[jira] [Updated] (TS-1201) Crash report: hostdb multicache, double free
[ https://issues.apache.org/jira/browse/TS-1201?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1201: -- Description: {code} *** glibc detected *** /usr/bin/traffic_server: corrupted double-linked list: 0x1fe10ef0 *** === Backtrace: = /lib64/libc.so.6[0x3db2072555] /lib64/libc.so.6(cfree+0x4b)[0x3db20728bb] /usr/bin/traffic_server(MultiCacheSync::mcEvent(int, Event*)+0xa4)[0x5dae04] /usr/bin/traffic_server(EThread::process_event(Event*, int)+0x22f)[0x691c8f] /usr/bin/traffic_server(EThread::execute()+0x6a1)[0x692681] /usr/bin/traffic_server[0x69115e] /lib64/libpthread.so.0[0x3db280673d] /lib64/libc.so.6(clone+0x6d)[0x3db20d44bd] === Memory map: {code} was: {code} *** glibc detected *** /usr/bin/traffic_server: corrupted double-linked list: 0x1fe10ef0 *** === Backtrace: = /lib64/libc.so.6[0x3db2072555] /lib64/libc.so.6(cfree+0x4b)[0x3db20728bb] /usr/bin/traffic_server(_ZN14MultiCacheSync7mcEventEiP5Event+0xa4)[0x5dae04] /usr/bin/traffic_server(_ZN7EThread13process_eventEP5Eventi+0x22f)[0x691c8f] /usr/bin/traffic_server(_ZN7EThread7executeEv+0x6a1)[0x692681] /usr/bin/traffic_server[0x69115e] /lib64/libpthread.so.0[0x3db280673d] /lib64/libc.so.6(clone+0x6d)[0x3db20d44bd] === Memory map: {code} Crash report: hostdb multicache, double free Key: TS-1201 URL: https://issues.apache.org/jira/browse/TS-1201 Project: Traffic Server Issue Type: Bug Reporter: Zhao Yongming Assignee: weijin {code} *** glibc detected *** /usr/bin/traffic_server: corrupted double-linked list: 0x1fe10ef0 *** === Backtrace: = /lib64/libc.so.6[0x3db2072555] /lib64/libc.so.6(cfree+0x4b)[0x3db20728bb] /usr/bin/traffic_server(MultiCacheSync::mcEvent(int, Event*)+0xa4)[0x5dae04] /usr/bin/traffic_server(EThread::process_event(Event*, int)+0x22f)[0x691c8f] /usr/bin/traffic_server(EThread::execute()+0x6a1)[0x692681] /usr/bin/traffic_server[0x69115e] /lib64/libpthread.so.0[0x3db280673d] /lib64/libc.so.6(clone+0x6d)[0x3db20d44bd] === Memory map: {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-980) change client_session schedule from global to thread local, and reduce the try_locks in UnixNetVConnection::reenable
[ https://issues.apache.org/jira/browse/TS-980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-980: - Fix Version/s: (was: 3.1.4) 3.3.0 reschedule to 3.3.0, may need more tweak testing change client_session schedule from global to thread local, and reduce the try_locks in UnixNetVConnection::reenable - Key: TS-980 URL: https://issues.apache.org/jira/browse/TS-980 Project: Traffic Server Issue Type: Improvement Components: Network, Performance Affects Versions: 3.1.0, 3.0.0 Environment: all Reporter: weijin Assignee: weijin Fix For: 3.3.0 Attachments: ts-980.diff I did some performance test on ats last days(disable cache, set share_server session 2, pure proxy mode), I did see significant improvement on low load, but it dropped rapidly when load is high. meanwhile, some stability problems happened. Through gdb, I found the client_session`s mutex can be acquired by two or more threads, I believe some schedules happened during the sm life_time. May be we need do some work to find these eventProcessor.schedules and change them to thread schedules. UnixVConnecton::reenable { if (nh-mutex-thread_holding == t) { // put into ready_list } else { MUTEX_TRY_LOCK(lock, nh-mutex, t); if (!lock) { // put into enable_list; } else { // put into ready_list; } } remove UnixNetVConnection::reenable try_lock operations, 3 reasons 1. try_lock operation means obj allocation and deallocation operation. frequently 2. try_lock hardly can lock the net-handler`s mutex.(net-handler is schedule by as soon as possible) 3. try_lock should not acquire the net-handler`s mutex. That may lead more net io latency if it is an epoll event need to be processed in other threads. If it is not an epoll event(time event), I don`t think putting vc in ready_list has any advantage than in enable_list. may be we can change reenale function like this: UnixVConnecton::reenable { if (nh-mutex-thread_holding == t) { // put into ready_list; } else { // put into enable_list; } my buddies, any advice? -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1034) reduce futex locking period
[ https://issues.apache.org/jira/browse/TS-1034?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1034: -- Fix Version/s: (was: 3.1.4) 3.3.0 reduce futex locking period --- Key: TS-1034 URL: https://issues.apache.org/jira/browse/TS-1034 Project: Traffic Server Issue Type: Improvement Components: Core, HTTP Affects Versions: 3.1.1 Reporter: Zhao Yongming Assignee: Zhao Yongming Fix For: 3.3.0 we need to reduce futex locking period, here is a simple testing in my 24cores HP380 system, with 24 ab, all cached in memory: {code} #!/bin/sh for i in {1..24} do ab -n 1 -c 16 -X 127.0.0.$i:8080 http://img02.taobaocdn.com/tps/i2/T1o0ypXk4w-1000-40.png?$i done {code} result: {code} Every 2.0s: echo show:proxy-stats | traffic_shell Mon Nov 28 16:06:42 2011 Successfully Initialized MgmtAPI in /var/run/trafficserver Document Hit Rate 100.00 % * Bandwidth Saving - 100.00 % * Cache Percent Free --- 99.999619 % Open Server Connections -- 0 Open Client Connections -- 9 Open Cache Connections --- 2 Client Throughput 6824.747070 MBit/Sec Transaction Per Second --- 53914.925781 * Value represents 10 second average. strace -c -p 11712 Process 11712 attached - interrupt to quit ^CProcess 11712 detached % time seconds usecs/call callserrors syscall -- --- --- - - 26.850.890335 15 58920 writev 24.450.810866 7118147 epoll_ctl 22.270.738451 13 58920 close 11.500.381362 6 59227 getsockname 9.860.326843 3119192 59228 read 3.530.117058 16 7100 1931 futex 1.530.050884 58 884 epoll_wait 0.000.37 0 404 rt_sigprocmask 0.000.00 0 3 write 0.000.00 0 2 brk 0.000.00 010 msync -- --- --- - - 100.003.315836422809 61159 total {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1031) reduce lock in netHandler and reduce the possiblity of acquiring expire server sessions
