Re: remap the .text segment into huge pages at run time - Mailing list pgsql-hackers

From John Naylor
Subject Re: remap the .text segment into huge pages at run time
Date
Msg-id CAFBsxsEW1fTbhciaGQM1FtJsKtidJG1QGs79nVEny4SZnpjEyg@mail.gmail.com
Whole thread Raw
In response to Re: remap the .text segment into huge pages at run time  (Andres Freund <andres@anarazel.de>)
Responses Re: remap the .text segment into huge pages at run time  (Andres Freund <andres@anarazel.de>)
Re: remap the .text segment into huge pages at run time  (John Naylor <john.naylor@enterprisedb.com>)
List pgsql-hackers
On Sat, Nov 5, 2022 at 3:27 PM Andres Freund <andres@anarazel.de> wrote:

>        /*
>         * Make huge pages out of it. Requires at least linux 6.1.  We could
>         * fall back to MADV_HUGEPAGE if it fails, but it doesn't do all that
>         * much in older kernels.
>         */
> #define MADV_COLLAPSE    25
>        r = madvise(addr, advlen, MADV_COLLAPSE);
>        if (r != 0)
>            fprintf(stderr, "MADV_COLLAPSE failed: %m\n");
>
>
> A real version would have to open /proc/self/maps and do this for at least
> postgres' r-xp mapping. We could do it for libraries too, if they're suitably
> aligned (both in memory and on-disk).

Hi Andres, my kernel has been new enough for a while now, and since TLBs and context switches came up in the thread on... threads, I'm swapping this back in my head.

For the postmaster, it should be simple to have a function that just takes the address of itself, then parses /proc/self/maps to find the boundaries within which it lies. I haven't thought about libraries much. Though with just the postmaster it seems that would give us the biggest bang for the buck?

--
John Naylor
EDB: http://www.enterprisedb.com

pgsql-hackers by date:

Previous
From: Amit Langote
Date:
Subject: Re: Views no longer in rangeTabls?
Next
From: Peter Smith
Date:
Subject: Re: [PATCH] Reuse Workers and Replication Slots during Logical Replication