LinuxQuestions.org
Did you know LQ has a Linux Hardware Compatibility List?
Go Back   LinuxQuestions.org > Forums > Linux Forums > Linux - Distributions > Red Hat
User Name
Password
Red Hat This forum is for the discussion of Red Hat Linux.

Notices

Reply
 
Search this Thread
Old 01-13-2013, 05:17 AM   #1
nallanisai
LQ Newbie
 
Registered: Dec 2010
Location: Bangalore
Distribution: Red Hat Linux
Posts: 28

Rep: Reputation: 0
kernel: INFO: task gzip:28803 blocked for more than 120 seconds


Hi All,

Iam getting below error in log messages.

kernel: INFO: task gzip:28803 blocked for more than 120 seconds.
kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
kernel: gzip D ffffffff80150790 0 28803 28802 (NOTLB)
kernel: ffff81019d853bf8 0000000000000082 0000000000095658 00000000247949e6
kernel: 0000000000000226 0000000000000007 ffff81013acfa100 ffff81031bf16100
kernel: 0001c0bac16ad10f 0000000000002b46 ffff81013acfa2e8 000000011938fcf8
kernel: Call Trace:
kernel: [<ffffffff8006e1d7>] do_gettimeofday+0x40/0x90
kernel: [<ffffffff885ca6e5>] :nfs:nfs_wait_bit_uninterruptible+0x0/0xd
kernel: [<ffffffff800637ea>] io_schedule+0x3f/0x67
kernel: [<ffffffff885ca6ee>] :nfs:nfs_wait_bit_uninterruptible+0x9/0xd
kernel: [<ffffffff80063a16>] __wait_on_bit+0x40/0x6e
kernel: [<ffffffff885ca6e5>] :nfs:nfs_wait_bit_uninterruptible+0x0/0xd

below is uname -a o/p

Linux spider 2.6.18-194.17.1.el5 #1 SMP Mon Sep 20 07:12:06 EDT 2010 x86_64 x86_64 x86_64 GNU/Linux

can you suggest what error is that and how to get rid of that.

Thanks,
Prasad
 
Old 01-13-2013, 09:30 AM   #2
nallanisai
LQ Newbie
 
Registered: Dec 2010
Location: Bangalore
Distribution: Red Hat Linux
Posts: 28

Original Poster
Rep: Reputation: 0
Above error message is repeating.
 
Old 01-13-2013, 10:09 AM   #3
unSpawn
Moderator
 
Registered: May 2001
Posts: 27,118
Blog Entries: 54

Rep: Reputation: 2787Reputation: 2787Reputation: 2787Reputation: 2787Reputation: 2787Reputation: 2787Reputation: 2787Reputation: 2787Reputation: 2787Reputation: 2787Reputation: 2787
Quote:
Originally Posted by nallanisai View Post
can you suggest what error is that and
It's either DETECT_SOFTLOCKUP or DETECT_HUNG_TASK: the process did enter uninterruptible sleep (capital "d") but I don't know if DETECT_HUNG_TASK was backported to your kernel version (which BTW is way too old so do upgrade RSN). In essence a single task blocked other tasks from running.


Quote:
Originally Posted by nallanisai View Post
how to get rid of that.
Sometimes it just is as simple as that: a single task hogging resources thereby denying other tasks from running. Bugzilla in some cases reports success using another scheduler like NOOP or doing chipset firmware upgrades. In other cases determining the cause may be hampered by lack of basic insights. By having some form of SAR (Atop, Dstat, Collectl, Nagios or whatever else SW you fancy) report increases in system and network resource usage like process state, memory usage, disk and network throughput and alert on logged errors you may become aware of potential problems before they turn ugly and crash the system. In some cases scheduling (nice, ionice, taskset, cgroups and whatever else) of jobs known or suspected to have increased resource usage may help but if in your case data was shoved over the network via NFS then any NFS or network-based glitches may have caused the task to block. In such cases you must anticipate network problems and make the process more resilient by for instance breaking up tasks in subtasks.

For example using nice + ionice (inherited) should stress the source system less and splitting up output means you only have to transmit failed parts:
Code:
ionice -c3 $$; renice +20 -p $$
dd if=/some/disk|split -C 1000m - diskname
md5sum diskname* >> /nfsv4/diskname.md5
bzip2 diskname* && cp diskname*.bz2 /nfsv4/
md5sum -c /nfsv4/diskname.md5 && rm -f diskname*.bz2
Because you broke up the task you can choose to handle part of processing on the remote machine. It's just an example to illustrate the benefits of breaking up a task so it may not work for you. You may have to look at other transport options.
 
1 members found this post helpful.
Old 01-16-2013, 06:48 AM   #4
nallanisai
LQ Newbie
 
Registered: Dec 2010
Location: Bangalore
Distribution: Red Hat Linux
Posts: 28

Original Poster
Rep: Reputation: 0
Hi, thanks for your reply.
 
  


Reply


Thread Tools Search this Thread
Search this Thread:

Advanced Search

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is Off
HTML code is Off


Similar Threads
Thread Thread Starter Forum Replies Last Post
Task blocked for more than 120 seconds errors and crashes Red Squirrel Linux - Server 17 04-01-2014 01:12 PM
INFO: task nfsd & INFO: task kjournald blocked junix88 Linux - Kernel 1 07-04-2012 10:36 AM
Task blocked for more than 120 seconds errors and crashes sanjay87 Linux - Server 3 06-19-2012 01:51 AM
Server crash - kernel: INFO: task blocked sh4ka Linux - Server 4 10-21-2011 05:16 AM
INFO: <application>blocked for more than 120 seconds alok.rhct Linux - Hardware 1 04-08-2009 01:35 AM


All times are GMT -5. The time now is 07:02 PM.

Main Menu
My LQ
Write for LQ
LinuxQuestions.org is looking for people interested in writing Editorials, Articles, Reviews, and more. If you'd like to contribute content, let us know.
Main Menu
Syndicate
RSS1  Latest Threads
RSS1  LQ News
Twitter: @linuxquestions
identi.ca: @linuxquestions
Facebook: linuxquestions Google+: linuxquestions
Open Source Consulting | Domain Registration