) = 0 [pid 18611] 18:18:16 close(9) = 0 [pid 18611] 18:18:16 close(5) = 0 [pid 18611] 18:18:16 write(1, "Child dies"..., 10) = -1 EPIPE (Broken pipe) [pid 18611] 18:18:16 --- SIGPIPE (Broken pipe) @ 0 (0) --- [pid 18611] 18:18:16 exit_group(1) = ? Process 18611 detached [pid 18612] 18:18:16 <... nanosleep resumed> 0) = ? ERESTART_RESTARTBLOCK (To be restarted) [pid 18614] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) [pid 18615] 18:18:16 <... nanosleep resumed> 0xf16fec68) = ? ERESTART_RESTARTBLOCK (To be restarted) [pid 18616] 18:18:16 <... nanosleep resumed> 0) = ? ERESTART_RESTARTBLOCK (To be restarted) [pid 18617] 18:18:16 <... nanosleep resumed> 0xf06fec68) = ? ERESTART_RESTARTBLOCK (To be restarted) [pid 18618] 18:18:16 <... nanosleep resumed> 0) = ? ERESTART_RESTARTBLOCK (To be restarted) [pid 18619] 18:18:16 <... epoll_wait resumed> ef6feb20, 100, -1) = -1 EINTR (Interrupted system call) [pid 18620] 18:18:16 <... poll resumed> ) = 1 ([{fd=5, revents=POLLNVAL}]) [pid 18622] 18:18:16 <... read resumed> 0xf7b59108, 8191) = -1 EINTR (Interrupted system call) [pid 18623] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) [pid 18624] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) [pid 18625] 18:18:16 <... read resumed> 0xf7b2839a, 1) = -1 EINTR (Interrupted system call) [pid 18626] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) [pid 18627] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) [pid 18628] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) [pid 18629] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) [pid 18630] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) Process 18611 detached Process 18984 detached }}} All I can see is the SIGPIPE and the ERESTARTSYS (those two things do not appear until the freeze). '''Varnish default conf''': -f /srv/varnish/conf/digisport.vcl -s malloc,1024M -a 0.0.0.0:8080 '''VCL:''' {{{ backend default { .host = "XX.YY.ZZ.WW"; .port = "80"; } sub vcl_recv { if (req.url ~ "cgi-bin") { return (pipe); } if (req.http.Accept-Encoding) { if (req.http.Accept-Encoding ~ "gzip") { set req.http.Accept-Encoding = "gzip"; } elsif (req.http.Accept-Encoding ~ "deflate") { set req.http.Accept-Encoding = "deflate"; } else { # unkown algorithm remove req.http.Accept-Encoding; } } if (req.http.Accept-Language) { remove req.http.Accept-Language; } if (req.http.User-Agent) { remove req.http.User-Agent; } if (req.http.Host ~ "live.XXXXXXXX.ro" || req.http.Host ~ "live2.XXXXXXXX.ro") { return (pipe); } if (req.request != "GET" && req.request != "HEAD") { return (pass); } if (req.url ~ "\.(png|gif|jpg|swf)" || req.url ~ "/img/" || req.url ~ "\.(js|css)") { remove req.http.cookie; return (lookup); } if ( !(req.url ~ "wp-(login|admin)") && !(req.http.Cookie ~ "wordpress_logged_in") ) { remove req.http.cookie; return (lookup); } else { return (pass); } if (req.http.Cookie ~ "wordpress_logged_in") { return (pass); } else { return (lookup); } } sub vcl_fetch { if (req.http.Host ~ "live.XXXXXXX.ro" || req.http.Host ~ "live2.XXXXXXXX.ro") { return(pass); } if (beresp.http.Content-Type ~ "text/html") { //set beresp.http.Cache-Control = "no-store, no-cache, must-revalidate, post-check=0, pre-check=0"; //set beresp.http.Pragma = "no-cache"; } if (!(req.url ~ "wp-(login|admin)")) { #remove beresp.http.set-cookie; } if (req.url ~ "\.(png|gif|jpg|swf)" || req.url ~ "/img/" || beresp.http.Content-Type ~ "javascript" || beresp.http.Content-Type ~ "css") { remove beresp.http.set-cookie; //log "request-ul se preteaza: " beresp.http.Content-Type; set beresp.ttl = 7200s; return (deliver); } else { set beresp.ttl = 240s; } } }}} I cannot link any request to the crash event. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Wed Dec 15 13:47:48 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Wed, 15 Dec 2010 13:47:48 -0000 Subject: [Varnish] #835: Varnish stops receiving incoming connections, but the process is still up In-Reply-To: <043.0b306324d23af01d5f961c07ada4c811@varnish-cache.org> References: <043.0b306324d23af01d5f961c07ada4c811@varnish-cache.org> Message-ID: <052.bb1fbe7734aea398aba8ae6ea4cd0c5a@varnish-cache.org> #835: Varnish stops receiving incoming connections, but the process is still up ----------------------+----------------------------------------------------- Reporter: blamer | Owner: phk Type: defect | Status: new Priority: high | Milestone: Varnish 2.1 release Component: varnishd | Version: 2.1.4 Severity: major | Keywords: broken pipe, freeze, crash ----------------------+----------------------------------------------------- Comment(by blamer): System: {{{ Linux myh0stz 2.6.26-2-sparc64-smp #1 SMP Fri Sep 17 02:49:30 UTC 2010 sparc64 GNU/Linux 32 Cores 8 GB RAM 1000 MBit Plently of disk space (> 100 gb free) Debian Sparc Varnish was compiled from 2.1.4 source }}} Symptom: At random moments (the resources of the servers are free in those moments), varnishd does not allow connections. It's like nothing is opened on those sockets. It just freezes. I strace-d it (strace -p PID -f -t) (last 500 lines): {{{ [pid 18629] 18:18:12 clock_gettime(CLOCK_REALTIME, {1291997892, 856942092}) = 0 [pid 18629] 18:18:12 poll([{fd=14, events=POLLIN}], 1, 50 [pid 18618] 18:18:12 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:12 write(8, "R"..., 1) = 1 [pid 18619] 18:18:12 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:12 nanosleep({0, 100000000}, [pid 18619] 18:18:12 read(7, "R"..., 1) = 1 [pid 18619] 18:18:12 clock_gettime(CLOCK_REALTIME, {1291997892, 871675208}) = 0 [pid 18619] 18:18:12 epoll_wait(10, [pid 18629] 18:18:12 <... poll resumed> ) = 0 (Timeout) [pid 18629] 18:18:12 ioctl(14, 0x8004667e, 0xf19d43bc) = 0 [pid 18629] 18:18:12 write(4, "\355\235 \10"..., 4) = 4 [pid 18619] 18:18:12 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, u64=2428082451382272}}}, 100, -1) = 1 [pid 18629] 18:18:12 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25621, NULL [pid 18619] 18:18:12 read(3, "\355\235 \10"..., 400) = 4 [pid 18619] 18:18:12 epoll_ctl(10, EPOLL_CTL_MOD, 14, {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3986497544, u64=17121876577064321024}}) = 0 [pid 18619] 18:18:12 epoll_wait(10, [pid 18618] 18:18:12 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:12 write(8, "R"..., 1) = 1 [pid 18619] 18:18:12 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:12 nanosleep({0, 100000000}, [pid 18619] 18:18:12 read(7, "R"..., 1) = 1 [pid 18619] 18:18:12 clock_gettime(CLOCK_REALTIME, {1291997892, 972535516}) = 0 [pid 18619] 18:18:12 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 73349872}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 174123604}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18620] 18:18:13 <... poll resumed> ) = 0 (Timeout) [pid 18620] 18:18:13 clock_gettime(CLOCK_REALTIME, [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=3998392328, u64=17172964285337305088}}}, 100, -1) = 1 [pid 18620] 18:18:13 <... clock_gettime resumed> {1291997893, 195829832}) = 0 [pid 18619] 18:18:13 read(15, [pid 18620] 18:18:13 poll([{fd=5, events=POLLIN}], 1, 1000 [pid 18619] 18:18:13 <... read resumed> "GET /wp- content/themes/XXXXXXXX/"..., 8191) = 589 [pid 18619] 18:18:13 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 [pid 18624] 18:18:13 <... futex resumed> ) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18624] 18:18:13 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b3842c) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 197972548}) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 198420916}) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 198734648}) = 0 [pid 18624] 18:18:13 writev(15, [{"HTTP/1.1"..., 8}, {" "..., 1}, {"404"..., 3}, {" "..., 1}, {"Not Found"..., 9}, {"\r\n"..., 2}, {"Server: Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"X-Pingback: http://www.XXXXXXXX."..., 46}, {"\r\n"..., 2}, {"Expires: Wed, 11 Jan 1984 05:00:0"..., 38}, {"\r\n"..., 2}, {"Last-Modified: Fri, 10 Dec 2010 1"..., 44}, {"\r\n"..., 2}, {"Cache-Control: no-cache, must-rev"..., 51}, {"\r\n"..., 2}, {"Pragma: no-cache"..., 16}, {"\r\n"..., 2}, {"Vary: Accept-Encoding"..., 21}, {"\r\n"..., 2}, {"Content-Encoding: gzip"..., 22}, {"\r\n"..., 2}, {"Content-Type: text/html; charset="..., 38}, {"\r\n"..., 2}, {"Content-Length: 17208"..., 21}, {"\r\n"..., 2}, {"Date: Fri, 10 Dec 2010 16:18:13 G"..., 35}, {"\r\n"..., 2}, {"X-Varnish: 1052092382 1052083617"..., 32}, {"\r\n"..., 2}, {"Age: 1073"..., 9}, {"\r\n"..., 2}, ...], 38) = 17700 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 200894048}) = 0 [pid 18624] 18:18:13 poll([{fd=15, events=POLLIN}], 1, 50 [pid 18612] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18612] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 240571564}) = 0 [pid 18612] 18:18:13 nanosleep({1, 0}, [pid 18617] 18:18:13 <... nanosleep resumed> {1, 0}) = 0 [pid 18617] 18:18:13 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18617] 18:18:13 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4033866460) = 0 [pid 18617] 18:18:13 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18617] 18:18:13 nanosleep({1, 0}, [pid 18615] 18:18:13 <... nanosleep resumed> {1, 0}) = 0 [pid 18615] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 250373144}) = 0 [pid 18615] 18:18:13 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18615] 18:18:13 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4050643676) = 0 [pid 18615] 18:18:13 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18615] 18:18:13 nanosleep({1, 0}, [pid 18624] 18:18:13 <... poll resumed> ) = 0 (Timeout) [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b383bc) = 0 [pid 18624] 18:18:13 write(4, "\356R\240\10"..., 4 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, u64=2428082451382272}}}, 100, -1) = 1 [pid 18624] 18:18:13 <... write resumed> ) = 4 [pid 18619] 18:18:13 read(3, [pid 18624] 18:18:13 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25917, NULL [pid 18619] 18:18:13 <... read resumed> "\356R\240\10"..., 400) = 4 [pid 18619] 18:18:13 epoll_ctl(10, EPOLL_CTL_MOD, 15, {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3998392328, u64=17172964285337305088}}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 274913284}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 375723208}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18625] 18:18:13 <... read resumed> "1"..., 1) = 1 [pid 18625] 18:18:13 read(11, "0"..., 1) = 1 [pid 18625] 18:18:13 read(11, "6"..., 1) = 1 [pid 18625] 18:18:13 read(11, "f"..., 1) = 1 [pid 18625] 18:18:13 read(11, "\r"..., 1) = 1 [pid 18625] 18:18:13 read(11, "\n"..., 1) = 1 [pid 18625] 18:18:13 read(11, "http://www.XXXXXXXX.ro/video\">Vi"..., 4207) = 4207 [pid 18625] 18:18:13 read(11, "\r"..., 1) = 1 [pid 18625] 18:18:13 read(11, "\n"..., 1) = 1 [pid 18625] 18:18:13 read(11, [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=3986497544, u64=17121876577064321024}}}, 100, -1) = 1 [pid 18619] 18:18:13 read(14, "GET /img/wp-content/uploads/2010/"..., 8191) = 703 [pid 18619] 18:18:13 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 [pid 18629] 18:18:13 <... futex resumed> ) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18629] 18:18:13 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18629] 18:18:13 ioctl(14, 0x8004667e, 0xf19d442c) = 0 [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 471524104}) = 0 [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 472037492}) = 0 [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 472340392}) = 0 [pid 18629] 18:18:13 writev(14, [{"HTTP/1.1"..., 8}, {" "..., 1}, {"200"..., 3}, {" "..., 1}, {"OK"..., 2}, {"\r\n"..., 2}, {"Server: Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"Content-Disposition: inline; file"..., 71}, {"\r\n"..., 2}, {"Last-Modified: Fri, 10 Dec 2010 1"..., 44}, {"\r\n"..., 2}, {"Content-Type: image/jpeg"..., 24}, {"\r\n"..., 2}, {"Content-Length: 34330"..., 21}, {"\r\n"..., 2}, {"Date: Fri, 10 Dec 2010 16:18:13 G"..., 35}, {"\r\n"..., 2}, {"X-Varnish: 1052092383 1052054539"..., 32}, {"\r\n"..., 2}, {"Age: 4457"..., 9}, {"\r\n"..., 2}, {"Via: 1.1 varnish"..., 16}, {"\r\n"..., 2}, {"Connection: keep-alive"..., 22}, {"\r\n"..., 2}, {"\r\n"..., 2}, {"\377\330\377\340\0\20JFIF\0\1\1\1\0\226\0\226\0\0\377\333\0C\0\10\6\6\7\6\5\10\7"..., 34330}], 28) = 34668 [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18629] 18:18:13 <... clock_gettime resumed> {1291997893, 475416560}) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1 [pid 18629] 18:18:13 poll([{fd=14, events=POLLIN}], 1, 50 [pid 18618] 18:18:13 <... write resumed> ) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 476985560}) = 0 [pid 18619] 18:18:13 epoll_wait(10, {{EPOLLIN, {u32=3998392328, u64=17172964285337305088}}}, 100, -1) = 1 [pid 18619] 18:18:13 read(15, "HEAD / HTTP/1.1\r\nX-Forwarded-For:"..., 8191) = 102 [pid 18619] 18:18:13 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 [pid 18624] 18:18:13 <... futex resumed> ) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18624] 18:18:13 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b3842c) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 495145448}) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 495574520}) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 495897344}) = 0 [pid 18624] 18:18:13 writev(15, [{"HTTP/1.1"..., 8}, {" "..., 1}, {"200"..., 3}, {" "..., 1}, {"OK"..., 2}, {"\r\n"..., 2}, {"Server: Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"Last-Modified: Tue, 03 Aug 2010 0"..., 44}, {"\r\n"..., 2}, {"ETag: \"40125-0-48ce652c74380\""..., 29}, {"\r\n"..., 2}, {"Vary: Accept-Encoding"..., 21}, {"\r\n"..., 2}, {"Content-Type: text/html"..., 23}, {"\r\n"..., 2}, {"Content-Length: 0"..., 17}, {"\r\n"..., 2}, {"Date: Fri, 10 Dec 2010 16:18:13 G"..., 35}, {"\r\n"..., 2}, {"X-Varnish: 1052092384 1052090630"..., 32}, {"\r\n"..., 2}, {"Age: 236"..., 8}, {"\r\n"..., 2}, {"Via: 1.1 varnish"..., 16}, {"\r\n"..., 2}, {"Connection: keep-alive"..., 22}, {"\r\n"..., 2}, {"\r\n"..., 2}], 29) = 313 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 497661528}) = 0 [pid 18624] 18:18:13 poll([{fd=15, events=POLLIN}], 1, 50 [pid 18629] 18:18:13 <... poll resumed> ) = 0 (Timeout) [pid 18629] 18:18:13 ioctl(14, 0x8004667e, 0xf19d43bc) = 0 [pid 18629] 18:18:13 write(4, "\355\235 \10"..., 4) = 4 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, u64=2428082451382272}}}, 100, -1) = 1 [pid 18629] 18:18:13 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25623, NULL [pid 18619] 18:18:13 read(3, "\355\235 \10"..., 400) = 4 [pid 18619] 18:18:13 epoll_ctl(10, EPOLL_CTL_MOD, 14, {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3986497544, u64=17121876577064321024}}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18624] 18:18:13 <... poll resumed> ) = 0 (Timeout) [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b383bc) = 0 [pid 18624] 18:18:13 write(4, "\356R\240\10"..., 4 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, u64=2428082451382272}}}, 100, -1) = 1 [pid 18624] 18:18:13 <... write resumed> ) = 4 [pid 18619] 18:18:13 read(3, [pid 18624] 18:18:13 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25919, NULL [pid 18619] 18:18:13 <... read resumed> "\356R\240\10"..., 400) = 4 [pid 18619] 18:18:13 epoll_ctl(10, EPOLL_CTL_MOD, 15, {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3998392328, u64=17172964285337305088}}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 577819076}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 678596784}) = 0 [pid 18619] 18:18:13 epoll_wait(10, {{EPOLLIN, {u32=3986497544, u64=17121876577064321024}}}, 100, -1) = 1 [pid 18619] 18:18:13 read(14, "GET /stiri HTTP/1.1\r\nUser-Agent: "..., 8191) = 773 [pid 18619] 18:18:13 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 [pid 18629] 18:18:13 <... futex resumed> ) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18629] 18:18:13 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18629] 18:18:13 ioctl(14, 0x8004667e, 0xf19d442c) = 0 [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 738793608}) = 0 [pid 18629] 18:18:13 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25625, NULL [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 779390960}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 880271512}) = 0 [pid 18619] 18:18:13 epoll_wait(10, [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 [pid 18620] 18:18:13 <... poll resumed> ) = 1 ([{fd=5, revents=POLLIN}]) [pid 18618] 18:18:13 write(8, "R"..., 1 [pid 18620] 18:18:13 clock_gettime(CLOCK_REALTIME, [pid 18618] 18:18:13 <... write resumed> ) = 1 [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:13 nanosleep({0, 100000000}, [pid 18619] 18:18:13 read(7, [pid 18620] 18:18:13 <... clock_gettime resumed> {1291997893, 980448784}) = 0 [pid 18619] 18:18:13 <... read resumed> "R"..., 1) = 1 [pid 18620] 18:18:13 accept(5, [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, [pid 18620] 18:18:13 <... accept resumed> {sa_family=AF_INET, sin_port=htons(50619), sin_addr=inet_addr("x.y.z.36")}, [16]) = 17 [pid 18619] 18:18:13 <... clock_gettime resumed> {1291997893, 981728996}) = 0 [pid 18620] 18:18:13 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1} [pid 18619] 18:18:13 epoll_wait(10, [pid 18620] 18:18:13 <... futex resumed> ) = 1 [pid 18624] 18:18:13 <... futex resumed> ) = 0 [pid 18620] 18:18:13 poll([{fd=5, events=POLLIN}], 1, 1000 [pid 18624] 18:18:13 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18624] 18:18:13 ioctl(17, 0x8004667e, 0xf7b3842c) = 0 [pid 18624] 18:18:13 poll([{fd=17, events=POLLIN}], 1, 50) = 1 ([{fd=17, revents=POLLIN}]) [pid 18624] 18:18:13 read(17, "GET /wp-content/themes/XXXXXXXX/"..., 8191) = 427 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 984534164}) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 984991888}) = 0 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 985292996}) = 0 [pid 18624] 18:18:13 writev(17, [{"HTTP/1.1"..., 8}, {" "..., 1}, {"200"..., 3}, {" "..., 1}, {"OK"..., 2}, {"\r\n"..., 2}, {"Server: Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"Last-Modified: Tue, 16 Feb 2010 0"..., 44}, {"\r\n"..., 2}, {"ETag: \"46853-65c-47fb4c59bb740\""..., 31}, {"\r\n"..., 2}, {"Content-Type: image/gif"..., 23}, {"\r\n"..., 2}, {"Content-Length: 1628"..., 20}, {"\r\n"..., 2}, {"Date: Fri, 10 Dec 2010 16:18:13 G"..., 35}, {"\r\n"..., 2}, {"X-Varnish: 1052092386 1052083384"..., 32}, {"\r\n"..., 2}, {"Age: 1100"..., 9}, {"\r\n"..., 2}, {"Via: 1.1 varnish"..., 16}, {"\r\n"..., 2}, {"Connection: keep-alive"..., 22}, {"\r\n"..., 2}, {"\r\n"..., 2}, {"GIF89a\34\0$\0\367\0\0\"\37\210w\344\363\235\237\314\36\271\336XZ\250\0\215\303\307\361"..., 1628}], 28) = 1924 [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 987145288}) = 0 [pid 18624] 18:18:13 poll([{fd=17, events=POLLIN}], 