> Anybody care to shed some light on this?
I'd suspect the directory cache ... using my stats. patch to track the "hits"
and "misses" on cache values in the kernel, the directory cache misses
4 times for every one hit, in general.. whereas in 2.0, just about
the opposite is true.
is there.
I can repost my profiling patch if need be.. it can be interesting..
(ignore the top data, just look at the dircache and bufcache numbers)
bufcache 984967 341583
dircache 13925051 43273352
fatcache 0 0
smbcache 0 0
--gKMricLos+KVdGMg
Content-Type: text/plain; charset=us-ascii
Content-Description: unedited /proc/stat
Content-Disposition: attachment; filename=stat
cpu 2659449 39937818 1893028 11317
disk 153138 0 0 0
disk_rio 80074 0 0 0
disk_wio 73064 0 0 0
disk_rblk 179426 0 0 0
disk_wblk 151726 0 0 0
page 219861 100810
swap 3213 3011
intr 130643997 44501612 103329 0 2018366 55061130 28805416 0 19 0 0 0 0 0 1 154124 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
ctxt 45335901
btime 902036292
processes 6616
bufcache 985058 341588
dircache 13929487 43288080
fatcache 0 0
smbcache 0 0
--gKMricLos+KVdGMg--
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html