[ https://issues.apache.org/jira/browse/TS-1031?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1031: -- Fix Version/s: (was: 3.1.4) 3.3.0 I think the patch should not be required after we fix the do_io_close issue, let us focus on other enhancement later. reduce lock in netHandler and reduce the possiblity of acquiring expire server sessions --- Key: TS-1031 URL: https://issues.apache.org/jira/browse/TS-1031 Project: Traffic Server Issue Type: Improvement Components: Core Affects Versions: 3.1.1 Reporter: Zhao Yongming Assignee: weijin Priority: Minor Fix For: 3.3.0 Attachments: ts-1031.diff reduce lock in netHandler and reduce the possiblity of acquiring expire server sessions. put your patch here for review :D -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1154) quick_filter on HEAD does not work
[ https://issues.apache.org/jira/browse/TS-1154?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1154: -- Fix Version/s: (was: 3.1.4) 3.0.4 we do not need to fix the current git master, let us just fix it in 3.0.4 quick_filter on HEAD does not work -- Key: TS-1154 URL: https://issues.apache.org/jira/browse/TS-1154 Project: Traffic Server Issue Type: Bug Components: HTTP Reporter: Zhao Yongming Assignee: weijin Fix For: 3.0.4 Attachments: head_method.diff we take quick filter as a good solution for some security concern, but when I set it to 0x0733, it does not allow HEAD in, but setting as 0x0723 does that. Weijin have the patch in our tree: https://gitorious.org/trafficserver/taobao/commit/cb23b87d167da4074e047fabc94786003ee94e9a/diffs/db7d0e5be69988b531e8d1e4eea717e6d46df5cd I will commit if no one complain in 2 days. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1151) in some strange situation, cop will crash
[ https://issues.apache.org/jira/browse/TS-1151?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1151: -- Description: we get some strange crash, the manager cop may die, we are not sure what that is, but I'd like to start one Issue here if we have other same issue. here is the log in /var/log/messages {code} Mar 19 10:08:24 cache172.cn77 kernel:: [1553138.961401] [ET_NET 2][17949]: segfault at 2aadf1387937 ip 003c5bc7bdbe sp 410f3188 error 4 in libc-2.5.so[3c5bc0+14d000] Mar 19 10:08:27 cache172.cn77 traffic_manager[17935]: {0x7ff0c8d51720} FATAL: [LocalManager::pollMgmtProcessServer] Error in read (errno: 104) Mar 19 10:08:27 cache172.cn77 traffic_manager[17935]: {0x7ff0c8d51720} FATAL: (last system error 104: Connection reset by peer) Mar 19 10:08:27 cache172.cn77 traffic_manager[17935]: {0x7ff0c8d51720} ERROR: [LocalManager::sendMgmtMsgToProcesses] Error writing message Mar 19 10:08:27 cache172.cn77 traffic_manager[17935]: {0x7ff0c8d51720} ERROR: (last system error 32: Broken pipe) Mar 19 10:08:33 cache172.cn77 traffic_cop[17933]: cop received child status signal [17935 2816] Mar 19 10:08:33 cache172.cn77 traffic_cop[17933]: traffic_manager not running, making sure traffic_server is dead Mar 19 10:08:33 cache172.cn77 traffic_cop[17933]: spawning traffic_manager Mar 19 10:08:40 cache172.cn77 traffic_manager[2760]: NOTE: --- Manager Starting --- Mar 19 10:08:40 cache172.cn77 traffic_manager[2760]: NOTE: Manager Version: Apache Traffic Server - traffic_manager - 3.0.2 - (build # 299 on Mar 9 2012 at 09:55:44) Mar 19 10:08:40 cache172.cn77 traffic_manager[2760]: {0x7fd03d265720} STATUS: opened /var/log/trafficserver/manager.log Mar 19 10:08:46 cache172.cn77 traffic_cop[17933]: (cli test) unable to retrieve manager_binary Mar 19 10:08:54 cache172.cn77 traffic_server[2789]: NOTE: --- Server Starting --- Mar 19 10:08:54 cache172.cn77 traffic_server[2789]: NOTE: Server Version: Apache Traffic Server - traffic_server - 3.0.2 - (build # 299 on Mar 9 2012 at 09:56:00) Mar 19 10:09:00 cache172.cn77 traffic_server[2789]: {0x2b5a8ef03970} STATUS: opened /var/log/trafficserver/diags.log Mar 19 10:14:02 cache172.cn77 kernel:: [1553476.364204] [ET_NET 0][2789]: segfault at 2aab1fa99ce3 ip 003c5bc7bdbe sp 7fff39743fa8 error 4 in libc-2.5.so[3c5bc0+14d000] Mar 19 10:14:03 cache172.cn77 traffic_manager[2760]: {0x7fd03d265720} FATAL: [LocalManager::pollMgmtProcessServer] Error in read (errno: 104) Mar 19 10:14:03 cache172.cn77 traffic_manager[2760]: {0x7fd03d265720} FATAL: (last system error 104: Connection reset by peer) Mar 19 10:14:03 cache172.cn77 traffic_manager[2760]: {0x7fd03d265720} ERROR: [LocalManager::sendMgmtMsgToProcesses] Error writing message Mar 19 10:14:03 cache172.cn77 traffic_manager[2760]: {0x7fd03d265720} ERROR: (last system error 32: Broken pipe) {code} here is the message in traffic.out {code} Mar 19 10:11:06 cache162.cn77 kernel:: [2510081.212455] [ET_NET 3][319]: segfault at 2aaae6e986bc ip 003f7f27bdbe sp 40be2188 error 4 in libc-2.5.so[3f7f20+14d000] Mar 19 10:11:09 cache162.cn77 traffic_manager[305]: {0x7fd3a665c720} FATAL: [LocalManager::pollMgmtProcessServer] Error in read (errno: 104) Mar 19 10:11:09 cache162.cn77 traffic_manager[305]: {0x7fd3a665c720} FATAL: (last system error 104: Connection reset by peer) Mar 19 10:11:09 cache162.cn77 traffic_manager[305]: {0x7fd3a665c720} ERROR: [LocalManager::sendMgmtMsgToProcesses] Error writing message Mar 19 10:11:09 cache162.cn77 traffic_manager[305]: {0x7fd3a665c720} ERROR: (last system error 32: Broken pipe) Mar 19 10:11:09 cache162.cn77 traffic_cop[303]: cop received child status signal [305 2816] Mar 19 10:11:09 cache162.cn77 traffic_cop[303]: traffic_manager not running, making sure traffic_server is dead Mar 19 10:11:09 cache162.cn77 traffic_cop[303]: spawning traffic_manager Mar 19 10:11:16 cache162.cn77 traffic_manager[1227]: NOTE: --- Manager Starting --- Mar 19 10:11:16 cache162.cn77 traffic_manager[1227]: NOTE: Manager Version: Apache Traffic Server - traffic_manager - 3.0.2 - (build # 299 on Mar 9 2012 at 09:55:44) Mar 19 10:11:16 cache162.cn77 traffic_manager[1227]: {0x7f8ae2f48720} STATUS: opened /var/log/trafficserver/manager.log Mar 19 10:11:23 cache162.cn77 traffic_cop[303]: (cli test) unable to retrieve manager_binary Mar 19 10:11:39 cache162.cn77 traffic_server[1260]: NOTE: --- Server Starting --- Mar 19 10:11:39 cache162.cn77 traffic_server[1260]: NOTE: Server Version: Apache Traffic Server - traffic_server - 3.0.2 - (build # 299 on Mar 9 2012 at 09:56:00) Mar 19 10:11:46 cache162.cn77 traffic_server[1260]: {0x2ad4afd3d970} STATUS: opened /var/log/trafficserver/diags.log Mar 19 10:15:06 cache162.cn77 kernel:: [2510320.713808] [ET_NET 3][1277]: segfault at 2aab1cfa6a03 ip 003f7f27bdbe sp 4141c188 error 4 in
