From: | Simon Riggs <simon(at)2ndQuadrant(dot)com> |
---|---|
To: | Gianni Ciolli <gianni(dot)ciolli(at)2ndquadrant(dot)it> |
Cc: | pgsql-hackers <pgsql-hackers(at)postgresql(dot)org> |
Subject: | Re: Proposed fix for NOTIFY performance degradation |
Date: | 2011-04-24 22:59:17 |
Message-ID: | BANLkTinnR5OQq8_MkD+7MkCn04qQSRv+XQ@mail.gmail.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-hackers |
On Sat, Apr 23, 2011 at 2:57 PM, Gianni Ciolli
<gianni(dot)ciolli(at)2ndquadrant(dot)it> wrote:
> * "avg_usec" denotes the average time in microseconds required by each
> NOTIFY statement.
>
> h2. Test 1 - PostgreSQL HEAD
>
> n | m | iter | avg_usec
> -------+-------+------+----------
> 10 | 1 | 10 | 43.730
> 100 | 1 | 10 | 37.630
> 1000 | 1 | 10 | 42.990
> 10000 | 1 | 10 | 36.225
> 10 | 10 | 10 | 43.960
> 100 | 100 | 10 | 46.537
> 1000 | 1000 | 10 | 126.115
> 10000 | 10000 | 10 | 906.501
I read that wrong first time around. So the wasted time from duplicate checks is
n | m | iter | msec
-------+-------+------+----------
10 | 10 | 10 | 0
100 | 100 | 10 | 0.3
1000 | 1000 | 10 | 80
10000 | 10000 | 10 | 8600
So the cost of the duplicate checks only kicks in at about 200 notifies.
--
Simon Riggs http://www.2ndQuadrant.com/
PostgreSQL Development, 24x7 Support, Training & Services
From | Date | Subject | |
---|---|---|---|
Next Message | Simon Riggs | 2011-04-24 23:06:34 | Re: Proposed fix for NOTIFY performance degradation |
Previous Message | Christopher Browne | 2011-04-24 22:31:55 | Re: Unlogged tables, persistent kind |