Re: Refactoring the checkpointer's fsync request queue

Hi,,

On 2019-01-22 08:27:48 -0600, Kevin Grittner wrote:
> With the help of VMware's Dirk Hohndel (VMware's Chief Open Source
> Officer, a VP position near the top of the organization, and a
> personal friend of Linus), I have been fortunate enough to make
> contact directly with Linus Torvalds to discuss this issue. In emails
> to me he has told me that this patch is no longer provisional:
>
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=fff75eb2a08c2ac96404a2d79685668f3cf5a7a3

Unfortunately, unless something has changed recently, that patch is
*not* sufficient to really solve the issue - we don't guarantee that
there's always an fd preventing the necessary information from being
evicted from memory:

Note that we might still lose the error if the inode gets evicted from
the cache before anything can reopen it, but that was the case before
errseq_t was merged. At LSF/MM we had some discussion about keeping
inodes with unreported writeback errors around in the cache for longer
(possibly indefinitely), but that's really a separate problem"

And that's entirely possibly in postgres. The commit was dicussed on
list too, btw...

Greetings,

Andres Freund