lkml.org 
[lkml]   [1996]   [Apr]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: Unices are created equal, but ...
Date
> 
> The differences shouldn't be that large any more. The asynchronous
> swapping code and the swap deamon in newer linux kernels help performance
> under load. Again, I'm more inclined to think that one system may be
> better on some hardware, while the other might be better at something
> else.
>
[stuff deleted]
>
> Unlike raw device accesses, I consider filesystem access speed very
> important, and I've mostly concentrated on getting good performance
> through good caching. Linux traditionally hasn't been as good in things
> where caches don't help (ie the cases you mention above), but that has
> improved a lot lately. Maybe somebody has access to FreeBSD-current and
> Linux-current on the same machine and can compare bonnie?
>
Right now I am benchmarking NetBSD, but I have an entire disk that I
regularly reload. Maybe it is time to try Linux again then. But,
remember I am not considered an unbiased observer.

>
> HOWEVER, despite the fact that I don't think it matters in real life, I'm
> all for people doing benchmarks, and crying out when one or the other is
> slower in something. Not because I think it makes much of a difference for
> normal users, but because it's good for development. It's a great way to
> motivate people to do better (show that the competition can do better at
> something, and you force us to try to improve ourselves).
>
That is similar to my position on competition. I do not think that a
"single" OS, compiler, etc. should be predominant in the free domain. It
makes the software fat & lazy.

>
> Indeed. Even on the same machine the placement of the partitions can make
> a noticeable difference for disk tests, so benchmarking is not a trivial
> thing.. It might still be interesting to see some kind of benchmarking
> done, just for "some data" as opposed to "THE data".
>
> If somebody wants to do benchmarking,I'd suggest using at least
> - lmbench (nice microbenchmark)
> - bonnie (reasonable disk performance benchmark)
> - webstone (or something similar. But use "apache" as the server, not
> some braindead horror like NCSA).
> - ???
>
Above list is ok, but CERTAINLY not sufficient.

> (the three mentioned should cover different areas, all very reasonable,
> but have I missed some important area?)
>
Above list has no testing under VM load. That is where memory scheduling
policies start taking effect. There are other forms of loading also, like
tty subsystems (some people still use those.) Another, is how well do big disk
farms work (lots of sustained concurrent I/O)? How does the system work
with many many TCP connections (little benchmarks like lmbench are interesting
but don't show performance in an ISP or large workstation situation)?

John


\
 
 \ /
  Last update: 2005-03-22 13:37    [W:0.120 / U:7.172 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site