1, 50) = 0 (Timeout) [pid 18624] 18:18:14 ioctl(17, 0x8004667e, 0xf7b383bc) = 0 [pid 18624] 18:18:14 write(4, "\367\244\200\10"..., 4 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, u64=2428082451382272}}}, 100, -1) = 1 [pid 18624] 18:18:14 <... write resumed> ) = 4 [pid 18619] 18:18:14 read(3, [pid 18624] 18:18:14 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25921, NULL [pid 18619] 18:18:14 <... read resumed> "\367\244\200\10"..., 400) = 4 [pid 18619] 18:18:14 epoll_ctl(10, EPOLL_CTL_ADD, 17, {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=4154753032, u64=17844528395396841472}}) = 0 [pid 18619] 18:18:14 epoll_wait(10, {{EPOLLIN, {u32=4154753032, u64=17844528395396841472}}}, 100, -1) = 1 [pid 18619] 18:18:14 read(17, "GET /stiri HTTP/1.1\r\nUser-Agent: "..., 8191) = 773 [pid 18619] 18:18:14 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 [pid 18629] 18:18:14 <... futex resumed> ) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18629] 18:18:14 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18629] 18:18:14 ioctl(17, 0x8004667e, 0xf19d442c) = 0 [pid 18629] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 47222624}) = 0 [pid 18629] 18:18:14 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25627, NULL [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 82163424}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 183055080}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18612] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18612] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 241243672}) = 0 [pid 18612] 18:18:14 nanosleep({1, 0}, [pid 18617] 18:18:14 <... nanosleep resumed> {1, 0}) = 0 [pid 18617] 18:18:14 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18617] 18:18:14 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4033866460) = 0 [pid 18617] 18:18:14 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18617] 18:18:14 nanosleep({1, 0}, [pid 18615] 18:18:14 <... nanosleep resumed> {1, 0}) = 0 [pid 18615] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 252058036}) = 0 [pid 18615] 18:18:14 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18615] 18:18:14 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4050643676) = 0 [pid 18615] 18:18:14 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18615] 18:18:14 nanosleep({1, 0}, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 283774800}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 384582084}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18620] 18:18:14 <... poll resumed> ) = 1 ([{fd=5, revents=POLLIN}]) [pid 18620] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 419035140}) = 0 [pid 18620] 18:18:14 accept(5, {sa_family=AF_INET, sin_port=htons(50630), sin_addr=inet_addr("x.y.z.36")}, [16]) = 18 [pid 18620] 18:18:14 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 [pid 18624] 18:18:14 <... futex resumed> ) = 0 [pid 18620] 18:18:14 poll([{fd=5, events=POLLIN}], 1, 1000 [pid 18624] 18:18:14 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18624] 18:18:14 ioctl(18, 0x8004667e, 0xf7b3842c) = 0 [pid 18624] 18:18:14 poll([{fd=18, events=POLLIN}], 1, 50) = 1 ([{fd=18, revents=POLLIN}]) [pid 18624] 18:18:14 read(18, "GET /stiri HTTP/1.1\r\nUser-Agent: "..., 8191) = 773 [pid 18624] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 421629696}) = 0 [pid 18624] 18:18:14 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25923, NULL [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 485429080}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 586203652}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 687050580}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 787847056}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 888672272}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:14 nanosleep({0, 100000000}, [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 989458320}) = 0 [pid 18619] 18:18:14 epoll_wait(10, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 90264196}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18611] 18:18:15 <... poll resumed> ) = 1 ([{fd=6, revents=POLLIN}]) [pid 18611] 18:18:15 read(6, "ping\n"..., 8191) = 5 [pid 18611] 18:18:15 time(NULL) = 1291997895 [pid 18611] 18:18:15 writev(9, [{"200 19 \n"..., 13}, {"PONG 1291997895 1.0"..., 19}, {"\n"..., 1}], 3) = 33 [pid 18611] 18:18:15 poll([{fd=6, events=POLLIN}], 1, -1 [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 191048264}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18612] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18612] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 241947668}) = 0 [pid 18612] 18:18:15 nanosleep({1, 0}, [pid 18617] 18:18:15 <... nanosleep resumed> {1, 0}) = 0 [pid 18617] 18:18:15 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18617] 18:18:15 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4033866460) = 0 [pid 18617] 18:18:15 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18617] 18:18:15 nanosleep({1, 0}, [pid 18615] 18:18:15 <... nanosleep resumed> {1, 0}) = 0 [pid 18615] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 253632384}) = 0 [pid 18615] 18:18:15 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18615] 18:18:15 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4050643676) = 0 [pid 18615] 18:18:15 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18615] 18:18:15 nanosleep({1, 0}, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 291949320}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 392767872}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18620] 18:18:15 <... poll resumed> ) = 0 (Timeout) [pid 18620] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 423866840}) = 0 [pid 18620] 18:18:15 poll([{fd=5, events=POLLIN}], 1, 1000 [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 493554528}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 594343716}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 695131520}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 795928848}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 896786468}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:15 nanosleep({0, 100000000}, [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 997543276}) = 0 [pid 18619] 18:18:15 epoll_wait(10, [pid 18618] 18:18:16 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:16 write(8, "R"..., 1) = 1 [pid 18619] 18:18:16 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:16 nanosleep({0, 100000000}, [pid 18619] 18:18:16 read(7, "R"..., 1) = 1 [pid 18619] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, 98361332}) = 0 [pid 18619] 18:18:16 epoll_wait(10, [pid 18618] 18:18:16 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:16 write(8, "R"..., 1) = 1 [pid 18619] 18:18:16 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:16 nanosleep({0, 100000000}, [pid 18619] 18:18:16 read(7, "R"..., 1) = 1 [pid 18619] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, 199182492}) = 0 [pid 18619] 18:18:16 epoll_wait(10, [pid 18612] 18:18:16 <... nanosleep resumed> NULL) = 0 [pid 18612] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, 242623312}) = 0 [pid 18612] 18:18:16 nanosleep({1, 0}, [pid 18617] 18:18:16 <... nanosleep resumed> {1, 0}) = 0 [pid 18617] 18:18:16 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18617] 18:18:16 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4033866460) = 0 [pid 18617] 18:18:16 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18617] 18:18:16 nanosleep({1, 0}, [pid 18615] 18:18:16 <... nanosleep resumed> {1, 0}) = 0 [pid 18615] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, 255275216}) = 0 [pid 18615] 18:18:16 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 [pid 18615] 18:18:16 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], SA_NOCLDSTOP}, 0, 4050643676) = 0 [pid 18615] 18:18:16 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 [pid 18615] 18:18:16 nanosleep({1, 0}, [pid 18618] 18:18:16 <... nanosleep resumed> NULL) = 0 [pid 18618] 18:18:16 write(8, "R"..., 1) = 1 [pid 18619] 18:18:16 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, u64=2452254527324160}}}, 100, -1) = 1 [pid 18618] 18:18:16 nanosleep({0, 100000000}, [pid 18619] 18:18:16 read(7, "R"..., 1) = 1 [pid 18619] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, 299975276}) = 0 [pid 18619] 18:18:16 epoll_wait(10, [pid 18620] 18:18:16 <... poll resumed> ) = 1 ([{fd=5, revents=POLLIN}]) [pid 18620] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, 315826092}) = 0 [pid 18620] 18:18:16 accept(5, {sa_family=AF_INET, sin_port=htons(42033), sin_addr=inet_addr("x.y.z.86")}, [16]) = 19 [pid 18620] 18:18:16 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 [pid 18629] 18:18:16 <... futex resumed> ) = 0 [pid 18620] 18:18:16 poll([{fd=5, events=POLLIN}], 1, 1000 [pid 18629] 18:18:16 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 [pid 18629] 18:18:16 ioctl(19, 0x8004667e, 0xf19d442c) = 0 [pid 18629] 18:18:16 poll([{fd=19, events=POLLIN}], 1, 50) = 1 ([{fd=19, revents=POLLIN}]) [pid 18629] 18:18:16 read(19, "GET / HTTP/1.1\r\nHost: www.Xspo"..., 8191) = 99 [pid 18629] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, 318403888}) = 0 [pid 18629] 18:18:16 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25629, NULL [pid 18611] 18:18:16 <... poll resumed> ) = 1 ([{fd=6, revents=POLLHUP}]) [pid 18611] 18:18:16 close(6) = 0 [pid 18611] 18:18:16 close(9) = 0 [pid 18611] 18:18:16 close(5) = 0 [pid 18611] 18:18:16 write(1, "Child dies"..., 10) = -1 EPIPE (Broken pipe) [pid 18611] 18:18:16 --- SIGPIPE (Broken pipe) @ 0 (0) --- [pid 18611] 18:18:16 exit_group(1) = ? Process 18611 detached [pid 18612] 18:18:16 <... nanosleep resumed> 0) = ? ERESTART_RESTARTBLOCK (To be restarted) [pid 18614] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) [pid 18615] 18:18:16 <... nanosleep resumed> 0xf16fec68) = ? ERESTART_RESTARTBLOCK (To be restarted) [pid 18616] 18:18:16 <... nanosleep resumed> 0) = ? ERESTART_RESTARTBLOCK (To be restarted) [pid 18617] 18:18:16 <... nanosleep resumed> 0xf06fec68) = ? ERESTART_RESTARTBLOCK (To be restarted) [pid 18618] 18:18:16 <... nanosleep resumed> 0) = ? ERESTART_RESTARTBLOCK (To be restarted) [pid 18619] 18:18:16 <... epoll_wait resumed> ef6feb20, 100, -1) = -1 EINTR (Interrupted system call) [pid 18620] 18:18:16 <... poll resumed> ) = 1 ([{fd=5, revents=POLLNVAL}]) [pid 18622] 18:18:16 <... read resumed> 0xf7b59108, 8191) = -1 EINTR (Interrupted system call) [pid 18623] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) [pid 18624] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) [pid 18625] 18:18:16 <... read resumed> 0xf7b2839a, 1) = -1 EINTR (Interrupted system call) [pid 18626] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) [pid 18627] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) [pid 18628] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) [pid 18629] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) [pid 18630] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be restarted) Process 18611 detached Process 18984 detached }}} All I can see is the SIGPIPE and the ERESTARTSYS (those two things do not appear until the freeze). Varnish default conf: -f /srv/varnish/conf/XXXXXXXX.vcl -s malloc,1024M -a 0.0.0.0:8080 VCL: {{{ backend default { .host = "XX.YY.ZZ.WW"; .port = "80"; } sub vcl_recv { if (req.url ~ "cgi-bin") { return (pipe); } if (req.http.Accept-Encoding) { if (req.http.Accept-Encoding ~ "gzip") { set req.http.Accept-Encoding = "gzip"; } elsif (req.http.Accept-Encoding ~ "deflate") { set req.http.Accept-Encoding = "deflate"; } else { # unkown algorithm remove req.http.Accept-Encoding; } } if (req.http.Accept-Language) { remove req.http.Accept-Language; } if (req.http.User-Agent) { remove req.http.User-Agent; } if (req.http.Host ~ "live.XXXXXXXX.ro" || req.http.Host ~ "live2.XXXXXXXX.ro") { return (pipe); } if (req.request != "GET" && req.request != "HEAD") { return (pass); } if (req.url ~ "\.(png|gif|jpg|swf)" || req.url ~ "/img/" || req.url ~ "\.(js|css)") { remove req.http.cookie; return (lookup); } if ( !(req.url ~ "wp-(login|admin)") && !(req.http.Cookie ~ "wordpress_logged_in") ) { remove req.http.cookie; return (lookup); } else { return (pass); } if (req.http.Cookie ~ "wordpress_logged_in") { return (pass); } else { return (lookup); } } sub vcl_fetch { if (req.http.Host ~ "live.XXXXXXX.ro" || req.http.Host ~ "live2.XXXXXXXX.ro") { return(pass); } if (beresp.http.Content-Type ~ "text/html") { //set beresp.http.Cache-Control = "no-store, no-cache, must-revalidate, post-check=0, pre-check=0"; //set beresp.http.Pragma = "no-cache"; } if (!(req.url ~ "wp-(login|admin)")) { #remove beresp.http.set-cookie; } if (req.url ~ "\.(png|gif|jpg|swf)" || req.url ~ "/img/" || beresp.http.Content-Type ~ "javascript" || beresp.http.Content-Type ~ "css") { remove beresp.http.set-cookie; //log "request-ul se preteaza: " beresp.http.Content-Type; set beresp.ttl = 7200s; return (deliver); } else { set beresp.ttl = 240s; } } }}} I cannot link any request to the crash event. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Wed Dec 15 16:35:30 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Wed, 15 Dec 2010 16:35:30 -0000 Subject: [Varnish] #310: WS_Reserve panic + error In-Reply-To: <040.75b83f2a5390779c25adf146cd0b53d5@varnish-cache.org> References: <040.75b83f2a5390779c25adf146cd0b53d5@varnish-cache.org> Message-ID: <049.1b0f9a7babcae90625677d501aacd75e@varnish-cache.org> #310: WS_Reserve panic + error ----------------------+----------------------------------------------------- Reporter: sky | Owner: phk Type: defect | Status: reopened Priority: normal | Milestone: Varnish 2.1 release Component: varnishd | Version: 2.1.4 Severity: normal | Resolution: Keywords: | ----------------------+----------------------------------------------------- Changes (by kristian): * priority: lowest => normal * status: closed => reopened * version: trunk => 2.1.4 * resolution: invalid => Old description: > Sep 3 00:20:20 varnish2 varnishd[25355]: Child (25376) died signal=6 > Sep 3 00:20:20 varnish2 varnishd[25355]: Child (25376) Panic message: > Assert error in WS_Reserve(), cache_ws.c line 156: Condition(ws->r == > NULL) not true. thread = (cache-worker)sp = 0x14a64fc8 { fd = 1507, id > = 1507, xid = 684175780, client = 72.81.232.3:1299, step = 0x8, > handling = 0x0, err_code = 301, err_reason = (null), ws = 0x14a65038 > { id = "sess", {s,f,r,e} = {0x14a65760,,+947,(nil),+32768}, }, > worker = 0x2aaee1db0c10 { }, vcl = { srcname = { > "/home/artur/wikia-beta.vcl", "Default", }, }, obj = > 0x2aabad2f3000 { refcnt = 3, xid = 676411472, ws = 0x2aabad2f3028 > { id = "obj", {s,f,r,e} = > {0x2aabad2f3348,,+530,(nil),+31928}, }, http = { ws = > 0x2aabad2f3028 { id = "obj", {s,f,r,e} = > {0x2aabad2f3348,,+530,(nil),+31928}, }, hd = { "Date: > Tue, 02 Sep 2008 20:44:22 GMT", "Server: Apache", "X > -Powered-By: PHP/5.2.6", "Content-language: en", > Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(7, sock) > Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(8, sock) > Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(9, cli_in) > Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(12, cli_out) > Sep 3 00:20:20 varnish2 varnishd[25355]: child (28791) Started > Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(9, (null)) > Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(12, (null)) > Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(7, (null)) > Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(8, (null)) > Sep 3 00:20:20 varnish2 varnishd[25355]: Pushing vcls failed: > dlopen(./vcl.1P9zoqAU.so): ./vcl.1P9zoqAU.so: cannot open shared object > file: No such file or directory > Sep 3 00:20:20 varnish2 varnishd[25355]: Child (28791) said Closed fds: > 5 6 10 11 13 14 > Sep 3 00:20:20 varnish2 varnishd[25355]: Child (28791) said Child starts > Sep 3 00:20:20 varnish2 varnishd[25355]: Child (28791) said managed to > mmap 15032385536 bytes of 15032385536 > Sep 3 00:20:20 varnish2 varnishd[25355]: Child (28791) said Ready > > > No core dump seem to have survived. > > Any suggestion for what to look for? New description: Sep 3 00:20:20 varnish2 varnishd[25355]: Child (25376) died signal=6 Sep 3 00:20:20 varnish2 varnishd[25355]: Child (25376) Panic message: Assert error in WS_Reserve(), cache_ws.c line 156: Condition(ws->r == NULL) not true. thread = (cache-worker)sp = 0x14a64fc8 { fd = 1507, id = 1507, xid = 684175780, client = 72.81.232.3:1299, step = 0x8, handling = 0x0, err_code = 301, err_reason = (null), ws = 0x14a65038 { id = "sess", {s,f,r,e} = {0x14a65760,,+947,(nil),+32768}, }, worker = 0x2aaee1db0c10 { }, vcl = { srcname = { "/home/artur/wikia-beta.vcl", "Default", }, }, obj = 0x2aabad2f3000 { refcnt = 3, xid = 676411472, ws = 0x2aabad2f3028 { id = "obj", {s,f,r,e} = {0x2aabad2f3348,,+530,(nil),+31928}, }, http = { ws = 0x2aabad2f3028 { id = "obj", {s,f,r,e} = {0x2aabad2f3348,,+530,(nil),+31928}, }, hd = { "Date: Tue, 02 Sep 2008 20:44:22 GMT", "Server: Apache", "X -Powered-By: PHP/5.2.6", "Content-language: en", Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(7, sock) Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(8, sock) Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(9, cli_in) Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(12, cli_out) Sep 3 00:20:20 varnish2 varnishd[25355]: child (28791) Started Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(9, (null)) Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(12, (null)) Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(7, (null)) Sep 3 00:20:20 varnish2 varnishd[25355]: mgt_child_inherit(8, (null)) Sep 3 00:20:20 varnish2 varnishd[25355]: Pushing vcls failed: dlopen(./vcl.1P9zoqAU.so): ./vcl.1P9zoqAU.so: cannot open shared object file: No such file or directory Sep 3 00:20:20 varnish2 varnishd[25355]: Child (28791) said Closed fds: 5 6 10 11 13 14 Sep 3 00:20:20 varnish2 varnishd[25355]: Child (28791) said Child starts Sep 3 00:20:20 varnish2 varnishd[25355]: Child (28791) said managed to mmap 15032385536 bytes of 15032385536 Sep 3 00:20:20 varnish2 varnishd[25355]: Child (28791) said Ready No core dump seem to have survived. Any suggestion for what to look for? -- Comment: Re-opening this: It's not applicable to trunk, but it is applicable to 2.1.4 and current 2.1 (ie: soon-to-be 2.1.5). Check committed with r5646 . Haven't had a chance to track it for 2.1. No practical impact to users who don't use vcl_hit for set obj.http (which should be all), but race and assert-issues for those who now do. -- Ticket URL: Varnish The Varnish HTTP Accelerator From renato at luren.com.br Wed Dec 15 16:51:15 2010 From: renato at luren.com.br (Renato Farias) Date: Wed, 15 Dec 2010 14:51:15 -0200 Subject: [Varnish] #835: Varnish