From: | Jakub Wartak <Jakub(dot)Wartak(at)tomtom(dot)com> |
---|---|
To: | Thomas Munro <thomas(dot)munro(at)gmail(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 13:59:20 |
Message-ID: | AM8PR07MB82480E22146937BAD6A4AE02F6B39@AM8PR07MB8248.eurprd07.prod.outlook.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).
Hey Thomas!
Apparently it's false theory. Redo-bench [1] results (1st is total recovery time in seconds, 3.1GB pgdata (out of which 2.6 pg_wals/166 files). Redo-bench was slightly hacked to drop fs caches always after copying so that there is nothing in fscache (both no pgdata and no pg_wals; shared fs). M_io_c is at default (10), recovery_prefetch same (try; on by default)
master, default Linux readahead (128kb):
33.979, 0.478
35.137, 0.504
34.649, 0.518
master, blockdev --setra 0 /dev/nvme0n1:
53.151, 0.603
58.329, 0.525
52.435, 0.536
master, with yours patch (readaheads disabled) -- double checked, calls to fadvise64(offset=0 len=0) were there
58.063, 0.593
51.369, 0.574
51.716, 0.59
master, with Kirill's original patch (readaheads disabled)
38.25, 1.134
36.563, 0.582
37.711, 0.584
I've noted also that in both cases POSIX_FADV_SEQUENTIAL is being used instead of WILLNEED (?).
I haven't quantified the tradeoff of master vs Kirill's with readahead, but I think that 1 additional syscall is not going to be cheap just for non-standard OS configurations (?)
-J.
From | Date | Subject | |
---|---|---|---|
Next Message | Przemysław Sztoch | 2022-06-21 14:55:40 | Re: generate_series for timestamptz and time zone problem |
Previous Message | Aleksander Alekseev | 2022-06-21 13:48:49 | Re: doc: Bring mention of unique index forced transaction wait behavior outside of the internal section |