CPU Utilization by the mogilefsd process

mischa.z mischa.z at gmail.com
Fri Feb 9 10:53:51 UTC 2007


Hi,

I'm dealing with the same problem here since I've updated from Rev 518
to 733.

Here's the collected debug info. Hope this helps to track down the problem.

Mischa




crash log: Error writing: Resource temporarily unavailable at
/usr/local/share/perl/5.8.4/MogileFS/Worker.pm line 89.

Child 14893 (monitor) died: 256 (UNEXPECTED)
.
.
.
Watchdog killing worker 14881 (replicate)
Child 14881 (replicate) died: 9 (UNEXPECTED)
Job replicate has only 0, wants 1, making 1.



lsof -p 14879
COMMAND     PID USER   FD   TYPE             DEVICE    SIZE      NODE NAME
mogilefsd 14879  mog  cwd    DIR                8,1    4096   8209418
/home/mog/trunk/api/perl
mogilefsd 14879  mog  rtd    DIR                8,1    4096         2 /
mogilefsd 14879  mog  txt    REG                8,1   14000  16991216
/usr/bin/perl
mogilefsd 14879  mog  mem    REG                0,0                 0
[heap] (stat: No such file or directory)
mogilefsd 14879  mog  mem    REG                8,1   90288   2671936
/lib/ld-2.3.2.so
mogilefsd 14879  mog  mem    REG                8,1  290448  17006739
/usr/lib/locale/locale-archive
mogilefsd 14879  mog  mem    REG                8,1 1229712  16991399
/usr/lib/libperl.so.5.8.4
mogilefsd 14879  mog  mem    REG                8,1   12072   2671941
/lib/libdl-2.3.2.so
mogilefsd 14879  mog  mem    REG                8,1  550208   2671942
/lib/libm-2.3.2.so
mogilefsd 14879  mog  mem    REG                8,1   93506   2671952
/lib/libpthread-0.60.so
mogilefsd 14879  mog  mem    REG                8,1 1295328   2671939
/lib/libc-2.3.2.so
mogilefsd 14879  mog  mem    REG                8,1   21536   2671940
/lib/libcrypt-2.3.2.so
mogilefsd 14879  mog  mem    REG                8,1   19920  17008592
/usr/lib/perl/5.8.4/auto/IO/IO.so
mogilefsd 14879  mog  mem    REG                8,1   23992  17008598
/usr/lib/perl/5.8.4/auto/Socket/Socket.so
mogilefsd 14879  mog  mem    REG                8,1  119344  17008595
/usr/lib/perl/5.8.4/auto/POSIX/POSIX.so
mogilefsd 14879  mog  mem    REG                8,1   11688  17008578
/usr/lib/perl/5.8.4/auto/Cwd/Cwd.so
mogilefsd 14879  mog  mem    REG                8,1    8152  17024809
/usr/lib/perl/5.8.4/auto/Sys/Hostname/Hostname.so
mogilefsd 14879  mog  mem    REG                8,1   16888  17024812
/usr/lib/perl/5.8.4/auto/Sys/Syslog/Syslog.so
mogilefsd 14879  mog  mem    REG                8,1   19488  17024816
/usr/lib/perl/5.8.4/auto/Time/HiRes/HiRes.so
mogilefsd 14879  mog  mem    REG                8,1   32456  17024751
/usr/lib/perl/5.8.4/auto/List/Util/Util.so
mogilefsd 14879  mog  mem    REG                8,1   20392  17042727
/usr/lib/perl5/auto/BSD/Resource/Resource.so
mogilefsd 14879  mog  mem    REG                8,1  130888  17432916
/usr/lib/perl5/auto/DBI/DBI.so
mogilefsd 14879  mog  mem    REG                8,1   98656  17432971
/usr/lib/perl5/auto/DBD/mysql/mysql.so
mogilefsd 14879  mog  mem    REG                8,1    1474  16991750
/usr/share/locale/en_GB/LC_MESSAGES/libc.mo
mogilefsd 14879  mog  mem    REG                8,1  270832  16996500
/usr/lib/libmysqlclient.so.12.0.0
mogilefsd 14879  mog  mem    REG                8,1   80872  16991239
/usr/lib/libz.so.1.2.2
mogilefsd 14879  mog  mem    REG                8,1   83000   2671944
/lib/libnsl-2.3.2.so
mogilefsd 14879  mog  mem    REG                8,1   41600   2671947
/lib/libnss_files-2.3.2.so
mogilefsd 14879  mog  mem    REG                8,1    7904  16991918
/usr/lib/gconv/ISO8859-1.so
mogilefsd 14879  mog    0u   CHR              136,3                 5
/dev/pts/3
mogilefsd 14879  mog    1u   CHR              136,3                 5
/dev/pts/3
mogilefsd 14879  mog    2u   CHR              136,3                 5
/dev/pts/3
mogilefsd 14879  mog    3r   REG                8,1    2131  16997081
/usr/bin/mogilefsd
mogilefsd 14879  mog    4u  sock                0,4         160966689
can't identify protocol
mogilefsd 14879  mog    5u  IPv4          160966690               TCP
*:afs3-callback (LISTEN)
mogilefsd 14879  mog    6r  0000                0,9       0 160966691
unknown inode type
mogilefsd 14879  mog    7u  unix 0xffff81004a337a80         160972304 socket
mogilefsd 14879  mog    8u  unix 0xffff81004a337080         160970596 socket
mogilefsd 14879  mog    9u  unix 0xffff8101aefb1a80         160966702 socket
mogilefsd 14879  mog   10u  unix 0xffff81013da44a80         160966704 socket
mogilefsd 14879  mog   11u  unix 0xffff81013da44580         160966706 socket
mogilefsd 14879  mog   12u  unix 0xffff81013da44080         160966708 socket
mogilefsd 14879  mog   13u  unix 0xffff810152194ac0         160966710 socket
mogilefsd 14879  mog   14u  unix 0xffff8101521945c0         160966712 socket
mogilefsd 14879  mog   15u  unix 0xffff8101521940c0         160966714 socket
mogilefsd 14879  mog   16u  unix 0xffff81016f2d8a80         160966716 socket
mogilefsd 14879  mog   17u  unix 0xffff81016f2d8580         160966718 socket
mogilefsd 14879  mog   18u  unix 0xffff81016f2d8080         160966720 socket
mogilefsd 14879  mog   19u  unix 0xffff81013da30ac0         160966724 socket
mogilefsd 14879  mog   20u  unix 0xffff81004a337580         160970670 socket
mogilefsd 14879  mog   21u  unix 0xffff81013da300c0         160966728 socket


