| From: | Jeff Davis <pgsql(at)j-davis(dot)com> |
|---|---|
| To: | serge(at)rielau(dot)com, Tomas Vondra <tomas(dot)vondra(at)2ndquadrant(dot)com>, David Rowley <david(dot)rowley(at)2ndquadrant(dot)com>, Andres Freund <andres(at)anarazel(dot)de> |
| Cc: | Heikki Linnakangas <hlinnaka(at)iki(dot)fi>, pgsql-hackers <pgsql-hackers(at)postgresql(dot)org> |
| Subject: | Re: Re: Spilling hashed SetOps and aggregates to disk |
| Date: | 2018-06-05 17:29:36 |
| Message-ID: | 1528219776.2742.42.camel@j-davis.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
On Tue, 2018-06-05 at 08:39 -0700, serge(at)rielau(dot)com wrote:
> Strange. We don't see this overeahd and measure a lot more than just
> a single metric:
Let's investigate again. I wasn't able to repro the overhead on x86;
Robert saw it on a POWER machine, and it was somewhat noisy. I don't
think we were ever very sure the overhead existed.
My basic opinion is that we make small changes all the time that may
have a small performance impact, and we shouldn't let that become a
blocker for an important feature. Nor should we let it make the design
overly complicated or awkward. We should just see what we can
reasonably do to understand and mitigate it.
Regards,
Jeff Davis
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Andres Freund | 2018-06-05 17:29:52 | Variable-length FunctionCallInfoData |
| Previous Message | Alvaro Herrera | 2018-06-05 17:28:54 | Re: [PATCH] Trim trailing whitespace in vim and emacs |