kernel: INFO: task sadc:14833 blocked for more than 120 seconds.

早上一到，发现oracle连不上。

到主机上，发现只有oracleora11g一个进程，其他进程全没了。

Nov 14 23:33:30 hs-test-10-20-30-15 kernel: INFO: task sadc:14833 blocked for more than 120 seconds.
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: Not tainted 2.6.32-431.el6.x86_64 #1
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: sadc D 0000000000000000 0 14833 14832 0x00000084
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: ffff88061533bdc8 0000000000000086 0000000000000000 ffff88061533bde8
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: ffff88061533bd88 ffffffff8111f3e0 ffff880528dab9d0 ffff88061533bde8
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: ffff880614125af8 ffff88061533bfd8 000000000000fbc8 ffff880614125af8
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: Call Trace:
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: [<ffffffff8111f3e0>] ? find_get_pages_tag+0x40/0x130
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: [<ffffffffa02b65a5>] jbd2_log_wait_commit+0xc5/0x140 [jbd2]
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: [<ffffffff8109b2a0>] ? autoremove_wake_function+0x0/0x40
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: [<ffffffff81134c91>] ? do_writepages+0x21/0x40
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: [<ffffffffa02b6938>] jbd2_complete_transaction+0x68/0xb0 [jbd2]
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: [<ffffffffa02d2231>] ext4_sync_file+0x121/0x1d0 [ext4]
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: [<ffffffff811baa61>] vfs_fsync_range+0xa1/0x100
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: [<ffffffff811bab2d>] vfs_fsync+0x1d/0x20
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: [<ffffffff811bab6e>] do_fsync+0x3e/0x60
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: [<ffffffff811baba3>] sys_fdatasync+0x13/0x20
Nov 14 23:33:30 hs-test-10-20-30-15 kernel: [<ffffffff8100b072>] system_call_fastpath+0x16/0x1b
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: INFO: task NetworkManager:2081 blocked for more than 120 seconds.
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: Not tainted 2.6.32-431.el6.x86_64 #1
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: NetworkManage D 0000000000000001 0 2081 1 0x00000080
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: ffff880614185dc8 0000000000000082 0000000000000000 ffff880613b13e80
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: 0000000000000000 ffff880612e5e0d0 0000000000000000 0000000000000000
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: ffff88061464bab8 ffff880614185fd8 000000000000fbc8 ffff88061464bab8
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: Call Trace:
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: [<ffffffffa02b65a5>] jbd2_log_wait_commit+0xc5/0x140 [jbd2]
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: [<ffffffff8109b2a0>] ? autoremove_wake_function+0x0/0x40
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: [<ffffffff81134c91>] ? do_writepages+0x21/0x40
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: [<ffffffffa02b6938>] jbd2_complete_transaction+0x68/0xb0 [jbd2]
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: [<ffffffffa02d2231>] ext4_sync_file+0x121/0x1d0 [ext4]
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: [<ffffffff811baa61>] vfs_fsync_range+0xa1/0x100
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: [<ffffffff811bab2d>] vfs_fsync+0x1d/0x20
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: [<ffffffff811bab6e>] do_fsync+0x3e/0x60
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: [<ffffffff811babc0>] sys_fsync+0x10/0x20
Nov 15 00:01:29 hs-test-10-20-30-15 kernel: [<ffffffff8100b072>] system_call_fastpath+0x16/0x1b
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: INFO: task NetworkManager:2081 blocked for more than 120 seconds.
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: Not tainted 2.6.32-431.el6.x86_64 #1
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: NetworkManage D 0000000000000001 0 2081 1 0x00000080
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: ffff880614185dc8 0000000000000082 0000000000000000 ffff880613b13e80
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: 0000000000000000 ffff880612e5e0d0 0000000000000000 0000000000000000
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: ffff88061464bab8 ffff880614185fd8 000000000000fbc8 ffff88061464bab8
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: Call Trace:
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: [<ffffffffa02b65a5>] jbd2_log_wait_commit+0xc5/0x140 [jbd2]
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: [<ffffffff8109b2a0>] ? autoremove_wake_function+0x0/0x40
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: [<ffffffff81134c91>] ? do_writepages+0x21/0x40
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: [<ffffffffa02b6938>] jbd2_complete_transaction+0x68/0xb0 [jbd2]
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: [<ffffffffa02d2231>] ext4_sync_file+0x121/0x1d0 [ext4]
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: [<ffffffff811baa61>] vfs_fsync_range+0xa1/0x100
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: [<ffffffff811bab2d>] vfs_fsync+0x1d/0x20
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: [<ffffffff811bab6e>] do_fsync+0x3e/0x60
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: [<ffffffff811babc0>] sys_fsync+0x10/0x20
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: [<ffffffff8100b072>] system_call_fastpath+0x16/0x1b
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: INFO: task sadc:15210 blocked for more than 120 seconds.
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: Not tainted 2.6.32-431.el6.x86_64 #1
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: sadc D 0000000000000000 0 15210 15209 0x00000084
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: ffff88091ed9bdc8 0000000000000082 0000000000000000 ffff88091ed9bde8
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: ffff88091ed9bd88 ffffffff8111f3e0 ffff88008f60a9d0 ffff88091ed9bde8
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: ffff88061439bab8 ffff88091ed9bfd8 000000000000fbc8 ffff88061439bab8
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: Call Trace:
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: [<ffffffff8111f3e0>] ? find_get_pages_tag+0x40/0x130
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: [<ffffffffa02b65a5>] jbd2_log_wait_commit+0xc5/0x140 [jbd2]
Nov 15 00:03:29 hs-test-10-20-30-15 kernel: [<ffffffff8109b2a0>] ? autoremove_wake_function+0x0/0x40

原因以及排查思路：

Under heavy IO load on servers you may see something like:

INFO: task nfsd:2252 blocked for more than 120 seconds.
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.

...probably followed by a call trace that mentions your filesystem, and probably io_schedule and sync_buffer.

This message is not an error.

It is an indication that a program has had to wait for a very long time, and what it was doing. (which is not so informative of the reason - it's common that the real IO load issue comes from another process)

The code behind this sits in hung_task.c and was added somewhere around 2.6.30. This is a kernel thread that detects tasks that stays in the D state for a while (which typically meaning it is waiting for IO).

It complains when it sees a process has been waiting on IO so long that the whole process has not been scheduled for any CPU-time for 120 seconds (default).

Notes:

• if it happens constantly your IO system is slower than your IO use

• most likely to happen to a process that was ioniced into the idle class. Which means it's working, idle-class is meant as an extreme politeness thing. It just indicates something else is doing a bunch of IO right now (for at least 120 seconds)

e.g. updatedb (may be victim if it were ioniced, cause if not)

• if it happens only nightly, look at your cron jobs

• a trashing system can cause this, and then it's purely a side effect of one program using too much RAM

• being blocked by a desktop-class drive with bad sectors (because they retry for a long while)

• NFS seems to be a common culprit, probably because it's good at filling the writeback cache, something which implies blocking while writeback happens - which is likely to block various things related to the same filesystem. (verify)

• if it happens on a fileserver, you may want to consider spreading to more fileservers, or using a parallel filesystem

• tweaking the linux io scheduler for the device may help (See Computer_data_storage_-_General_&_RAID_performance_tweaking#OS_scheduling)

if your load is fairly sequential, you may get some relief from using the noop io scheduler (instead of cfq) though note that that disables ionice)

if your load is relatively random, upping the queue depth may help