[OpenAFS] cache performance

[Neulinger, Nathan]

One thing I don't like about fstrace is that it seems like the polling
mechanism would be a performance hog.

Seems like offering both would be ideal -

	a. Connect and grab current buffer if enabled
or
	b. Logging only generated when a process is connected, and while
it is connected, it receives continual updates.

Not sure though which would be less impact on server without writing and
testing.

-- Nathan

------------------------------------------------------------
Nathan Neulinger                       EMail:  nneul@umr.edu
University of Missouri - Rolla         Phone: (573) 341-4841
Computing Services                       Fax: (573) 341-4216


> -----Original Message-----
> From: Derrick J Brashear [mailto:shadow@dementia.org]=20
> Sent: Wednesday, October 30, 2002 3:19 PM
> To: openafs-info@openafs.org
> Subject: RE: [OpenAFS] cache performance
>=20
>=20
> On Wed, 30 Oct 2002 Phil.Moore@morganstanley.com wrote:
>=20
> > >>>>> "Nathan" =3D=3D Neulinger, Nathan <nneul@umr.edu> writes:
> >=20
> > Nathan> Have you considered using the -syslog log mechanism, or are
> > Nathan> you running on a platform with a syslogd that can't handle
> > Nathan> heavy loading.
> >=20
> > I think that option post-dates my hands on administration of AFS :-(
>=20
> Nathan wrote it for OpenAFS, so, yeah, pretty much;-)
>=20
> > Nathan> Yeah, that's what Derrick and I were thinking,=20
> something similar in
> > Nathan> nature to fstrace.
> >=20
> > However, I want to architect the mechanism to be a bit more=20
> manageable
> > and robust than a debugging tool, and most importantly, we need to
> > minimize the performance impact, of course.
>=20
> Do you consider fstrace robust?
>=20
>=20
>=20
> _______________________________________________
> OpenAFS-info mailing list
> OpenAFS-info@openafs.org
> https://lists.openafs.org/mailman/listinfo/openafs-info
>=20