strace
epoll_wait(6, {{EPOLLOUT, {u32=9, u64=9}}}, 1000, 250) = 1
time(NULL)                              = 1170939715
epoll_wait(6, {{EPOLLOUT, {u32=9, u64=9}}}, 1000, 250) = 1
time(NULL)                              = 1170939715
epoll_wait(6, {{EPOLLOUT, {u32=9, u64=9}}}, 1000, 250) = 1
time(NULL)                              = 1170939715
epoll_wait(6, {{EPOLLOUT, {u32=9, u64=9}}}, 1000, 250) = 1
time(NULL)                              = 1170939715
epoll_wait(6, {{EPOLLOUT, {u32=9, u64=9}}}, 1000, 250) = 1
time(NULL)                              = 1170939715
epoll_wait(6, {{EPOLLOUT, {u32=9, u64=9}}}, 1000, 250) = 1
time(NULL)                              = 1170939715
epoll_wait(6, {{EPOLLOUT, {u32=9, u64=9}}}, 1000, 250) = 1
time(NULL)                              = 1170939715
epoll_wait(6, {{EPOLLOUT, {u32=9, u64=9}}}, 1000, 250) = 1
time(NULL)                              = 1170939715
epoll_wait(6, {{EPOLLOUT, {u32=9, u64=9}}}, 1000, 250) = 1
time(NULL)                              = 1170939715
epoll_wait(6, {{EPOLLOUT, {u32=9, u64=9}}}, 1000, 250) = 1
time(NULL)                              = 1170939715
epoll_wait(6, {{EPOLLOUT, {u32=9, u64=9}}}, 1000, 250) = 1
time(NULL)                              = 1170939715
.
.



> 
> What version?
> 
> strace it and tell me what it's doing?  And show output of lsof -p <pid>
> as well?
> 
> 
> 
> On Wed, 7 Feb 2007, Carl Forsythe wrote:
> 
>> Hi all,
>>
>> On our trackers I see one mogilefsd process in top (the parent process)
>> sitting at 100% cpu utilization, is this typical behavior for the parent
>> mogilefsd? The tracker platform is CentOS 4.4 64 bit running on AMD
>> Opteron processors.
>>
>> Thanks,
>>
>> -Carl
>>
>>
>>
>>
> 




More information about the mogilefs mailing list