Not logged in
Log in now
Create an account
Subscribe to LWN
LWN.net Weekly Edition for May 16, 2013
A look at the PyPy 2.0 release
PostgreSQL 9.3 beta: Federated databases and more
LWN.net Weekly Edition for May 9, 2013
(Nearly) full tickless operation in 3.10
You gotta be kiddin' me, Phoronix. Putting up measurements of CPU-bound tasks (read: compression) in a filesystems benchmark
A short history of btrfs
Posted Jul 23, 2009 14:51 UTC (Thu) by nix (subscriber, #2304)
i.e. they have iozone benchmarks in there... but then they have compression, and I've seen them look at things like 'how long it takes to boot' and even game frame rates (!?) in filesystem benchmarks before.
So I treat Phoronix benchmarks largely as a source of amusement these days. Sometimes (rarely) they might tell us things we don't already know...
Posted Jul 23, 2009 15:26 UTC (Thu) by dlang (✭ supporter ✭, #313)
Posted Jul 23, 2009 22:11 UTC (Thu) by tialaramex (subscriber, #21167)
I'd like to see more investigation. I think that would follow from narrowing results down to only those that were significant. If you find 500 tiny differences between two things, most of which are just measurement noise, you have no reason to investigate further. But if you make one big significant finding you can do a whole article about what it means - why is the Frooqux significantly faster ? Is it the same on an AMD machine ? In OpenSolaris ? With a different network card ?
Posted Jul 23, 2009 22:31 UTC (Thu) by dlang (✭ supporter ✭, #313)
Posted Jul 24, 2009 7:34 UTC (Fri) by nix (subscriber, #2304)
Moving to a decent ISP as soon as
BT get around to it... but that's a week away, plus another week for the
new MX record to propagate around. Three weeks without properly-working
Posted Jul 24, 2009 9:44 UTC (Fri) by dlang (✭ supporter ✭, #313)
Posted Jul 23, 2009 16:59 UTC (Thu) by kjp (subscriber, #39639)
Posted Jul 23, 2009 17:04 UTC (Thu) by jengelh (subscriber, #33263)
Posted Jul 25, 2009 21:20 UTC (Sat) by bronson (subscriber, #4806)
Just timing a file decompression is a lot easier for all involved, no? It's not a great benchmark, true, but it will quickly and reliably tell you if one FS requires more CPU than another. And that's the most important thing.
The problem is not with benchmark itself...
Posted Jul 23, 2009 17:50 UTC (Thu) by khim (subscriber, #9252)
Uh, having the cpu loaded will find problems if the FS code
itself is too cpu hoggy....
The problem is not with low-level CPU bound benchmark but with average
taken from many different benchmarks without a case or thought. In the end
you are getting average temperature of hospice patients: some are having
fever, some are in morgue already, so in the end average temperature is
If you plan to mix a lot of different benchmarks you must be ready to
carefully study the results, separate expected results from unexpected
cluster them in groups (by relevance to this or that real-word task), etc.
Ortherwise it's just pointless race where winner is more-or-less
And it's also pointless to try to fix the situation by adding more
benchmarks to the mix: when you mix a lot of differend kinds of food - you
are getting pile of garbage as a result and if you'll add some more dishes
- you'll just get a bigger pile of garbage.
Copyright © 2013, Eklektix, Inc.
Comments and public postings are copyrighted by their creators.
Linux is a registered trademark of Linus Torvalds