[OpenAFS] Poor OpenAFS performance on Lion

[Derrick Brashear]

control for one variable. what does 10.6.8 with 1.6.0 do?

does scan stat() a lot of stuff? no bulkstat, currently.

On Wed, Oct 26, 2011 at 10:13 AM, Ken Hornstein <kenh@cmf.nrl.navy.mil> wro=
te:
> We've recently got some MacOS Lion systems in, and we've noticed that Ope=
nAFS
> seems to perform rather poorly on then.
>
> Specifically, we've noticed this when using nmh on these systems. =A0Here=
's
> an example of what I mean. =A0On an older iMac running 10.6.8/OpenAFS 1.4=
.11:
>
> % /usr/bin/time scan +kerberos
> =A0 =A0 =A0 =A04.29 real =A0 =A0 =A0 0.02 user =A0 =A0 =A0 0.08 sys
>
> On a brand-new new Mac Pro system running Lion/OpenAFS 1.6.0
> % /usr/bin/time scan +kerberos
> =A0 =A0 =A0 =A044.29 real =A0 =A0 =A0(I don't remember the rest, it was o=
n another system)
>
> These systems are on the exact same network, so that's not the issue.
>
> I realize that even the "old" Mac performance isn't wonderful. =A0On my
> end-of-lifed-12-years-ago Sparc system running Solaris 10 (same deal,
> on the same exact network):
>
> % /usr/bin/time scan +kerberos
> real =A0 =A0 =A0 =A01.6
> user =A0 =A0 =A0 =A00.1
> sys =A0 =A0 =A0 =A0 0.5
>
> Any ideas where to start tracking this down? =A0I could maybe believe
> something like statahead is the issue; the scan performance on the Lion
> system is very "spurty".
>
> --Ken
> _______________________________________________
> OpenAFS-info mailing list
> OpenAFS-info@openafs.org
> https://lists.openafs.org/mailman/listinfo/openafs-info
>



--=20
Derrick