httpd-bugs mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From bugzi...@apache.org
Subject DO NOT REPLY [Bug 45362] Threads spinning on CPU
Date Thu, 10 Jul 2008 09:14:48 GMT
https://issues.apache.org/bugzilla/show_bug.cgi?id=45362





--- Comment #5 from Igor Galic <i.galic@brainsware.org>  2008-07-10 02:14:48 PST ---
Updates: After rpluem asked me to ltrace, I tried, but failed in achieving
anything meaningful. ltracing the parent I'm getting stuff like:

11:21:25.046949 SYS_wait4(-1, 0x7fff60c1555c, 3, 0, 0x667168)                  
                 = 0
11:21:25.047094 <... apr_proc_wait_all_procs resumed> )                        
                 = 70006
11:21:25.047157 apr_sleep(0xf4240, 0x7fff60c1555c, 70006, -1, 0x667168
<unfinished ...>
11:21:25.047260 SYS_select(0, 0, 0, 0, 0x7fff60c15570)                         
                 = 0
11:21:26.046765 <... apr_sleep resumed> )                                      
                 = 0
11:21:26.046874 apr_proc_wait_all_procs(0x7fff60c15690, 0x7fff60c156b8,
0x7fff60c156bc, 1, 0x667168 <unfinished ...>
11:21:26.046997 SYS_wait4(-1, 0x7fff60c1555c, 3, 0, 0x667168)                  
                 = 0
11:21:26.047141 <... apr_proc_wait_all_procs resumed> )                        
                 = 70006
11:21:26.047204 apr_sleep(0xf4240, 0x7fff60c1555c, 70006, -1, 0x667168
<unfinished ...>
11:21:26.047307 SYS_select(0, 0, 0, 0, 0x7fff60c15570)                         
                 = 0
11:21:27.046849 <... apr_sleep resumed> )                                      
                 = 0
11:21:27.046950 apr_proc_wait_all_procs(0x7fff60c15690, 0x7fff60c156b8,
0x7fff60c156bc, 1, 0x667168 <unfinished ...>
11:21:27.047068 SYS_wait4(-1, 0x7fff60c1555c, 3, 0, 0x667168)                  
                 = 0
11:21:27.047230 <... apr_proc_wait_all_procs resumed> )                        
                 = 70006
11:21:27.047296 apr_sleep(0xf4240, 0x7fff60c1555c, 70006, -1, 0x667168
<unfinished ...>
11:21:27.047402 SYS_select(0, 0, 0, 0, 0x7fff60c15570)                         
                 = 0
11:21:28.046897 <... apr_sleep resumed> )                                      
                 = 0
11:21:28.047003 apr_proc_wait_all_procs(0x7fff60c15690, 0x7fff60c156b8,
0x7fff60c156bc, 1, 0x667168 <unfinished ...>
11:21:28.047126 SYS_wait4(-1, 0x7fff60c1555c, 3, 0, 0x667168)                  
                 = 0
11:21:28.047273 <... apr_proc_wait_all_procs resumed> )                        
                 = 70006
11:21:28.047335 apr_sleep(0xf4240, 0x7fff60c1555c, 70006, -1, 0x667168
<unfinished ...>
11:21:28.047439 SYS_select(0, 0, 0, 0, 0x7fff60c15570)                         
                 = 0
11:21:29.046945 <... apr_sleep resumed> )                                      
                 = 0
11:21:29.047046 apr_proc_wait_all_procs(0x7fff60c15690, 0x7fff60c156b8,
0x7fff60c156bc, 1, 0x667168 <unfinished ...>
11:21:29.047164 SYS_wait4(-1, 0x7fff60c1555c, 3, 0, 0x667168)                  
                 = 0
11:21:29.047323 <... apr_proc_wait_all_procs resumed> )                        
                 = 70006
11:21:29.047389 apr_sleep(0xf4240, 0x7fff60c1555c, 70006, -1, 0x667168
<unfinished ...>
11:21:29.047492 SYS_select(0, 0, 0, 0, 0x7fff60c15570)                         
                 = 0

which seems natural.
Now, if I try to ltrace a LWP, I'm hitting a limitation of ltrace itself:
http://lists.alioth.debian.org/pipermail/ltrace-devel/2006-April/000039.html


After ca 36~ hours of runtime: I finally got: 

top - 12:16:45 up 96 days, 20:11,  4 users,  load average: 0.00, 0.01, 0.25
Tasks: 253 total,   2 running, 219 sleeping,  30 stopped,   2 zombie
Cpu(s):  0.0%us,  0.3%sy,  0.0%ni, 99.7%id,  0.0%wa,  0.0%hi,  0.0%si,  0.0%st
Mem:   2097152k total,  1903600k used,   193552k free,   299744k buffers
Swap:  2097144k total,    18924k used,  2078220k free,  1072724k cached

  PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+   PPID nDRT WCHAN  
  COMMAND
24125 www       15   0  168m  26m  19m T  0.0  1.3   0:00.00 17149    0
finish_st httpd-worker
24151 www       18   0  168m  26m  19m T  0.0  1.3 845:53.74 17149    0
finish_st httpd-worker
 5136 www       18   0  345m  11m 2728 T  0.0  0.6   0:00.00 17149    0
finish_st httpd-worker
 5138 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.13 17149    0
finish_st httpd-worker
 5139 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.10 17149    0
finish_st httpd-worker
 5140 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.12 17149    0
finish_st httpd-worker
 5141 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.13 17149    0
finish_st httpd-worker
 5142 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.10 17149    0
finish_st httpd-worker
 5143 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.08 17149    0
finish_st httpd-worker
 5144 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.08 17149    0
finish_st httpd-worker
 5145 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.08 17149    0
finish_st httpd-worker
 5146 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.07 17149    0
finish_st httpd-worker
 5147 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.60 17149    0
finish_st httpd-worker
 5148 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.11 17149    0
finish_st httpd-worker
 5149 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.15 17149    0
finish_st httpd-worker
 5150 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.11 17149    0
finish_st httpd-worker
 5151 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.11 17149    0
finish_st httpd-worker
 5152 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.12 17149    0
finish_st httpd-worker
 5153 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.10 17149    0
finish_st httpd-worker
 5154 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.14 17149    0
finish_st httpd-worker
 5155 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.14 17149    0
finish_st httpd-worker
 5156 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.16 17149    0
finish_st httpd-worker
 5157 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.15 17149    0
finish_st httpd-worker
 5158 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.08 17149    0
finish_st httpd-worker
 5159 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.13 17149    0
finish_st httpd-worker
 5160 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.12 17149    0
finish_st httpd-worker
 5161 www       18   0  345m  11m 2728 T  0.0  0.6  51:08.45 17149    0
finish_st httpd-worker
 5162 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.10 17149    0
finish_st httpd-worker
 5163 www       15   0  345m  11m 2728 T  0.0  0.6   0:00.21 17149    0
finish_st httpd-worker
 5902 www       17   0     0    0    0 Z  0.0  0.0   0:04.58 17149    0 exit   
  httpd-worker <defunct>
 6251 www       17   0     0    0    0 Z  0.0  0.0   0:00.21 17149    0 exit   
  httpd-worker <defunct>


No longer LISTENing (according to netstat), not reacting to apachectl stop, or
kill for that matter. I had to kill -9 it.


-- 
Configure bugmail: https://issues.apache.org/bugzilla/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug.

---------------------------------------------------------------------
To unsubscribe, e-mail: bugs-unsubscribe@httpd.apache.org
For additional commands, e-mail: bugs-help@httpd.apache.org


Mime
View raw message