[jira] [Updated] (TS-1114) Crash report: HttpTransactCache::SelectFromAlternates
[ https://issues.apache.org/jira/browse/TS-1114?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1114: -- Fix Version/s: (was: 3.1.5) 3.1.3 this patch runs perfect in our production for weeks Crash report: HttpTransactCache::SelectFromAlternates - Key: TS-1114 URL: https://issues.apache.org/jira/browse/TS-1114 Project: Traffic Server Issue Type: Bug Reporter: Zhao Yongming Assignee: weijin Fix For: 3.1.3 Attachments: cache_crash.diff it may or may not be the upstream issue, let us open it for tracking. {code} #0 0x0053075e in HttpTransactCache::SelectFromAlternates (cache_vector=0x2aaab80ff500, client_request=0x2aaab80ff4c0, http_config_params=0x2aaab547b800) at ../../proxy/hdrs/HTTP.h:1375 1375((int32_t *) val)[0] = m_alt-m_object_key[0]; {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1002) log unmapped HOST when pristine_host_hdr disabled
[ https://issues.apache.org/jira/browse/TS-1002?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1002: -- Attachment: TS-1002.patch I have create a new cquuh ( client_req_unmapped_url_host ), which is what your needs, this patch will apply to git master config: Format = %cquuc %cquup %cquuh / result: http://cdn.zymlinux.net/trafficserver/ts75.png /trafficserver/ts75.png cdn.zymlinux.net please test review log unmapped HOST when pristine_host_hdr disabled - Key: TS-1002 URL: https://issues.apache.org/jira/browse/TS-1002 Project: Traffic Server Issue Type: Wish Components: Logging Reporter: Conan Wang Assignee: Zhao Yongming Priority: Minor Fix For: 3.1.5 Attachments: TS-1002.patch I want to log user request's Host in http header before remap. I write logs_xml.config, like: %{Host}cqh When proxy.config.url_remap.pristine_host_hdr is enabled, I will get the right Host which is not rewritten. When disable the config, I always get the rewritten/mapped Host which is not what I need. logs_xml reference: http://trafficserver.apache.org/docs/v2/admin/logfmts.htm#66912 -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1002) log unmapped HOST when pristine_host_hdr disabled
[ https://issues.apache.org/jira/browse/TS-1002?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1002: -- Fix Version/s: (was: 3.1.5) 3.1.3 log unmapped HOST when pristine_host_hdr disabled - Key: TS-1002 URL: https://issues.apache.org/jira/browse/TS-1002 Project: Traffic Server Issue Type: Wish Components: Logging Reporter: Conan Wang Assignee: Zhao Yongming Priority: Minor Fix For: 3.1.3 Attachments: TS-1002.patch I want to log user request's Host in http header before remap. I write logs_xml.config, like: %{Host}cqh When proxy.config.url_remap.pristine_host_hdr is enabled, I will get the right Host which is not rewritten. When disable the config, I always get the rewritten/mapped Host which is not what I need. logs_xml reference: http://trafficserver.apache.org/docs/v2/admin/logfmts.htm#66912 -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-348) Infinite core file creation
[ https://issues.apache.org/jira/browse/TS-348?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-348: - Assignee: Zhao Yongming we should make sure the admin user is there, the attached patch is a good proposal. Infinite core file creation --- Key: TS-348 URL: https://issues.apache.org/jira/browse/TS-348 Project: Traffic Server Issue Type: Bug Components: Configuration Affects Versions: 2.1.0 Reporter: Mladen Turk Assignee: Zhao Yongming Priority: Critical Fix For: sometime Attachments: ts-348-proposed.patch If traffic server is started with non root user account the launch script endlessly loops in start attempts generating core.PID file on each iteration. This creates 80+ MB core file about each second until the disk gets full. The following log entry is added on each iteration: E. Mgmt] log == [TrafficManager] using root directory '/home/mturk/tmp/trafficserver-trunk/trunk-svn/release1/usr/local' [May 13 12:50:18.299] {3086546656} STATUS: opened var/log/trafficserver/manager.log [TrafficServer] using root directory '/home/mturk/tmp/trafficserver-trunk/trunk-svn/release1/usr/local' [May 13 12:50:20.830] {1074246896} STATUS: opened var/log/trafficserver/diags.log FATAL: Can't change group to user: nobody, gid: 99 /home/mturk/tmp/trafficserver-trunk/trunk-svn/release1/usr/local/bin/traffic_server - STACK TRACE: /home/mturk/tmp/trafficserver-trunk/trunk-svn/release1/usr/local/bin/traffic_server(ink_fatal_va+0x8f)[0x83451c7] /home/mturk/tmp/trafficserver-trunk/trunk-svn/release1/usr/local/bin/traffic_server(ink_fatal_die+0x1d)[0x83451f7] /home/mturk/tmp/trafficserver-trunk/trunk-svn/release1/usr/local/bin/traffic_server(_Z14change_uid_gidPKc+0xd8)[0x8152a52] /home/mturk/tmp/trafficserver-trunk/trunk-svn/release1/usr/local/bin/traffic_server(main+0x1296)[0x8153e68] /lib/libc.so.6(__libc_start_main+0xdc)[0x7bee9c] /home/mturk/tmp/trafficserver-trunk/trunk-svn/release1/usr/local/bin/traffic_server[0x80f3b31] [May 13 12:50:21.176] Manager {3086546656} ERROR: [LocalManager::pollMgmtProcessServer] Server Process terminated due to Sig 6: Aborted [May 13 12:50:21.176] Manager {3086546656} ERROR: (last system error 2: No such file or directory) [May 13 12:50:21.176] Manager {3086546656} ERROR: [Alarms::signalAlarm] Server Process was reset [May 13 12:50:21.176] Manager {3086546656} ERROR: (last system error 2: No such file or directory) -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1111) crash in RangeTransform::handle_event
