| From: | Thomas Munro <thomas(dot)munro(at)gmail(dot)com> |
|---|---|
| To: | Jakub Wartak <Jakub(dot)Wartak(at)tomtom(dot)com> |
| Cc: | Andrey Borodin <x4mmm(at)yandex-team(dot)ru>, Amit Kapila <amit(dot)kapila16(at)gmail(dot)com>, Kirill Reshke <reshke(at)double(dot)cloud>, PostgreSQL Hackers <pgsql-hackers(at)lists(dot)postgresql(dot)org> |
| Subject: | Re: Use fadvise in wal replay |
| Date: | 2022-06-21 10:51:38 |
| Message-ID: | CA+hUKG+Wr6JSpPibxVME8ksRUTNFrsnjOBrc3U6uyhzs-DePRw@mail.gmail.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Tue, Jun 21, 2022 at 10:33 PM Jakub Wartak <Jakub(dot)Wartak(at)tomtom(dot)com> wrote:
> > > Maybe the important question is why would be readahead mechanism be
> > disabled in the first place via /sys | blockdev ?
> >
> > Because database should know better than OS which data needs to be
> > prefetched and which should not. Big OS readahead affects index scan
> > performance.
>
> OK fair point, however the patch here is adding 1 syscall per XLOG_BLCKSZ which is not cheap either. The code is already hot and there is example from the past where syscalls were limiting the performance [1]. Maybe it could be prefetching in larger batches (128kB? 1MB? 16MB?) ?
I've always thought we'd want to tell it about the *next* segment
file, to smooth the transition from one file to the next, something
like the attached (not tested).
| Attachment | Content-Type | Size |
|---|---|---|
| prefetch-wal-segments.patch | text/x-patch | 2.2 KB |
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Thomas Munro | 2022-06-21 11:02:57 | Re: Is RecoveryConflictInterrupt() entirely safe in a signal handler? |
| Previous Message | Peter Eisentraut | 2022-06-21 10:49:24 | gcc -ftabstop option |