[nycbug-talk] Measuring Disk Performance

[Pete Wright]

On Thu, Dec 15, 2011 at 09:13:55AM -0500, Isaac Levy wrote:
> > hey ike!
> > there is actually a pretty decent chapter on measuring disk and
> > filesystem performance in "High Performance PostgreSQL 9.0".  
> 
> Is it this book:
> "PostgreSQL 9.0 High Performance"
> Author: Gregory Smith
> Publisher: Packt Publishing

yea that's the one - can't recommend it enough for both sys admins as
well as for DBA's and programmers.  it is on everyone's desk here that
is involved in our datawarehouse/ETL projects.

> 
> Understood, really comprehensive, and valuable!
> 
> Have you posted your methodology and/or resulting tests anywhere?
>
well it's on talk@ now :p  i have been meaning to do a more in depth
write-up but b/w work, and trying not to think about work when i'm not
at work it's been hard to find the time :)

although i'm going to be testing solaris vs. freebsd zfs early next
year, maybe i should do a proper write-up...
 
> --
> Conversely, what I'm looking to really do here, is more of a cave-man sanity test: test a few small common cases in a relative vaccum, ideally using UNIX builtins spitting a few integers back to stdout.  (mix a bit of xargs with rm, mkdir, dd, etc?)
> 
> I'm actually looking to avoid going down this path alltogether, as I'd rather focus this level of detail on measuring disk/system performance as the team hammers our apps.
> 
> > 
> > I have also done some interesting testing using
> ..
> > http://tsung.erlang-projects.org/
> 
> *That* looks rad- way off direct disk testing, but that's a very compelling toolkit...
>
yea what i really liked about this tool was that i was able to do more
end-to-end testing of my disk subsystem.  we had a pool of
lighttpd+wscgi nodes mounting a NFS filesystem.  i was able to see how
the filer, OS and web scripts worked under pretty close to real-world
condition, which was pretty good.  so maybe tsung could help you with
your tests.



-pete
 
-- 
Pete Wright
pete at nomadlogic.org