Re: [PATCH] dtrace probes for memory manager
Joshua D. Drake <jd@commandprompt.com>
From: "Joshua D. Drake" <jd@commandprompt.com>
To: Tom Lane <tgl@sss.pgh.pa.us>
Cc: Zdenek Kotala <Zdenek.Kotala@Sun.COM>, "pgsql-hackers@postgresql.org" <pgsql-hackers@postgresql.org>
Date: 2009-11-13T21:09:06Z
Lists: pgsql-hackers
On Fri, 2009-11-13 at 16:06 -0500, Tom Lane wrote: > Zdenek Kotala <Zdenek.Kotala@Sun.COM> writes: > > Attached patch contains new dtrace probes for memory management. > > This is a bad idea and I want to reject it outright. No ordinary user > is really going to care about those details, and palloc is a > sufficiently hot hot-spot that even the allegedly negligible overhead > of an inactive dtrace probe is going to cost us. No ordinary user is going to use dtrace at all. > > If this goes in, I will disable dtrace support in Red Hat's builds, > and I rather imagine that other packagers will react similarly. Is it possible to have a set of probes that would only be enabled with say, --enable-debug compile time option? I could certainly see the benefit to these probes for profiling but that is such as specific use that it seems to need a specific flag anyway. Sincerely, Joshua D. Drake > > regards, tom lane > -- PostgreSQL.org Major Contributor Command Prompt, Inc: http://www.commandprompt.com/ - 503.667.4564 Consulting, Training, Support, Custom Development, Engineering If the world pushes look it in the eye and GRR. Then push back harder. - Salamander