reproduce_sync_stuck.sh
[LU-16315] sync I/O stuck on refreshing layout for PFL Created: 15/Nov/22 Updated: 16/Nov/22 |
|
| Status: | Open |
| Project: | Lustre |
| Component/s: | None |
| Affects Version/s: | None |
| Fix Version/s: | None |
| Type: | Bug | Priority: | Major |
| Reporter: | Li Xi | Assignee: | WC Triage |
| Resolution: | Unresolved | Votes: | 0 |
| Labels: | None | ||
| Attachments: |
reproduce_sync_stuck.sh
|
| Rank (Obsolete): | 9223372036854775807 |
| Description |
|
When testing PFL, got the client stuck.
[ 360.010400] INFO: task dd:1542 blocked for more than 120 seconds. [ 360.014017] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 360.018530] dd D ffff8c3578f10000 0 1542 1 0x00000080 [ 360.022370] Call Trace: [ 360.023463] [<ffffffff9018d309>] schedule_preempt_disabled+0x29/0x70 [ 360.026263] [<ffffffff9018b457>] __mutex_lock_slowpath+0xc7/0x1d0 [ 360.029179] [<ffffffff9018a82f>] mutex_lock+0x1f/0x2f [ 360.031242] [<ffffffffc0b8ff9e>] ll_layout_refresh+0x1ee/0x910 [lustre] [ 360.033751] [<ffffffff8faad8b0>] ? requeue_timers+0x170/0x170 [ 360.036043] [<ffffffff8fac6b41>] ? remove_wait_queue+0x31/0x40 [ 360.038309] [<ffffffffc0bd81df>] vvp_io_init+0x34f/0x490 [lustre] [ 360.040660] [<ffffffffc057725b>] cl_io_init0.isra.14+0x8b/0x160 [obdclass] [ 360.043188] [<ffffffffc05773f3>] cl_io_init+0x43/0x80 [obdclass] [ 360.045369] [<ffffffffc0b8ca78>] cl_sync_file_range+0x1b8/0x380 [lustre] [ 360.047729] [<ffffffffc0b8cf01>] ll_fsync+0x2c1/0x4e0 [lustre] [ 360.049821] [<ffffffff8fc8408f>] generic_write_sync+0x4f/0x70 [ 360.052050] [<ffffffffc0bd77b0>] vvp_io_write_start+0x660/0xd40 [lustre] [ 360.054437] [<ffffffffc0a3a265>] ? lov_lock_enqueue+0x95/0x150 [lov] [ 360.056721] [<ffffffff8fac7050>] ? wake_bit_function_rh+0x40/0x40 [ 360.058785] [<ffffffffc0576d20>] cl_io_start+0x70/0x140 [obdclass] [ 360.060868] [<ffffffffc057922f>] cl_io_loop+0x9f/0x200 [obdclass] [ 360.062917] [<ffffffffc0b864cc>] ll_file_io_generic+0x90c/0xe50 [lustre] [ 360.065092] [<ffffffffc0b86ca5>] ll_file_aio_write+0x295/0x6d0 [lustre] [ 360.067185] [<ffffffffc0b871e0>] ll_file_write+0x100/0x1c0 [lustre] [ 360.069146] [<ffffffff8fc4e590>] vfs_write+0xc0/0x1f0 [ 360.070728] [<ffffffff8fc4f36f>] SyS_write+0x7f/0xf0 [ 360.072323] [<ffffffff90199f92>] system_call_fastpath+0x25/0x2a [ 360.074179] INFO: task dd:1544 blocked for more than 120 seconds. [ 360.076000] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 360.078951] dd D ffff8c3575eb12c0 0 1544 1 0x00000080 [ 360.082129] Call Trace: [ 360.083834] [<ffffffff9018d309>] schedule_preempt_disabled+0x29/0x70 [ 360.087082] [<ffffffff9018b457>] __mutex_lock_slowpath+0xc7/0x1d0 [ 360.090202] [<ffffffff8fadae02>] ? default_wake_function+0x12/0x20 [ 360.093104] [<ffffffff9018a82f>] mutex_lock+0x1f/0x2f [ 360.095580] [<ffffffffc0b8ff9e>] ll_layout_refresh+0x1ee/0x910 [lustre] [ 360.098712] [<ffffffffc084b370>] ? lustre_msg_buf_v2+0x1e0/0x1e0 [ptlrpc] [ 360.101765] [<ffffffffc0873293>] ? __req_capsule_get+0x163/0x740 [ptlrpc] [ 360.104431] [<ffffffffc0bd81df>] vvp_io_init+0x34f/0x490 [lustre] [ 360.106929] [<ffffffffc0b0db93>] ? mdc_reint+0xd3/0x160 [mdc] [ 360.109495] [<ffffffffc057725b>] cl_io_init0.isra.14+0x8b/0x160 [obdclass] [ 360.112127] [<ffffffffc05773f3>] cl_io_init+0x43/0x80 [obdclass] [ 360.114365] [<ffffffffc0bcda2e>] cl_setattr_ost+0x14e/0x3e0 [lustre] [ 360.116748] [<ffffffffc0ba5978>] ll_setattr_raw+0xd58/0x10d0 [lustre] [ 360.119143] [<ffffffffc0ba5d53>] ll_setattr+0x63/0xc0 [lustre] [ 360.121326] [<ffffffff8fc6e1ac>] notify_change+0x30c/0x4d0 [ 360.123258] [<ffffffff8fc4c2c5>] do_truncate+0x75/0xc0 [ 360.125079] [<ffffffff8fc514e8>] ? __sb_start_write+0x58/0x120 [ 360.127025] [<ffffffff8fc4c6e9>] do_sys_ftruncate.constprop.14+0x139/0x1a0 [ 360.129204] [<ffffffff8fc4c78e>] SyS_ftruncate+0xe/0x10 [ 360.131046] [<ffffffff90199f92>] system_call_fastpath+0x25/0x2a [ 360.132917] INFO: task dd:1546 blocked for more than 120 seconds. [ 360.134923] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 360.137185] dd D ffff8c35359d0000 0 1546 1 0x00000080 [ 360.139334] Call Trace: [ 360.140439] [<ffffffff9018d309>] schedule_preempt_disabled+0x29/0x70 [ 360.142365] [<ffffffff9018b457>] __mutex_lock_slowpath+0xc7/0x1d0 [ 360.144239] [<ffffffff8fadae02>] ? default_wake_function+0x12/0x20 [ 360.146119] [<ffffffff9018a82f>] mutex_lock+0x1f/0x2f [ 360.147743] [<ffffffffc0b8ff9e>] ll_layout_refresh+0x1ee/0x910 [lustre] [ 360.149742] [<ffffffffc0545a59>] ? lprocfs_counter_add+0xf9/0x160 [obdclass] [ 360.152566] [<ffffffffc0bd81df>] vvp_io_init+0x34f/0x490 [lustre] [ 360.155100] [<ffffffffc0566803>] ? lu_context_init+0xd3/0x1f0 [obdclass] [ 360.157804] [<ffffffffc056693a>] ? lu_env_init+0x1a/0x30 [obdclass] [ 360.160377] [<ffffffffc057725b>] cl_io_init0.isra.14+0x8b/0x160 [obdclass] [ 360.163160] [<ffffffffc05773f3>] cl_io_init+0x43/0x80 [obdclass] [ 360.165699] [<ffffffffc0bcda2e>] cl_setattr_ost+0x14e/0x3e0 [lustre] [ 360.168375] [<ffffffffc0ba5978>] ll_setattr_raw+0xd58/0x10d0 [lustre] [ 360.171046] [<ffffffffc0bb0978>] ? ll_stats_ops_tally+0x98/0x100 [lustre] [ 360.173759] [<ffffffffc0ba5d53>] ll_setattr+0x63/0xc0 [lustre] [ 360.176170] [<ffffffff8fc6e1ac>] notify_change+0x30c/0x4d0 [ 360.178468] [<ffffffff8fc4c2c5>] do_truncate+0x75/0xc0 [ 360.180644] [<ffffffff8fc514e8>] ? __sb_start_write+0x58/0x120 [ 360.183035] [<ffffffff8fc4c6e9>] do_sys_ftruncate.constprop.14+0x139/0x1a0 [ 360.185726] [<ffffffff8fc4c78e>] SyS_ftruncate+0xe/0x10 [ 360.187880] [<ffffffff90199f92>] system_call_fastpath+0x25/0x2a [ 360.190291] INFO: task dd:1548 blocked for more than 120 seconds. [ 360.192658] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 360.195512] dd D ffff8c3575eb2580 0 1548 1 0x00000080 [ 360.198271] Call Trace: [ 360.199497] [<ffffffff9018d309>] schedule_preempt_disabled+0x29/0x70 [ 360.201642] [<ffffffff9018b457>] __mutex_lock_slowpath+0xc7/0x1d0 [ 360.203630] [<ffffffff8fadae02>] ? default_wake_function+0x12/0x20 [ 360.205629] [<ffffffff9018a82f>] mutex_lock+0x1f/0x2f [ 360.207363] [<ffffffffc0b8ff9e>] ll_layout_refresh+0x1ee/0x910 [lustre] [ 360.209491] [<ffffffffc0545a59>] ? lprocfs_counter_add+0xf9/0x160 [obdclass] [ 360.211639] [<ffffffffc0bd81df>] vvp_io_init+0x34f/0x490 [lustre] [ 360.213527] [<ffffffffc0566803>] ? lu_context_init+0xd3/0x1f0 [obdclass] [ 360.215616] [<ffffffffc056693a>] ? lu_env_init+0x1a/0x30 [obdclass] [ 360.218169] [<ffffffffc057725b>] cl_io_init0.isra.14+0x8b/0x160 [obdclass] [ 360.221050] [<ffffffffc05773f3>] cl_io_init+0x43/0x80 [obdclass] [ 360.223613] [<ffffffffc0bcda2e>] cl_setattr_ost+0x14e/0x3e0 [lustre] [ 360.226325] [<ffffffffc0ba5978>] ll_setattr_raw+0xd58/0x10d0 [lustre] [ 360.229000] [<ffffffffc0bb0978>] ? ll_stats_ops_tally+0x98/0x100 [lustre] [ 360.231775] [<ffffffffc0ba5d53>] ll_setattr+0x63/0xc0 [lustre] [ 360.234252] [<ffffffff8fc6e1ac>] notify_change+0x30c/0x4d0 [ 360.236582] [<ffffffff8fc4c2c5>] do_truncate+0x75/0xc0 [ 360.238765] [<ffffffff8fc514e8>] ? __sb_start_write+0x58/0x120 [ 360.241177] [<ffffffff8fc4c6e9>] do_sys_ftruncate.constprop.14+0x139/0x1a0 [ 360.243907] [<ffffffff8fc4c78e>] SyS_ftruncate+0xe/0x10 [ 360.246121] [<ffffffff90199f92>] system_call_fastpath+0x25/0x2a [ 360.248472] INFO: task dd:1550 blocked for more than 120 seconds. [ 360.250771] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 360.253713] dd D ffff8c3575eb4b00 0 1550 1 0x00000080 [ 360.256549] Call Trace: [ 360.257818] [<ffffffff9018d309>] schedule_preempt_disabled+0x29/0x70 [ 360.260412] [<ffffffff9018b457>] __mutex_lock_slowpath+0xc7/0x1d0 [ 360.262933] [<ffffffff8fadae02>] ? default_wake_function+0x12/0x20 [ 360.265412] [<ffffffff9018a82f>] mutex_lock+0x1f/0x2f [ 360.267590] [<ffffffffc0b8ff9e>] ll_layout_refresh+0x1ee/0x910 [lustre] [ 360.270278] [<ffffffffc084b370>] ? lustre_msg_buf_v2+0x1e0/0x1e0 [ptlrpc] [ 360.272960] [<ffffffffc0545a59>] ? lprocfs_counter_add+0xf9/0x160 [obdclass] [ 360.275668] [<ffffffffc0bd81df>] vvp_io_init+0x34f/0x490 [lustre] [ 360.278056] [<ffffffffc0566803>] ? lu_context_init+0xd3/0x1f0 [obdclass] [ 360.280641] [<ffffffffc056693a>] ? lu_env_init+0x1a/0x30 [obdclass] [ 360.282985] [<ffffffffc057725b>] cl_io_init0.isra.14+0x8b/0x160 [obdclass] [ 360.285188] [<ffffffffc05773f3>] cl_io_init+0x43/0x80 [obdclass] [ 360.287171] [<ffffffffc0bcda2e>] cl_setattr_ost+0x14e/0x3e0 [lustre] [ 360.289272] [<ffffffffc0ba5978>] ll_setattr_raw+0xd58/0x10d0 [lustre] [ 360.291359] [<ffffffffc0bb0978>] ? ll_stats_ops_tally+0x98/0x100 [lustre] [ 360.293485] [<ffffffffc0ba5d53>] ll_setattr+0x63/0xc0 [lustre] [ 360.295310] [<ffffffff8fc6e1ac>] notify_change+0x30c/0x4d0 [ 360.297073] [<ffffffff8fc4c2c5>] do_truncate+0x75/0xc0 [ 360.298735] [<ffffffff8fc514e8>] ? __sb_start_write+0x58/0x120 [ 360.300574] [<ffffffff8fc4c6e9>] do_sys_ftruncate.constprop.14+0x139/0x1a0 [ 360.302787] [<ffffffff8fc4c78e>] SyS_ftruncate+0xe/0x10 [ 360.305020] [<ffffffff90199f92>] system_call_fastpath+0x25/0x2a [ 360.307466] INFO: task dd:1552 blocked for more than 120 seconds. [ 360.309924] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 360.312957] dd D ffff8c3577ff2580 0 1552 1 0x00000080 [ 360.315859] Call Trace: [ 360.317176] [<ffffffff9018d309>] schedule_preempt_disabled+0x29/0x70 [ 360.319743] [<ffffffff9018b457>] __mutex_lock_slowpath+0xc7/0x1d0 [ 360.322237] [<ffffffff8fadae02>] ? default_wake_function+0x12/0x20 [ 360.324739] [<ffffffff9018a82f>] mutex_lock+0x1f/0x2f [ 360.326887] [<ffffffffc0b8ff9e>] ll_layout_refresh+0x1ee/0x910 [lustre] [ 360.329540] [<ffffffffc084b370>] ? lustre_msg_buf_v2+0x1e0/0x1e0 [ptlrpc] [ 360.332210] [<ffffffffc0545a59>] ? lprocfs_counter_add+0xf9/0x160 [obdclass] [ 360.334944] [<ffffffffc0bd81df>] vvp_io_init+0x34f/0x490 [lustre] [ 360.337388] [<ffffffffc0566803>] ? lu_context_init+0xd3/0x1f0 [obdclass] [ 360.339590] [<ffffffffc056693a>] ? lu_env_init+0x1a/0x30 [obdclass] [ 360.341641] [<ffffffffc057725b>] cl_io_init0.isra.14+0x8b/0x160 [obdclass] [ 360.343843] [<ffffffffc05773f3>] cl_io_init+0x43/0x80 [obdclass] [ 360.345835] [<ffffffffc0bcda2e>] cl_setattr_ost+0x14e/0x3e0 [lustre] [ 360.348485] [<ffffffffc0ba5978>] ll_setattr_raw+0xd58/0x10d0 [lustre] [ 360.350812] [<ffffffffc0bb0978>] ? ll_stats_ops_tally+0x98/0x100 [lustre] [ 360.353149] [<ffffffffc0ba5d53>] ll_setattr+0x63/0xc0 [lustre] [ 360.355632] [<ffffffff8fc6e1ac>] notify_change+0x30c/0x4d0 [ 360.358007] [<ffffffff8fc4c2c5>] do_truncate+0x75/0xc0 [ 360.360257] [<ffffffff8fc514e8>] ? __sb_start_write+0x58/0x120 [ 360.362753] [<ffffffff8fc4c6e9>] do_sys_ftruncate.constprop.14+0x139/0x1a0 [ 360.365512] [<ffffffff8fc4c78e>] SyS_ftruncate+0xe/0x10 [ 360.367642] [<ffffffff90199f92>] system_call_fastpath+0x25/0x2a [ 360.370023] INFO: task dd:1553 blocked for more than 120 seconds. [ 360.372519] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 360.375566] dd D ffff8c3577ea2100 0 1553 1 0x00000080 [ 360.378447] Call Trace: [ 360.379713] [<ffffffff9018d309>] schedule_preempt_disabled+0x29/0x70 [ 360.382254] [<ffffffff9018b457>] __mutex_lock_slowpath+0xc7/0x1d0 [ 360.384734] [<ffffffff8fadae02>] ? default_wake_function+0x12/0x20 [ 360.387242] [<ffffffff9018a82f>] mutex_lock+0x1f/0x2f [ 360.389380] [<ffffffffc0b8ff9e>] ll_layout_refresh+0x1ee/0x910 [lustre] [ 360.391983] [<ffffffffc084b370>] ? lustre_msg_buf_v2+0x1e0/0x1e0 [ptlrpc] [ 360.394676] [<ffffffffc0873293>] ? __req_capsule_get+0x163/0x740 [ptlrpc] [ 360.397328] [<ffffffffc0bd81df>] vvp_io_init+0x34f/0x490 [lustre] [ 360.399580] [<ffffffffc0b0db93>] ? mdc_reint+0xd3/0x160 [mdc] [ 360.401481] [<ffffffffc057725b>] cl_io_init0.isra.14+0x8b/0x160 [obdclass] [ 360.404077] [<ffffffffc05773f3>] cl_io_init+0x43/0x80 [obdclass] [ 360.406518] [<ffffffffc0bcda2e>] cl_setattr_ost+0x14e/0x3e0 [lustre] [ 360.409073] [<ffffffffc0ba5978>] ll_setattr_raw+0xd58/0x10d0 [lustre] [ 360.411643] [<ffffffffc0ba5d53>] ll_setattr+0x63/0xc0 [lustre] [ 360.413942] [<ffffffff8fc6e1ac>] notify_change+0x30c/0x4d0 [ 360.416027] [<ffffffff8fc4c2c5>] do_truncate+0x75/0xc0 [ 360.418064] [<ffffffff8fc514e8>] ? __sb_start_write+0x58/0x120 [ 360.420292] [<ffffffff8fc4c6e9>] do_sys_ftruncate.constprop.14+0x139/0x1a0 [ 360.422788] [<ffffffff8fc4c78e>] SyS_ftruncate+0xe/0x10 [ 360.424538] [<ffffffff90199f92>] system_call_fastpath+0x25/0x2a [ 360.426441] INFO: task dd:1554 blocked for more than 120 seconds. [ 360.428364] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 360.430641] dd D ffff8c3577ff3200 0 1554 1 0x00000080 [ 360.432802] Call Trace: [ 360.433824] [<ffffffff9018d309>] schedule_preempt_disabled+0x29/0x70 [ 360.436037] [<ffffffff9018b457>] __mutex_lock_slowpath+0xc7/0x1d0 [ 360.437969] [<ffffffffc05667c6>] ? lu_context_init+0x96/0x1f0 [obdclass] [ 360.440009] [<ffffffff9018a82f>] mutex_lock+0x1f/0x2f [ 360.441665] [<ffffffffc0b8ff9e>] ll_layout_refresh+0x1ee/0x910 [lustre] [ 360.443668] [<ffffffffc05667c6>] ? lu_context_init+0x96/0x1f0 [obdclass] [ 360.446100] [<ffffffffc0545a59>] ? lprocfs_counter_add+0xf9/0x160 [obdclass] [ 360.448858] [<ffffffffc0bd81df>] vvp_io_init+0x34f/0x490 [lustre] [ 360.451385] [<ffffffffc0566803>] ? lu_context_init+0xd3/0x1f0 [obdclass] [ 360.454093] [<ffffffffc056693a>] ? lu_env_init+0x1a/0x30 [obdclass] [ 360.456657] [<ffffffffc057725b>] cl_io_init0.isra.14+0x8b/0x160 [obdclass] [ 360.459390] [<ffffffffc05773f3>] cl_io_init+0x43/0x80 [obdclass] [ 360.461852] [<ffffffffc0bcda2e>] cl_setattr_ost+0x14e/0x3e0 [lustre] [ 360.464397] [<ffffffffc0ba5978>] ll_setattr_raw+0xd58/0x10d0 [lustre] [ 360.466973] [<ffffffffc0bb0978>] ? ll_stats_ops_tally+0x98/0x100 [lustre] [ 360.469597] [<ffffffffc0ba5d53>] ll_setattr+0x63/0xc0 [lustre] [ 360.471907] [<ffffffff8fc6e1ac>] notify_change+0x30c/0x4d0 [ 360.473816] [<ffffffff8fc4c2c5>] do_truncate+0x75/0xc0 [ 360.475572] [<ffffffff8fc514e8>] ? __sb_start_write+0x58/0x120 [ 360.477526] [<ffffffff8fc4c6e9>] do_sys_ftruncate.constprop.14+0x139/0x1a0 [ 360.479686] [<ffffffff8fc4c78e>] SyS_ftruncate+0xe/0x10 [ 360.481434] [<ffffffff90199f92>] system_call_fastpath+0x25/0x2a [ 360.483323] INFO: task dd:1555 blocked for more than 120 seconds. [ 360.485141] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 360.487359] dd D ffff8c3577ea0000 0 1555 1 0x00000080 [ 360.489460] Call Trace: [ 360.490507] [<ffffffff9018d309>] schedule_preempt_disabled+0x29/0x70 [ 360.492432] [<ffffffff9018b457>] __mutex_lock_slowpath+0xc7/0x1d0 [ 360.494284] [<ffffffff9018a82f>] mutex_lock+0x1f/0x2f [ 360.495913] [<ffffffffc0b8ff9e>] ll_layout_refresh+0x1ee/0x910 [lustre] [ 360.497887] [<ffffffffc0545a59>] ? lprocfs_counter_add+0xf9/0x160 [obdclass] [ 360.499951] [<ffffffffc0bd81df>] vvp_io_init+0x34f/0x490 [lustre] [ 360.501812] [<ffffffffc0566803>] ? lu_context_init+0xd3/0x1f0 [obdclass] [ 360.503857] [<ffffffffc056693a>] ? lu_env_init+0x1a/0x30 [obdclass] [ 360.505747] [<ffffffffc057725b>] cl_io_init0.isra.14+0x8b/0x160 [obdclass] [ 360.507767] [<ffffffffc05773f3>] cl_io_init+0x43/0x80 [obdclass] [ 360.509599] [<ffffffffc0bcda2e>] cl_setattr_ost+0x14e/0x3e0 [lustre] [ 360.511507] [<ffffffffc0ba5978>] ll_setattr_raw+0xd58/0x10d0 [lustre] [ 360.513432] [<ffffffffc0bb0978>] ? ll_stats_ops_tally+0x98/0x100 [lustre] [ 360.515433] [<ffffffffc0ba5d53>] ll_setattr+0x63/0xc0 [lustre] [ 360.517218] [<ffffffff8fc6e1ac>] notify_change+0x30c/0x4d0 [ 360.518923] [<ffffffff8fc4c2c5>] do_truncate+0x75/0xc0 [ 360.520542] [<ffffffff8fc514e8>] ? __sb_start_write+0x58/0x120 [ 360.522326] [<ffffffff8fc4c6e9>] do_sys_ftruncate.constprop.14+0x139/0x1a0 [ 360.524853] [<ffffffff8fc4c78e>] SyS_ftruncate+0xe/0x10 [ 360.527127] [<ffffffff90199f92>] system_call_fastpath+0x25/0x2a [ 360.529619] INFO: task dd:1558 blocked for more than 120 seconds. [ 360.532135] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 360.535914] dd D ffff8c3578473180 0 1558 1 0x00000080 [ 360.539991] Call Trace: [ 360.541984] [<ffffffff9018d309>] schedule_preempt_disabled+0x29/0x70 [ 360.545418] [<ffffffff9018b457>] __mutex_lock_slowpath+0xc7/0x1d0 [ 360.548747] [<ffffffff9018a82f>] mutex_lock+0x1f/0x2f [ 360.551666] [<ffffffffc0b8ff9e>] ll_layout_refresh+0x1ee/0x910 [lustre] [ 360.555106] [<ffffffffc0545a59>] ? lprocfs_counter_add+0xf9/0x160 [obdclass] [ 360.558524] [<ffffffffc0bd81df>] vvp_io_init+0x34f/0x490 [lustre] [ 360.561638] [<ffffffffc0566803>] ? lu_context_init+0xd3/0x1f0 [obdclass] [ 360.564847] [<ffffffffc056693a>] ? lu_env_init+0x1a/0x30 [obdclass] [ 360.567832] [<ffffffffc057725b>] cl_io_init0.isra.14+0x8b/0x160 [obdclass] [ 360.571007] [<ffffffffc05773f3>] cl_io_init+0x43/0x80 [obdclass] [ 360.574113] [<ffffffffc0bcda2e>] cl_setattr_ost+0x14e/0x3e0 [lustre] [ 360.576943] [<ffffffffc0ba5978>] ll_setattr_raw+0xd58/0x10d0 [lustre] [ 360.579788] [<ffffffffc0bb0978>] ? ll_stats_ops_tally+0x98/0x100 [lustre] [ 360.582826] [<ffffffffc0ba5d53>] ll_setattr+0x63/0xc0 [lustre] [ 360.585399] [<ffffffff8fc6e1ac>] notify_change+0x30c/0x4d0 [ 360.587813] [<ffffffff8fc4c2c5>] do_truncate+0x75/0xc0 [ 360.590117] [<ffffffff8fc514e8>] ? __sb_start_write+0x58/0x120 [ 360.592621] [<ffffffff8fc4c6e9>] do_sys_ftruncate.constprop.14+0x139/0x1a0 [ 360.595400] [<ffffffff8fc4c78e>] SyS_ftruncate+0xe/0x10 [ 360.597612] [<ffffffff90199f92>] system_call_fastpath+0x25/0x2a |
| Comments |
| Comment by Li Xi [ 15/Nov/22 ] |
|
With the attached script reproduce_sync_stuck.sh, the problem is very easy to reproduce.
|
| Comment by Li Xi [ 15/Nov/22 ] |
|
This looks like, but is not the same with |
| Comment by Li Xi [ 15/Nov/22 ] |
|
The reproduce script is able to reproduce |
| Comment by Gerrit Updater [ 15/Nov/22 ] |
|
"Zhenyu Xu <bobijam@hotmail.com>" uploaded a new patch: https://review.whamcloud.com/c/fs/lustre-release/+/49164 |