stops receiving incoming connections, but the process is still up In-Reply-To: <052.bb1fbe7734aea398aba8ae6ea4cd0c5a@varnish-cache.org> References: <043.0b306324d23af01d5f961c07ada4c811@varnish-cache.org> <052.bb1fbe7734aea398aba8ae6ea4cd0c5a@varnish-cache.org> Message-ID: Hi blamer, Can you see how many connection is opened (ESTABILISHED, TIME_WAIT, SYN_SENT), three months ago I had same issue, my server cannot open new connection after 15K. Cya Renato On Wed, Dec 15, 2010 at 11:47 AM, Varnish wrote: > #835: Varnish stops receiving incoming connections, but the process is > still up > > ----------------------+----------------------------------------------------- > Reporter: blamer | Owner: phk > Type: defect | Status: new > Priority: high | Milestone: Varnish 2.1 release > Component: varnishd | Version: 2.1.4 > Severity: major | Keywords: broken pipe, freeze, crash > > ----------------------+----------------------------------------------------- > > Comment(by blamer): > > System: > {{{ > Linux myh0stz 2.6.26-2-sparc64-smp #1 SMP Fri Sep 17 02:49:30 UTC 2010 > sparc64 GNU/Linux > 32 Cores > 8 GB RAM > 1000 MBit > Plently of disk space (> 100 gb free) > Debian Sparc > Varnish was compiled from 2.1.4 source > }}} > > Symptom: At random moments (the resources of the servers are free in those > moments), varnishd does not allow connections. It's like nothing is opened > on those sockets. It just freezes. I strace-d it (strace -p PID -f -t) > (last 500 lines): > {{{ > [pid 18629] 18:18:12 clock_gettime(CLOCK_REALTIME, {1291997892, > 856942092}) = 0 > [pid 18629] 18:18:12 poll([{fd=14, events=POLLIN}], 1, 50 > [pid 18618] 18:18:12 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:12 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:12 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:12 nanosleep({0, 100000000}, > [pid 18619] 18:18:12 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:12 clock_gettime(CLOCK_REALTIME, {1291997892, > 871675208}) = 0 > [pid 18619] 18:18:12 epoll_wait(10, > [pid 18629] 18:18:12 <... poll resumed> ) = 0 (Timeout) > [pid 18629] 18:18:12 ioctl(14, 0x8004667e, 0xf19d43bc) = 0 > [pid 18629] 18:18:12 write(4, "\355\235 \10"..., 4) = 4 > [pid 18619] 18:18:12 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, > u64=2428082451382272}}}, 100, -1) = 1 > [pid 18629] 18:18:12 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25621, NULL > > [pid 18619] 18:18:12 read(3, "\355\235 \10"..., 400) = 4 > [pid 18619] 18:18:12 epoll_ctl(10, EPOLL_CTL_MOD, 14, > {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3986497544, > u64=17121876577064321024}}) = 0 > [pid 18619] 18:18:12 epoll_wait(10, > [pid 18618] 18:18:12 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:12 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:12 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:12 nanosleep({0, 100000000}, > [pid 18619] 18:18:12 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:12 clock_gettime(CLOCK_REALTIME, {1291997892, > 972535516}) = 0 > [pid 18619] 18:18:12 epoll_wait(10, > [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:13 nanosleep({0, 100000000}, > [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, 73349872}) > = 0 > [pid 18619] 18:18:13 epoll_wait(10, > [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:13 nanosleep({0, 100000000}, > [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 174123604}) = 0 > [pid 18619] 18:18:13 epoll_wait(10, > [pid 18620] 18:18:13 <... poll resumed> ) = 0 (Timeout) > [pid 18620] 18:18:13 clock_gettime(CLOCK_REALTIME, > [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=3998392328, > u64=17172964285337305088}}}, 100, -1) = 1 > [pid 18620] 18:18:13 <... clock_gettime resumed> {1291997893, 195829832}) > = 0 > [pid 18619] 18:18:13 read(15, > [pid 18620] 18:18:13 poll([{fd=5, events=POLLIN}], 1, 1000 ...> > [pid 18619] 18:18:13 <... read resumed> "GET /wp- > content/themes/XXXXXXXX/"..., 8191) = 589 > [pid 18619] 18:18:13 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, > 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 > [pid 18624] 18:18:13 <... futex resumed> ) = 0 > [pid 18619] 18:18:13 epoll_wait(10, > [pid 18624] 18:18:13 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 > [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b3842c) = 0 > [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 197972548}) = 0 > [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 198420916}) = 0 > [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 198734648}) = 0 > [pid 18624] 18:18:13 writev(15, [{"HTTP/1.1"..., 8}, {" "..., 1}, > {"404"..., 3}, {" "..., 1}, {"Not Found"..., 9}, {"\r\n"..., 2}, {"Server: > Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"X-Pingback: > http://www.XXXXXXXX."..., 46}, {"\r\n"..., 2}, {"Expires: Wed, 11 Jan > 1984 > 05:00:0"..., 38}, {"\r\n"..., 2}, {"Last-Modified: Fri, 10 Dec 2010 1"..., > 44}, {"\r\n"..., 2}, {"Cache-Control: no-cache, must-rev"..., 51}, > {"\r\n"..., 2}, {"Pragma: no-cache"..., 16}, {"\r\n"..., 2}, {"Vary: > Accept-Encoding"..., 21}, {"\r\n"..., 2}, {"Content-Encoding: gzip"..., > 22}, {"\r\n"..., 2}, {"Content-Type: text/html; charset="..., 38}, > {"\r\n"..., 2}, {"Content-Length: 17208"..., 21}, {"\r\n"..., 2}, {"Date: > Fri, 10 Dec 2010 16:18:13 G"..., 35}, {"\r\n"..., 2}, {"X-Varnish: > 1052092382 1052083617"..., 32}, {"\r\n"..., 2}, {"Age: 1073"..., 9}, > {"\r\n"..., 2}, ...], 38) = 17700 > [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 200894048}) = 0 > [pid 18624] 18:18:13 poll([{fd=15, events=POLLIN}], 1, 50 > [pid 18612] 18:18:13 <... nanosleep resumed> NULL) = 0 > [pid 18612] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 240571564}) = 0 > [pid 18612] 18:18:13 nanosleep({1, 0}, > [pid 18617] 18:18:13 <... nanosleep resumed> {1, 0}) = 0 > [pid 18617] 18:18:13 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 > [pid 18617] 18:18:13 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], > SA_NOCLDSTOP}, 0, 4033866460) = 0 > [pid 18617] 18:18:13 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 > [pid 18617] 18:18:13 nanosleep({1, 0}, > [pid 18615] 18:18:13 <... nanosleep resumed> {1, 0}) = 0 > [pid 18615] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 250373144}) = 0 > [pid 18615] 18:18:13 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 > [pid 18615] 18:18:13 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], > SA_NOCLDSTOP}, 0, 4050643676) = 0 > [pid 18615] 18:18:13 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 > [pid 18615] 18:18:13 nanosleep({1, 0}, > [pid 18624] 18:18:13 <... poll resumed> ) = 0 (Timeout) > [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b383bc) = 0 > [pid 18624] 18:18:13 write(4, "\356R\240\10"..., 4 > [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, > u64=2428082451382272}}}, 100, -1) = 1 > [pid 18624] 18:18:13 <... write resumed> ) = 4 > [pid 18619] 18:18:13 read(3, > [pid 18624] 18:18:13 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25917, NULL > > [pid 18619] 18:18:13 <... read resumed> "\356R\240\10"..., 400) = 4 > [pid 18619] 18:18:13 epoll_ctl(10, EPOLL_CTL_MOD, 15, > {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3998392328, > u64=17172964285337305088}}) = 0 > [pid 18619] 18:18:13 epoll_wait(10, > [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:13 nanosleep({0, 100000000}, > [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 274913284}) = 0 > [pid 18619] 18:18:13 epoll_wait(10, > [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:13 nanosleep({0, 100000000}, > [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 375723208}) = 0 > [pid 18619] 18:18:13 epoll_wait(10, > [pid 18625] 18:18:13 <... read resumed> "1"..., 1) = 1 > [pid 18625] 18:18:13 read(11, "0"..., 1) = 1 > [pid 18625] 18:18:13 read(11, "6"..., 1) = 1 > [pid 18625] 18:18:13 read(11, "f"..., 1) = 1 > [pid 18625] 18:18:13 read(11, "\r"..., 1) = 1 > [pid 18625] 18:18:13 read(11, "\n"..., 1) = 1 > [pid 18625] 18:18:13 read(11, "http://www.XXXXXXXX.ro/video\ > ">Vi"..., > 4207) = 4207 > [pid 18625] 18:18:13 read(11, "\r"..., 1) = 1 > [pid 18625] 18:18:13 read(11, "\n"..., 1) = 1 > [pid 18625] 18:18:13 read(11, > [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=3986497544, > u64=17121876577064321024}}}, 100, -1) = 1 > [pid 18619] 18:18:13 read(14, "GET /img/wp-content/uploads/2010/"..., > 8191) = 703 > [pid 18619] 18:18:13 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, > 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 > [pid 18629] 18:18:13 <... futex resumed> ) = 0 > [pid 18619] 18:18:13 epoll_wait(10, > [pid 18629] 18:18:13 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 > [pid 18629] 18:18:13 ioctl(14, 0x8004667e, 0xf19d442c) = 0 > [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 471524104}) = 0 > [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 472037492}) = 0 > [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 472340392}) = 0 > [pid 18629] 18:18:13 writev(14, [{"HTTP/1.1"..., 8}, {" "..., 1}, > {"200"..., 3}, {" "..., 1}, {"OK"..., 2}, {"\r\n"..., 2}, {"Server: > Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"Content-Disposition: inline; > file"..., 71}, {"\r\n"..., 2}, {"Last-Modified: Fri, 10 Dec 2010 1"..., > 44}, {"\r\n"..., 2}, {"Content-Type: image/jpeg"..., 24}, {"\r\n"..., 2}, > {"Content-Length: 34330"..., 21}, {"\r\n"..., 2}, {"Date: Fri, 10 Dec 2010 > 16:18:13 G"..., 35}, {"\r\n"..., 2}, {"X-Varnish: 1052092383 > 1052054539"..., 32}, {"\r\n"..., 2}, {"Age: 4457"..., 9}, {"\r\n"..., 2}, > {"Via: 1.1 varnish"..., 16}, {"\r\n"..., 2}, {"Connection: keep-alive"..., > 22}, {"\r\n"..., 2}, {"\r\n"..., 2}, > > {"\377\330\377\340\0\20JFIF\0\1\1\1\0\226\0\226\0\0\377\333\0C\0\10\6\6\7\6\5\10\7"..., > 34330}], 28) = 34668 > [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, > [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 > [pid 18629] 18:18:13 <... clock_gettime resumed> {1291997893, 475416560}) > = 0 > [pid 18618] 18:18:13 write(8, "R"..., 1 > [pid 18629] 18:18:13 poll([{fd=14, events=POLLIN}], 1, 50 > [pid 18618] 18:18:13 <... write resumed> ) = 1 > [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:13 nanosleep({0, 100000000}, > [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 476985560}) = 0 > [pid 18619] 18:18:13 epoll_wait(10, {{EPOLLIN, {u32=3998392328, > u64=17172964285337305088}}}, 100, -1) = 1 > [pid 18619] 18:18:13 read(15, "HEAD / HTTP/1.1\r\nX-Forwarded-For:"..., > 8191) = 102 > [pid 18619] 18:18:13 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, > 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 > [pid 18624] 18:18:13 <... futex resumed> ) = 0 > [pid 18619] 18:18:13 epoll_wait(10, > [pid 18624] 18:18:13 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 > [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b3842c) = 0 > [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 495145448}) = 0 > [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 495574520}) = 0 > [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 495897344}) = 0 > [pid 18624] 18:18:13 writev(15, [{"HTTP/1.1"..., 8}, {" "..., 1}, > {"200"..., 3}, {" "..., 1}, {"OK"..., 2}, {"\r\n"..., 2}, {"Server: > Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"Last-Modified: Tue, 03 Aug > 2010 0"..., 44}, {"\r\n"..., 2}, {"ETag: \"40125-0-48ce652c74380\""..., > 29}, {"\r\n"..., 2}, {"Vary: Accept-Encoding"..., 21}, {"\r\n"..., 2}, > {"Content-Type: text/html"..., 23}, {"\r\n"..., 2}, {"Content-Length: > 0"..., 17}, {"\r\n"..., 2}, {"Date: Fri, 10 Dec 2010 16:18:13 G"..., 35}, > {"\r\n"..., 2}, {"X-Varnish: 1052092384 1052090630"..., 32}, {"\r\n"..., > 2}, {"Age: 236"..., 8}, {"\r\n"..., 2}, {"Via: 1.1 varnish"..., 16}, > {"\r\n"..., 2}, {"Connection: keep-alive"..., 22}, {"\r\n"..., 2}, > {"\r\n"..., 2}], 29) = 313 > [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 497661528}) = 0 > [pid 18624] 18:18:13 poll([{fd=15, events=POLLIN}], 1, 50 > [pid 18629] 18:18:13 <... poll resumed> ) = 0 (Timeout) > [pid 18629] 18:18:13 ioctl(14, 0x8004667e, 0xf19d43bc) = 0 > [pid 18629] 18:18:13 write(4, "\355\235 \10"..., 4) = 4 > [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, > u64=2428082451382272}}}, 100, -1) = 1 > [pid 18629] 18:18:13 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25623, NULL > > [pid 18619] 18:18:13 read(3, "\355\235 \10"..., 400) = 4 > [pid 18619] 18:18:13 epoll_ctl(10, EPOLL_CTL_MOD, 14, > {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3986497544, > u64=17121876577064321024}}) = 0 > [pid 18619] 18:18:13 epoll_wait(10, > [pid 18624] 18:18:13 <... poll resumed> ) = 0 (Timeout) > [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b383bc) = 0 > [pid 18624] 18:18:13 write(4, "\356R\240\10"..., 4 > [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, > u64=2428082451382272}}}, 100, -1) = 1 > [pid 18624] 18:18:13 <... write resumed> ) = 4 > [pid 18619] 18:18:13 read(3, > [pid 18624] 18:18:13 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25919, NULL > > [pid 18619] 18:18:13 <... read resumed> "\356R\240\10"..., 400) = 4 > [pid 18619] 18:18:13 epoll_ctl(10, EPOLL_CTL_MOD, 15, > {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3998392328, > u64=17172964285337305088}}) = 0 > [pid 18619] 18:18:13 epoll_wait(10, > [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:13 nanosleep({0, 100000000}, > [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 577819076}) = 0 > [pid 18619] 18:18:13 epoll_wait(10, > [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:13 nanosleep({0, 100000000}, > [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 678596784}) = 0 > [pid 18619] 18:18:13 epoll_wait(10, {{EPOLLIN, {u32=3986497544, > u64=17121876577064321024}}}, 100, -1) = 1 > [pid 18619] 18:18:13 read(14, "GET /stiri HTTP/1.1\r\nUser-Agent: "..., > 8191) = 773 > [pid 18619] 18:18:13 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, > 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 > [pid 18629] 18:18:13 <... futex resumed> ) = 0 > [pid 18619] 18:18:13 epoll_wait(10, > [pid 18629] 18:18:13 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 > [pid 18629] 18:18:13 ioctl(14, 0x8004667e, 0xf19d442c) = 0 > [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 738793608}) = 0 > [pid 18629] 18:18:13 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25625, NULL > > [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:13 nanosleep({0, 100000000}, > [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 779390960}) = 0 > [pid 18619] 18:18:13 epoll_wait(10, > [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:13 nanosleep({0, 100000000}, > [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 880271512}) = 0 > [pid 18619] 18:18:13 epoll_wait(10, > [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 > [pid 18620] 18:18:13 <... poll resumed> ) = 1 ([{fd=5, revents=POLLIN}]) > [pid 18618] 18:18:13 write(8, "R"..., 1 > [pid 18620] 18:18:13 clock_gettime(CLOCK_REALTIME, > [pid 18618] 18:18:13 <... write resumed> ) = 1 > [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:13 nanosleep({0, 100000000}, > [pid 18619] 18:18:13 read(7, > [pid 18620] 18:18:13 <... clock_gettime resumed> {1291997893, 980448784}) > = 0 > [pid 18619] 18:18:13 <... read resumed> "R"..., 1) = 1 > [pid 18620] 18:18:13 accept(5, > [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, > [pid 18620] 18:18:13 <... accept resumed> {sa_family=AF_INET, > sin_port=htons(50619), sin_addr=inet_addr("x.y.z.36")}, [16]) = 17 > [pid 18619] 18:18:13 <... clock_gettime resumed> {1291997893, 981728996}) > = 0 > [pid 18620] 18:18:13 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, > 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1} > [pid 18619] 18:18:13 epoll_wait(10, > [pid 18620] 18:18:13 <... futex resumed> ) = 1 > [pid 18624] 18:18:13 <... futex resumed> ) = 0 > [pid 18620] 18:18:13 poll([{fd=5, events=POLLIN}], 1, 1000 ...> > [pid 18624] 18:18:13 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 > [pid 18624] 18:18:13 ioctl(17, 0x8004667e, 0xf7b3842c) = 0 > [pid 18624] 18:18:13 poll([{fd=17, events=POLLIN}], 1, 50) = 1 ([{fd=17, > revents=POLLIN}]) > [pid 18624] 18:18:13 read(17, "GET /wp-content/themes/XXXXXXXX/"..., 8191) > = 427 > [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 984534164}) = 0 > [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 984991888}) = 0 > [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 985292996}) = 0 > [pid 18624] 18:18:13 writev(17, [{"HTTP/1.1"..., 8}, {" "..., 1}, > {"200"..., 3}, {" "..., 1}, {"OK"..., 2}, {"\r\n"..., 2}, {"Server: > Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"Last-Modified: Tue, 16 Feb > 2010 0"..., 44}, {"\r\n"..., 2}, {"ETag: \"46853-65c-47fb4c59bb740\""..., > 31}, {"\r\n"..., 2}, {"Content-Type: image/gif"..., 23}, {"\r\n"..., 2}, > {"Content-Length: 1628"..., 20}, {"\r\n"..., 2}, {"Date: Fri, 10 Dec 2010 > 16:18:13 G"..., 35}, {"\r\n"..., 2}, {"X-Varnish: 1052092386 > 1052083384"..., 32}, {"\r\n"..., 2}, {"Age: 1100"..., 9}, {"\r\n"..., 2}, > {"Via: 1.1 varnish"..., 16}, {"\r\n"..., 2}, {"Connection: keep-alive"..., > 22}, {"\r\n"..., 2}, {"\r\n"..., 2}, > > {"GIF89a\34\0$\0\367\0\0\"\37\210w\344\363\235\237\314\36\271\336XZ\250\0\215\303\307\361"..., > 1628}], 28) = 1924 > [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, > 987145288}) = 0 > [pid 18624] 18:18:13 poll([{fd=17, events=POLLIN}], 1, 50) = 0 (Timeout) > [pid 18624] 18:18:14 ioctl(17, 0x8004667e, 0xf7b383bc) = 0 > [pid 18624] 18:18:14 write(4, "\367\244\200\10"..., 4 > [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, > u64=2428082451382272}}}, 100, -1) = 1 > [pid 18624] 18:18:14 <... write resumed> ) = 4 > [pid 18619] 18:18:14 read(3, > [pid 18624] 18:18:14 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25921, NULL > > [pid 18619] 18:18:14 <... read resumed> "\367\244\200\10"..., 400) = 4 > [pid 18619] 18:18:14 epoll_ctl(10, EPOLL_CTL_ADD, 17, > {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=4154753032, > u64=17844528395396841472}}) = 0 > [pid 18619] 18:18:14 epoll_wait(10, {{EPOLLIN, {u32=4154753032, > u64=17844528395396841472}}}, 100, -1) = 1 > [pid 18619] 18:18:14 read(17, "GET /stiri HTTP/1.1\r\nUser-Agent: "..., > 8191) = 773 > [pid 18619] 18:18:14 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, > 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 > [pid 18629] 18:18:14 <... futex resumed> ) = 0 > [pid 18619] 18:18:14 epoll_wait(10, > [pid 18629] 18:18:14 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 > [pid 18629] 18:18:14 ioctl(17, 0x8004667e, 0xf19d442c) = 0 > [pid 18629] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 47222624}) > = 0 > [pid 18629] 18:18:14 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25627, NULL > > [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:14 nanosleep({0, 100000000}, > [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, 82163424}) > = 0 > [pid 18619] 18:18:14 epoll_wait(10, > [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:14 nanosleep({0, 100000000}, > [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, > 183055080}) = 0 > [pid 18619] 18:18:14 epoll_wait(10, > [pid 18612] 18:18:14 <... nanosleep resumed> NULL) = 0 > [pid 18612] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, > 241243672}) = 0 > [pid 18612] 18:18:14 nanosleep({1, 0}, > [pid 18617] 18:18:14 <... nanosleep resumed> {1, 0}) = 0 > [pid 18617] 18:18:14 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 > [pid 18617] 18:18:14 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], > SA_NOCLDSTOP}, 0, 4033866460) = 0 > [pid 18617] 18:18:14 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 > [pid 18617] 18:18:14 nanosleep({1, 0}, > [pid 18615] 18:18:14 <... nanosleep resumed> {1, 0}) = 0 > [pid 18615] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, > 252058036}) = 0 > [pid 18615] 18:18:14 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 > [pid 18615] 18:18:14 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], > SA_NOCLDSTOP}, 0, 4050643676) = 0 > [pid 18615] 18:18:14 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 > [pid 18615] 18:18:14 nanosleep({1, 0}, > [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:14 nanosleep({0, 100000000}, > [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, > 283774800}) = 0 > [pid 18619] 18:18:14 epoll_wait(10, > [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:14 nanosleep({0, 100000000}, > [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, > 384582084}) = 0 > [pid 18619] 18:18:14 epoll_wait(10, > [pid 18620] 18:18:14 <... poll resumed> ) = 1 ([{fd=5, revents=POLLIN}]) > [pid 18620] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, > 419035140}) = 0 > [pid 18620] 18:18:14 accept(5, {sa_family=AF_INET, sin_port=htons(50630), > sin_addr=inet_addr("x.y.z.36")}, [16]) = 18 > [pid 18620] 18:18:14 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, > 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 > [pid 18624] 18:18:14 <... futex resumed> ) = 0 > [pid 18620] 18:18:14 poll([{fd=5, events=POLLIN}], 1, 1000 ...