| From: | Andres Freund <andres(at)anarazel(dot)de> |
|---|---|
| To: | Tomas Vondra <tomas(at)vondra(dot)me> |
| Cc: | Peter Geoghegan <pg(at)bowt(dot)ie>, Robert Haas <robertmhaas(at)gmail(dot)com>, Melanie Plageman <melanieplageman(at)gmail(dot)com>, PostgreSQL Hackers <pgsql-hackers(at)lists(dot)postgresql(dot)org>, Georgios <gkokolatos(at)protonmail(dot)com>, Thomas Munro <thomas(dot)munro(at)gmail(dot)com>, Konstantin Knizhnik <knizhnik(at)garret(dot)ru>, Dilip Kumar <dilipbalaut(at)gmail(dot)com> |
| Subject: | Re: index prefetching |
| Date: | 2025-07-16 14:25:06 |
| Message-ID: | tpzzzmjo22mon54wi3443rl55jvdk6jqckkxmr32vbtqv2xigk@vu3ykzppyjsc |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
Hi,
On 2025-07-16 16:20:25 +0200, Tomas Vondra wrote:
> On 7/16/25 16:07, Peter Geoghegan wrote:
> >> Te pattern of fadvise+pread for the same block seems a bit silly. And
> >> this is not just about "sync" method, the other methods will have a
> >> similar issue with no starting the I/O earlier. The fadvise is just
> >> easier to trace/inspect.
> >
> > It's not at all surprising that you're seeing duplicate prefetch
> > requests. I have no reason to believe that it's important to suppress
> > those ourselves, rather than leaving it up to the OS (though I also
> > have no reason to believe that the opposite is true).
> >
>
> True, but in practice those duplicate calls are fairly expensive. Even
> just calling fadvise() on data you already have in page cache costs
> something (not much, but it's clearly visible for cached queries).
This imo isn't something worth optimizing for - if you use an io_method that
actually can execute IO asynchronously this issue does not exist, as the start
of the IO will already have populated the buffer entry (without BM_VALID set,
of course). Thus we won't start another IO for that block.
Greetings,
Andres Freund
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Peter Geoghegan | 2025-07-16 14:27:25 | Re: index prefetching |
| Previous Message | Tomas Vondra | 2025-07-16 14:20:25 | Re: index prefetching |