Re: LWLock statistics collector - Mailing list pgsql-hackers

From ITAGAKI Takahiro
Subject Re: LWLock statistics collector
Date
Msg-id 20060807100812.525D.ITAGAKI.TAKAHIRO@oss.ntt.co.jp
Whole thread Raw
In response to Re: LWLock statistics collector  (Robert Lor <Robert.Lor@Sun.COM>)
Responses Re: LWLock statistics collector
List pgsql-hackers
Robert Lor <Robert.Lor@Sun.COM> wrote:

> CVS head now has the following LWLock probes, and more can easily be 
> added. These probes can be enabled using the sample DTrace scripts at 
> http://pgfoundry.org/projects/dtrace/
> 
> lwlock-acquire
> lwlock-release
> lwlock-startwait
> lwlock-endwait
> lwlock-condacquire
> lwlock-condacquire-fail
> 
> If anyone wants to have access to a Solaris machine to play with DTrace, 
> let me know.

I assure you that DTrace is a powerful tool, but as for LWLock statistics,
can we gather them well with it? There is a "color coding" problem in the
persent dump-to-stderr and DTrace methods. I assume we want to gather the
statistics per resource (represented by LWLockKind in my patch), not per
LWLockId.

Even if we use DTrace, do we need some supports for coloring of lwlocks?

Regards,
---
ITAGAKI Takahiro
NTT Open Source Software Center



pgsql-hackers by date:

Previous
From: Andrew Dunstan
Date:
Subject: installcheck-parallel
Next
From: "Greg Sabino Mullane"
Date:
Subject: Re: 8.2 features status