On Mon, Jul 25, 2005 at 06:00:21PM +0200, Bohdan Horst wrote:
On Mon, Jul 25, 2005 at 10:15:41PM +1200, Mark Kirkwood wrote:
Hmm - looks like I missed that thread, never mind - repeatability of
findings is sound scientific principle :-)
With respect to changing the default for
Hmm - looks like I missed that thread, never mind - repeatability of
findings is sound scientific principle :-)
With respect to changing the default for vfs.read_max - makes sense to
me, but it would be interesting to know if anyone has a system that
performs *worse* with it set to 16.
On Mon, Jul 25, 2005 at 10:15:41PM +1200, Mark Kirkwood wrote:
Hmm - looks like I missed that thread, never mind - repeatability of
findings is sound scientific principle :-)
With respect to changing the default for vfs.read_max - makes sense to
me, but it would be interesting to know if
Its been mentioned before and most experience the same as you by
setting it to 16 a dramatic improvement in the sequential read, I
currently run all my 5.x servers like this with no issues as a result.
I am curious if the default will ever be changed.
Chris
On 22/07/05, Mark Kirkwood [EMAIL
I happened to have received a 'new' machine, and wanted to see what its
IO system was capable of. So took the opportunity to run 4.10 and 5.4
against each other a few times. (fresh re-installs each time).
Its documented at:
http://homepages.paradise.net.nz/markir/freebsd/
I wanted to play with