Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

zfs hang when read/write data on file system(ext4) formatted from zvol #1909

Closed
Vicente-Cheng opened this issue Nov 28, 2013 · 4 comments
Closed
Milestone

Comments

@Vicente-Cheng
Copy link

I apologize in advance if this is a duplicate.

We got the zfs hang problem with following scenario:
1. Initiator format the exported volumes to file system(ext4).
2. Read/Write data on this file system (loading may be heavy).
3. The volumes often offline under 24 hours.

I got these code trace in server side.

Nov 21 00:08:25 ubuntu27 kernel: [480028.008998] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Nov 21 00:08:25 ubuntu27 kernel: [480028.009856] zvol/0          D ffff880627c14580     0  2369      2 0x00000000
Nov 21 00:08:25 ubuntu27 kernel: [480028.009861]  ffff880c1ca89b70 0000000000000046 ffff880c1ca89fd8 0000000000014580
Nov 21 00:08:25 ubuntu27 kernel: [480028.009866]  ffff880c1ca89fd8 0000000000014580 ffff880c1bf42ee0 ffff880627c14e28
Nov 21 00:08:25 ubuntu27 kernel: [480028.009870]  ffff880576be8360 ffff880576be8390 0000000000000001 0000000000000002
Nov 21 00:08:25 ubuntu27 kernel: [480028.009875] Call Trace:
Nov 21 00:08:25 ubuntu27 kernel: [480028.009884]  [<ffffffff816ea87d>] io_schedule+0x9d/0x130
Nov 21 00:08:25 ubuntu27 kernel: [480028.009901]  [<ffffffffa036a1ad>] cv_wait_common+0x9d/0x1a0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.009907]  [<ffffffff81085580>] ? wake_up_atomic_t+0x30/0x30
Nov 21 00:08:25 ubuntu27 kernel: [480028.009916]  [<ffffffffa036a308>] __cv_wait_io+0x18/0x20 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.009954]  [<ffffffffa0d7af83>] zio_wait+0x103/0x1c0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.009977]  [<ffffffffa0cf98c3>] dmu_tx_count_write+0x663/0x6f0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.009985]  [<ffffffffa03610c6>] ? kmem_alloc_debug+0x96/0x3c0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.010009]  [<ffffffffa0cfd0e7>] ? dnode_hold_impl+0x437/0x5c0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.010015]  [<ffffffff8133501e>] ? freed_request+0x4e/0x80
Nov 21 00:08:25 ubuntu27 kernel: [480028.010038]  [<ffffffffa0cf9986>] dmu_tx_hold_write+0x36/0x50 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.010069]  [<ffffffffa0d8479a>] zvol_write+0x9a/0x480 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.010072]  [<ffffffff816ea120>] ? __schedule+0x3b0/0x7e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.010081]  [<ffffffffa03646c7>] taskq_thread+0x237/0x4b0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.010086]  [<ffffffff81091420>] ? finish_task_switch+0x50/0xf0
Nov 21 00:08:25 ubuntu27 kernel: [480028.010090]  [<ffffffff81094950>] ? wake_up_state+0x20/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.010098]  [<ffffffffa0364490>] ? taskq_cancel_id+0x1f0/0x1f0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.010104]  [<ffffffff810847b0>] kthread+0xc0/0xd0
Nov 21 00:08:25 ubuntu27 kernel: [480028.010108]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.010113]  [<ffffffff816f516c>] ret_from_fork+0x7c/0xb0
Nov 21 00:08:25 ubuntu27 kernel: [480028.010117]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.010120] INFO: task zvol/1:2370 blocked for more than 120 seconds.
Nov 21 00:08:25 ubuntu27 kernel: [480028.010817] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Nov 21 00:08:25 ubuntu27 kernel: [480028.011669] zvol/1          D ffff880627c34580     0  2370      2 0x00000000