[ https://issues.apache.org/jira/browse/TS-?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-: -- Fix Version/s: (was: 3.1.4) 3.1.3 crash in RangeTransform::handle_event - Key: TS- URL: https://issues.apache.org/jira/browse/TS- Project: Traffic Server Issue Type: Bug Reporter: Zhao Yongming Assignee: weijin Labels: crash Fix For: 3.1.3 Attachments: transform.patch we have some crashing in range requesting processing, it is on our own tree based on 3.0.x, that maybe the root cause of the do_io_close issue, we are still look at how to fix that, feedback is welcome {code} #0 0x004dc624 in RangeTransform::handle_event (this=0x2aaed0001fb0, event=1, edata=value optimized out) at Transform.cc:926 926 Debug(transform_range, RangeTransform destroy: %d, m_output_vio ? m_output_vio-ndone : 0); (gdb) bt #0 0x004dc624 in RangeTransform::handle_event (this=0x2aaed0001fb0, event=1, edata=value optimized out) at Transform.cc:926 #1 0x0069145f in EThread::process_event (this=0x2b332010, e=0x591d410, calling_code=1) at I_Continuation.h:146 #2 0x00691b8b in EThread::execute (this=0x2b332010) at UnixEThread.cc:218 #3 0x0069092e in spawn_thread_internal (a=0x440bfa0) at Thread.cc:88 #4 0x00359fe0673d in pthread_create@@GLIBC_2.2.5 () from /lib64/libpthread.so.0 #5 0x in ?? () (gdb) p m_output_vio $1 = (VIO *) 0x2aaed0029fe8 (gdb) p *m_output_vio Cannot access memory at address 0x2aaed0029fe8 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1109) stack dump may crash too
[ https://issues.apache.org/jira/browse/TS-1109?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1109: -- Fix Version/s: (was: 3.1.4) 3.1.3 stack dump may crash too Key: TS-1109 URL: https://issues.apache.org/jira/browse/TS-1109 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 3.1.2 Reporter: Zhao Yongming Assignee: weijin Labels: crash Fix For: 3.1.3 Attachments: cop_crash.diff the codes doing stack dump may crash, in this case you will not able to get a core file, that will hide most of the rare issues. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1111) crash in RangeTransform::handle_event
[ https://issues.apache.org/jira/browse/TS-?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-: -- Attachment: transform.patch this is a stupid patch for the current issue, it will not prevent all the crashing. taorui(Wei Jin) will submit a cool fix and clear all the do_io_close related crashing. we are testing in our production, so far so good till now. crash in RangeTransform::handle_event - Key: TS- URL: https://issues.apache.org/jira/browse/TS- Project: Traffic Server Issue Type: Bug Reporter: Zhao Yongming Assignee: weijin Labels: crash Fix For: 3.1.3 Attachments: transform.patch we have some crashing in range requesting processing, it is on our own tree based on 3.0.x, that maybe the root cause of the do_io_close issue, we are still look at how to fix that, feedback is welcome {code} #0 0x004dc624 in RangeTransform::handle_event (this=0x2aaed0001fb0, event=1, edata=value optimized out) at Transform.cc:926 926 Debug(transform_range, RangeTransform destroy: %d, m_output_vio ? m_output_vio-ndone : 0); (gdb) bt #0 0x004dc624 in RangeTransform::handle_event (this=0x2aaed0001fb0, event=1, edata=value optimized out) at Transform.cc:926 #1 0x0069145f in EThread::process_event (this=0x2b332010, e=0x591d410, calling_code=1) at I_Continuation.h:146 #2 0x00691b8b in EThread::execute (this=0x2b332010) at UnixEThread.cc:218 #3 0x0069092e in spawn_thread_internal (a=0x440bfa0) at Thread.cc:88 #4 0x00359fe0673d in pthread_create@@GLIBC_2.2.5 () from /lib64/libpthread.so.0 #5 0x in ?? () (gdb) p m_output_vio $1 = (VIO *) 0x2aaed0029fe8 (gdb) p *m_output_vio Cannot access memory at address 0x2aaed0029fe8 {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1068) we should not wait all the prefetch clients finish
[ https://issues.apache.org/jira/browse/TS-1068?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1068: -- Component/s: HTTP Description: when one request is on prefetching, we should not wait for all the prefetch clients, as there will be minutes or even hours. Affects Version/s: 3.1.1 we should not wait all the prefetch clients finish -- Key: TS-1068 URL: https://issues.apache.org/jira/browse/TS-1068 Project: Traffic Server Issue Type: Sub-task Components: HTTP Affects Versions: 3.1.1 Reporter: Zhao Yongming Fix For: 3.1.4 when one request is on prefetching, we should not wait for all the prefetch clients, as there will be minutes or even hours. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1069) better handle of the gzipped content
[ https://issues.apache.org/jira/browse/TS-1069?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1069: -- Description: when the triggered URL is gzipped, prefetch engine will skip that request, while not put that URL in the prefetch url list, and start another request without accept gzip encodes? Summary: better handle of the gzipped content (was: better handle of the gziped content) better handle of the gzipped content Key: TS-1069 URL: https://issues.apache.org/jira/browse/TS-1069 Project: Traffic Server Issue Type: Sub-task Reporter: Zhao Yongming Fix For: 3.1.4 when the triggered URL is gzipped, prefetch engine will skip that request, while not put that URL in the prefetch url list, and start another request without accept gzip encodes? -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1059) prefetch segment fault
[ https://issues.apache.org/jira/browse/TS-1059?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1059: -- Fix Version/s: 3.1.3 Labels: crash (was: ) prefetch segment fault -- Key: TS-1059 URL: https://issues.apache.org/jira/browse/TS-1059 Project: Traffic Server Issue Type: Sub-task Components: HTTP Affects Versions: 3.0.2 Environment: linux(ubuntu) Reporter: yunfei chen Labels: crash Fix For: 3.1.3 I encountered a segment faut when I was testing Prefetch module。 ab -n 1 -c 1 -X 192.168.16.198:8080 -d http://club.baobao.sohu.com/r-mmbb-3954004-0-29-900.html configuration in records.config CONFIG proxy.config.prefetch.prefetch_enabled INT 1 configuration in prefetch.config prefetch_children 192.168.16.198 html_tag img src #0 0x08124f17 in VIO::reenable (this=0x0) at ../iocore/eventsystem/P_VIO.h:123 #1 0x08147fe3 in KeepAliveConn::append (this=0xab9aef20, rdr=0x9c91b794) at Prefetch.cc:1984 #2 0x08145fd7 in KeepAliveConnTable::append (this=0xb2393608, ip=16777343, buf=0x9c91b780, reader=0x9c91b794) at Prefetch.cc:2039 #3 0x0814679b in KeepAliveLockHandler::handleEvent (this=0xb23e0b30, event=2, data=0x8ab2f60) at Prefetch.cc:2168 #4 0x08104ba5 in Continuation::handleEvent (this=0xb23e0b30, event=2, data=0x8ab2f60) at ../iocore/eventsystem/I_Continuation.h:146 #5 0x0830a9f5 in EThread::process_event (this=0xb7396008, e=0x8ab2f60, calling_code=2) at UnixEThread.cc:140 #6 0x0830add5 in EThread::execute (this=0xb7396008) at UnixEThread.cc:217 #7 0x0830900e in spawn_thread_internal (a=0x895eed8) at Thread.cc:88 #8 0x00165cc9 in start_thread (arg=0xb6f91b70) at pthread_create.c:304 #9 0x0066f69e in clone () at ../sysdeps/unix/sysv/linux/i386/clone.S:130 #0 0x08124f17 in VIO::reenable (this=0x0) at ../iocore/eventsystem/P_VIO.h:123 #1 0x08147fe3 in KeepAliveConn::append (this=0xa5736888, rdr=0x8d0b2f4) at Prefetch.cc:1984 #2 0x08145fd7 in KeepAliveConnTable::append (this=0xb2393608, ip=16777343, buf=0x8d0b2e0, reader=0x8d0b2f4) at Prefetch.cc:2039 #3 0x08141db3 in PrefetchUrlBlaster::udpUrlBlaster (this=0x8abd3e0, event=3300, data=0x0) at Prefetch.cc:885 #4 0x0813e4ea in PrefetchUrlBlaster::init (this=0x8abd3e0, list_head=0xabc59ac0, u_proto=TCP_BLAST) at Prefetch.h:280 #5 0x08147806 in BlasterUrlList::invokeUrlBlaster (this=0xa7c22260) at Prefetch.h:287 #6 0x08141ac8 in BlasterUrlList::handleEvent (this=0xa7c22260, event=3302, data=0xabc59ac0) at Prefetch.cc:803 #7 0x08143c89 in PrefetchBlaster::handleEvent (this=0xa5739920, event=2, data=0x0) at Prefetch.cc:1420 #8 0x08144f42 in PrefetchBlaster::invokeBlaster (this=0xa5739920) at Prefetch.cc:1769 #9 0x08143e22 in PrefetchBlaster::handleEvent (this=0xa5739920, event=1102, data=0xb23cdca0) at Prefetch.cc:1448 #10 0x08104ba5 in Continuation::handleEvent (this=0xa5739920, event=1102, data=0xb23cdca0) at ../iocore/eventsystem/I_Continuation.h:146 #11 0x082c1abf in CacheVC::callcont (this=0xb23cdca0, event=1102) at P_CacheInternal.h:629 #12 0x082c1487 in CacheVC::openReadStartHead (this=0xb23cdca0, event=3900, e=0x0) at CacheRead.cc:1115 #13 0x08104ba5 in Continuation::handleEvent (this=0xb23cdca0, event=3900, data=0x0) at ../iocore/eventsystem/I_Continuation.h:146 #14 0x082c1431 in CacheVC::openReadStartHead (this=0xb23cdca0, event=2, e=0x8ab48a0) at CacheRead.cc:1112 #15 0x08104ba5 in Continuation::handleEvent (this=0xb23cdca0, event=2, data=0x8ab48a0) at ../iocore/eventsystem/I_Continuation.h:146 #16 0x0830a9f5 in EThread::process_event (this=0xb7295008, e=0x8ab48a0, calling_code=2) at UnixEThread.cc:140 #17 0x0830add5 in EThread::execute (this=0xb7295008) at UnixEThread.cc:217 #18 0x0830900e in spawn_thread_internal (a=0x895dd00) at Thread.cc:88 #19 0x00165cc9 in start_thread (arg=0xb6e90b70) at pthread_create.c:304 #20 0x0066f69e in clone () at ../sysdeps/unix/sysv/linux/i386/clone.S:130 -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1059) prefetch segment fault
[ https://issues.apache.org/jira/browse/TS-1059?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1059: -- Issue Type: Sub-task (was: Bug) Parent: TS-893 prefetch segment fault -- Key: TS-1059 URL: https://issues.apache.org/jira/browse/TS-1059 Project: Traffic Server Issue Type: Sub-task Components: HTTP Affects Versions: 3.0.2 Environment: linux(ubuntu) Reporter: yunfei chen I encountered a segment faut when I was testing Prefetch module。 ab -n 1 -c 1 -X 192.168.16.198:8080 -d http://club.baobao.sohu.com/r-mmbb-3954004-0-29-900.html configuration in records.config CONFIG proxy.config.prefetch.prefetch_enabled INT 1 configuration in prefetch.config prefetch_children 192.168.16.198 html_tag img src #0 0x08124f17 in VIO::reenable (this=0x0) at ../iocore/eventsystem/P_VIO.h:123 #1 0x08147fe3 in KeepAliveConn::append (this=0xab9aef20, rdr=0x9c91b794) at Prefetch.cc:1984 #2 0x08145fd7 in KeepAliveConnTable::append (this=0xb2393608, ip=16777343, buf=0x9c91b780, reader=0x9c91b794) at Prefetch.cc:2039 #3 0x0814679b in KeepAliveLockHandler::handleEvent (this=0xb23e0b30, event=2, data=0x8ab2f60) at Prefetch.cc:2168 #4 0x08104ba5 in Continuation::handleEvent (this=0xb23e0b30, event=2, data=0x8ab2f60) at ../iocore/eventsystem/I_Continuation.h:146 #5 0x0830a9f5 in EThread::process_event (this=0xb7396008, e=0x8ab2f60, calling_code=2) at UnixEThread.cc:140 #6 0x0830add5 in EThread::execute (this=0xb7396008) at UnixEThread.cc:217 #7 0x0830900e in spawn_thread_internal (a=0x895eed8) at Thread.cc:88 #8 0x00165cc9 in start_thread (arg=0xb6f91b70) at pthread_create.c:304 #9 0x0066f69e in clone () at ../sysdeps/unix/sysv/linux/i386/clone.S:130 #0 0x08124f17 in VIO::reenable (this=0x0) at ../iocore/eventsystem/P_VIO.h:123 #1 0x08147fe3 in KeepAliveConn::append (this=0xa5736888, rdr=0x8d0b2f4) at Prefetch.cc:1984 #2 0x08145fd7 in KeepAliveConnTable::append (this=0xb2393608, ip=16777343, buf=0x8d0b2e0, reader=0x8d0b2f4) at Prefetch.cc:2039 #3 0x08141db3 in PrefetchUrlBlaster::udpUrlBlaster (this=0x8abd3e0, event=3300, data=0x0) at Prefetch.cc:885 #4 0x0813e4ea in PrefetchUrlBlaster::init (this=0x8abd3e0, list_head=0xabc59ac0, u_proto=TCP_BLAST) at Prefetch.h:280 #5 0x08147806 in BlasterUrlList::invokeUrlBlaster (this=0xa7c22260) at Prefetch.h:287 #6 0x08141ac8 in BlasterUrlList::handleEvent (this=0xa7c22260, event=3302, data=0xabc59ac0) at Prefetch.cc:803 #7 0x08143c89 in PrefetchBlaster::handleEvent (this=0xa5739920, event=2, data=0x0) at Prefetch.cc:1420 #8 0x08144f42 in PrefetchBlaster::invokeBlaster (this=0xa5739920) at Prefetch.cc:1769 #9 0x08143e22 in PrefetchBlaster::handleEvent (this=0xa5739920, event=1102, data=0xb23cdca0) at Prefetch.cc:1448 #10 0x08104ba5 in Continuation::handleEvent (this=0xa5739920, event=1102, data=0xb23cdca0) at ../iocore/eventsystem/I_Continuation.h:146 #11 0x082c1abf in CacheVC::callcont (this=0xb23cdca0, event=1102) at P_CacheInternal.h:629 #12 0x082c1487 in CacheVC::openReadStartHead (this=0xb23cdca0, event=3900, e=0x0) at CacheRead.cc:1115 #13 0x08104ba5 in Continuation::handleEvent (this=0xb23cdca0, event=3900, data=0x0) at ../iocore/eventsystem/I_Continuation.h:146 #14 0x082c1431 in CacheVC::openReadStartHead (this=0xb23cdca0, event=2, e=0x8ab48a0) at CacheRead.cc:1112 #15 0x08104ba5 in Continuation::handleEvent (this=0xb23cdca0, event=2, data=0x8ab48a0) at ../iocore/eventsystem/I_Continuation.h:146 #16 0x0830a9f5 in EThread::process_event (this=0xb7295008, e=0x8ab48a0, calling_code=2) at UnixEThread.cc:140 #17 0x0830add5 in EThread::execute (this=0xb7295008) at UnixEThread.cc:217 #18 0x0830900e in spawn_thread_internal (a=0x895dd00) at Thread.cc:88 #19 0x00165cc9 in start_thread (arg=0xb6e90b70) at pthread_create.c:304 #20 0x0066f69e in clone () at ../sysdeps/unix/sysv/linux/i386/clone.S:130 -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1034) reduce futex locking period