> > [pid 18624] 18:18:14 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 > [pid 18624] 18:18:14 ioctl(18, 0x8004667e, 0xf7b3842c) = 0 > [pid 18624] 18:18:14 poll([{fd=18, events=POLLIN}], 1, 50) = 1 ([{fd=18, > revents=POLLIN}]) > [pid 18624] 18:18:14 read(18, "GET /stiri HTTP/1.1\r\nUser-Agent: "..., > 8191) = 773 > [pid 18624] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, > 421629696}) = 0 > [pid 18624] 18:18:14 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25923, NULL > > [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:14 nanosleep({0, 100000000}, > [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, > 485429080}) = 0 > [pid 18619] 18:18:14 epoll_wait(10, > [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:14 nanosleep({0, 100000000}, > [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, > 586203652}) = 0 > [pid 18619] 18:18:14 epoll_wait(10, > [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:14 nanosleep({0, 100000000}, > [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, > 687050580}) = 0 > [pid 18619] 18:18:14 epoll_wait(10, > [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:14 nanosleep({0, 100000000}, > [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, > 787847056}) = 0 > [pid 18619] 18:18:14 epoll_wait(10, > [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:14 nanosleep({0, 100000000}, > [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, > 888672272}) = 0 > [pid 18619] 18:18:14 epoll_wait(10, > [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:14 nanosleep({0, 100000000}, > [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, > 989458320}) = 0 > [pid 18619] 18:18:14 epoll_wait(10, > [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:15 nanosleep({0, 100000000}, > [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, 90264196}) > = 0 > [pid 18619] 18:18:15 epoll_wait(10, > [pid 18611] 18:18:15 <... poll resumed> ) = 1 ([{fd=6, revents=POLLIN}]) > [pid 18611] 18:18:15 read(6, "ping\n"..., 8191) = 5 > [pid 18611] 18:18:15 time(NULL) = 1291997895 > [pid 18611] 18:18:15 writev(9, [{"200 19 \n"..., 13}, {"PONG > 1291997895 1.0"..., 19}, {"\n"..., 1}], 3) = 33 > [pid 18611] 18:18:15 poll([{fd=6, events=POLLIN}], 1, -1 > [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:15 nanosleep({0, 100000000}, > [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, > 191048264}) = 0 > [pid 18619] 18:18:15 epoll_wait(10, > [pid 18612] 18:18:15 <... nanosleep resumed> NULL) = 0 > [pid 18612] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, > 241947668}) = 0 > [pid 18612] 18:18:15 nanosleep({1, 0}, > [pid 18617] 18:18:15 <... nanosleep resumed> {1, 0}) = 0 > [pid 18617] 18:18:15 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 > [pid 18617] 18:18:15 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], > SA_NOCLDSTOP}, 0, 4033866460) = 0 > [pid 18617] 18:18:15 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 > [pid 18617] 18:18:15 nanosleep({1, 0}, > [pid 18615] 18:18:15 <... nanosleep resumed> {1, 0}) = 0 > [pid 18615] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, > 253632384}) = 0 > [pid 18615] 18:18:15 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 > [pid 18615] 18:18:15 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], > SA_NOCLDSTOP}, 0, 4050643676) = 0 > [pid 18615] 18:18:15 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 > [pid 18615] 18:18:15 nanosleep({1, 0}, > [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:15 nanosleep({0, 100000000}, > [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, > 291949320}) = 0 > [pid 18619] 18:18:15 epoll_wait(10, > [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:15 nanosleep({0, 100000000}, > [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, > 392767872}) = 0 > [pid 18619] 18:18:15 epoll_wait(10, > [pid 18620] 18:18:15 <... poll resumed> ) = 0 (Timeout) > [pid 18620] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, > 423866840}) = 0 > [pid 18620] 18:18:15 poll([{fd=5, events=POLLIN}], 1, 1000 ...> > [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:15 nanosleep({0, 100000000}, > [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, > 493554528}) = 0 > [pid 18619] 18:18:15 epoll_wait(10, > [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:15 nanosleep({0, 100000000}, > [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, > 594343716}) = 0 > [pid 18619] 18:18:15 epoll_wait(10, > [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:15 nanosleep({0, 100000000}, > [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, > 695131520}) = 0 > [pid 18619] 18:18:15 epoll_wait(10, > [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:15 nanosleep({0, 100000000}, > [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, > 795928848}) = 0 > [pid 18619] 18:18:15 epoll_wait(10, > [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:15 nanosleep({0, 100000000}, > [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, > 896786468}) = 0 > [pid 18619] 18:18:15 epoll_wait(10, > [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:15 nanosleep({0, 100000000}, > [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, > 997543276}) = 0 > [pid 18619] 18:18:15 epoll_wait(10, > [pid 18618] 18:18:16 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:16 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:16 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:16 nanosleep({0, 100000000}, > [pid 18619] 18:18:16 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, 98361332}) > = 0 > [pid 18619] 18:18:16 epoll_wait(10, > [pid 18618] 18:18:16 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:16 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:16 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:16 nanosleep({0, 100000000}, > [pid 18619] 18:18:16 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, > 199182492}) = 0 > [pid 18619] 18:18:16 epoll_wait(10, > [pid 18612] 18:18:16 <... nanosleep resumed> NULL) = 0 > [pid 18612] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, > 242623312}) = 0 > [pid 18612] 18:18:16 nanosleep({1, 0}, > [pid 18617] 18:18:16 <... nanosleep resumed> {1, 0}) = 0 > [pid 18617] 18:18:16 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 > [pid 18617] 18:18:16 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], > SA_NOCLDSTOP}, 0, 4033866460) = 0 > [pid 18617] 18:18:16 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 > [pid 18617] 18:18:16 nanosleep({1, 0}, > [pid 18615] 18:18:16 <... nanosleep resumed> {1, 0}) = 0 > [pid 18615] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, > 255275216}) = 0 > [pid 18615] 18:18:16 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 > [pid 18615] 18:18:16 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], > SA_NOCLDSTOP}, 0, 4050643676) = 0 > [pid 18615] 18:18:16 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 > [pid 18615] 18:18:16 nanosleep({1, 0}, > [pid 18618] 18:18:16 <... nanosleep resumed> NULL) = 0 > [pid 18618] 18:18:16 write(8, "R"..., 1) = 1 > [pid 18619] 18:18:16 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, > u64=2452254527324160}}}, 100, -1) = 1 > [pid 18618] 18:18:16 nanosleep({0, 100000000}, > [pid 18619] 18:18:16 read(7, "R"..., 1) = 1 > [pid 18619] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, > 299975276}) = 0 > [pid 18619] 18:18:16 epoll_wait(10, > [pid 18620] 18:18:16 <... poll resumed> ) = 1 ([{fd=5, revents=POLLIN}]) > [pid 18620] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, > 315826092}) = 0 > [pid 18620] 18:18:16 accept(5, {sa_family=AF_INET, sin_port=htons(42033), > sin_addr=inet_addr("x.y.z.86")}, [16]) = 19 > [pid 18620] 18:18:16 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, > 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 > [pid 18629] 18:18:16 <... futex resumed> ) = 0 > [pid 18620] 18:18:16 poll([{fd=5, events=POLLIN}], 1, 1000 ...> > [pid 18629] 18:18:16 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 > [pid 18629] 18:18:16 ioctl(19, 0x8004667e, 0xf19d442c) = 0 > [pid 18629] 18:18:16 poll([{fd=19, events=POLLIN}], 1, 50) = 1 ([{fd=19, > revents=POLLIN}]) > [pid 18629] 18:18:16 read(19, "GET / HTTP/1.1\r\nHost: www.Xspo"..., 8191) > = 99 > [pid 18629] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, > 318403888}) = 0 > [pid 18629] 18:18:16 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25629, NULL > > [pid 18611] 18:18:16 <... poll resumed> ) = 1 ([{fd=6, revents=POLLHUP}]) > [pid 18611] 18:18:16 close(6) = 0 > [pid 18611] 18:18:16 close(9) = 0 > [pid 18611] 18:18:16 close(5) = 0 > [pid 18611] 18:18:16 write(1, "Child dies"..., 10) = -1 EPIPE (Broken > pipe) > [pid 18611] 18:18:16 --- SIGPIPE (Broken pipe) @ 0 (0) --- > [pid 18611] 18:18:16 exit_group(1) = ? > Process 18611 detached > [pid 18612] 18:18:16 <... nanosleep resumed> 0) = ? ERESTART_RESTARTBLOCK > (To be restarted) > [pid 18614] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be > restarted) > [pid 18615] 18:18:16 <... nanosleep resumed> 0xf16fec68) = ? > ERESTART_RESTARTBLOCK (To be restarted) > [pid 18616] 18:18:16 <... nanosleep resumed> 0) = ? ERESTART_RESTARTBLOCK > (To be restarted) > [pid 18617] 18:18:16 <... nanosleep resumed> 0xf06fec68) = ? > ERESTART_RESTARTBLOCK (To be restarted) > [pid 18618] 18:18:16 <... nanosleep resumed> 0) = ? ERESTART_RESTARTBLOCK > (To be restarted) > [pid 18619] 18:18:16 <... epoll_wait resumed> ef6feb20, 100, -1) = -1 > EINTR (Interrupted system call) > [pid 18620] 18:18:16 <... poll resumed> ) = 1 ([{fd=5, revents=POLLNVAL}]) > [pid 18622] 18:18:16 <... read resumed> 0xf7b59108, 8191) = -1 EINTR > (Interrupted system call) > [pid 18623] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be > restarted) > [pid 18624] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be > restarted) > [pid 18625] 18:18:16 <... read resumed> 0xf7b2839a, 1) = -1 EINTR > (Interrupted system call) > [pid 18626] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be > restarted) > [pid 18627] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be > restarted) > [pid 18628] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be > restarted) > [pid 18629] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be > restarted) > [pid 18630] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be > restarted) > Process 18611 detached > Process 18984 detached > }}} > All I can see is the SIGPIPE and the ERESTARTSYS (those two things do not > appear until the freeze). > > Varnish default conf: -f /srv/varnish/conf/XXXXXXXX.vcl -s malloc,1024M -a > 0.0.0.0:8080 > > VCL: > {{{ > backend default { > .host = "XX.YY.ZZ.WW"; > .port = "80"; > } > > > sub vcl_recv { > if (req.url ~ "cgi-bin") { > return (pipe); > } > > if (req.http.Accept-Encoding) { > if (req.http.Accept-Encoding ~ "gzip") { > set req.http.Accept-Encoding = "gzip"; > } elsif (req.http.Accept-Encoding ~ "deflate") { > set req.http.Accept-Encoding = "deflate"; > } else { > # unkown algorithm > remove req.http.Accept-Encoding; > } > } > > if (req.http.Accept-Language) { > remove req.http.Accept-Language; > } > > if (req.http.User-Agent) { > remove req.http.User-Agent; > } > > if (req.http.Host ~ "live.XXXXXXXX.ro" || req.http.Host ~ > "live2.XXXXXXXX.ro") { > return (pipe); > } > > if (req.request != "GET" && req.request != "HEAD") { > return (pass); > } > > if (req.url ~ "\.(png|gif|jpg|swf)" || req.url ~ "/img/" || req.url ~ > "\.(js|css)") { > > > remove req.http.cookie; > return (lookup); > } > > if ( > !(req.url ~ "wp-(login|admin)") && > !(req.http.Cookie ~ "wordpress_logged_in") > ) { > remove req.http.cookie; > return (lookup); > } else { > return (pass); > } > > > > > if (req.http.Cookie ~ "wordpress_logged_in") { > return (pass); > } else { > return (lookup); > } > } > > sub vcl_fetch { > > if (req.http.Host ~ "live.XXXXXXX.ro" || req.http.Host ~ > "live2.XXXXXXXX.ro") { > return(pass); > } > > if (beresp.http.Content-Type ~ "text/html") { > //set beresp.http.Cache-Control = "no-store, no-cache, > must-revalidate, post-check=0, pre-check=0"; > //set beresp.http.Pragma = "no-cache"; > } > > if (!(req.url ~ "wp-(login|admin)")) { > #remove beresp.http.set-cookie; > } > > if (req.url ~ "\.(png|gif|jpg|swf)" || req.url ~ "/img/" || > beresp.http.Content-Type ~ "javascript" || beresp.http.Content-Type ~ > "css") { > remove beresp.http.set-cookie; > //log "request-ul se preteaza: " beresp.http.Content-Type; > set beresp.ttl = 7200s; > return (deliver); > } else { > set beresp.ttl = 240s; > } > > } > }}} > I cannot link any request to the crash event. > > -- > Ticket URL: > Varnish > The Varnish HTTP Accelerator > > _______________________________________________ > varnish-bugs mailing list > varnish-bugs at varnish-cache.org > http://www.varnish-cache.org/lists/mailman/listinfo/varnish-bugs > -- Att, Renato Farias -------------- next part -------------- An HTML attachment was scrubbed... URL: From advertising at freegsm.ro Thu Dec 16 07:15:15 2010 From: advertising at freegsm.ro (Mihai Valentin) Date: Thu, 16 Dec 2010 09:15:15 +0200 Subject: [Varnish] #835: Varnish stops receiving incoming connections, but the process is still up In-Reply-To: References: <043.0b306324d23af01d5f961c07ada4c811@varnish-cache.org> <052.bb1fbe7734aea398aba8ae6ea4cd0c5a@varnish-cache.org> Message-ID: Hi Renato, Before it crashes, the number of TCP connections is really small. ~30 connections. It has nothing to do with the traffic volume. On Wed, Dec 15, 2010 at 6:51 PM, Renato Farias wrote: > Hi blamer, > > Can you see how many connection is opened (ESTABILISHED, TIME_WAIT, > SYN_SENT), three months ago I had same issue, my server cannot open new > connection after 15K. > > Cya > > Renato > > On Wed, Dec 15, 2010 at 11:47 AM, Varnish wrote: > >> #835: Varnish stops receiving incoming connections, but the process is >> still up >> >> ----------------------+----------------------------------------------------- >> Reporter: blamer | Owner: phk >> Type: defect | Status: new >> Priority: high | Milestone: Varnish 2.1 release >> Component: varnishd | Version: 2.1.4 >> Severity: major | Keywords: broken pipe, freeze, crash >> >> ----------------------+----------------------------------------------------- >> >> Comment(by blamer): >> >> System: >> {{{ >> Linux myh0stz 2.6.26-2-sparc64-smp #1 SMP Fri Sep 17 02:49:30 UTC 2010 >> sparc64 GNU/Linux >> 32 Cores >> 8 GB RAM >> 1000 MBit >> Plently of disk space (> 100 gb free) >> Debian Sparc >> Varnish was compiled from 2.1.4 source >> }}} >> >> Symptom: At random moments (the resources of the servers are free in >> those >> moments), varnishd does not allow connections. It's like nothing is >> opened >> on those sockets. It just freezes. I strace-d it (strace -p PID -f -t) >> (last 500 lines): >> {{{ >> [pid 18629] 18:18:12 clock_gettime(CLOCK_REALTIME, {1291997892, >> 856942092}) = 0 >> [pid 18629] 18:18:12 poll([{fd=14, events=POLLIN}], 1, 50 > ...> >> [pid 18618] 18:18:12 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:12 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:12 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:12 nanosleep({0, 100000000}, >> [pid 18619] 18:18:12 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:12 clock_gettime(CLOCK_REALTIME, {1291997892, >> 871675208}) = 0 >> [pid 18619] 18:18:12 epoll_wait(10, >> [pid 18629] 18:18:12 <... poll resumed> ) = 0 (Timeout) >> [pid 18629] 18:18:12 ioctl(14, 0x8004667e, 0xf19d43bc) = 0 >> [pid 18629] 18:18:12 write(4, "\355\235 \10"..., 4) = 4 >> [pid 18619] 18:18:12 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, >> u64=2428082451382272}}}, 100, -1) = 1 >> [pid 18629] 18:18:12 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25621, NULL >> >> [pid 18619] 18:18:12 read(3, "\355\235 \10"..., 400) = 4 >> [pid 18619] 18:18:12 epoll_ctl(10, EPOLL_CTL_MOD, 14, >> {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3986497544, >> u64=17121876577064321024}}) = 0 >> [pid 18619] 18:18:12 epoll_wait(10, >> [pid 18618] 18:18:12 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:12 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:12 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:12 nanosleep({0, 100000000}, >> [pid 18619] 18:18:12 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:12 clock_gettime(CLOCK_REALTIME, {1291997892, >> 972535516}) = 0 >> [pid 18619] 18:18:12 epoll_wait(10, >> [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:13 nanosleep({0, 100000000}, >> [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 73349872}) >> = 0 >> [pid 18619] 18:18:13 epoll_wait(10, >> [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:13 nanosleep({0, 100000000}, >> [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 174123604}) = 0 >> [pid 18619] 18:18:13 epoll_wait(10, >> [pid 18620] 18:18:13 <... poll resumed> ) = 0 (Timeout) >> [pid 18620] 18:18:13 clock_gettime(CLOCK_REALTIME, >> [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=3998392328, >> u64=17172964285337305088}}}, 100, -1) = 1 >> [pid 18620] 18:18:13 <... clock_gettime resumed> {1291997893, 195829832}) >> = 0 >> [pid 18619] 18:18:13 read(15, >> [pid 18620] 18:18:13 poll([{fd=5, events=POLLIN}], 1, 1000 > ...> >> [pid 18619] 18:18:13 <... read resumed> "GET /wp- >> content/themes/XXXXXXXX/"..., 8191) = 589 >> [pid 18619] 18:18:13 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, >> 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 >> [pid 18624] 18:18:13 <... futex resumed> ) = 0 >> [pid 18619] 18:18:13 epoll_wait(10, >> [pid 18624] 18:18:13 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 >> [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b3842c) = 0 >> [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 197972548}) = 0 >> [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 198420916}) = 0 >> [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 198734648}) = 0 >> [pid 18624] 18:18:13 writev(15, [{"HTTP/1.1"..., 8}, {" "..., 1}, >> {"404"..., 3}, {" "..., 1}, {"Not Found"..., 9}, {"\r\n"..., 2}, >> {"Server: >> Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"X-Pingback: >> http://www.XXXXXXXX."..., 46}, {"\r\n"..., 2}, {"Expires: Wed, 11 Jan >> 1984 >> 05:00:0"..., 38}, {"\r\n"..., 2}, {"Last-Modified: Fri, 10 Dec 2010 >> 1"..., >> 44}, {"\r\n"..., 2}, {"Cache-Control: no-cache, must-rev"..., 51}, >> {"\r\n"..., 2}, {"Pragma: no-cache"..., 16}, {"\r\n"..., 2}, {"Vary: >> Accept-Encoding"..., 21}, {"\r\n"..., 2}, {"Content-Encoding: gzip"..., >> 22}, {"\r\n"..., 2}, {"Content-Type: text/html; charset="..., 38}, >> {"\r\n"..., 2}, {"Content-Length: 17208"..., 21}, {"\r\n"..., 2}, {"Date: >> Fri, 10 Dec 2010 16:18:13 G"..., 35}, {"\r\n"..., 2}, {"X-Varnish: >> 1052092382 1052083617"..., 32}, {"\r\n"..., 2}, {"Age: 1073"..., 9}, >> {"\r\n"..., 2}, ...], 38) = 17700 >> [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 200894048}) = 0 >> [pid 18624] 18:18:13 poll([{fd=15, events=POLLIN}], 1, 50 > ...> >> [pid 18612] 18:18:13 <... nanosleep resumed> NULL) = 0 >> [pid 18612] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 240571564}) = 0 >> [pid 18612] 18:18:13 nanosleep({1, 0}, >> [pid 18617] 18:18:13 <... nanosleep resumed> {1, 0}) = 0 >> [pid 18617] 18:18:13 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 >> [pid 18617] 18:18:13 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], >> SA_NOCLDSTOP}, 0, 4033866460) = 0 >> [pid 18617] 18:18:13 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 >> [pid 18617] 18:18:13 nanosleep({1, 0}, >> [pid 18615] 18:18:13 <... nanosleep resumed> {1, 0}) = 0 >> [pid 18615] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 250373144}) = 0 >> [pid 18615] 18:18:13 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 >> [pid 18615] 18:18:13 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], >> SA_NOCLDSTOP}, 0, 4050643676) = 0 >> [pid 18615] 18:18:13 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 >> [pid 18615] 18:18:13 nanosleep({1, 0}, >> [pid 18624] 18:18:13 <... poll resumed> ) = 0 (Timeout) >> [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b383bc) = 0 >> [pid 18624] 18:18:13 write(4, "\356R\240\10"..., 4 >> [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, >> u64=2428082451382272}}}, 100, -1) = 1 >> [pid 18624] 18:18:13 <... write resumed> ) = 4 >> [pid 18619] 18:18:13 read(3, >> [pid 18624] 18:18:13 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25917, NULL >> >> [pid 18619] 18:18:13 <... read resumed> "\356R\240\10"..., 400) = 4 >> [pid 18619] 18:18:13 epoll_ctl(10, EPOLL_CTL_MOD, 15, >> {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3998392328, >> u64=17172964285337305088}}) = 0 >> [pid 18619] 18:18:13 epoll_wait(10, >> [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:13 nanosleep({0, 100000000}, >> [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 274913284}) = 0 >> [pid 18619] 18:18:13 epoll_wait(10, >> [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:13 nanosleep({0, 100000000}, >> [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 375723208}) = 0 >> [pid 18619] 18:18:13 epoll_wait(10, >> [pid 18625] 18:18:13 <... read resumed> "1"..., 1) = 1 >> [pid 18625] 18:18:13 read(11, "0"..., 1) = 1 >> [pid 18625] 18:18:13 read(11, "6"..., 1) = 1 >> [pid 18625] 18:18:13 read(11, "f"..., 1) = 1 >> [pid 18625] 18:18:13 read(11, "\r"..., 1) = 1 >> [pid 18625] 18:18:13 read(11, "\n"..., 1) = 1 >> [pid 18625] 18:18:13 read(11, "http://www.XXXXXXXX.ro/video\ >> ">Vi"..., >> 4207) = 4207 >> [pid 18625] 18:18:13 read(11, "\r"..., 1) = 1 >> [pid 18625] 18:18:13 read(11, "\n"..., 1) = 1 >> [pid 18625] 18:18:13 read(11, >> [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=3986497544, >> u64=17121876577064321024}}}, 100, -1) = 1 >> [pid 18619] 18:18:13 read(14, "GET /img/wp-content/uploads/2010/"..., >> 8191) = 703 >> [pid 18619] 18:18:13 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, >> 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 >> [pid 18629] 18:18:13 <... futex resumed> ) = 0 >> [pid 18619] 18:18:13 epoll_wait(10, >> [pid 18629] 18:18:13 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 >> [pid 18629] 18:18:13 ioctl(14, 0x8004667e, 0xf19d442c) = 0 >> [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 471524104}) = 0 >> [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 472037492}) = 0 >> [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 472340392}) = 0 >> [pid 18629] 18:18:13 writev(14, [{"HTTP/1.1"..., 8}, {" "..., 1}, >> {"200"..., 3}, {" "..., 1}, {"OK"..., 2}, {"\r\n"..., 2}, {"Server: >> Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"Content-Disposition: >> inline; >> file"..., 71}, {"\r\n"..., 2}, {"Last-Modified: Fri, 10 Dec 2010 1"..., >> 44}, {"\r\n"..., 2}, {"Content-Type: image/jpeg"..., 24}, {"\r\n"..., 2}, >> {"Content-Length: 34330"..., 21}, {"\r\n"..., 2}, {"Date: Fri, 10 Dec >> 2010 >> 16:18:13 G"..., 35}, {"\r\n"..., 2}, {"X-Varnish: 1052092383 >> 1052054539"..., 32}, {"\r\n"..., 2}, {"Age: 4457"..., 9}, {"\r\n"..., 2}, >> {"Via: 1.1 varnish"..., 16}, {"\r\n"..., 2}, {"Connection: >> keep-alive"..., >> 22}, {"\r\n"..., 2}, {"\r\n"..., 2}, >> >> {"\377\330\377\340\0\20JFIF\0\1\1\1\0\226\0\226\0\0\377\333\0C\0\10\6\6\7\6\5\10\7"..., >> 34330}], 28) = 34668 >> [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, >> [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 >> [pid 18629] 18:18:13 <... clock_gettime resumed> {1291997893, 475416560}) >> = 0 >> [pid 18618] 18:18:13 write(8, "R"..., 1 >> [pid 18629] 18:18:13 poll([{fd=14, events=POLLIN}], 1, 50 > ...> >> [pid 18618] 18:18:13 <... write resumed> ) = 1 >> [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:13 nanosleep({0, 100000000}, >> [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 476985560}) = 0 >> [pid 18619] 18:18:13 epoll_wait(10, {{EPOLLIN, {u32=3998392328, >> u64=17172964285337305088}}}, 100, -1) = 1 >> [pid 18619] 18:18:13 read(15, "HEAD / HTTP/1.1\r\nX-Forwarded-For:"..., >> 8191) = 102 >> [pid 18619] 18:18:13 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, >> 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 >> [pid 18624] 18:18:13 <... futex resumed> ) = 0 >> [pid 18619] 18:18:13 epoll_wait(10, >> [pid 18624] 18:18:13 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 >> [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b3842c) = 0 >> [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 495145448}) = 0 >> [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 495574520}) = 0 >> [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 495897344}) = 0 >> [pid 18624] 18:18:13 writev(15, [{"HTTP/1.1"..., 8}, {" "..., 1}, >> {"200"..., 3}, {" "..., 1}, {"OK"..., 2}, {"\r\n"..., 2}, {"Server: >> Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"Last-Modified: Tue, 03 Aug >> 2010 0"..., 44}, {"\r\n"..., 2}, {"ETag: \"40125-0-48ce652c74380\""..., >> 29}, {"\r\n"..., 2}, {"Vary: Accept-Encoding"..., 21}, {"\r\n"..., 2}, >> {"Content-Type: text/html"..., 23}, {"\r\n"..., 2}, {"Content-Length: >> 0"..., 17}, {"\r\n"..., 2}, {"Date: Fri, 10 Dec 2010 16:18:13 G"..., 35}, >> {"\r\n"..., 2}, {"X-Varnish: 1052092384 1052090630"..., 32}, {"\r\n"..., >> 2}, {"Age: 236"..., 8}, {"\r\n"..., 2}, {"Via: 1.1 varnish"..., 16}, >> {"\r\n"..., 2}, {"Connection: keep-alive"..., 22}, {"\r\n"..., 2}, >> {"\r\n"..., 2}], 29) = 313 >> [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 497661528}) = 0 >> [pid 18624] 18:18:13 poll([{fd=15, events=POLLIN}], 1, 50 > ...> >> [pid 18629] 18:18:13 <... poll resumed> ) = 0 (Timeout) >> [pid 18629] 18:18:13 ioctl(14, 0x8004667e, 0xf19d43bc) = 0 >> [pid 18629] 18:18:13 write(4, "\355\235 \10"..., 4) = 4 >> [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, >> u64=2428082451382272}}}, 100, -1) = 1 >> [pid 18629] 18:18:13 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25623, NULL >> >> [pid 18619] 18:18:13 read(3, "\355\235 \10"..., 400) = 4 >> [pid 18619] 18:18:13 epoll_ctl(10, EPOLL_CTL_MOD, 14, >> {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3986497544, >> u64=17121876577064321024}}) = 0 >> [pid 18619] 18:18:13 epoll_wait(10, >> [pid 18624] 18:18:13 <... poll resumed> ) = 0 (Timeout) >> [pid 18624] 18:18:13 ioctl(15, 0x8004667e, 0xf7b383bc) = 0 >> [pid 18624] 18:18:13 write(4, "\356R\240\10"..., 4 >> [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, >> u64=2428082451382272}}}, 100, -1) = 1 >> [pid 18624] 18:18:13 <... write resumed> ) = 4 >> [pid 18619] 18:18:13 read(3, >> [pid 18624] 18:18:13 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25919, NULL >> >> [pid 18619] 18:18:13 <... read resumed> "\356R\240\10"..., 400) = 4 >> [pid 18619] 18:18:13 epoll_ctl(10, EPOLL_CTL_MOD, 15, >> {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=3998392328, >> u64=17172964285337305088}}) = 0 >> [pid 18619] 18:18:13 epoll_wait(10, >> [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:13 nanosleep({0, 100000000}, >> [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 577819076}) = 0 >> [pid 18619] 18:18:13 epoll_wait(10, >> [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:13 nanosleep({0, 100000000}, >> [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 678596784}) = 0 >> [pid 18619] 18:18:13 epoll_wait(10, {{EPOLLIN, {u32=3986497544, >> u64=17121876577064321024}}}, 100, -1) = 1 >> [pid 18619] 18:18:13 read(14, "GET /stiri HTTP/1.1\r\nUser-Agent: "..., >> 8191) = 773 >> [pid 18619] 18:18:13 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, >> 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 >> [pid 18629] 18:18:13 <... futex resumed> ) = 0 >> [pid 18619] 18:18:13 epoll_wait(10, >> [pid 18629] 18:18:13 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 >> [pid 18629] 18:18:13 ioctl(14, 0x8004667e, 0xf19d442c) = 0 >> [pid 18629] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 738793608}) = 0 >> [pid 18629] 18:18:13 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25625, NULL >> >> [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:13 nanosleep({0, 100000000}, >> [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 779390960}) = 0 >> [pid 18619] 18:18:13 epoll_wait(10, >> [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:13 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:13 nanosleep({0, 100000000}, >> [pid 18619] 18:18:13 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 880271512}) = 0 >> [pid 18619] 18:18:13 epoll_wait(10, >> [pid 18618] 18:18:13 <... nanosleep resumed> NULL) = 0 >> [pid 18620] 18:18:13 <... poll resumed> ) = 1 ([{fd=5, revents=POLLIN}]) >> [pid 18618] 18:18:13 write(8, "R"..., 1 >> [pid 18620] 18:18:13 clock_gettime(CLOCK_REALTIME, >> [pid 18618] 18:18:13 <... write resumed> ) = 1 >> [pid 18619] 18:18:13 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:13 nanosleep({0, 100000000}, >> [pid 18619] 18:18:13 read(7, >> [pid 18620] 18:18:13 <... clock_gettime resumed> {1291997893, 980448784}) >> = 0 >> [pid 18619] 18:18:13 <... read resumed> "R"..., 1) = 1 >> [pid 18620] 18:18:13 accept(5, >> [pid 18619] 18:18:13 clock_gettime(CLOCK_REALTIME, >> [pid 18620] 18:18:13 <... accept resumed> {sa_family=AF_INET, >> sin_port=htons(50619), sin_addr=inet_addr("x.y.z.36")}, [16]) = 17 >> [pid 18619] 18:18:13 <... clock_gettime resumed> {1291997893, 981728996}) >> = 0 >> [pid 18620] 18:18:13 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, >> 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1} >> [pid 18619] 18:18:13 epoll_wait(10, >> [pid 18620] 18:18:13 <... futex resumed> ) = 1 >> [pid 18624] 18:18:13 <... futex resumed> ) = 0 >> [pid 18620] 18:18:13 poll([{fd=5, events=POLLIN}], 1, 1000 > ...> >> [pid 18624] 18:18:13 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 >> [pid 18624] 18:18:13 ioctl(17, 0x8004667e, 0xf7b3842c) = 0 >> [pid 18624] 18:18:13 poll([{fd=17, events=POLLIN}], 1, 50) = 1 ([{fd=17, >> revents=POLLIN}]) >> [pid 18624] 18:18:13 read(17, "GET /wp-content/themes/XXXXXXXX/"..., >> 8191) >> = 427 >> [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 984534164}) = 0 >> [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 984991888}) = 0 >> [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 985292996}) = 0 >> [pid 18624] 18:18:13 writev(17, [{"HTTP/1.1"..., 8}, {" "..., 1}, >> {"200"..., 3}, {" "..., 1}, {"OK"..., 2}, {"\r\n"..., 2}, {"Server: >> Microsoft-IIS/7.5"..., 25}, {"\r\n"..., 2}, {"Last-Modified: Tue, 16 Feb >> 2010 0"..., 44}, {"\r\n"..., 2}, {"ETag: \"46853-65c-47fb4c59bb740\""..., >> 31}, {"\r\n"..., 2}, {"Content-Type: image/gif"..., 23}, {"\r\n"..., 2}, >> {"Content-Length: 1628"..., 20}, {"\r\n"..., 2}, {"Date: Fri, 10 Dec 2010 >> 16:18:13 G"..., 35}, {"\r\n"..., 2}, {"X-Varnish: 1052092386 >> 1052083384"..., 32}, {"\r\n"..., 2}, {"Age: 1100"..., 9}, {"\r\n"..., 2}, >> {"Via: 1.1 varnish"..., 16}, {"\r\n"..., 2}, {"Connection: >> keep-alive"..., >> 22}, {"\r\n"..., 2}, {"\r\n"..., 2}, >> >> {"GIF89a\34\0$\0\367\0\0\"\37\210w\344\363\235\237\314\36\271\336XZ\250\0\215\303\307\361"..., >> 1628}], 28) = 1924 >> [pid 18624] 18:18:13 clock_gettime(CLOCK_REALTIME, {1291997893, >> 987145288}) = 0 >> [pid 18624] 18:18:13 poll([{fd=17, events=POLLIN}], 1, 50) = 0 (Timeout) >> [pid 18624] 18:18:14 ioctl(17, 0x8004667e, 0xf7b383bc) = 0 >> [pid 18624] 18:18:14 write(4, "\367\244\200\10"..., 4 >> [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=565332, >> u64=2428082451382272}}}, 100, -1) = 1 >> [pid 18624] 18:18:14 <... write resumed> ) = 4 >> [pid 18619] 18:18:14 read(3, >> [pid 18624] 18:18:14 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25921, NULL >> >> [pid 18619] 18:18:14 <... read resumed> "\367\244\200\10"..., 400) = 4 >> [pid 18619] 18:18:14 epoll_ctl(10, EPOLL_CTL_ADD, 17, >> {EPOLLIN|EPOLLPRI|EPOLLONESHOT|0x2000, {u32=4154753032, >> u64=17844528395396841472}}) = 0 >> [pid 18619] 18:18:14 epoll_wait(10, {{EPOLLIN, {u32=4154753032, >> u64=17844528395396841472}}}, 100, -1) = 1 >> [pid 18619] 18:18:14 read(17, "GET /stiri HTTP/1.1\r\nUser-Agent: "..., >> 8191) = 773 >> [pid 18619] 18:18:14 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, >> 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 >> [pid 18629] 18:18:14 <... futex resumed> ) = 0 >> [pid 18619] 18:18:14 epoll_wait(10, >> [pid 18629] 18:18:14 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 >> [pid 18629] 18:18:14 ioctl(17, 0x8004667e, 0xf19d442c) = 0 >> [pid 18629] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, >> 47222624}) >> = 0 >> [pid 18629] 18:18:14 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25627, NULL >> >> [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:14 nanosleep({0, 100000000}, >> [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, >> 82163424}) >> = 0 >> [pid 18619] 18:18:14 epoll_wait(10, >> [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:14 nanosleep({0, 100000000}, >> [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, >> 183055080}) = 0 >> [pid 18619] 18:18:14 epoll_wait(10, >> [pid 18612] 18:18:14 <... nanosleep resumed> NULL) = 0 >> [pid 18612] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, >> 241243672}) = 0 >> [pid 18612] 18:18:14 nanosleep({1, 0}, >> [pid 18617] 18:18:14 <... nanosleep resumed> {1, 0}) = 0 >> [pid 18617] 18:18:14 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 >> [pid 18617] 18:18:14 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], >> SA_NOCLDSTOP}, 0, 4033866460) = 0 >> [pid 18617] 18:18:14 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 >> [pid 18617] 18:18:14 nanosleep({1, 0}, >> [pid 18615] 18:18:14 <... nanosleep resumed> {1, 0}) = 0 >> [pid 18615] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, >> 252058036}) = 0 >> [pid 18615] 18:18:14 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 >> [pid 18615] 18:18:14 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], >> SA_NOCLDSTOP}, 0, 4050643676) = 0 >> [pid 18615] 18:18:14 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 >> [pid 18615] 18:18:14 nanosleep({1, 0}, >> [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:14 nanosleep({0, 100000000}, >> [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, >> 283774800}) = 0 >> [pid 18619] 18:18:14 epoll_wait(10, >> [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:14 nanosleep({0, 100000000}, >> [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, >> 384582084}) = 0 >> [pid 18619] 18:18:14 epoll_wait(10, >> [pid 18620] 18:18:14 <... poll resumed> ) = 1 ([{fd=5, revents=POLLIN}]) >> [pid 18620] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, >> 419035140}) = 0 >> [pid 18620] 18:18:14 accept(5, {sa_family=AF_INET, sin_port=htons(50630), >> sin_addr=inet_addr("x.y.z.36")}, [16]) = 18 >> [pid 18620] 18:18:14 futex(0xf7b3f18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, >> 0xf7b3f188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 >> [pid 18624] 18:18:14 <... futex resumed> ) = 0 >> [pid 18620] 18:18:14 poll([{fd=5, events=POLLIN}], 1, 1000 > ...