pcp
[Top] [All Lists]

RE: PCP patch for top/libgtop conversion

To: "Davis, Todd C" <todd.c.davis@xxxxxxxxx>
Subject: RE: PCP patch for top/libgtop conversion
From: Ken McDonell <kenmcd@xxxxxxxxxxxxxxxxx>
Date: Thu, 26 Sep 2002 10:10:57 +1000
Cc: Mike Mason <mmlnx@xxxxxxxxxx>, Mark Goodwin <markgw@xxxxxxx>, <pcp@xxxxxxxxxxx>
In-reply-to: <29AD895CE780D511A8870002A50A666D04F9083B@xxxxxxxxxxxxxxxxxxxxxx>
Sender: pcp-bounce@xxxxxxxxxxx
On Tue, 24 Sep 2002, Davis, Todd C wrote:

> How are patches like this and other changes to PCP tested and verified to be
> correct? I think enterprise class system utilities like PCP require a much
> higher level of qualify assurance than the typical open source project. ...

Agreed.  I think Mark has responded to this, but I'd like to add ...

- for about 6 years before we made the open source release, PCP was a
  successful production-hardened proprietary product deployed on varied
  and some very large (500+ CPUs, multi-Tb memory, 10's of Tb of disk,
  ...) systems, so we are very QA-sensitive.

- the PCP QA infrastructure grew with PCP, it is not an after thought

- we use common source code internally to generate both the proprietary and
  the open source versions, so we have a vested interest in quality that
  extends beyond the open source code base

- as all those who've worked with me on PCP will attest, I'm inclined to
  be obsessive about QA!

> ... What
> verification procedures does SGI go through before making a source tarball
> release?  I think test suites should be made available to developers to use
> when making enhancements and bug fixes so changes can be verified. Tests
> could also be submitted with any enhancements before being accepted by the
> PCP project. Test suites can also be useful in verifying an installation of
> PCP.

I posted a detailed response on this topic earlier today.


<Prev in Thread] Current Thread [Next in Thread>