[ https://issues.apache.org/jira/browse/TS-1034?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1034: -- Description: we need to reduce futex locking period, here is a simple testing in my 24cores HP380 system, with 24 ab, all cached in memory: {code} #!/bin/sh for i in {1..24} do ab -n 1 -c 16 -X 127.0.0.$i:8080 http://img02.taobaocdn.com/tps/i2/T1o0ypXk4w-1000-40.png?$i done {code} result: {code} Every 2.0s: echo show:proxy-stats | traffic_shell Mon Nov 28 16:06:42 2011 Successfully Initialized MgmtAPI in /var/run/trafficserver Document Hit Rate 100.00 % * Bandwidth Saving - 100.00 % * Cache Percent Free --- 99.999619 % Open Server Connections -- 0 Open Client Connections -- 9 Open Cache Connections --- 2 Client Throughput 6824.747070 MBit/Sec Transaction Per Second --- 53914.925781 * Value represents 10 second average. strace -c -p 11712 Process 11712 attached - interrupt to quit ^CProcess 11712 detached % time seconds usecs/call callserrors syscall -- --- --- - - 26.850.890335 15 58920 writev 24.450.810866 7118147 epoll_ctl 22.270.738451 13 58920 close 11.500.381362 6 59227 getsockname 9.860.326843 3119192 59228 read 3.530.117058 16 7100 1931 futex 1.530.050884 58 884 epoll_wait 0.000.37 0 404 rt_sigprocmask 0.000.00 0 3 write 0.000.00 0 2 brk 0.000.00 010 msync -- --- --- - - 100.003.315836422809 61159 total {code} was: we need to reduce futex locking period, here is a simple testing in my 24cores HP380 system, with 24 ab: {codes} #!/bin/sh for i in {1..24} do ab -n 1 -c 16 -X 127.0.0.$i:8080 http://img02.taobaocdn.com/tps/i2/T1o0ypXk4w-1000-40.png?$i done {codes} result: {codes} Every 2.0s: echo show:proxy-stats | traffic_shell Mon Nov 28 16:06:42 2011 Successfully Initialized MgmtAPI in /var/run/trafficserver Document Hit Rate 100.00 % * Bandwidth Saving - 100.00 % * Cache Percent Free --- 99.999619 % Open Server Connections -- 0 Open Client Connections -- 9 Open Cache Connections --- 2 Client Throughput 6824.747070 MBit/Sec Transaction Per Second --- 53914.925781 * Value represents 10 second average. [r...@hp380g7test.sqa.cm4 ~]# strace -c -p 11712 Process 11712 attached - interrupt to quit ^CProcess 11712 detached % time seconds usecs/call callserrors syscall -- --- --- - - 26.850.890335 15 58920 writev 24.450.810866 7118147 epoll_ctl 22.270.738451 13 58920 close 11.500.381362 6 59227 getsockname 9.860.326843 3119192 59228 read 3.530.117058 16 7100 1931 futex 1.530.050884 58 884 epoll_wait 0.000.37 0 404 rt_sigprocmask 0.000.00 0 3 write 0.000.00 0 2 brk 0.000.00 010 msync -- --- --- - - 100.003.315836422809 61159 total [r...@hp380g7test.sqa.cm4 ~]# {codes} reduce futex locking period --- Key: TS-1034 URL: https://issues.apache.org/jira/browse/TS-1034 Project: Traffic Server Issue Type: Improvement Components: Core, HTTP Affects Versions: 3.1.1 Reporter: Zhao Yongming Assignee: Zhao Yongming we need to reduce futex locking period, here is a simple testing in my 24cores HP380 system, with 24 ab, all cached in memory: {code} #!/bin/sh for i in {1..24} do ab -n 1 -c 16 -X 127.0.0.$i:8080 http://img02.taobaocdn.com/tps/i2/T1o0ypXk4w-1000-40.png?$i done {code} result: {code} Every 2.0s: echo show:proxy-stats | traffic_shell Mon Nov 28 16:06:42 2011 Successfully Initialized MgmtAPI in /var/run/trafficserver Document Hit Rate 100.00 % * Bandwidth Saving - 100.00 % * Cache Percent Free --- 99.999619 % Open Server Connections -- 0 Open
[jira] [Updated] (TS-1006) memory management, cut down memory waste ?
[ https://issues.apache.org/jira/browse/TS-1006?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1006: -- Attachment: memusage.ods This is the result after mohan_zl's patch that use Da rbtree to reduce the mem alignemnt memory, 1.8G for my env. memory management, cut down memory waste ? -- Key: TS-1006 URL: https://issues.apache.org/jira/browse/TS-1006 Project: Traffic Server Issue Type: Improvement Components: Core Affects Versions: 3.1.1 Reporter: Zhao Yongming Assignee: Zhao Yongming Fix For: 3.1.3 Attachments: memusage.ods, memusage.ods when we review the memory usage in the production, there is something abnormal, ie, looks like TS take much memory than index data + common system waste, and here is some memory dump result by set proxy.config.dump_mem_info_frequency 1, the one on a not so busy forwarding system: physics memory: 32G RAM cache: 22G DISK: 6140 GB average_object_size 64000 {code} allocated |in-use | type size | free list name |||-- 671088640 | 37748736 |2097152 | memory/ioBufAllocator[14] 2248146944 | 2135949312 |1048576 | memory/ioBufAllocator[13] 1711276032 | 1705508864 | 524288 | memory/ioBufAllocator[12] 1669332992 | 1667760128 | 262144 | memory/ioBufAllocator[11] 2214592512 | 221184 | 131072 | memory/ioBufAllocator[10] 2325741568 | 2323775488 | 65536 | memory/ioBufAllocator[9] 2091909120 | 2089123840 | 32768 | memory/ioBufAllocator[8] 1956642816 | 1956478976 | 16384 | memory/ioBufAllocator[7] 2094530560 | 2094071808 | 8192 | memory/ioBufAllocator[6] 356515840 | 355540992 | 4096 | memory/ioBufAllocator[5] 1048576 | 14336 | 2048 | memory/ioBufAllocator[4] 131072 | 0 | 1024 | memory/ioBufAllocator[3] 65536 | 0 |512 | memory/ioBufAllocator[2] 32768 | 0 |256 | memory/ioBufAllocator[1] 16384 | 0 |128 | memory/ioBufAllocator[0] 0 | 0 |576 | memory/ICPRequestCont_allocator 0 | 0 |112 | memory/ICPPeerReadContAllocator 0 | 0 |432 | memory/PeerReadDataAllocator 0 | 0 | 32 | memory/MIMEFieldSDKHandle 0 | 0 |240 | memory/INKVConnAllocator 0 | 0 | 96 | memory/INKContAllocator 4096 | 0 | 32 | memory/apiHookAllocator 0 | 0 |288 | memory/FetchSMAllocator 0 | 0 | 80 | memory/prefetchLockHandlerAllocator 0 | 0 |176 | memory/PrefetchBlasterAllocator 0 | 0 | 80 | memory/prefetchUrlBlaster 0 | 0 | 96 | memory/blasterUrlList 0 | 0 | 96 | memory/prefetchUrlEntryAllocator 0 | 0 |128 | memory/socksProxyAllocator 0 | 0 |144 | memory/ObjectReloadCont 3258368 | 576016 |592 | memory/httpClientSessionAllocator 825344 | 139568 |208 | memory/httpServerSessionAllocator 22597632 |1284848 | 9808 | memory/httpSMAllocator 0 | 0 | 32 | memory/CacheLookupHttpConfigAllocator 0 | 0 | 9856 | memory/httpUpdateSMAllocator 0 | 0 |128 | memory/RemapPluginsAlloc 0 | 0 | 48 | memory/CongestRequestParamAllocator 0 | 0 |128 | memory/CongestionDBContAllocator 5767168 | 704512 | 2048 | memory/hdrStrHeap 18350080 |1153024 | 2048 | memory/hdrHeap 53248 | 2912 |208 | memory/httpCacheAltAllocator 0 | 0 |112 | memory/OneWayTunnelAllocator 157696 |