> >> [pid 18624] 18:18:14 futex(0xf7a10984, FUTEX_WAKE_PRIVATE, 1) = 0 >> [pid 18624] 18:18:14 ioctl(18, 0x8004667e, 0xf7b3842c) = 0 >> [pid 18624] 18:18:14 poll([{fd=18, events=POLLIN}], 1, 50) = 1 ([{fd=18, >> revents=POLLIN}]) >> [pid 18624] 18:18:14 read(18, "GET /stiri HTTP/1.1\r\nUser-Agent: "..., >> 8191) = 773 >> [pid 18624] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, >> 421629696}) = 0 >> [pid 18624] 18:18:14 futex(0xf7b3f18c, FUTEX_WAIT_PRIVATE, 25923, NULL >> >> [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:14 nanosleep({0, 100000000}, >> [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, >> 485429080}) = 0 >> [pid 18619] 18:18:14 epoll_wait(10, >> [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:14 nanosleep({0, 100000000}, >> [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, >> 586203652}) = 0 >> [pid 18619] 18:18:14 epoll_wait(10, >> [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:14 nanosleep({0, 100000000}, >> [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, >> 687050580}) = 0 >> [pid 18619] 18:18:14 epoll_wait(10, >> [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:14 nanosleep({0, 100000000}, >> [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, >> 787847056}) = 0 >> [pid 18619] 18:18:14 epoll_wait(10, >> [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:14 nanosleep({0, 100000000}, >> [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, >> 888672272}) = 0 >> [pid 18619] 18:18:14 epoll_wait(10, >> [pid 18618] 18:18:14 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:14 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:14 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:14 nanosleep({0, 100000000}, >> [pid 18619] 18:18:14 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:14 clock_gettime(CLOCK_REALTIME, {1291997894, >> 989458320}) = 0 >> [pid 18619] 18:18:14 epoll_wait(10, >> [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:15 nanosleep({0, 100000000}, >> [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, >> 90264196}) >> = 0 >> [pid 18619] 18:18:15 epoll_wait(10, >> [pid 18611] 18:18:15 <... poll resumed> ) = 1 ([{fd=6, revents=POLLIN}]) >> [pid 18611] 18:18:15 read(6, "ping\n"..., 8191) = 5 >> [pid 18611] 18:18:15 time(NULL) = 1291997895 >> [pid 18611] 18:18:15 writev(9, [{"200 19 \n"..., 13}, {"PONG >> 1291997895 1.0"..., 19}, {"\n"..., 1}], 3) = 33 >> [pid 18611] 18:18:15 poll([{fd=6, events=POLLIN}], 1, -1 >> [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:15 nanosleep({0, 100000000}, >> [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, >> 191048264}) = 0 >> [pid 18619] 18:18:15 epoll_wait(10, >> [pid 18612] 18:18:15 <... nanosleep resumed> NULL) = 0 >> [pid 18612] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, >> 241947668}) = 0 >> [pid 18612] 18:18:15 nanosleep({1, 0}, >> [pid 18617] 18:18:15 <... nanosleep resumed> {1, 0}) = 0 >> [pid 18617] 18:18:15 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 >> [pid 18617] 18:18:15 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], >> SA_NOCLDSTOP}, 0, 4033866460) = 0 >> [pid 18617] 18:18:15 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 >> [pid 18617] 18:18:15 nanosleep({1, 0}, >> [pid 18615] 18:18:15 <... nanosleep resumed> {1, 0}) = 0 >> [pid 18615] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, >> 253632384}) = 0 >> [pid 18615] 18:18:15 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 >> [pid 18615] 18:18:15 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], >> SA_NOCLDSTOP}, 0, 4050643676) = 0 >> [pid 18615] 18:18:15 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 >> [pid 18615] 18:18:15 nanosleep({1, 0}, >> [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:15 nanosleep({0, 100000000}, >> [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, >> 291949320}) = 0 >> [pid 18619] 18:18:15 epoll_wait(10, >> [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:15 nanosleep({0, 100000000}, >> [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, >> 392767872}) = 0 >> [pid 18619] 18:18:15 epoll_wait(10, >> [pid 18620] 18:18:15 <... poll resumed> ) = 0 (Timeout) >> [pid 18620] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, >> 423866840}) = 0 >> [pid 18620] 18:18:15 poll([{fd=5, events=POLLIN}], 1, 1000 > ...> >> [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:15 nanosleep({0, 100000000}, >> [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, >> 493554528}) = 0 >> [pid 18619] 18:18:15 epoll_wait(10, >> [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:15 nanosleep({0, 100000000}, >> [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, >> 594343716}) = 0 >> [pid 18619] 18:18:15 epoll_wait(10, >> [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:15 nanosleep({0, 100000000}, >> [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, >> 695131520}) = 0 >> [pid 18619] 18:18:15 epoll_wait(10, >> [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:15 nanosleep({0, 100000000}, >> [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, >> 795928848}) = 0 >> [pid 18619] 18:18:15 epoll_wait(10, >> [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:15 nanosleep({0, 100000000}, >> [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, >> 896786468}) = 0 >> [pid 18619] 18:18:15 epoll_wait(10, >> [pid 18618] 18:18:15 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:15 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:15 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:15 nanosleep({0, 100000000}, >> [pid 18619] 18:18:15 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:15 clock_gettime(CLOCK_REALTIME, {1291997895, >> 997543276}) = 0 >> [pid 18619] 18:18:15 epoll_wait(10, >> [pid 18618] 18:18:16 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:16 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:16 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:16 nanosleep({0, 100000000}, >> [pid 18619] 18:18:16 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, >> 98361332}) >> = 0 >> [pid 18619] 18:18:16 epoll_wait(10, >> [pid 18618] 18:18:16 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:16 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:16 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:16 nanosleep({0, 100000000}, >> [pid 18619] 18:18:16 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, >> 199182492}) = 0 >> [pid 18619] 18:18:16 epoll_wait(10, >> [pid 18612] 18:18:16 <... nanosleep resumed> NULL) = 0 >> [pid 18612] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, >> 242623312}) = 0 >> [pid 18612] 18:18:16 nanosleep({1, 0}, >> [pid 18617] 18:18:16 <... nanosleep resumed> {1, 0}) = 0 >> [pid 18617] 18:18:16 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 >> [pid 18617] 18:18:16 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], >> SA_NOCLDSTOP}, 0, 4033866460) = 0 >> [pid 18617] 18:18:16 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 >> [pid 18617] 18:18:16 nanosleep({1, 0}, >> [pid 18615] 18:18:16 <... nanosleep resumed> {1, 0}) = 0 >> [pid 18615] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, >> 255275216}) = 0 >> [pid 18615] 18:18:16 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 >> [pid 18615] 18:18:16 rt_sigaction(SIGCHLD, NULL, {0xf7f30798, [], >> SA_NOCLDSTOP}, 0, 4050643676) = 0 >> [pid 18615] 18:18:16 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 >> [pid 18615] 18:18:16 nanosleep({1, 0}, >> [pid 18618] 18:18:16 <... nanosleep resumed> NULL) = 0 >> [pid 18618] 18:18:16 write(8, "R"..., 1) = 1 >> [pid 18619] 18:18:16 <... epoll_wait resumed> {{EPOLLIN, {u32=570960, >> u64=2452254527324160}}}, 100, -1) = 1 >> [pid 18618] 18:18:16 nanosleep({0, 100000000}, >> [pid 18619] 18:18:16 read(7, "R"..., 1) = 1 >> [pid 18619] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, >> 299975276}) = 0 >> [pid 18619] 18:18:16 epoll_wait(10, >> [pid 18620] 18:18:16 <... poll resumed> ) = 1 ([{fd=5, revents=POLLIN}]) >> [pid 18620] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, >> 315826092}) = 0 >> [pid 18620] 18:18:16 accept(5, {sa_family=AF_INET, sin_port=htons(42033), >> sin_addr=inet_addr("x.y.z.86")}, [16]) = 19 >> [pid 18620] 18:18:16 futex(0xf19db18c, FUTEX_WAKE_OP_PRIVATE, 1, 1, >> 0xf19db188, {FUTEX_OP_SET, 0, FUTEX_OP_CMP_GT, 1}) = 1 >> [pid 18629] 18:18:16 <... futex resumed> ) = 0 >> [pid 18620] 18:18:16 poll([{fd=5, events=POLLIN}], 1, 1000 > ...> >> [pid 18629] 18:18:16 futex(0xf7a109b4, FUTEX_WAKE_PRIVATE, 1) = 0 >> [pid 18629] 18:18:16 ioctl(19, 0x8004667e, 0xf19d442c) = 0 >> [pid 18629] 18:18:16 poll([{fd=19, events=POLLIN}], 1, 50) = 1 ([{fd=19, >> revents=POLLIN}]) >> [pid 18629] 18:18:16 read(19, "GET / HTTP/1.1\r\nHost: www.Xspo"..., >> 8191) >> = 99 >> [pid 18629] 18:18:16 clock_gettime(CLOCK_REALTIME, {1291997896, >> 318403888}) = 0 >> [pid 18629] 18:18:16 futex(0xf19db18c, FUTEX_WAIT_PRIVATE, 25629, NULL >> >> [pid 18611] 18:18:16 <... poll resumed> ) = 1 ([{fd=6, revents=POLLHUP}]) >> [pid 18611] 18:18:16 close(6) = 0 >> [pid 18611] 18:18:16 close(9) = 0 >> [pid 18611] 18:18:16 close(5) = 0 >> [pid 18611] 18:18:16 write(1, "Child dies"..., 10) = -1 EPIPE (Broken >> pipe) >> [pid 18611] 18:18:16 --- SIGPIPE (Broken pipe) @ 0 (0) --- >> [pid 18611] 18:18:16 exit_group(1) = ? >> Process 18611 detached >> [pid 18612] 18:18:16 <... nanosleep resumed> 0) = ? ERESTART_RESTARTBLOCK >> (To be restarted) >> [pid 18614] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be >> restarted) >> [pid 18615] 18:18:16 <... nanosleep resumed> 0xf16fec68) = ? >> ERESTART_RESTARTBLOCK (To be restarted) >> [pid 18616] 18:18:16 <... nanosleep resumed> 0) = ? ERESTART_RESTARTBLOCK >> (To be restarted) >> [pid 18617] 18:18:16 <... nanosleep resumed> 0xf06fec68) = ? >> ERESTART_RESTARTBLOCK (To be restarted) >> [pid 18618] 18:18:16 <... nanosleep resumed> 0) = ? ERESTART_RESTARTBLOCK >> (To be restarted) >> [pid 18619] 18:18:16 <... epoll_wait resumed> ef6feb20, 100, -1) = -1 >> EINTR (Interrupted system call) >> [pid 18620] 18:18:16 <... poll resumed> ) = 1 ([{fd=5, >> revents=POLLNVAL}]) >> [pid 18622] 18:18:16 <... read resumed> 0xf7b59108, 8191) = -1 EINTR >> (Interrupted system call) >> [pid 18623] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be >> restarted) >> [pid 18624] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be >> restarted) >> [pid 18625] 18:18:16 <... read resumed> 0xf7b2839a, 1) = -1 EINTR >> (Interrupted system call) >> [pid 18626] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be >> restarted) >> [pid 18627] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be >> restarted) >> [pid 18628] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be >> restarted) >> [pid 18629] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be >> restarted) >> [pid 18630] 18:18:16 <... futex resumed> ) = ? ERESTARTSYS (To be >> restarted) >> Process 18611 detached >> Process 18984 detached >> }}} >> All I can see is the SIGPIPE and the ERESTARTSYS (those two things do not >> appear until the freeze). >> >> Varnish default conf: -f /srv/varnish/conf/XXXXXXXX.vcl -s malloc,1024M >> -a >> 0.0.0.0:8080 >> >> VCL: >> {{{ >> backend default { >> .host = "XX.YY.ZZ.WW"; >> .port = "80"; >> } >> >> >> sub vcl_recv { >> if (req.url ~ "cgi-bin") { >> return (pipe); >> } >> >> if (req.http.Accept-Encoding) { >> if (req.http.Accept-Encoding ~ "gzip") { >> set req.http.Accept-Encoding = "gzip"; >> } elsif (req.http.Accept-Encoding ~ "deflate") { >> set req.http.Accept-Encoding = "deflate"; >> } else { >> # unkown algorithm >> remove req.http.Accept-Encoding; >> } >> } >> >> if (req.http.Accept-Language) { >> remove req.http.Accept-Language; >> } >> >> if (req.http.User-Agent) { >> remove req.http.User-Agent; >> } >> >> if (req.http.Host ~ "live.XXXXXXXX.ro" || req.http.Host ~ >> "live2.XXXXXXXX.ro") { >> return (pipe); >> } >> >> if (req.request != "GET" && req.request != "HEAD") { >> return (pass); >> } >> >> if (req.url ~ "\.(png|gif|jpg|swf)" || req.url ~ "/img/" || req.url ~ >> "\.(js|css)") { >> >> >> remove req.http.cookie; >> return (lookup); >> } >> >> if ( >> !(req.url ~ "wp-(login|admin)") && >> !(req.http.Cookie ~ "wordpress_logged_in") >> ) { >> remove req.http.cookie; >> return (lookup); >> } else { >> return (pass); >> } >> >> >> >> >> if (req.http.Cookie ~ "wordpress_logged_in") { >> return (pass); >> } else { >> return (lookup); >> } >> } >> >> sub vcl_fetch { >> >> if (req.http.Host ~ "live.XXXXXXX.ro" || req.http.Host ~ >> "live2.XXXXXXXX.ro") { >> return(pass); >> } >> >> if (beresp.http.Content-Type ~ "text/html") { >> //set beresp.http.Cache-Control = "no-store, no-cache, >> must-revalidate, post-check=0, pre-check=0"; >> //set beresp.http.Pragma = "no-cache"; >> } >> >> if (!(req.url ~ "wp-(login|admin)")) { >> #remove beresp.http.set-cookie; >> } >> >> if (req.url ~ "\.(png|gif|jpg|swf)" || req.url ~ "/img/" || >> beresp.http.Content-Type ~ "javascript" || beresp.http.Content-Type ~ >> "css") { >> remove beresp.http.set-cookie; >> //log "request-ul se preteaza: " beresp.http.Content-Type; >> set beresp.ttl = 7200s; >> return (deliver); >> } else { >> set beresp.ttl = 240s; >> } >> >> } >> }}} >> I cannot link any request to the crash event. >> >> -- >> Ticket URL: >> Varnish >> The Varnish HTTP Accelerator >> >> _______________________________________________ >> varnish-bugs mailing list >> varnish-bugs at varnish-cache.org >> http://www.varnish-cache.org/lists/mailman/listinfo/varnish-bugs >> > > > > -- > > Att, > > Renato Farias > > -------------- next part -------------- An HTML attachment was scrubbed... URL: From varnish-bugs at varnish-cache.org Thu Dec 16 15:02:04 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Thu, 16 Dec 2010 15:02:04 -0000 Subject: [Varnish] #836: Display bug in varnishstat Message-ID: <043.a9f7b1ffc8082a1c667fa3db7404a740@varnish-cache.org> #836: Display bug in varnishstat -------------------------+-------------------------------------------------- Reporter: jelder | Owner: phk Type: defect | Status: new Priority: normal | Milestone: After Varnish 2.1 Component: varnishstat | Version: trunk Severity: normal | Keywords: -------------------------+-------------------------------------------------- The varnishstat hitrate average header will display "nan" instead of the expected information if the user resizes the terminal window, or if the user presses any of the arrow keys. I am running the official debs for 2.1.2-1~hardy1 on amd64 and running varnishstat over SSH from Terminal.app. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Fri Dec 17 03:03:40 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Fri, 17 Dec 2010 03:03:40 -0000 Subject: [Varnish] #736: Migration to Cygwin plataform In-Reply-To: <042.6ef2981e8cf7eb068adf1551551220f4@varnish-cache.org> References: <042.6ef2981e8cf7eb068adf1551551220f4@varnish-cache.org> Message-ID: <051.25a6fa91ec62fda949a9b75411fef83e@varnish-cache.org> #736: Migration to Cygwin plataform ----------------------+----------------------------------------------------- Reporter: jdzst | Type: enhancement Status: closed | Priority: normal Milestone: | Component: build Version: | Severity: normal Resolution: invalid | Keywords: cygwin, windows ----------------------+----------------------------------------------------- Comment(by jdzst): Hello, I have updated my version of varnish for cygwin. It is based on subversion trunk (r5646) The new improvements are: * Better compilation of VCL archives (in the past they were compiled using objects from varnish compilation directory) * Fixed regresion tests: varnishtest program server_thread function in vtc_server.c, after "fd = accept(s->sock, addr, &l);" If socket returned is wrong, it is not used. * Fixed regresion tests: varnishtest program is blocked in some tests. Test is executed succesfully but varnishtest program is blocked when it stops server thread, so varnishtest timeouts and FAILS. - Server thread is blocked in TCP accept, waiting a request (server_thread function in vtc_server.c file) and main varnishtest is blocked in pthread_join (server_wait function in vtc_server.c file) waiting server thread to end. - In linux, pthread_join unblocks thread from its TCP accept but in Cygwin it does not. - The solution is to send a signal using pthread_kill (only in cygwin). The signal unblocks thread from its TCP accept. - I have tested varnish cache in cygwin against one apache server and it works fine. The patch applied in a Solaris and Linux server works properly. After this changes, the result of regression test are: 9 tests failed, 202 tests passed Failed tests: '''c00005.vtc "Test simple ACL"''' error IPv6 [DNS lookup(::): hostname nor servname provided, or not known\n] CYGWIN does not support IPv6 in Windows XP. Maybe it works in newer versions '''s00002.vtc "Check grace with sick backends"''' "Write failed: Bad file descriptor" UNKNOWN ERROR '''b00015.vtc "Check synthetic error page caching" and v00009.vtc "Test round robin director"''' bind(): Address already in use [Assert error in server_start(), vtc_server.c line 183: Condition(s->sock >= 0) not true.] UNKNOWN ERROR: test server is started two times, the second time it says that port it is in use '''VMOD regresion tests: m00000.vtc, m00001.vtc, m00002.vtc, m00003.vtc and m00004.vtc''' CYGWIN does not find new VMOD shared libraries A fix is need in order to load shared libraries of VMOD LIST OF FAILED TESTS: # top TEST tests/b00015.vtc FAILED (7.039) # top TEST tests/c00005.vtc FAILED (7.766) # top TEST tests/m00000.vtc FAILED (3.131) # top TEST tests/m00001.vtc FAILED (3.007) # top TEST tests/m00002.vtc FAILED (2.830) # top TEST tests/m00003.vtc FAILED (2.894) # top TEST tests/m00004.vtc FAILED (3.279) # top TEST tests/s00002.vtc FAILED (9.977) # top TEST tests/v00009.vtc FAILED (5.509) -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Fri Dec 17 03:07:51 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Fri, 17 Dec 2010 03:07:51 -0000 Subject: [Varnish] #736: Migration to Cygwin plataform In-Reply-To: <042.6ef2981e8cf7eb068adf1551551220f4@varnish-cache.org> References: <042.6ef2981e8cf7eb068adf1551551220f4@varnish-cache.org> Message-ID: <051.fc353d688fca10c761ad9ba417716151@varnish-cache.org> #736: Migration to Cygwin plataform ----------------------+----------------------------------------------------- Reporter: jdzst | Type: enhancement Status: closed | Priority: normal Milestone: | Component: build Version: | Severity: normal Resolution: invalid | Keywords: cygwin, windows ----------------------+----------------------------------------------------- Comment(by jdzst): Hello, I have updated my version of varnish for cygwin. It is based on subversion trunk (r5646)[[BR]] The new improvements are:[[BR]] * Better compilation of VCL archives (in the past they were compiled using objects from varnish compilation directory) * Fixed regresion tests: varnishtest program server_thread function in vtc_server.c, after "fd = accept(s->sock, addr, &l);" If socket returned is wrong, it is not used. * Fixed regresion tests: varnishtest program is blocked in some tests. Test is executed succesfully but varnishtest program is blocked when it stops server