From: Mark Kirkwood <markir@paradise.net.nz>
To: Scott Marlowe <scott.marlowe@gmail.com>
Cc: Brad Nicholson <bnichols@ca.afilias.info>
Cc: Kevin Kempter <kevin@consistentstate.com>
Cc: pgsql-performance@postgresql.org
Subject: Re: Monitoring buffercache...
Date: Wed, 26 Nov 2008 08:37:57 +1300
Message-ID: <492C5415.6090205@paradise.net.nz> (raw)
In-Reply-To: <dcc563d10811241324t116f6e71j4863632b2c0c09a5@mail.gmail.com>
References: <200811241143.57182.kevin@kevinkempterllc.com>
<dcc563d10811241146l95302b1wd0e88756883e4401@mail.gmail.com>
<1227556326.18990.98.camel@bnicholson-desktop>
<dcc563d10811241324t116f6e71j4863632b2c0c09a5@mail.gmail.com>
Scott Marlowe wrote:
> On Mon, Nov 24, 2008 at 12:52 PM, Brad Nicholson
> <bnichols@ca.afilias.info> wrote:
>
>>> I just ran it in a loop over and over on my 8 core opteron server and
>>> it ran the load factor up by almost exactly 1.0. Under our normal
>>> daily load, it sits at 1.9 to 2.5, and it climbed to 2.9 under the new
>>> load of running that query over and over. So, it doesn't seem to be
>>> blocking or anything.
>>>
>> The internal docs for pg_buffercache_pages.c state:
>>
>> "To get a consistent picture of the buffer state, we must lock all
>> partitions of the buffer map. Needless to say, this is horrible
>> for concurrency. Must grab locks in increasing order to avoid
>> possible deadlocks."
>>
>
> Well, the pg hackers tend to take a parnoid view (it's a good thing
> TM) on things like this. My guess is that the period of time for
> which pg_buffercache takes locks on the buffer map are short enough
> that it isn't a real big deal on a fast enough server. On mine, it
> certainly had no real negative effects for the 5 minutes or so it was
> running in a loop. None I could see, and we run hundreds of queries
> per second on our system.
>
> Of course, for certain other types of loads it could be a much bigger
> issue. But for our load, on our machine, it was virtually
> unnoticeable.
>
>
Yeah, I wouldn't worry about accessing it every 15 minutes! I put the
comment there to make it clear that (like pg_locks) selecting from it
*very frequently* could effect performance.
Cheers
Mark
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Reply to all the recipients using the --to and --cc options:
reply via email
To: pgsql-performance@postgresql.org
Cc: markir@paradise.net.nz, scott.marlowe@gmail.com, bnichols@ca.afilias.info, kevin@consistentstate.com
Subject: Re: Monitoring buffercache...
In-Reply-To: <492C5415.6090205@paradise.net.nz>
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox