On 5/31/22 5:39 PM, Theodore Ts'o wrote:
> Hmmm. I think this patch should fix your issues.
Thanks a lot. Unfortunately, it didn't, I still occasionally get
[368259.560885] EXT4-fs (dm-0): ext4_writepages: jbd2_start: 344 pages, ino
279244; err -5
D.
>
> If the journal has been abor
On 5/31/22 12:38 PM, Jan Kara wrote:
Late reply but maybe it is still useful :)
That's very welcome!
On Thu 14-04-22 17:19:49, Donald Buczek wrote:
We have a cluster scheduler which provides each cluster job with a
private scratch filesystem (TMPDIR). These are created when a job starts
and
Hmmm. I think this patch should fix your issues.
If the journal has been aborted (which happens as part of the
shutdown, we will never write out the commit block --- so it should be
fine to skip the writeback of any dirty inodes in data=ordered mode.
BTW, if you know that the file system is g
Late reply but maybe it is still useful :)
On Thu 14-04-22 17:19:49, Donald Buczek wrote:
> We have a cluster scheduler which provides each cluster job with a
> private scratch filesystem (TMPDIR). These are created when a job starts
> and removed when a job completes. The setup works by fallocate
We have a cluster scheduler which provides each cluster job with a private scratch
filesystem (TMPDIR). These are created when a job starts and removed when a job
completes. The setup works by fallocate, losetup, mkfs.ext4, mkdir, mount, "losetup
-d", rm and the teardown just does a umount and