thread, so varnishtest timeouts and FAILS. * Server thread is blocked in TCP accept, waiting a request (server_thread function in vtc_server.c file) and main varnishtest is blocked in pthread_join (server_wait function in vtc_server.c file) waiting server thread to end. * In linux, pthread_join unblocks thread from its TCP accept but in Cygwin it does not. * The solution is to send a signal using pthread_kill (only in cygwin). The signal unblocks thread from its TCP accept. * I have tested varnish cache in cygwin against one apache server and it works fine. The patch applied in a Solaris and Linux server works properly. After this changes, the result of regression test are: 9 tests failed, 202 tests passed Failed tests: '''c00005.vtc "Test simple ACL"''' {{{error IPv6 [DNS lookup(::): hostname nor servname provided, or not known\n] CYGWIN does not support IPv6 in Windows XP. Maybe it works in newer versions}}} '''s00002.vtc "Check grace with sick backends"''' {{{"Write failed: Bad file descriptor" UNKNOWN ERROR}}} '''b00015.vtc "Check synthetic error page caching" and v00009.vtc "Test round robin director"''' {{{bind(): Address already in use [Assert error in server_start(), vtc_server.c line 183: Condition(s->sock >= 0) not true.] UNKNOWN ERROR: test server is started two times, the second time it says that port it is in use}}} '''VMOD regresion tests: m00000.vtc, m00001.vtc, m00002.vtc, m00003.vtc and m00004.vtc''' {{{CYGWIN does not find new VMOD shared libraries A fix is need in order to load shared libraries of VMOD}}} {{{ LIST OF FAILED TESTS: # top TEST tests/b00015.vtc FAILED (7.039) # top TEST tests/c00005.vtc FAILED (7.766) # top TEST tests/m00000.vtc FAILED (3.131) # top TEST tests/m00001.vtc FAILED (3.007) # top TEST tests/m00002.vtc FAILED (2.830) # top TEST tests/m00003.vtc FAILED (2.894) # top TEST tests/m00004.vtc FAILED (3.279) # top TEST tests/s00002.vtc FAILED (9.977) # top TEST tests/v00009.vtc FAILED (5.509) }}} -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Fri Dec 17 03:09:34 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Fri, 17 Dec 2010 03:09:34 -0000 Subject: [Varnish] #736: Migration to Cygwin plataform In-Reply-To: <042.6ef2981e8cf7eb068adf1551551220f4@varnish-cache.org> References: <042.6ef2981e8cf7eb068adf1551551220f4@varnish-cache.org> Message-ID: <051.45bf53787007d0e0f1a28a1715178b6c@varnish-cache.org> #736: Migration to Cygwin plataform ----------------------+----------------------------------------------------- Reporter: jdzst | Type: enhancement Status: closed | Priority: normal Milestone: | Component: build Version: | Severity: normal Resolution: invalid | Keywords: cygwin, windows ----------------------+----------------------------------------------------- Comment(by jdzst): After this changes, the result of regression test are: 9 tests failed, 202 tests passed Failed tests: '''c00005.vtc "Test simple ACL"''' {{{ error IPv6 [DNS lookup(::): hostname nor servname provided, or not known\n] CYGWIN does not support IPv6 in Windows XP. Maybe it works in newer versions }}} '''s00002.vtc "Check grace with sick backends"''' {{{ "Write failed: Bad file descriptor" UNKNOWN ERROR }}} '''b00015.vtc "Check synthetic error page caching" and v00009.vtc "Test round robin director"''' {{{ bind(): Address already in use [Assert error in server_start(), vtc_server.c line 183: Condition(s->sock >= 0) not true.] UNKNOWN ERROR: test server is started two times, the second time it says that port it is in use }}} '''VMOD regresion tests: m00000.vtc, m00001.vtc, m00002.vtc, m00003.vtc and m00004.vtc''' {{{ CYGWIN does not find new VMOD shared libraries A fix is need in order to load shared libraries of VMOD }}} -- Ticket URL: Varnish The Varnish HTTP Accelerator From jhalfmoon at milksnot.com Fri Dec 17 12:36:14 2010 From: jhalfmoon at milksnot.com (Johnny Halfmoon) Date: Fri, 17 Dec 2010 13:36:14 +0100 Subject: Build error during test c00003.vtc Message-ID: <20101217133614.2ygt2o704kwk0gs8@webmail.milksnot.com> Hi, a small bugreport here. I had a bit of a hard time building a Varnish 2.1.4 RPM on a RHEL6 machine. The build kept failing during the selftest part, specifically the c00003.vtc test: ---- v1 FAIL CLI response 200 expected 300 ------8<------ snip --------8<----------------- ### v1 debug| child (6300) Started\n ### v1 CLI RX 200 ## v1 CLI 200 ---- v1 FAIL CLI response 200 expected 300 ### v1 debug| Child (6300) said \n ### v1 debug| Child (6300) said Child starts\n ### v1 debug| Child (6300) said managed to mmap 10485760 bytes of 10485760\n # top Test timed out # top TEST ././tests/c00003.vtc FAILED FAIL: ./tests/c00003.vtc Eventually I found the cause to be the following: If /proc/net/ipv4/ip_nonlocal_bind is set to '1' , then the test error will occur. The solution is to do the following: echo 0 > /proc/net/ipv4/ip_nonlocal_bind The default setting for ip_nonlocal_bind on most Linux systems will be '0', but in my case, the buildmachine was also a testmachine for fail-over setup, which required ip_nonlocal_bind to be set to '1'. I hope this helps. From varnish-bugs at varnish-cache.org Fri Dec 17 16:08:12 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Fri, 17 Dec 2010 16:08:12 -0000 Subject: [Varnish] #837: varnishadm purge.list fails frequently Message-ID: <043.a2d15772321998574922abae75b7be94@varnish-cache.org> #837: varnishadm purge.list fails frequently ----------------------+----------------------------------------------------- Reporter: jelder | Owner: phk Type: defect | Status: new Priority: normal | Milestone: After Varnish 2.1 Component: varnishd | Version: trunk Severity: normal | Keywords: purge.list ----------------------+----------------------------------------------------- On a site with a relatively busy purge list, the following command fails most of the time: {{{ # varnishadm -S /etc/varnish/secret -T localhost:6082 purge.list CLI communication error (body) Command failed with error code 400 }}} "Relatively busy" being defined as: {{{ # varnishstat -1 -f n_purge,n_purge_add,n_purge_retire,n_purge,n_purge_obj_test,n_purge_re_test,n_purge_dups n_purge 11434 . N total active purges n_purge_add 13699 0.04 N new purges added n_purge_retire 2265 0.01 N old purges deleted n_purge_obj_test 26524085 84.55 N objects tested n_purge_re_test 139179733 443.65 N regexps tested against n_purge_dups 12974 0.04 N duplicate purges removed }}} This is with Varnish 2.1.2-1~hardy1. A strace is attached. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 20 08:36:43 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 20 Dec 2010 08:36:43 -0000 Subject: [Varnish] #838: file backend storage file should be removed at package upgrade Message-ID: <043.0a5310132f8efd5e6fb2a78ef728781f@varnish-cache.org> #838: file backend storage file should be removed at package upgrade -----------------------+---------------------------------------------------- Reporter: ingvar | Owner: Type: defect | Status: new Priority: normal | Milestone: Component: packaging | Version: trunk Severity: normal | Keywords: -----------------------+---------------------------------------------------- According to Are here, running varnish witht the file storage backend, if varnish-2.1.0 (ubuntu lucid) is updated to varnish-2.1.(x, x>0), varnishd will not start unless varnish_storage.bin (the argument to -s file) is first removed, as varnishd, at least on 2.1.0, checks if the file backing the file storage has the correct version number it was generated for. OS packages should have a script that (solely on upgrade) removes the file storage backend file, if it exists. This was tested on Ubuntu, but may be a problem on Red Hat as well. Ingvar -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 20 08:44:33 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 20 Dec 2010 08:44:33 -0000 Subject: [Varnish] #833: Panic message: Assert error in VRT_int_string() In-Reply-To: <044.59103fb3a1a0b5a0e4c1e9aa1e0ede0c@varnish-cache.org> References: <044.59103fb3a1a0b5a0e4c1e9aa1e0ede0c@varnish-cache.org> Message-ID: <053.bc70bd61b18eb9baeda8abbe84db218b@varnish-cache.org> #833: Panic message: Assert error in VRT_int_string() ----------------------+----------------------------------------------------- Reporter: mandark | Owner: kristian Type: defect | Status: assigned Priority: low | Milestone: Component: varnishd | Version: 2.1.2 Severity: normal | Keywords: panic, assert error, VRT_int_string ----------------------+----------------------------------------------------- Changes (by kristian): * priority: normal => low Comment: Any further update on this issue? It could also conceptually be triggered by some undefined aspects of VCL, so I'd like to see the VCL before I close this ticket. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 20 08:45:53 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 20 Dec 2010 08:45:53 -0000 Subject: [Varnish] #774: Panic message: Assert error in STV_alloc() In-Reply-To: <046.ecc2f4bc4f7ae0ce88547b074a00b027@varnish-cache.org> References: <046.ecc2f4bc4f7ae0ce88547b074a00b027@varnish-cache.org> Message-ID: <055.7d9d33f942ac906d10ff89762a3514c4@varnish-cache.org> #774: Panic message: Assert error in STV_alloc() -----------------------+---------------------------------------------------- Reporter: wittwerch | Owner: kristian Type: defect | Status: assigned Priority: low | Milestone: Component: varnishd | Version: 2.0 Severity: normal | Keywords: -----------------------+---------------------------------------------------- Comment(by kristian): Any further updates? Otherwise I'll have to close the ticket. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 20 09:28:31 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 20 Dec 2010 09:28:31 -0000 Subject: [Varnish] #774: Panic message: Assert error in STV_alloc() In-Reply-To: <046.ecc2f4bc4f7ae0ce88547b074a00b027@varnish-cache.org> References: <046.ecc2f4bc4f7ae0ce88547b074a00b027@varnish-cache.org> Message-ID: <055.249caa62251fcebccb93f15425b9ec86@varnish-cache.org> #774: Panic message: Assert error in STV_alloc() -----------------------+---------------------------------------------------- Reporter: wittwerch | Owner: kristian Type: defect | Status: assigned Priority: low | Milestone: Component: varnishd | Version: 2.0 Severity: normal | Keywords: -----------------------+---------------------------------------------------- Comment(by David Busby): Hi kristian, updating our varnish resolved this issue, apologies for not updating sooner, at the time the startup params were those bundled with the 2.0.x version from fedora EPEL, no special configurations were in place. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 20 09:37:24 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 20 Dec 2010 09:37:24 -0000 Subject: [Varnish] #774: Panic message: Assert error in STV_alloc() In-Reply-To: <046.ecc2f4bc4f7ae0ce88547b074a00b027@varnish-cache.org> References: <046.ecc2f4bc4f7ae0ce88547b074a00b027@varnish-cache.org> Message-ID: <055.f145baf16aab5fc5acc1fa78a5fccef7@varnish-cache.org> #774: Panic message: Assert error in STV_alloc() -----------------------+---------------------------------------------------- Reporter: wittwerch | Owner: kristian Type: defect | Status: closed Priority: low | Milestone: Component: varnishd | Version: 2.0 Severity: normal | Resolution: worksforme Keywords: | -----------------------+---------------------------------------------------- Changes (by kristian): * status: assigned => closed * resolution: => worksforme Comment: Ok, thanks for the feedback. Closing as worksforme since we never did really track it down properly - but it's seemingly fixed. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 20 10:04:00 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 20 Dec 2010 10:04:00 -0000 Subject: [Varnish] #833: Panic message: Assert error in VRT_int_string() In-Reply-To: <044.59103fb3a1a0b5a0e4c1e9aa1e0ede0c@varnish-cache.org> References: <044.59103fb3a1a0b5a0e4c1e9aa1e0ede0c@varnish-cache.org> Message-ID: <053.dc6ca046ab3a588ddf8ac3d3028f200d@varnish-cache.org> #833: Panic message: Assert error in VRT_int_string() ----------------------+----------------------------------------------------- Reporter: mandark | Owner: kristian Type: defect | Status: assigned Priority: low | Milestone: Component: varnishd | Version: 2.1.2 Severity: normal | Keywords: panic, assert error, VRT_int_string ----------------------+----------------------------------------------------- Comment(by mandark): Sorry, my VCL have a lot of changes every days, and I can't figure how it was this day. I'll increase sess_workspace and will reopen the ticket if the bug come back. Sorry for the missing informations )o: In the other hand, how can I monitor the available sess_workspace so I can anticipate this failure and calculate how much sess_workspace I need ? -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 20 10:12:12 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 20 Dec 2010 10:12:12 -0000 Subject: [Varnish] #833: Panic message: Assert error in VRT_int_string() In-Reply-To: <044.59103fb3a1a0b5a0e4c1e9aa1e0ede0c@varnish-cache.org> References: <044.59103fb3a1a0b5a0e4c1e9aa1e0ede0c@varnish-cache.org> Message-ID: <053.3351cdb6abd20712d06c8991c8f30d58@varnish-cache.org> #833: Panic message: Assert error in VRT_int_string() -------------------------------------------------+-------------------------- Reporter: mandark | Owner: kristian Type: defect | Status: closed Priority: low | Milestone: Component: varnishd | Version: 2.1.2 Severity: normal | Resolution: fixed Keywords: panic, assert error, VRT_int_string | -------------------------------------------------+-------------------------- Changes (by kristian): * status: assigned => closed * resolution: => fixed Comment: There isn't really a universal way to monitor it, I'm afraid. Certain things tend to eat up session workspace (esi being chief among the sinners). It's one of the things that sort of requires a bit of trial-and- error to get right. For further discussion on that, I recommend using the mail list (-misc) as you'll have a much larger audience (as will the reply). If you do run into this problem again, feel free to re-open the ticket though. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 20 10:12:46 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 20 Dec 2010 10:12:46 -0000 Subject: [Varnish] #833: Panic message: Assert error in VRT_int_string() In-Reply-To: <044.59103fb3a1a0b5a0e4c1e9aa1e0ede0c@varnish-cache.org> References: <044.59103fb3a1a0b5a0e4c1e9aa1e0ede0c@varnish-cache.org> Message-ID: <053.dae25739fb19bc8b05170a37f81a7f97@varnish-cache.org> #833: Panic message: Assert error in VRT_int_string() -------------------------------------------------+-------------------------- Reporter: mandark | Owner: kristian Type: defect | Status: reopened Priority: low | Milestone: Component: varnishd | Version: 2.1.2 Severity: normal | Resolution: Keywords: panic, assert error, VRT_int_string | -------------------------------------------------+-------------------------- Changes (by kristian): * status: closed => reopened * resolution: fixed => -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 20 10:12:53 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 20 Dec 2010 10:12:53 -0000 Subject: [Varnish] #833: Panic message: Assert error in VRT_int_string() In-Reply-To: <044.59103fb3a1a0b5a0e4c1e9aa1e0ede0c@varnish-cache.org> References: <044.59103fb3a1a0b5a0e4c1e9aa1e0ede0c@varnish-cache.org> Message-ID: <053.04abefdd4d22d41f888103c5108a885e@varnish-cache.org> #833: Panic message: Assert error in VRT_int_string() -------------------------------------------------+-------------------------- Reporter: mandark | Owner: kristian Type: defect | Status: closed Priority: low | Milestone: Component: varnishd | Version: 2.1.2 Severity: normal | Resolution: invalid Keywords: panic, assert error, VRT_int_string | -------------------------------------------------+-------------------------- Changes (by kristian): * status: reopened => closed * resolution: => invalid -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 20 13:13:29 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 20 Dec 2010 13:13:29 -0000 Subject: [Varnish] #838: file backend storage file should be removed at package upgrade In-Reply-To: <043.0a5310132f8efd5e6fb2a78ef728781f@varnish-cache.org> References: <043.0a5310132f8efd5e6fb2a78ef728781f@varnish-cache.org> Message-ID: <052.0eed745c2f1df9221762e8d5d3efb9b0@varnish-cache.org> #838: file backend storage file should be removed at package upgrade -----------------------+---------------------------------------------------- Reporter: ingvar | Owner: Type: defect | Status: new Priority: normal | Milestone: Component: packaging | Version: trunk Severity: normal | Keywords: -----------------------+---------------------------------------------------- Comment(by phk): I'm confused, I don't recall -sfile having any version numbers in the file ? Are you sure we are not talking -spersistent here ? -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 20 13:20:58 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 20 Dec 2010 13:20:58 -0000 Subject: [Varnish] #836: Display bug in varnishstat In-Reply-To: <043.a9f7b1ffc8082a1c667fa3db7404a740@varnish-cache.org> References: <043.a9f7b1ffc8082a1c667fa3db7404a740@varnish-cache.org> Message-ID: <052.8bdebc57d9009de434b15e794011eda5@varnish-cache.org> #836: Display bug in varnishstat -------------------------+-------------------------------------------------- Reporter: jelder | Owner: martin Type: defect | Status: new Priority: normal | Milestone: After Varnish 2.1 Component: varnishstat | Version: trunk Severity: normal | Keywords: -------------------------+-------------------------------------------------- Changes (by martin): * owner: phk => martin -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 20 13:44:52 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 20 Dec 2010 13:44:52 -0000 Subject: [Varnish] #837: varnishadm purge.list fails frequently In-Reply-To: <043.a2d15772321998574922abae75b7be94@varnish-cache.org> References: <043.a2d15772321998574922abae75b7be94@varnish-cache.org> Message-ID: <052.3a6019ee6bc5a2fafdcea45ef20d8dda@varnish-cache.org> #837: varnishadm purge.list fails frequently ----------------------+----------------------------------------------------- Reporter: jelder | Owner: kristian Type: defect | Status: new Priority: normal | Milestone: After Varnish 2.1 Component: varnishd | Version: trunk Severity: normal | Keywords: purge.list ----------------------+----------------------------------------------------- Changes (by kristian): * owner: phk => kristian Comment: Can you try if it fails in telnet too? You may have to disable the secret file to test it. Chances are you are running out of cli buffer-space. While you can adjust this with cli_buffer, that's obviously not a perfect solution when you have 11.5k purges. What I do suggest is using "smart bans" and the ban lurker, though, to keep the ban list shorter: http://kristianlyng.wordpress.com/2010/07/28 /smart-bans-with-varnish/ - it's not a solution to the freezing CLI, but it might be a work-around (and possibly a performance/utilization boost). -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 20 13:56:06 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 20 Dec 2010 13:56:06 -0000 Subject: [Varnish] #835: Varnish stops receiving incoming connections, but the process is still up In-Reply-To: <043.0b306324d23af01d5f961c07ada4c811@varnish-cache.org> References: <043.0b306324d23af01d5f961c07ada4c811@varnish-cache.org> Message-ID: <052.71def02bbf495a10f64313661353249c@varnish-cache.org> #835: Varnish stops receiving incoming connections, but the process is still up ----------------------+----------------------------------------------------- Reporter: blamer | Owner: kristian Type: defect | Status: new Priority: normal | Milestone: Varnish 2.1 release Component: varnishd | Version: 2.1.4 Severity: major | Keywords: broken pipe, freeze, crash ----------------------+----------------------------------------------------- Changes (by kristian): * owner: phk => kristian * priority: high => normal Comment: Can you check if syslog contains any information on Varnish? And/or possibly run varnish with -d in the foreground in some way... It would also be interesting if you're able to attach gdb to varnish and do 'thread apply all bt full' after the fact. We're also somewhat curious about general disk performance. As for the vcl, you probably want to make sure "connection: close" is set for piped connections: {{{ sub vcl_pipe { set bereq.http.connection = "close"; } }}} (I doubt pipe is the issue here - but it's conceptually possible.) The most likely culprit is epoll, so you may want to test a different waiter: -p waiter=poll Also: How often does this happen? What's the request-pressure when it happens? Can you check what netstat says at the time? Also: ls /proc/`pidof -s varnishd`/fd/ is of some interest (mostly the size/number of fd's in use). -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 20 17:02:14 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 20 Dec 2010 17:02:14 -0000 Subject: [Varnish] #837: varnishadm purge.list fails frequently In-Reply-To: <043.a2d15772321998574922abae75b7be94@varnish-cache.org> References: <043.a2d15772321998574922abae75b7be94@varnish-cache.org> Message-ID: <052.cfc0c827e715298e5c42df97b020be0d@varnish-cache.org> #837: varnishadm purge.list fails frequently ----------------------+----------------------------------------------------- Reporter: jelder | Owner: kristian Type: defect | Status: new Priority: normal | Milestone: After Varnish 2.1 Component: varnishd | Version: trunk Severity: normal | Keywords: purge.list ----------------------+----------------------------------------------------- Comment(by jelder): I've disabled the secret in one of the varnish instances in our staging environment. I will reply to the ticket once we've reached the absurd level of purges in production, and can verify that the issue is reproducible via telnet. We rely on saint mode (obj.grace = 1h), and as I understand things, enabling the ban lurker would purge objects from the cache which we might want to serve during an outage. Unless I misunderstand things, we would need ban lurker to be aware of the grace period in some way, right? {{{ sub vcl_recv { set req.backend = haproxy; if (req.backend.healthy) { /* A different thread has already made a request to the backend but it * hasn't completed yet. */ set req.grace = 30s; } else { /* Either HAProxy is down or it's telling us via /haproxy_test that all * of its backends are down. */ set req.grace = 1h; } } sub vcl_fetch { /* Enter saint mode when we see at least backend.saintmode_threshold of the * following errors in a period of 10 seconds. */ if ( beresp.status == 500 || /* Internal Server Error */ beresp.status == 502 || /* Bad Gateway */ beresp.status == 503 || /* Service Unavailable */ beresp.status == 504 /* Gateway Timeout */ ) { set beresp.saintmode = 10s; restart; } set beresp.grace = 1h; } }}} -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 20 17:07:06 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 20 Dec 2010 17:07:06 -0000 Subject: [Varnish] #837: varnishadm purge.list fails frequently In-Reply-To: <043.a2d15772321998574922abae75b7be94@varnish-cache.org> References: <043.a2d15772321998574922abae75b7be94@varnish-cache.org> Message-ID: <052.d9a0a73a6e5c8bc8d64e39286f84e1c7@varnish-cache.org> #837: varnishadm purge.list fails frequently ----------------------+----------------------------------------------------- Reporter: jelder | Owner: kristian Type: defect | Status: new Priority: normal | Milestone: After Varnish 2.1 Component: varnishd | Version: trunk Severity: normal | Keywords: purge.list ----------------------+----------------------------------------------------- Comment(by kristian): Once you purge the content it's not accessible through grace- or saint- mode. Grace is only for expired (not purged/banned) content. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Tue Dec 21 16:22:27 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Tue, 21 Dec 2010 16:22:27 -0000 Subject: [Varnish] #839: Varnish fails to start on boot for some FreeBSD machines Message-ID: <054.631b323b9c05fe09e2b12eed8c556e4e@varnish-cache.org> #839: Varnish fails to start on boot for some FreeBSD machines -------------------------------+-------------------------------------------- Reporter: james.m.henderson | Owner: phk Type: defect | Status: new Priority: normal | Milestone: Component: varnishd | Version: trunk Severity: normal | Keywords: -------------------------------+-------------------------------------------- Problem: When init tries to start varnish, the main network interface is not yet up (it is still loading asynchronously). When Varnish parses its configuration files, it tests each of the backend urls addresses to see if it responds. If any of the backends do not respond, varnish throws an error and will not start. Since the interface is not yet up, the first backend will not respond and varnish will not start. In this case all that is required is that Varnish waits a few seconds before giving up on the backend. As a workaround I ended up modifying my varnishd rc script to wait until the backend was responding before trying to run varnish. This is not an issue that is likely to occur on every machine as usually the interfaces would be up by the time that varnish is run, but evidently sometimes it takes a few seconds and the resulting race condition can stop the server from running varnish on boot. In particular the machines this happened on were both chroot jail virtual machines. -- Ticket URL: Varnish The Varnish HTTP Accelerator From jhalfmoon at milksnot.com Thu Dec 23 12:10:44 2010 From: jhalfmoon at milksnot.com (Johnny Halfmoon) Date: Thu, 23 Dec 2010 13:10:44 +0100 Subject: svn access broken? In-Reply-To: <20101217133614.2ygt2o704kwk0gs8@webmail.milksnot.com> References: <20101217133614.2ygt2o704kwk0gs8@webmail.milksnot.com> Message-ID: <20101223131044.xnn23be2skkgwkgo@webmail.milksnot.com> Hi, subversion access seems to be broken: $ svn co svn+ssh://varnish-cache.org/svn/varnish The authenticity of host 'varnish-cache.org (87.238.36.107)' can't be established. RSA key fingerprint is 2a:83:c8:16:b8:c6:44:b1:68:21:4f:04:20:86:6c:d9. Are you sure you want to continue connecting (yes/no)? yes svn: Network connection closed unexpectedly Either it is broken, or these instructions are: http://www.varnish-cache.org/trac/wiki/UsingSvnSvk I'm guessing svn is kaput. Maybe someone can fix it. Cheers, Johnny From phk at phk.freebsd.dk Thu Dec 23 22:07:09 2010 From: phk at phk.freebsd.dk (Poul-Henning Kamp) Date: Thu, 23 Dec 2010 22:07:09 +0000 Subject: svn access broken? In-Reply-To: Your message of "Thu, 23 Dec 2010 13:10:44 +0100." <20101223131044.xnn23be2skkgwkgo@webmail.milksnot.com> Message-ID: <17997.1293142029@critter.freebsd.dk> In message <20101223131044.xnn23be2skkgwkgo at webmail.milksnot.com>, Johnny Halfm oon writes: >subversion access seems to be broken: It works for me. Not sure if you can use svn+ssh without a login on the server. Try http: instead. -- Poul-Henning Kamp | UNIX since Zilog Zeus 3.20 phk at FreeBSD.ORG | TCP/IP since RFC 956 FreeBSD committer | BSD since 4.3-tahoe Never attribute to malice what can adequately be explained by incompetence. From varnish-bugs at varnish-cache.org Fri Dec 24 10:30:21 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Fri, 24 Dec 2010 10:30:21 -0000 Subject: [Varnish] #659: Varnish hcb_cleaner asset crash In-Reply-To: <044.b7bb3aeb2310d4da5e1d8404a8d9bb02@varnish-cache.org> References: <044.b7bb3aeb2310d4da5e1d8404a8d9bb02@varnish-cache.org> Message-ID: <053.3baac332bd5a6ab7c060c544768dbdf5@varnish-cache.org> #659: Varnish hcb_cleaner asset crash -------------------------+-------------------------------------------------- Reporter: victori | Type: defect Status: closed | Priority: normal Milestone: | Component: build Version: trunk | Severity: normal Resolution: worksforme | Keywords: -------------------------+-------------------------------------------------- Comment(by harm): I've seen this too on a relative low traffic site (<1000 visits/day). version: varnish 2.1.0-2 OS: Ubuntu 10.04.1 LTS This was marked worksforme 9 months ago, please check if the varnish version I see this bug in is later, and if so consider reopening this bug. {{{ Dec 24 10:42:13 true1 varnishd[24391]: Child (24392) died signal=6 Dec 24 10:42:13 true1 varnishd[24391]: Child (24392) Panic message: Assert error in hcb_cleaner(), hash_critbit.c line 362:#012 Condition((oh->refcnt) == 0) not true.#012thread = (hcb_cleaner)#012ident = Linux,2.6.32-26-server,x86_64,-smalloc,-hcritbit,epoll#012Backtrace:#012 0x4242e8: /usr/sbin/varnishd() [0x4242e8]#012 0x430199: /usr/sbin/varnishd() [0x430199]#012 0x7f613d6e19ca: /lib/libpthread.so.0(+0x69ca) [0x7f613d6e19ca]#012 0x7f613cfa170d: /lib/libc.so.6(clone+0x6d) [0x7f613cfa170d]#012 Dec 24 10:42:13 true1 varnishd[24391]: Child cleanup complete Dec 24 10:42:13 true1 varnishd[24391]: child (565) Started Dec 24 10:42:13 true1 varnishd[24391]: Child (565) said Closed fds: 3 4 5 6 7 11 12 14 15 Dec 24 10:42:13 true1 varnishd[24391]: Child (565) said Child starts }}} -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Sun Dec 26 21:35:21 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Sun, 26 Dec 2010 21:35:21 -0000 Subject: [Varnish] #659: Varnish hcb_cleaner asset crash In-Reply-To: <044.b7bb3aeb2310d4da5e1d8404a8d9bb02@varnish-cache.org> References: <044.b7bb3aeb2310d4da5e1d8404a8d9bb02@varnish-cache.org> Message-ID: <053.5b30601e2874e19a1f3783fd6d999c06@varnish-cache.org> #659: Varnish hcb_cleaner asset crash -------------------------+-------------------------------------------------- Reporter: victori | Type: defect Status: closed | Priority: normal Milestone: | Component: build Version: trunk | Severity: normal Resolution: worksforme | Keywords: -------------------------+-------------------------------------------------- Old description: > {{{ > > Feb 28 16:48:58 web varnishd[12]: [ID 192877 local0.error] Child (21) not > responding to ping, killing it. > Feb 28 16:49:01 web last message repeated 1 time > Feb 28 16:49:01 web varnishd[12]: [ID 214034 local0.error] Child (21) > Panic message: Assert error in hcb_cleaner(), hash_critbit.c line 362: > Feb 28 08:49:01 web Condition((oh->refcnt) == 0) not true. > Feb 28 08:49:01 web thread = (hcb_cleaner) > Feb 28 08:49:01 web ident = -sfile,-hcritbit,poll > Feb 28 08:49:01 web Backtrace: > Feb 28 08:49:01 web 430f73: /opt/extra/sbin/varnishd'pan_ic+0xc3 > [0x430f73] > Feb 28 08:49:01 web 18b41c0: [0x18b41c0] > > }}} New description: {{{ Feb 28 16:48:58 web varnishd[12]: [ID 192877 local0.error] Child (21) not responding to ping, killing it. Feb 28 16:49:01 web last message repeated 1 time Feb 28 16:49:01 web varnishd[12]: [ID 214034 local0.error] Child (21) Panic message: Assert error in hcb_cleaner(), hash_critbit.c line 362: Feb 28 08:49:01 web Condition((oh->refcnt) == 0) not true. Feb 28 08:49:01 web thread = (hcb_cleaner) Feb 28 08:49:01 web ident = -sfile,-hcritbit,poll Feb 28 08:49:01 web Backtrace: Feb 28 08:49:01 web 430f73: /opt/extra/sbin/varnishd'pan_ic+0xc3 [0x430f73] Feb 28 08:49:01 web 18b41c0: [0x18b41c0] }}} -- Comment(by kristian): Harm: You are running 2.1.0 which has known bugs with critbit which has been fixed. This is most likely one of them. Please upgrade. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Mon Dec 27 19:55:20 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Mon, 27 Dec 2010 19:55:20 -0000 Subject: [Varnish] #659: Varnish hcb_cleaner asset crash In-Reply-To: <044.b7bb3aeb2310d4da5e1d8404a8d9bb02@varnish-cache.org> References: <044.b7bb3aeb2310d4da5e1d8404a8d9bb02@varnish-cache.org> Message-ID: <053.dcce597e85b13eba699eae105865444c@varnish-cache.org> #659: Varnish hcb_cleaner asset crash -------------------------+-------------------------------------------------- Reporter: victori | Type: defect Status: closed | Priority: normal Milestone: | Component: build Version: trunk | Severity: normal Resolution: worksforme | Keywords: -------------------------+-------------------------------------------------- Comment(by harm): I'm seeing this crash every ~42 hours. I'm not sure if more ppl are seeing this problem, but it looks that the current version in ubuntu LTS is not up to par ? As ubuntu LTS is quite popular, maybe a fix is worth pushing downstream ? What is the appropriate path to get a fix for this pushed to ubuntu 10.04 LTS ? -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Tue Dec 28 01:17:08 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Tue, 28 Dec 2010 01:17:08 -0000 Subject: [Varnish] #840: Varnish on Cygwin-Windows Platform Message-ID: <042.766fbd7234f41043875c033a4974cac8@varnish-cache.org> #840: Varnish on Cygwin-Windows Platform -----------------------------+---------------------------------------------- Reporter: jdzst | Type: enhancement Status: new | Priority: normal Milestone: | Component: build Version: trunk | Severity: normal Keywords: cygwin, windows | -----------------------------+---------------------------------------------- I have been working last weeks improving varnish support of cygwin (windows) platform. [[BR]] Software version numbers are Cygwin 1.7.7(0.230/5/3) over Windows XP SP3 and varnish-trunk SVN 5661M Al my previous modifications for Cygwin support are explained in: [http://www.varnish-cache.org/trac/ticket/736 Ticket 736] After some changes and bugfixes in varnish, all regression tests works properly. There are three minor issues in some tests: - '''c00005.vtc''' test fails because there is a IPv6 address "::" in VCL that it is not supported by Cygwin in Windows XP. c00005.vtc works OK removing the IPv6 address and testing only IPv4. Perhaps in Windows Vista it will work: [http://www.cygwin.com/cygwin-ug-net/ov-new1.7.html] - '''m00002.vtc''' tests some random functions (drand48). The test checks the value returned for srand48 seed=1. In Cygwin after some fixes, the random numbers works OK, but their values are diferent than test expected for Unix systems. - '''s00002.vtc''' (Check grace with sick backends). The test does not works properly, but if we use the revision 4554 instead newer 5412, it works ok. There are also new improvements: - VMOD functionality that exists in svn trunk is added to Cygwin version. - Windows paths "c:\path, c:/path, \\machine\path" now are allowed in configuration parameters, only for Cygwin Builds. This allows to launch Varnish from Windows cmd.exe, outside Cygwin bash environment (using the Cygwin DLL) - It is possible to compile against windows native PDCurses ([http://pdcurses.sourceforge.net/]) instead Cygwin Ncurses 10. PDCurses programs can be used in Windows cmd.exe shell and Cygwin bash. NCurses 10 library only works inside Cygwin bash environment. After all this modifications, I am able to compile a Varnish-cygwin version that is linked against the following libraries: - '''cygwin1.dll :''' Cygwin main library - '''pdcurses.dll :''' PDCurses windows32 '''native''' library (http://pdcurses.sourceforge.net/) - '''pcre3.dll :''' Pcre for windows '''native''' library (http://gnuwin32.sourceforge.net/packages/pcre.htm) - '''Varnish own libraries:''' cygvarnish-1.dll, cygvarnishapi-1.dll, cygvarnishcompat-1.dll, cygvcl-1.dll - '''Windows own libraries:''' kernel32.dll, msvcrt.dll, ntdll.dll, GDI32.dll, etc... This minimal subset of DLL allows us to get rid of all the BIG cygwin installation and only install the proper '''cygwin1.dll''', our natives DLL (curses, pcre, varnish) and a reduced copy of a GCC installation in order to compile VCL. I have prepared a ZIP file with a complete Cygwin-Windows Varnish enviroment. It is a compressed ZIP of 5 Mb and does not need any previous software installation. It is stored in a sourceforge project: [https://sourceforge.net/projects/cygvarnish/files/] In the future I think it will be possible to make a source rewrite and replace in Windows all the Unix functions that now are managed by Cygwin1.dll. In that case, Cygwin could be used as only a Build plataform, using automake, make, gcc and others that will produce a native win32 program but this changes will be expensive. -- Ticket URL: Varnish The Varnish HTTP Accelerator From varnish-bugs at varnish-cache.org Tue Dec 28 03:16:35 2010 From: varnish-bugs at varnish-cache.org (Varnish) Date: Tue, 28 Dec 2010 03:16:35 -0000 Subject: [Varnish] #659: Varnish hcb_cleaner asset crash In-Reply-To: <044.b7bb3aeb2310d4da5e1d8404a8d9bb02@varnish-cache.org> References: <044.b7bb3aeb2310d4da5e1d8404a8d9bb02@varnish-cache.org> Message-ID: <053.58f12fe188cb6915e517812b29a39a61@varnish-cache.org> #659: Varnish hcb_cleaner asset crash -------------------------+-------------------------------------------------- Reporter: victori | Type: defect Status: closed | Priority: normal Milestone: | Component: build Version: trunk | Severity: normal Resolution: worksforme | Keywords: -------------------------+-------------------------------------------------- Comment(by kristian): Please don't use the bug tracker for general discussion. This issue is resolved and whatever Ubuntu does with regards to backporting fixes is not a topic of discussion in the upstream bug tracker. You'll have to take that up with Ubuntu - or at the very least use a mailing list (we have several). -- Ticket URL: Varnish The Varnish HTTP Accelerator