Re: lazy vxid locks, v1 - Mailing list pgsql-hackers

From Kevin Grittner
Subject Re: lazy vxid locks, v1
Date
Msg-id 4DF5BC4E020000250003E50D@gw.wicourts.gov
Whole thread Raw
In response to lazy vxid locks, v1  (Robert Haas <robertmhaas@gmail.com>)
Responses Re: lazy vxid locks, v1
List pgsql-hackers
Stefan Kaltenbrunner  wrote:
> on that particular 40cores/80 threads box:
> unpatched:
> c40:    tps = 107689.945323 (including connections establishing)
> c80:    tps = 101885.549081 (including connections establishing)
> fast locks:
> c40:    tps = 215807.263233 (including connections establishing)
> c80:    tps = 118266.615543 (including connections establishing)
> fast locks + lazy vxid:
> c40:    tps = 223308.779212 (including connections establishing)
> c80:    tps = 65738.046558 (including connections establishing)
Is there any way to disable the HT (or whatever technology attempts
to make each core look like 2)?  In my benchmarking that has kept
performance from tanking as badly when a large number of processes
are contending for CPU.
-Kevin


pgsql-hackers by date:

Previous
From: Robert Haas
Date:
Subject: Re: wrong message on REASSIGN OWNED
Next
From: Robert Haas
Date:
Subject: Re: FOREIGN TABLE doc fix