Re: [PATCH] dtrace probes for memory manager

Robert Haas <robertmhaas@gmail.com>

From: Robert Haas <robertmhaas@gmail.com>
To: Zdenek Kotala <Zdenek.Kotala@sun.com>
Cc: Alvaro Herrera <alvherre@commandprompt.com>, "pgsql-hackers@postgresql.org" <pgsql-hackers@postgresql.org>
Date: 2009-11-13T22:16:15Z
Lists: pgsql-hackers
On Fri, Nov 13, 2009 at 4:41 PM, Zdenek Kotala <Zdenek.Kotala@sun.com> wrote:
> Alvaro Herrera píše v pá 13. 11. 2009 v 18:34 -0300:
>> Zdenek Kotala wrote:
>> > Attached patch contains new dtrace probes for memory management. Main
>> > purpose is to analyze memory footprint - for example how many memory
>> > needs transaction, peak memory per context, when memory block is reused
>> > or when it is allocate by malloc and so on.
>>
>> Having had to instrument these to figure out some problems, I'd give
>> this patch a +1.  However, the performance argument is compelling.  As a
>> compromise, maybe we could have a #define that needs to be turned on at
>> compile time to enable these probes; so a regular dtrace-enabled build
>> would not have them, but if you really needed to analyze memory
>> allocations, you could recompile to turn them on.
>
> But point of dtrace probes is that they are here without
> recompilation :(. Do we have any test which we could use for performance
> penalty testing? I don't think that overhead is significant.

Don't think.  Benchmark.  :-)

(If you can measure it at all, it's too much, at least IMHO.)

...Robert