Subject: RE: Has anybody studied the interrupt latency and preemption latency in netBSD?
To: Perry E. Metzger <perry@piermont.com>
From: Jun Sun <jsun@docomolabs-usa.com>
List: tech-embed
Date: 12/29/2004 11:34:49
On the interrupt latency I am looking for the typical interrupt blocking
times (on some typical SBCs) and also interested in knowing where the
outliers are.
On the preemption latency I am looking for the long execution pathes in
syscalls for some typical benchmark workload. (netbsd kernel is not
preemptible, right?)
Since the workload works on both Linux and netbsd, it would be
interesting to do a side-by-side comparison between them. Mvista.com
used to have some numbers posted on their website for Linux, but I can't
find anymore. But it is easy in general to find out those tests and
numbers for Linux.
Jun
> -----Original Message-----
> From: Perry E. Metzger [mailto:perry@piermont.com]
> Sent: Tuesday, December 28, 2004 3:34 PM
> To: Jun Sun
> Cc: tech-embed@NetBSD.org
> Subject: Re: Has anybody studied the interrupt latency and preemption
> latency in netBSD?
>=20
>=20
> "Jun Sun" <jsun@docomolabs-usa.com> writes:
> > Has anybody studied the interrupt latency and preemption latency in
> NetBSD?
> > I am curious. Any pointers are appreciated.
>=20
> People have, but I'm unaware of a public study.
>=20
> What sort of information are you looking for?
>=20
> Perry