* page-cluster tuning
@ 2000-10-11 11:34 Eric Lowe
0 siblings, 0 replies; only message in thread
From: Eric Lowe @ 2000-10-11 11:34 UTC (permalink / raw)
To: linux-mm
Hi,
Over the weekend I played with page-cluster after booting my
box with mem=8M. I ran a kernel build and updatedb simultaneously
driving it into the swap rather heavily during I/O and found that
_both_ processes made much more progress with page-cluster set
to 8 than to 4, and the default of 2 was painfully slow because
it didn't swap agressively enough.
I have yet to do any streaming I/O while swapping tests, but
should get to it later in the week. Would anybody like to
confirm my results that 8 appears to be an optimum value for
page-cluster in 8MB?
More to come..
--
Eric Lowe
Software Engineer, Systran Corporation
elowe@systran.com
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux.eu.org/Linux-MM/
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2000-10-11 11:34 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2000-10-11 11:34 page-cluster tuning Eric Lowe
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox