I have just completed extensive benchmarking on 2.6.31.2 and 2.6.24
with a new benchmark program I have written, to measure real-world
io performance in high load situations where readers and writers
are compeeting.
I am looking at HW RAID setups as well a normal single harddrive
situations. The bottom line is that on a single harddrive only
data=writeback with cfq scheduler
has decent performance when readers and writers are in competition
and even then, there will be huge outliers of many seconds happeing
every now and then. See
I have just completed extensive benchmarking on 2.6.31.2 and 2.6.24
with a new benchmark program I have written, to measure real-world
io performance in high load situations where readers and writers
are compeeting.
I am looking at HW RAID setups as well a normal single harddrive
situations. The bottom line is that on a single harddrive only
data=writeback with cfq scheduler
has decent performance when readers and writers are in competition
and even then, there will be huge outliers of many seconds happeing
every now and then. See
http:// insights. oetiker. ch/linux/ fsopbench/
for details.
cheers
tobi
-- it.oetiker. ch <email address hidden> ++41 62 775 9902 / sb: -9900
Tobi Oetiker, OETIKER+PARTNER AG, Aarweg 15 CH-4600 Olten, Switzerland
http://