[jira] [Updated] (TS-1029) DNS crash if we free the memory into system
[ https://issues.apache.org/jira/browse/TS-1029?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1029: -- Description: when we start to testing free memory into system, the DNS will cause crashing at: dns_result() {code} if (!e-post(h, ent)) { for (int i = 0; i MAX_DNS_RETRIES; i++) { if (e-id[i] 0) break; h-release_query_id(e-id[i]); } return; } {code} was: when we start to testing free memory into system, the DNS will cause crashing at: dns_result() {codes} if (!e-post(h, ent)) { for (int i = 0; i MAX_DNS_RETRIES; i++) { if (e-id[i] 0) break; h-release_query_id(e-id[i]); } return; } {codes} DNS crash if we free the memory into system --- Key: TS-1029 URL: https://issues.apache.org/jira/browse/TS-1029 Project: Traffic Server Issue Type: Bug Components: DNS Affects Versions: 3.1.2 Reporter: Zhao Yongming Assignee: weijin Fix For: 3.1.2 when we start to testing free memory into system, the DNS will cause crashing at: dns_result() {code} if (!e-post(h, ent)) { for (int i = 0; i MAX_DNS_RETRIES; i++) { if (e-id[i] 0) break; h-release_query_id(e-id[i]); } return; } {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1003) prefetch: the config file
[ https://issues.apache.org/jira/browse/TS-1003?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1003: -- Component/s: Configuration Description: PreFetch and Update is the most strange plugin that keep in the proxy dir. and we have some PreFetch API that should make some usage, but the config file for prefetch and configs not managed live other config files in the tree. we should make PreFetch a big feature for TS, and smooth all the ugly coded issue. Fix Version/s: (was: 3.1.4) 2.1.3 when dealing with the config file and config options updates, I think we need figure out some of the issues later: 1, how to deal with configs that our plugins need: 1.1, how to add config file to the mgmt system. the config file is monitored by mgmt, and the file list is hard coded into fileUpdated(), that will show no flex while the config file keeping increasing for now. 1.2, how to deal with the config option call backs? is there any guide in the coding? 2, should we bring up the config file syntax talk? 2.1, why so many types and so many codes in handling these syntaxes? I think we need some roadmap on the configs, at least some directons :D prefetch: the config file - Key: TS-1003 URL: https://issues.apache.org/jira/browse/TS-1003 Project: Traffic Server Issue Type: Sub-task Components: Configuration Reporter: Zhao Yongming Assignee: Zhao Yongming Fix For: 2.1.3 PreFetch and Update is the most strange plugin that keep in the proxy dir. and we have some PreFetch API that should make some usage, but the config file for prefetch and configs not managed live other config files in the tree. we should make PreFetch a big feature for TS, and smooth all the ugly coded issue. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-1003) prefetch: the config file
[ https://issues.apache.org/jira/browse/TS-1003?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-1003: -- Attachment: TS-1003.patch here is the patch that will make the config same as other. prefetch: the config file - Key: TS-1003 URL: https://issues.apache.org/jira/browse/TS-1003 Project: Traffic Server Issue Type: Sub-task Components: Configuration Reporter: Zhao Yongming Assignee: Zhao Yongming Fix For: 2.1.3 Attachments: TS-1003.patch PreFetch and Update is the most strange plugin that keep in the proxy dir. and we have some PreFetch API that should make some usage, but the config file for prefetch and configs not managed live other config files in the tree. we should make PreFetch a big feature for TS, and smooth all the ugly coded issue. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-994) X-Forwarded-For should follow the squid way
[ https://issues.apache.org/jira/browse/TS-994?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-994: - Attachment: XFF.patch a quick fix X-Forwarded-For should follow the squid way --- Key: TS-994 URL: https://issues.apache.org/jira/browse/TS-994 Project: Traffic Server Issue Type: Improvement Components: HTTP Affects Versions: 3.1.1 Reporter: Zhao Yongming Assignee: Zhao Yongming Priority: Minor Fix For: 3.1.1 Attachments: XFF.patch TS will append the IP in the format of: X-Forwarded-For: 127.0.0.1, 10.32.102.41\r\n while http://en.wikipedia.org/wiki/X-Forwarded-For says: X-Forwarded-For: client1, proxy1, proxy2 there is 2 spaces -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-899) ts crash
[ https://issues.apache.org/jira/browse/TS-899?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-899: - Fix Version/s: (was: 3.1.1) 3.1.3 the transform related issue is still in progress, not that easy to fix. weijin is moving forward slowly. ts crash Key: TS-899 URL: https://issues.apache.org/jira/browse/TS-899 Project: Traffic Server Issue Type: Sub-task Components: HTTP, MIME Affects Versions: 3.0.1 Environment: readhat5.5, ts-3.0.1, X86-64 Reporter: weijin Assignee: weijin Fix For: 3.1.3 If a request url is forbidden then redirected to another url, TS crash. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-910) log collation in custom log will make dedicate connection to the same collation server
[ https://issues.apache.org/jira/browse/TS-910?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-910: - Fix Version/s: (was: 3.1.1) 3.1.3 well, it is not that hurry as most of the cluster is under 32hosts. I will try the fix in the next releases log collation in custom log will make dedicate connection to the same collation server -- Key: TS-910 URL: https://issues.apache.org/jira/browse/TS-910 Project: Traffic Server Issue Type: Bug Components: Logging Affects Versions: 3.1.0 Reporter: Zhao Yongming Assignee: Zhao Yongming Fix For: 3.1.3 when you define LogObject in logs_xml.config, and set CollationHosts, it will open connections for each LogObject, despite you put the same host in CollationHosts. it will affect the default squid logging too. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (TS-801) Crash Report: enable update will triger Segmentation fault
