* Slabinfo memory usage after big box benchmarks
@ 2002-05-25 18:24 rwhron
0 siblings, 0 replies; only message in thread
From: rwhron @ 2002-05-25 18:24 UTC (permalink / raw)
To: linux-kernel; +Cc: andrea
I don't know if this is related to the negative
dentry thread or not. After running various
benchmarks on quad Xeon with 3.75 GB RAM,
there are some big differences in slab size.
inode_cache and dentry_cache have the biggest
difference between kernels.
total slab size inode_cache
2.4.19-pre7-rmap13 45.9 MB 9.9 MB
2.4.19-pre8 278.0 MB 202.8 MB
2.4.19-pre8-aa2 306.1 MB 233.9 MB
2.4.19-pre8-ac4 44.3 MB 4.5 MB
2.4.19-pre8-jam2 263.9 MB 182.1 MB
The benchmarks create a million or more temp
files during the run. Updatedb runs several
times too.
bonnie++ is one of the benches that creates a lot
of files. On runs with vastly different "number
of files to create", there was little difference
in slabinfo memory usage on 2.4.19-pre8-jam2.
More slabinfo detail at:
http://home.earthlink.net/~rwhron/kernel/bigbox/slabinfo.txt
Script to create slabinfo.txt in url above:
http://home.earthlink.net/~rwhron/kernel/bigbox/si_sum
Big box benchmarks:
http://home.earthlink.net/~rwhron/kernel/bigbox.html
--
Randy Hron
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2002-05-25 18:24 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2002-05-25 18:24 Slabinfo memory usage after big box benchmarks rwhron
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).