I'm seeing bcache writeback threads sleep uninterruptably for
significant periods on 3.13.6 [1], on a NFS fileserver with 1-2
clients, exporting a 2TB BTRFS filesystem with a write-through bcache
overlaid from a 50GB SSD partition. The workload is low-depth and
light (kernel builds, git activity).
Would any information help, or is this a known issue?
Many thanks; bcache is indeed a superb mechanism.
Daniel
-- [1]
INFO: task :bcache_writebac345 blocked for more than 120 seconds.
Not tainted 3.13.6-031306-generic #201403070154
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
bcache_writebac D ffffffff818114c0 0 345 2 0x00000000
ffff8804050bdea8 0000000000000002 ffff8804050bde58 ffff8804050bdfd8
0000000000014440 0000000000014440 ffff8804095a0000 ffff880405445fc0
0000000000000282 ffff880404d426c0 ffff8804038a0000 ffffffffa0099380
Call Trace:
[<ffffffffa0099380>] ? write_dirty+0xc0/0xc0 [bcache]
[<ffffffff81747679>] schedule+0x29/0x70
[<ffffffff8108e424>] kthread+0xa4/0xe0
[<ffffffff8108e380>] ? flush_kthread_worker+0xb0/0xb0
[<ffffffff8175403c>] ret_from_fork+0x7c/0xb0
[<ffffffff8108e380>] ? flush_kthread_worker+0xb0/0xb0
--
Daniel J Blueman
--
To unsubscribe from this list: send the line "unsubscribe linux-bcache" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
