Puzzling change in performance
Borja Marcos
borjamar at sarenet.es
Sun Feb 1 14:40:46 PST 2009
On Jan 31, 2009, at 7:27 PM, Robert Watson wrote:
> There are basically three ways to go about exploring this, none
> particularly good:
>
> (1) Do a more formal before and after analysis of performance on the
> box,
> perhaps using tools like kernel profiling, hwpmc, dtrace, etc.
Machine in production, I cannot do it :(
> (2) Do a binary search to narrow down the date of the change that
> improved
> things until it becomes clear which mattered.
> (3) Hope someone annecdotally remembers something that might or
> might not be
> it and assume they're right.
>
> Of these, I'd guess (2) is actually the most effective way to go
> about it, but is potentially time-consuming. As you point out, the
> most interesting question is whether, when you go back to 7.0,
> things suddenly get slower again, or not. Typically long uptimes
> don't lead to performance problems on FreeBSD (in my experience) so
> I think that's unlikely to be the source. There are a lot of
> improvements in 7.1 relating to performance, but none particularly
> stands out for me as having the effect you describe. If you're
> really curious, I would try to pin it down with a binary search.
I will have to learn how to use dtrace, I think. This is quite weird.
And in a lot of years I haven't seen a FreeBSD system degraded because
of a long uptime. Something in userland must be the culprit...
As I see (I don't administer the machine but co-administer it) there's
a Qmail system with some AV crap... and now I see that active memory
had gone up, and is much lower after the update.
I'll keep investigating.. the kind of answer I was looking for was a
"oh, yes, there was a problem that degraded, blah, blah, blah".
The graphs can be accessed here: http://194.30.110.21/orca/
It's behind an ADSL, so expect slow performance.
Borja.
More information about the freebsd-stable
mailing list