| From: | Andres Freund <andres(at)anarazel(dot)de> |
|---|---|
| To: | Simon Riggs <simon(at)2ndQuadrant(dot)com> |
| Cc: | PostgreSQL-development <pgsql-hackers(at)postgresql(dot)org> |
| Subject: | Re: Separating Buffer LWlocks |
| Date: | 2015-09-06 13:28:40 |
| Message-ID: | 20150906132840.GC19425@alap3.anarazel.de |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
Hi,
On 2015-09-06 14:10:24 +0100, Simon Riggs wrote:
> It separates the Buffer LWLocks from the main LW locks, allowing them to
> have different padding.
>
> Tests showed noticeable/significant performance gain due to reduced false
> sharing on main LWlocks, though without wasting memory on the buffer
> LWlocks.
Hm. I found that the buffer content lwlocks can actually also be a
significant source of contention - I'm not sure reducing padding for
those is going to be particularly nice. I think we should rather move
the *content* lock inline into the buffer descriptor. The io lock
doesn't matter and can be as small as possible.
Additionally I think we should increase the lwlock padding to 64byte
(i.e. the by far most command cacheline size). In the past I've seen
that to be rather beneficial.
Greetings,
Andres Freund
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Julien Rouhaud | 2015-09-06 13:49:54 | Re: Allow a per-tablespace effective_io_concurrency setting |
| Previous Message | Michael Paquier | 2015-09-06 13:27:37 | Re: replication slot restart_lsn initialization |