From: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
---|---|
To: | Andres Freund <andres(at)anarazel(dot)de> |
Cc: | Tomas Vondra <tv(at)fuzzy(dot)cz>, Simon Riggs <simon(at)2ndquadrant(dot)com>, pgsql-committers <pgsql-committers(at)postgresql(dot)org> |
Subject: | Re: pgsql: Generational memory allocator |
Date: | 2017-11-25 21:46:02 |
Message-ID: | 2875.1511646362@sss.pgh.pa.us |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-committers |
I wrote:
> Instead I propose that we should make sure that the palloc request size
> for XLogReaderState->main_data is always maxalign'd. The existing
> behavior in DecodeXLogRecord of palloc'ing it only just barely big
> enough for the current record seems pretty brain-dead performance-wise
> even without this consideration. Generally, if we need to enlarge
> that buffer, we should enlarge it significantly, IMO.
I've confirmed that the attached is sufficient to stop the valgrind crash
on my machine. But as I said, I think we should be more aggressive at
resizing the buffer, to reduce resize cycles. I'm inclined to start out
with a buffer size of 128 or 256 or so bytes and double it when needed.
Anybody have a feeling for a typical size for the "main data" part
of a WAL record?
regards, tom lane
Attachment | Content-Type | Size |
---|---|---|
pad-xlog-buffer-size.patch | text/x-diff | 792 bytes |
From | Date | Subject | |
---|---|---|---|
Next Message | Tom Lane | 2017-11-25 23:15:46 | pgsql: Update MSVC build process for new timezone data. |
Previous Message | Tom Lane | 2017-11-25 21:19:20 | Re: pgsql: Generational memory allocator |