Re: [PATCH] dtrace probes for memory manager - Mailing list pgsql-hackers

From Zdenek Kotala
Subject Re: [PATCH] dtrace probes for memory manager
Date
Msg-id 1260554117.2642.37.camel@localhost
Whole thread Raw
In response to Re: [PATCH] dtrace probes for memory manager  (Bernd Helmle <mailings@oopsware.de>)
Responses Re: [PATCH] dtrace probes for memory manager  (Robert Haas <robertmhaas@gmail.com>)
List pgsql-hackers
Bernd Helmle píše v pá 11. 12. 2009 v 17:13 +0100:
> 
> --On 11. Dezember 2009 11:28:54 -0300 Alvaro Herrera 
> <alvherre@commandprompt.com> wrote:
> 
> >>
> >> without compiled probes: AVG(2531.68)
> >> with compiled probes: AVG(2511.97)
> >
> > Were the probes enabled?
> 
> Hmm, they were just compiled in, i didn't anything to instrument them with 
> dtrace.
> 
> I've just started a pgbench/dtrace run with instrumented probes aset_alloc, 
> aset_free and aset_realloc which just counts the calls to them during 
> pgbench, the first run gives me
> 
> tps = 1035.045523 (excluding connections establishing)
> 
> Ideas?

When probes are activated they have performance impact. It is normal.
Important is that you can use it when you need it on production system.
No recompilation, no extra binary, no downtime and it is safe.
Performance impact depends on Dscript
Zdenek



pgsql-hackers by date:

Previous
From: "David P. Quigley"
Date:
Subject: Re: Adding support for SE-Linux security
Next
From: "David P. Quigley"
Date:
Subject: Re: SE-PostgreSQL/Lite Review