[ https://issues.apache.org/jira/browse/TS-801?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-801: - Fix Version/s: (was: 3.1.1) 3.1.2 I think the update still need to check, as I can get the crash from trunk: {code} [Oct 13 10:35:28.724] Server {0x2b71049b3860} DEBUG: (update) (R) speculative start update id: 7 [http://cdn.zymlinux.net/icons/blank.gif] [Oct 13 10:35:28.724] Server {0x2b710587e700} DEBUG: (update) Start HTTP GET id: 7 [http://cdn.zymlinux.net/icons/blank.gif] NOTE: Traffic Server received Sig 11: Segmentation fault /opt/ats/bin/traffic_server - STACK TRACE: /opt/ats/bin/traffic_server[0x53b188] /lib64/libpthread.so.0(+0xf400)[0x2b7101e84400] [0x6e] /opt/ats/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x6e)[0x591a86] /opt/ats/bin/traffic_server(HttpSM::set_next_state()+0x165)[0x591cdf] /opt/ats/bin/traffic_server(HttpUpdateSM::set_next_state()+0xad)[0x5c8861] /opt/ats/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x13d)[0x591b55] /opt/ats/bin/traffic_server(HttpSM::handle_api_return()+0x138)[0x5816ca] /opt/ats/bin/traffic_server(HttpUpdateSM::handle_api_return()+0x45)[0x5c84d1] /opt/ats/bin/traffic_server(HttpSM::do_api_callout()+0x3f)[0x596d69] /opt/ats/bin/traffic_server(HttpSM::set_next_state()+0x64)[0x591bde] /opt/ats/bin/traffic_server(HttpUpdateSM::set_next_state()+0xad)[0x5c8861] /opt/ats/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x13d)[0x591b55] /opt/ats/bin/traffic_server(HttpSM::handle_api_return()+0x138)[0x5816ca] /opt/ats/bin/traffic_server(HttpUpdateSM::handle_api_return()+0x45)[0x5c84d1] /opt/ats/bin/traffic_server(HttpSM::do_api_callout()+0x3f)[0x596d69] /opt/ats/bin/traffic_server(HttpSM::set_next_state()+0x64)[0x591bde] /opt/ats/bin/traffic_server(HttpUpdateSM::set_next_state()+0xad)[0x5c8861] /opt/ats/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x13d)[0x591b55] /opt/ats/bin/traffic_server(HttpUpdateSM::handle_api_return()+0x34)[0x5c84c0] /opt/ats/bin/traffic_server(HttpSM::do_api_callout()+0x3f)[0x596d69] /opt/ats/bin/traffic_server(HttpSM::state_add_to_list(int, void*)+0x2b3)[0x57e31f] /opt/ats/bin/traffic_server(HttpSM::main_handler(int, void*)+0x2a0)[0x584860] /opt/ats/bin/traffic_server(Continuation::handleEvent(int, void*)+0x68)[0x4f4e90] /opt/ats/bin/traffic_server(HttpUpdateSM::start_scheduled_update(Continuation*, HTTPHdr*)+0x174)[0x5c8438] /opt/ats/bin/traffic_server(UpdateSM::http_scheme(UpdateSM*)+0x279)[0x54a1b5] /opt/ats/bin/traffic_server(UpdateSM::HandleSMEvent(int, Event*)+0x1ab)[0x549d0f] /opt/ats/bin/traffic_server(Continuation::handleEvent(int, void*)+0x68)[0x4f4e90] /opt/ats/bin/traffic_server(EThread::process_event(Event*, int)+0x127)[0x704069] /opt/ats/bin/traffic_server(EThread::execute()+0x9a)[0x704272] /opt/ats/bin/traffic_server[0x703240] /lib64/libpthread.so.0(+0x6d5c)[0x2b7101e7bd5c] /lib64/libc.so.6(clone+0x6d)[0x2b71044f72dd] /lib64/libc.so.6(clone+0x6d)[0x2b71044f72dd] [Oct 13 10:35:28.794] Manager {0x7f8adbb55720} ERROR: [LocalManager::pollMgmtProcessServer] Server Process terminated due to Sig 11: Segmentation fault [Oct 13 10:35:28.794] Manager {0x7f8adbb55720} ERROR: (last system error 2: No such file or directory) [Oct 13 10:35:28.794] Manager {0x7f8adbb55720} ERROR: [Alarms::signalAlarm] Server Process was reset [Oct 13 10:35:28.794] Manager {0x7f8adbb55720} ERROR: (last system error 2: No such file or directory) [Oct 13 10:35:29.798] Manager {0x7f8adbb55720} NOTE: [LocalManager::startProxy] Launching ts process {code} Crash Report: enable update will triger Segmentation fault -- Key: TS-801 URL: https://issues.apache.org/jira/browse/TS-801 Project: Traffic Server Issue Type: Bug Components: HTTP Affects Versions: 2.1.8 Environment: v2.1.8 and update function enabled. Reporter: Zhao Yongming Labels: update Fix For: 3.1.2 {code} b13621367...@hotmail.com: NOTE: Traffic Server received Sig 11: Segmentation fault /usr/local/ts/bin/traffic_server - STACK TRACE: b13621367...@hotmail.com: /usr/local/ts/bin/traffic_server[0x5260c9] /lib64/libpthread.so.0[0x3088e0f4c0] [0x6e] /usr/local/ts/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x6e)[0x57e0e2] /usr/local/ts/bin/traffic_server(HttpSM::set_next_state()+0x18b)[0x57e369] /usr/local/ts/bin/traffic_server(HttpUpdateSM::set_next_state()+0xad)[0x5b604b] /usr/local/ts/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x15e)[0x57e1d2]
[jira] [Updated] (TS-893) the prefetch function in codes need more love to show up
[ https://issues.apache.org/jira/browse/TS-893?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Zhao Yongming updated TS-893: - Fix Version/s: (was: 3.1.1) 3.1.2 Assignee: Zhao Yongming I have done some working on the target #1, for the config files, as the ugly RecCore usage and config file watching interface, there will need more long term tweak for better design for such a transform related in tree plugin. I will separate the job and setup more tickets for different target, I will take this issue as a key to cleanup all the related issues. the prefetch function in codes need more love to show up Key: TS-893 URL: https://issues.apache.org/jira/browse/TS-893 Project: Traffic Server Issue Type: Improvement Reporter: Zhao Yongming Assignee: Zhao Yongming Fix For: 3.1.2 the prefetch function in proxy is a good solution when you really need to faster up your user download time, it can parse any allowed plean html file, get all resource tags out and do batch loading from OS. I am going to preload my site before we put it online, as it will get about 1 month to get the disk full and hit rate stable. it is a cool feature but it have the following issues: 1, the prefetch config file is not managed well. ie, it is not managed by cluster 2, the it does not any document in the admin guide or old pdf file. 3, prefetching just care plean html file, without compressing, should we do some decompressing? is that possible? hopes this is the starting of make prefetch really useful for some cutting edge situation. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira