Comment 50 for bug 1942935

Hello, got the same issue with Ubuntu 22.04.3 LTS (GNU/Linux 5.15.0-91-generic x86_64). Also tried 5.19 kernel and got the same problem.

Jan 7 02:28:26 cache4 systemd[1]: Starting MD array scrubbing...
Jan 7 02:28:26 cache4 root: mdcheck start checking /dev/md0
Jan 7 08:28:44 cache4 kernel: [2914434.326024] md: md0: data-check interrupted.
Jan 7 08:32:08 cache4 kernel: [2914638.397357] INFO: task jbd2/md0-8:1337 blocked for more than 120 seconds.
Jan 7 08:32:08 cache4 kernel: [2914638.397420] Not tainted 5.15.0-91-generic #99-Ubuntu
Jan 7 08:32:08 cache4 kernel: [2914638.397457] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Jan 7 08:32:08 cache4 kernel: [2914638.397505] task:jbd2/md0-8 state:D stack: 0 pid: 1337 ppid: 2 flags:0x00004000
Jan 7 08:32:08 cache4 kernel: [2914638.397512] Call Trace:
Jan 7 08:32:08 cache4 kernel: [2914638.397515] <TASK>
Jan 7 08:32:08 cache4 kernel: [2914638.397520] __schedule+0x24e/0x590
Jan 7 08:32:08 cache4 kernel: [2914638.397530] schedule+0x69/0x110
Jan 7 08:32:08 cache4 kernel: [2914638.397535] md_write_start.part.0+0x174/0x220
Jan 7 08:32:08 cache4 kernel: [2914638.397540] ? wait_woken+0x70/0x70
Jan 7 08:32:08 cache4 kernel: [2914638.397547] md_write_start+0x14/0x30
Jan 7 08:32:08 cache4 kernel: [2914638.397553] raid5_make_request+0x77/0x540 [raid456]
Jan 7 08:32:08 cache4 kernel: [2914638.397566] ? jbd2_transaction_committed+0x1b/0x60
Jan 7 08:32:08 cache4 kernel: [2914638.397573] ? ext4_set_iomap+0x5a/0x1d0
Jan 7 08:32:08 cache4 kernel: [2914638.397579] ? wait_woken+0x70/0x70
Jan 7 08:32:08 cache4 kernel: [2914638.397584] md_handle_request+0x12d/0x1b0
Jan 7 08:32:08 cache4 kernel: [2914638.397589] ? submit_bio_checks+0x1a5/0x560
Jan 7 08:32:08 cache4 kernel: [2914638.397595] md_submit_bio+0x76/0xc0
Jan 7 08:32:08 cache4 kernel: [2914638.397600] __submit_bio+0x1a5/0x220
Jan 7 08:32:08 cache4 kernel: [2914638.397603] ? mempool_alloc_slab+0x17/0x20
Jan 7 08:32:08 cache4 kernel: [2914638.397611] __submit_bio_noacct+0x85/0x200
Jan 7 08:32:08 cache4 kernel: [2914638.397614] ? kmem_cache_alloc+0x1ab/0x2f0
Jan 7 08:32:08 cache4 kernel: [2914638.397619] submit_bio_noacct+0x4e/0x120
Jan 7 08:32:08 cache4 kernel: [2914638.397623] submit_bio+0x4a/0x130
Jan 7 08:32:08 cache4 kernel: [2914638.397627] submit_bh_wbc+0x18d/0x1c0
Jan 7 08:32:08 cache4 kernel: [2914638.397632] submit_bh+0x13/0x20
Jan 7 08:32:08 cache4 kernel: [2914638.397635] jbd2_journal_commit_transaction+0x861/0x17a0
Jan 7 08:32:08 cache4 kernel: [2914638.397640] ? __update_idle_core+0x93/0x120
Jan 7 08:32:08 cache4 kernel: [2914638.397649] kjournald2+0xa9/0x280
Jan 7 08:32:08 cache4 kernel: [2914638.397653] ? wait_woken+0x70/0x70
Jan 7 08:32:08 cache4 kernel: [2914638.397657] ? load_superblock.part.0+0xc0/0xc0
Jan 7 08:32:08 cache4 kernel: [2914638.397662] kthread+0x12a/0x150
Jan 7 08:32:08 cache4 kernel: [2914638.397667] ? set_kthread_struct+0x50/0x50
Jan 7 08:32:08 cache4 kernel: [2914638.397672] ret_from_fork+0x22/0x30
Jan 7 08:32:08 cache4 kernel: [2914638.397680] </TASK>

# cat /sys/block/md0/md/array_state
write-pending

This is happening on all our servers with NVMe devices.