|From:||Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>|
|To:||Andres Freund <andres(at)anarazel(dot)de>|
|Cc:||Robert Haas <robertmhaas(at)gmail(dot)com>, Simon Riggs <simon(at)2ndquadrant(dot)com>, PostgreSQL-development <pgsql-hackers(at)postgresql(dot)org>|
|Subject:||Re: Changing WAL Header to reduce contention during ReserveXLogInsertLocation()|
|Views:||Raw Message | Whole Thread | Download mbox|
Andres Freund <andres(at)anarazel(dot)de> writes:
> On 2018-01-12 17:24:54 -0500, Tom Lane wrote:
>> Andres Freund <andres(at)anarazel(dot)de> writes:
>>> Right. I wonder if it be reasonable to move that to a page's header
>>> instead of individual records? To avoid torn page issues we'd have to
>>> reduce the page size to a sector size, but I'm not sure that's that bad?
>> Giving up a dozen or two bytes out of every 512 sounds like quite an
> It's not nothing, that's true. But if it avoids 8 bytes in every record,
> that'd probably at least as much in most usecases.
Fair point. I don't have a very good handle on what "typical" WAL record
sizes are, but we might be fine with that --- some quick counting on the
fingers says we'd break even with an average record size of ~160 bytes,
and be ahead below that.
We'd need to investigate the page-crossing overhead carefully though.
regards, tom lane
|Next Message||Tomas Vondra||2018-01-12 22:51:05||Re: [HACKERS] PATCH: multivariate histograms and MCV lists|
|Previous Message||Daniel Gustafsson||2018-01-12 22:35:48||Re: [HACKERS] Refactoring identifier checks to consistently use strcmp|