task blocked for more than 120 seconds (2.6.26.1)

[Michael Madore]

Hi,

Running 2.6.26.1 I am receiving errors similar to the following when
stress testing systems:

INFO: task kjournald:1004 blocked for more than 120 seconds.
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
kjournald     D ffff81013d347000     0  1004      2
 ffff81013cce9de0 0000000000000046 ffff81013cce9d90 ffffffff810478c5
 ffff810001069378 ffff81013cdd2cc0 ffff810120454320 ffff81013cdd3010
 ffff81013cce9de0 ffffffff81048096 ffff81013cce9db0 0000000000000246
Call Trace:
 [<ffffffff810478c5>] ? enqueue_hrtimer+0xd1/0xdf
 [<ffffffff81048096>] ? hrtimer_start+0x122/0x144
 [<ffffffffa0023be3>] :jbd:journal_commit_transaction+0xe9/0xd1e
 [<ffffffff8103bb2d>] ? lock_timer_base+0x26/0x4a
 [<ffffffff81045534>] ? autoremove_wake_function+0x0/0x38
 [<ffffffff8103bba7>] ? try_to_del_timer_sync+0x56/0x62
 [<ffffffffa002713e>] :jbd:kjournald+0xc3/0x1fb
 [<ffffffff81045534>] ? autoremove_wake_function+0x0/0x38
 [<ffffffffa002707b>] ? :jbd:kjournald+0x0/0x1fb
 [<ffffffff810453ff>] kthread+0x49/0x76
 [<ffffffff8100cd08>] child_rip+0xa/0x12
 [<ffffffff810453b6>] ? kthread+0x0/0x76
 [<ffffffff8100ccfe>] ? child_rip+0x0/0x12

This is on a 16 core Intel system with a single SATA disk and 4GB of
memory.  This particular instance of the error occurred after about an
hour.

I was previously using 2.6.24.7 from Fedora 8 and that did not exhibit
the problem.

Mike Madore
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/