Nov 21 00:08:25 ubuntu27 kernel: [480028.011672]  ffff880c19effbb0 0000000000000046 ffff880c19efffd8 0000000000014580
Nov 21 00:08:25 ubuntu27 kernel: [480028.011676]  ffff880c19efffd8 0000000000014580 ffff880c19fdaee0 ffff880c19d8d1d8
Nov 21 00:08:25 ubuntu27 kernel: [480028.011680]  ffff880c19d8d1dc ffff880c19fdaee0 00000000ffffffff ffff880c19d8d1e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.011684] Call Trace:
Nov 21 00:08:25 ubuntu27 kernel: [480028.011688]  [<ffffffff816eb4d9>] schedule_preempt_disabled+0x29/0x70
Nov 21 00:08:25 ubuntu27 kernel: [480028.011695]  [<ffffffff816e951f>] __mutex_lock_slowpath+0x13f/0x1c0
Nov 21 00:08:25 ubuntu27 kernel: [480028.011699]  [<ffffffff816e890f>] mutex_lock+0x1f/0x2f
Nov 21 00:08:25 ubuntu27 kernel: [480028.011732]  [<ffffffffa0d34791>] txg_delay+0x61/0x130 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.011759]  [<ffffffffa0d0dbc1>] dsl_pool_tempreserve_space+0xd1/0xe0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.011785]  [<ffffffffa0d0b5a7>] dsl_dir_tempreserve_space+0x137/0x200 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.011791]  [<ffffffff81019e89>] ? read_tsc+0x9/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.011814]  [<ffffffffa0cf8bce>] dmu_tx_assign+0x3ee/0x420 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.011845]  [<ffffffffa0d847a7>] zvol_write+0xa7/0x480 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.011848]  [<ffffffff816ea120>] ? __schedule+0x3b0/0x7e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.011857]  [<ffffffffa03646c7>] taskq_thread+0x237/0x4b0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.011861]  [<ffffffff81091420>] ? finish_task_switch+0x50/0xf0
Nov 21 00:08:25 ubuntu27 kernel: [480028.011864]  [<ffffffff81094950>] ? wake_up_state+0x20/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.011872]  [<ffffffffa0364490>] ? taskq_cancel_id+0x1f0/0x1f0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.011876]  [<ffffffff810847b0>] kthread+0xc0/0xd0
Nov 21 00:08:25 ubuntu27 kernel: [480028.011880]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.011883]  [<ffffffff816f516c>] ret_from_fork+0x7c/0xb0
Nov 21 00:08:25 ubuntu27 kernel: [480028.011887]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.011890] INFO: task zvol/2:2371 blocked for more than 120 seconds.
Nov 21 00:08:25 ubuntu27 kernel: [480028.012649] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Nov 21 00:08:25 ubuntu27 kernel: [480028.034760] zvol/2          D ffff880627c54580     0  2371      2 0x00000000
Nov 21 00:08:25 ubuntu27 kernel: [480028.034764]  ffff880c188e3bb0 0000000000000046 ffff880c188e3fd8 0000000000014580
Nov 21 00:08:25 ubuntu27 kernel: [480028.034768]  ffff880c188e3fd8 0000000000014580 ffff880c1d102ee0 ffff880c19d8d1d8
Nov 21 00:08:25 ubuntu27 kernel: [480028.034772]  ffff880c19d8d1dc ffff880c1d102ee0 00000000ffffffff ffff880c19d8d1e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.034776] Call Trace:
Nov 21 00:08:25 ubuntu27 kernel: [480028.034781]  [<ffffffff816eb4d9>] schedule_preempt_disabled+0x29/0x70
Nov 21 00:08:25 ubuntu27 kernel: [480028.034785]  [<ffffffff816e951f>] __mutex_lock_slowpath+0x13f/0x1c0
Nov 21 00:08:25 ubuntu27 kernel: [480028.034789]  [<ffffffff816e890f>] mutex_lock+0x1f/0x2f
Nov 21 00:08:25 ubuntu27 kernel: [480028.034822]  [<ffffffffa0d34791>] txg_delay+0x61/0x130 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.034849]  [<ffffffffa0d0dbc1>] dsl_pool_tempreserve_space+0xd1/0xe0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.034875]  [<ffffffffa0d0b5a7>] dsl_dir_tempreserve_space+0x137/0x200 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.034878]  [<ffffffff81019e89>] ? read_tsc+0x9/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.034901]  [<ffffffffa0cf8bce>] dmu_tx_assign+0x3ee/0x420 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.034932]  [<ffffffffa0d847a7>] zvol_write+0xa7/0x480 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.034935]  [<ffffffff816ea120>] ? __schedule+0x3b0/0x7e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.034944]  [<ffffffffa03646c7>] taskq_thread+0x237/0x4b0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.034948]  [<ffffffff81091420>] ? finish_task_switch+0x50/0xf0
Nov 21 00:08:25 ubuntu27 kernel: [480028.034951]  [<ffffffff81094950>] ? wake_up_state+0x20/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.034959]  [<ffffffffa0364490>] ? taskq_cancel_id+0x1f0/0x1f0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.034963]  [<ffffffff810847b0>] kthread+0xc0/0xd0
Nov 21 00:08:25 ubuntu27 kernel: [480028.034967]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.034970]  [<ffffffff816f516c>] ret_from_fork+0x7c/0xb0
Nov 21 00:08:25 ubuntu27 kernel: [480028.034974]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.034977] INFO: task zvol/3:2373 blocked for more than 120 seconds.
Nov 21 00:08:25 ubuntu27 kernel: [480028.057364] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Nov 21 00:08:25 ubuntu27 kernel: [480028.080374] zvol/3          D ffff880627c74580     0  2373      2 0x00000000
Nov 21 00:08:25 ubuntu27 kernel: [480028.080378]  ffff880c1c75dbb0 0000000000000046 ffff880c1c75dfd8 0000000000014580
Nov 21 00:08:25 ubuntu27 kernel: [480028.080382]  ffff880c1c75dfd8 0000000000014580 ffff880c1bfdc650 ffff880c19d8d1d8
Nov 21 00:08:25 ubuntu27 kernel: [480028.080386]  ffff880c19d8d1dc ffff880c1bfdc650 00000000ffffffff ffff880c19d8d1e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.080390] Call Trace:
Nov 21 00:08:25 ubuntu27 kernel: [480028.080394]  [<ffffffff816eb4d9>] schedule_preempt_disabled+0x29/0x70
Nov 21 00:08:25 ubuntu27 kernel: [480028.080399]  [<ffffffff816e951f>] __mutex_lock_slowpath+0x13f/0x1c0
Nov 21 00:08:25 ubuntu27 kernel: [480028.080402]  [<ffffffff816e890f>] mutex_lock+0x1f/0x2f
Nov 21 00:08:25 ubuntu27 kernel: [480028.080436]  [<ffffffffa0d34791>] txg_delay+0x61/0x130 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.080463]  [<ffffffffa0d0dbc1>] dsl_pool_tempreserve_space+0xd1/0xe0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.080490]  [<ffffffffa0d0b5a7>] dsl_dir_tempreserve_space+0x137/0x200 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.080494]  [<ffffffff81019e89>] ? read_tsc+0x9/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.080517]  [<ffffffffa0cf8bce>] dmu_tx_assign+0x3ee/0x420 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.080548]  [<ffffffffa0d847a7>] zvol_write+0xa7/0x480 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.080551]  [<ffffffff816ea120>] ? __schedule+0x3b0/0x7e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.080560]  [<ffffffffa03646c7>] taskq_thread+0x237/0x4b0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.080564]  [<ffffffff81091420>] ? finish_task_switch+0x50/0xf0
Nov 21 00:08:25 ubuntu27 kernel: [480028.080567]  [<ffffffff81094950>] ? wake_up_state+0x20/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.080575]  [<ffffffffa0364490>] ? taskq_cancel_id+0x1f0/0x1f0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.080579]  [<ffffffff810847b0>] kthread+0xc0/0xd0
Nov 21 00:08:25 ubuntu27 kernel: [480028.080583]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.080586]  [<ffffffff816f516c>] ret_from_fork+0x7c/0xb0
Nov 21 00:08:25 ubuntu27 kernel: [480028.080590]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.080593] INFO: task zvol/4:2374 blocked for more than 120 seconds.
Nov 21 00:08:25 ubuntu27 kernel: [480028.103958] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Nov 21 00:08:25 ubuntu27 kernel: [480028.128010] zvol/4          D ffff880627c94580     0  2374      2 0x00000000
Nov 21 00:08:25 ubuntu27 kernel: [480028.128014]  ffff880c1c635a30 0000000000000046 ffff880c1c635fd8 0000000000014580
Nov 21 00:08:25 ubuntu27 kernel: [480028.128018]  ffff880c1c635fd8 0000000000014580 ffff880c1c610000 ffff880627c94e28
Nov 21 00:08:25 ubuntu27 kernel: [480028.128022]  ffff880913d99990 ffff880913d999c0 0000000000000001 0000000000000002
Nov 21 00:08:25 ubuntu27 kernel: [480028.128026] Call Trace:
Nov 21 00:08:25 ubuntu27 kernel: [480028.128030]  [<ffffffff816ea87d>] io_schedule+0x9d/0x130
Nov 21 00:08:25 ubuntu27 kernel: [480028.128041]  [<ffffffffa036a1ad>] cv_wait_common+0x9d/0x1a0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.128044]  [<ffffffff81085580>] ? wake_up_atomic_t+0x30/0x30
Nov 21 00:08:25 ubuntu27 kernel: [480028.128052]  [<ffffffffa036a308>] __cv_wait_io+0x18/0x20 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.128084]  [<ffffffffa0d7af83>] zio_wait+0x103/0x1c0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.128102]  [<ffffffffa0ce59c7>] dbuf_read+0x2d7/0x880 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.128120]  [<ffffffffa0ce6362>] __dbuf_hold_impl+0x3f2/0x4a0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.128138]  [<ffffffffa0ce648b>] dbuf_hold_impl+0x7b/0xa0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.128161]  [<ffffffffa0cf9627>] dmu_tx_count_write+0x3c7/0x6f0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.128184]  [<ffffffffa0cf9986>] dmu_tx_hold_write+0x36/0x50 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.128342]  [<ffffffffa0d8479a>] zvol_write+0x9a/0x480 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.128346]  [<ffffffff816ea120>] ? __schedule+0x3b0/0x7e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.128354]  [<ffffffffa03646c7>] taskq_thread+0x237/0x4b0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.128358]  [<ffffffff81091420>] ? finish_task_switch+0x50/0xf0
Nov 21 00:08:25 ubuntu27 kernel: [480028.128361]  [<ffffffff81094950>] ? wake_up_state+0x20/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.128369]  [<ffffffffa0364490>] ? taskq_cancel_id+0x1f0/0x1f0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.128380]  [<ffffffff810847b0>] kthread+0xc0/0xd0
Nov 21 00:08:25 ubuntu27 kernel: [480028.128384]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.128387]  [<ffffffff816f516c>] ret_from_fork+0x7c/0xb0
Nov 21 00:08:25 ubuntu27 kernel: [480028.128390]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.128393] INFO: task zvol/5:2375 blocked for more than 120 seconds.
Nov 21 00:08:25 ubuntu27 kernel: [480028.152494] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Nov 21 00:08:25 ubuntu27 kernel: [480028.176851] zvol/5          D ffff880627cb4580     0  2375      2 0x00000000
Nov 21 00:08:25 ubuntu27 kernel: [480028.176855]  ffff880c1cd81b20 0000000000000046 ffff880c1cd81fd8 0000000000014580
Nov 21 00:08:25 ubuntu27 kernel: [480028.176859]  ffff880c1cd81fd8 0000000000014580 ffff880c1cbc1770 ffff880c19d8d1d8
Nov 21 00:08:25 ubuntu27 kernel: [480028.176863]  ffff880c19d8d1dc ffff880c1cbc1770 00000000ffffffff ffff880c19d8d1e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.176867] Call Trace:
Nov 21 00:08:25 ubuntu27 kernel: [480028.176871]  [<ffffffff816eb4d9>] schedule_preempt_disabled+0x29/0x70
Nov 21 00:08:25 ubuntu27 kernel: [480028.176875]  [<ffffffff816e951f>] __mutex_lock_slowpath+0x13f/0x1c0
Nov 21 00:08:25 ubuntu27 kernel: [480028.176879]  [<ffffffff816e890f>] mutex_lock+0x1f/0x2f
Nov 21 00:08:25 ubuntu27 kernel: [480028.176890]  [<ffffffffa036a3c9>] __cv_timedwait_common+0xb9/0x210 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.176910]  [<ffffffffa0ce3b21>] ? dbuf_destroy+0x161/0x170 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.176918]  [<ffffffff8118de55>] ? __kmalloc+0x175/0x180
Nov 21 00:08:25 ubuntu27 kernel: [480028.176921]  [<ffffffff81085580>] ? wake_up_atomic_t+0x30/0x30
Nov 21 00:08:25 ubuntu27 kernel: [480028.176930]  [<ffffffffa036a533>] __cv_timedwait+0x13/0x20 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.176961]  [<ffffffffa0d3480f>] txg_delay+0xdf/0x130 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.176987]  [<ffffffffa0d0dbc1>] dsl_pool_tempreserve_space+0xd1/0xe0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.177013]  [<ffffffffa0d0b5a7>] dsl_dir_tempreserve_space+0x137/0x200 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.177017]  [<ffffffff81019e89>] ? read_tsc+0x9/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.177039]  [<ffffffffa0cf8bce>] dmu_tx_assign+0x3ee/0x420 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.177070]  [<ffffffffa0d847a7>] zvol_write+0xa7/0x480 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.177073]  [<ffffffff816ea120>] ? __schedule+0x3b0/0x7e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.177082]  [<ffffffffa03646c7>] taskq_thread+0x237/0x4b0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.177085]  [<ffffffff81091420>] ? finish_task_switch+0x50/0xf0
Nov 21 00:08:25 ubuntu27 kernel: [480028.177089]  [<ffffffff81094950>] ? wake_up_state+0x20/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.177097]  [<ffffffffa0364490>] ? taskq_cancel_id+0x1f0/0x1f0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.177101]  [<ffffffff810847b0>] kthread+0xc0/0xd0
Nov 21 00:08:25 ubuntu27 kernel: [480028.177105]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.177108]  [<ffffffff816f516c>] ret_from_fork+0x7c/0xb0
Nov 21 00:08:25 ubuntu27 kernel: [480028.177112]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.177115] INFO: task zvol/6:2376 blocked for more than 120 seconds.
Nov 21 00:08:25 ubuntu27 kernel: [480028.201534] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Nov 21 00:08:25 ubuntu27 kernel: [480028.226420] zvol/6          D ffff880c3fc14580     0  2376      2 0x00000000
Nov 21 00:08:25 ubuntu27 kernel: [480028.226424]  ffff880c1cbb9bb0 0000000000000046 ffff880c1cbb9fd8 0000000000014580
Nov 21 00:08:25 ubuntu27 kernel: [480028.226428]  ffff880c1cbb9fd8 0000000000014580 ffff880c1cbc0000 ffff880c19d8d1d8
Nov 21 00:08:25 ubuntu27 kernel: [480028.226432]  ffff880c19d8d1dc ffff880c1cbc0000 00000000ffffffff ffff880c19d8d1e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.226436] Call Trace:
Nov 21 00:08:25 ubuntu27 kernel: [480028.226441]  [<ffffffff816eb4d9>] schedule_preempt_disabled+0x29/0x70
Nov 21 00:08:25 ubuntu27 kernel: [480028.226445]  [<ffffffff816e951f>] __mutex_lock_slowpath+0x13f/0x1c0
Nov 21 00:08:25 ubuntu27 kernel: [480028.226448]  [<ffffffff816e890f>] mutex_lock+0x1f/0x2f
Nov 21 00:08:25 ubuntu27 kernel: [480028.226482]  [<ffffffffa0d34791>] txg_delay+0x61/0x130 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.226508]  [<ffffffffa0d0dbc1>] dsl_pool_tempreserve_space+0xd1/0xe0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.226534]  [<ffffffffa0d0b5a7>] dsl_dir_tempreserve_space+0x137/0x200 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.226538]  [<ffffffff81019e89>] ? read_tsc+0x9/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.226561]  [<ffffffffa0cf8bce>] dmu_tx_assign+0x3ee/0x420 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.226592]  [<ffffffffa0d847a7>] zvol_write+0xa7/0x480 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.226595]  [<ffffffff816ea120>] ? __schedule+0x3b0/0x7e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.226604]  [<ffffffffa03646c7>] taskq_thread+0x237/0x4b0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.226608]  [<ffffffff81091420>] ? finish_task_switch+0x50/0xf0
Nov 21 00:08:25 ubuntu27 kernel: [480028.226611]  [<ffffffff81094950>] ? wake_up_state+0x20/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.226619]  [<ffffffffa0364490>] ? taskq_cancel_id+0x1f0/0x1f0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.226623]  [<ffffffff810847b0>] kthread+0xc0/0xd0
Nov 21 00:08:25 ubuntu27 kernel: [480028.226627]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.226630]  [<ffffffff816f516c>] ret_from_fork+0x7c/0xb0
Nov 21 00:08:25 ubuntu27 kernel: [480028.226634]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.226637] INFO: task zvol/7:2377 blocked for more than 120 seconds.
Nov 21 00:08:25 ubuntu27 kernel: [480028.251721] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Nov 21 00:08:25 ubuntu27 kernel: [480028.277500] zvol/7          D ffff880c3fc34580     0  2377      2 0x00000000
Nov 21 00:08:25 ubuntu27 kernel: [480028.277503]  ffff880c1c57bbb0 0000000000000046 ffff880c1c57bfd8 0000000000014580
Nov 21 00:08:25 ubuntu27 kernel: [480028.277508]  ffff880c1c57bfd8 0000000000014580 ffff880c1bfe8000 ffff880c19d8d1d8
Nov 21 00:08:25 ubuntu27 kernel: [480028.277511]  ffff880c19d8d1dc ffff880c1bfe8000 00000000ffffffff ffff880c19d8d1e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.277516] Call Trace:
Nov 21 00:08:25 ubuntu27 kernel: [480028.277520]  [<ffffffff816eb4d9>] schedule_preempt_disabled+0x29/0x70
Nov 21 00:08:25 ubuntu27 kernel: [480028.277524]  [<ffffffff816e951f>] __mutex_lock_slowpath+0x13f/0x1c0
Nov 21 00:08:25 ubuntu27 kernel: [480028.277528]  [<ffffffff816e890f>] mutex_lock+0x1f/0x2f
Nov 21 00:08:25 ubuntu27 kernel: [480028.277562]  [<ffffffffa0d34791>] txg_delay+0x61/0x130 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.277588]  [<ffffffffa0d0dbc1>] dsl_pool_tempreserve_space+0xd1/0xe0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.277614]  [<ffffffffa0d0b5a7>] dsl_dir_tempreserve_space+0x137/0x200 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.277617]  [<ffffffff81019e89>] ? read_tsc+0x9/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.277640]  [<ffffffffa0cf8bce>] dmu_tx_assign+0x3ee/0x420 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.277671]  [<ffffffffa0d847a7>] zvol_write+0xa7/0x480 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.277674]  [<ffffffff816ea120>] ? __schedule+0x3b0/0x7e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.277684]  [<ffffffffa03646c7>] taskq_thread+0x237/0x4b0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.277687]  [<ffffffff81091420>] ? finish_task_switch+0x50/0xf0
Nov 21 00:08:25 ubuntu27 kernel: [480028.277691]  [<ffffffff81094950>] ? wake_up_state+0x20/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.277699]  [<ffffffffa0364490>] ? taskq_cancel_id+0x1f0/0x1f0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.277703]  [<ffffffff810847b0>] kthread+0xc0/0xd0
Nov 21 00:08:25 ubuntu27 kernel: [480028.277707]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.277710]  [<ffffffff816f516c>] ret_from_fork+0x7c/0xb0
Nov 21 00:08:25 ubuntu27 kernel: [480028.277714]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.277716] INFO: task zvol/8:2380 blocked for more than 120 seconds.
Nov 21 00:08:25 ubuntu27 kernel: [480028.303859] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Nov 21 00:08:25 ubuntu27 kernel: [480028.330217] zvol/8          D ffff880c3fc54580     0  2380      2 0x00000000
Nov 21 00:08:25 ubuntu27 kernel: [480028.330220]  ffff880c1c6efb70 0000000000000046 ffff880c1c6effd8 0000000000014580
Nov 21 00:08:25 ubuntu27 kernel: [480028.330224]  ffff880c1c6effd8 0000000000014580 ffff880c1af35dc0 ffff880c3fc54e28
Nov 21 00:08:25 ubuntu27 kernel: [480028.330228]  ffff8800a40990b0 ffff8800a40990e0 0000000000000001 0000000000000002
Nov 21 00:08:25 ubuntu27 kernel: [480028.330232] Call Trace:
Nov 21 00:08:25 ubuntu27 kernel: [480028.330236]  [<ffffffff816ea87d>] io_schedule+0x9d/0x130
Nov 21 00:08:25 ubuntu27 kernel: [480028.330247]  [<ffffffffa036a1ad>] cv_wait_common+0x9d/0x1a0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.330250]  [<ffffffff81085580>] ? wake_up_atomic_t+0x30/0x30
Nov 21 00:08:25 ubuntu27 kernel: [480028.330258]  [<ffffffffa036a308>] __cv_wait_io+0x18/0x20 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.330290]  [<ffffffffa0d7af83>] zio_wait+0x103/0x1c0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.330313]  [<ffffffffa0cf98c3>] dmu_tx_count_write+0x663/0x6f0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.330322]  [<ffffffffa03610c6>] ? kmem_alloc_debug+0x96/0x3c0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.330345]  [<ffffffffa0cfd0e7>] ? dnode_hold_impl+0x437/0x5c0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.330349]  [<ffffffff8133501e>] ? freed_request+0x4e/0x80
Nov 21 00:08:25 ubuntu27 kernel: [480028.330372]  [<ffffffffa0cf9986>] dmu_tx_hold_write+0x36/0x50 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.330403]  [<ffffffffa0d8479a>] zvol_write+0x9a/0x480 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.330406]  [<ffffffff816ea120>] ? __schedule+0x3b0/0x7e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.330414]  [<ffffffffa03646c7>] taskq_thread+0x237/0x4b0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.330418]  [<ffffffff81091420>] ? finish_task_switch+0x50/0xf0
Nov 21 00:08:25 ubuntu27 kernel: [480028.330421]  [<ffffffff81094950>] ? wake_up_state+0x20/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.330429]  [<ffffffffa0364490>] ? taskq_cancel_id+0x1f0/0x1f0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.330433]  [<ffffffff810847b0>] kthread+0xc0/0xd0
Nov 21 00:08:25 ubuntu27 kernel: [480028.330437]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.330440]  [<ffffffff816f516c>] ret_from_fork+0x7c/0xb0
Nov 21 00:08:25 ubuntu27 kernel: [480028.330444]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.330447] INFO: task zvol/9:2381 blocked for more than 120 seconds.
Nov 21 00:08:25 ubuntu27 kernel: [480028.356583] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Nov 21 00:08:25 ubuntu27 kernel: [480028.383074] zvol/9          D ffff880c3fc74580     0  2381      2 0x00000000
Nov 21 00:08:25 ubuntu27 kernel: [480028.383078]  ffff880c1cf6fb70 0000000000000046 ffff880c1cf6ffd8 0000000000014580
Nov 21 00:08:25 ubuntu27 kernel: [480028.383082]  ffff880c1cf6ffd8 0000000000014580 ffff880c1a418000 ffff880c3fc74e28
Nov 21 00:08:25 ubuntu27 kernel: [480028.383086]  ffff8805e7985c20 ffff8805e7985c50 0000000000000001 0000000000000002
Nov 21 00:08:25 ubuntu27 kernel: [480028.383090] Call Trace:
Nov 21 00:08:25 ubuntu27 kernel: [480028.383094]  [<ffffffff816ea87d>] io_schedule+0x9d/0x130
Nov 21 00:08:25 ubuntu27 kernel: [480028.383105]  [<ffffffffa036a1ad>] cv_wait_common+0x9d/0x1a0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.383108]  [<ffffffff81085580>] ? wake_up_atomic_t+0x30/0x30
Nov 21 00:08:25 ubuntu27 kernel: [480028.383116]  [<ffffffffa036a308>] __cv_wait_io+0x18/0x20 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.383149]  [<ffffffffa0d7af83>] zio_wait+0x103/0x1c0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.383172]  [<ffffffffa0cf98c3>] dmu_tx_count_write+0x663/0x6f0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.383180]  [<ffffffffa03610c6>] ? kmem_alloc_debug+0x96/0x3c0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.383203]  [<ffffffffa0cfd0e7>] ? dnode_hold_impl+0x437/0x5c0 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.383207]  [<ffffffff8133501e>] ? freed_request+0x4e/0x80
Nov 21 00:08:25 ubuntu27 kernel: [480028.383230]  [<ffffffffa0cf9986>] dmu_tx_hold_write+0x36/0x50 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.383260]  [<ffffffffa0d8479a>] zvol_write+0x9a/0x480 [zfs]
Nov 21 00:08:25 ubuntu27 kernel: [480028.383264]  [<ffffffff816ea120>] ? __schedule+0x3b0/0x7e0
Nov 21 00:08:25 ubuntu27 kernel: [480028.383272]  [<ffffffffa03646c7>] taskq_thread+0x237/0x4b0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.383276]  [<ffffffff81091420>] ? finish_task_switch+0x50/0xf0
Nov 21 00:08:25 ubuntu27 kernel: [480028.383279]  [<ffffffff81094950>] ? wake_up_state+0x20/0x20
Nov 21 00:08:25 ubuntu27 kernel: [480028.383287]  [<ffffffffa0364490>] ? taskq_cancel_id+0x1f0/0x1f0 [spl]
Nov 21 00:08:25 ubuntu27 kernel: [480028.383291]  [<ffffffff810847b0>] kthread+0xc0/0xd0
Nov 21 00:08:25 ubuntu27 kernel: [480028.383295]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120
Nov 21 00:08:25 ubuntu27 kernel: [480028.383298]  [<ffffffff816f516c>] ret_from_fork+0x7c/0xb0
Nov 21 00:08:25 ubuntu27 kernel: [480028.383302]  [<ffffffff810846f0>] ? kthread_create_on_node+0x120/0x120

pool/volume information:
6 disks format 1 raidz vdev
pool consist of 4 vdevs
volume export from this pool

are there some problems when dmu assign txg ?

or these may be caused by other reasons.

thanks for replying!

@GregorKopka
Copy link
Contributor

What setting for PREEMT do you have in your kernel?

Should you have CONFIG_PREEMPT_NONE=y then try to set CONFIG_PREEMPT_VOLUNTARY=y instead, this fixed lockups (which iirc looked like yours) on my machines.

@Vicente-Cheng
Copy link
Author

My PREEMT setting now is following:

# CONFIG_PREEMPT_NONE is not set
CONFIG_PREEMPT_VOLUNTARY=y

Is this setting the same in your machines?

@GregorKopka
Copy link
Contributor

@Vicente-Cheng yes, this is the setting that lead to my machines working without hanging on stacktraces similar to the one you posted. YMMV but i hope this helps.

@behlendorf
Copy link
Contributor

Closing, setting CONFIG_PREEMPT_VOLUNTARY=y resolved the issue.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants