| From: | Greg Stark <stark(at)mit(dot)edu> |
|---|---|
| To: | Andres Freund <andres(at)2ndquadrant(dot)com> |
| Cc: | Mel Gorman <mgorman(at)suse(dot)de>, PostgreSQL-development <pgsql-hackers(at)postgresql(dot)org>, Josh Berkus <josh(at)agliodbs(dot)com>, Hannu Krosing <hannu(at)2ndquadrant(dot)com>, Trond Myklebust <trondmy(at)gmail(dot)com>, Kevin Grittner <kgrittn(at)ymail(dot)com>, Jonathan Corbet <corbet(at)lwn(dot)net>, Dave Chinner <david(at)fromorbit(dot)com>, Joshua Drake <jd(at)commandprompt(dot)com>, James Bottomley <James(dot)Bottomley(at)hansenpartnership(dot)com>, Claudio Freire <klaussfreire(at)gmail(dot)com>, Robert Haas <robertmhaas(at)gmail(dot)com>, Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, "lsf-pc(at)lists(dot)linux-foundation(dot)org" <lsf-pc(at)lists(dot)linux-foundation(dot)org>, Magnus Hagander <magnus(at)hagander(dot)net> |
| Subject: | Re: [Lsf-pc] Linux kernel impact on PostgreSQL performance (summary v2 2014-1-17) |
| Date: | 2014-01-18 00:18:49 |
| Message-ID: | CAM-w4HPDmGQWgqsxu1Sm3ph_3U3m7wP0Zx9ksuHUqFKa0ePPgw@mail.gmail.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Fri, Jan 17, 2014 at 9:14 AM, Andres Freund <andres(at)2ndquadrant(dot)com> wrote:
> The scheme that'd allow us is the following:
> When postgres reads a data page, it will continue to first look up the
> page in its shared buffers, if it's not there, it will perform a page
> cache backed read, but instruct that read to immediately remove from the
> page cache afterwards (new API or, posix_fadvise() or whatever). As long
> as it's in shared_buffers, postgres will not need to issue new reads, so
> there's no no benefit keeping it in the page cache.
> If the page is dirtied, it will be written out normally telling the
> kernel to forget about the caching the page (using 3) or possibly direct
> io).
> When a page in postgres's buffers (which wouldn't be set to very large
> values) isn't needed anymore and *not* dirty, it will seed the kernel
> page cache with the current data.
This seems like mostly an exact reimplementation of DIRECT_IO
semantics using posix_fadvise.
--
greg
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Andres Freund | 2014-01-18 00:28:19 | Re: Add %z support to elog/ereport? |
| Previous Message | Tom Lane | 2014-01-18 00:01:30 | Re: [PATCH] Negative Transition Aggregate Functions (WIP) |