I was running a simple stress test program that basically memsets 1.5GB
of memory continously on a 1GB dual 866MHz Xeon machine. With
2.2.17-pre6 I see kswapd consuming about 66% of a CPU, whereas with
2.2.16 + Alan's combo fixes kswapd doesn't even show up in top. I was
also seeing higher throughput with this test with 2.2.16.
One other difference is that with 2.2.17-pre6 I have CONFIG_2GB=y to use
all of my 1GB, whereas in 2.2.16 I had CONFIG_1GB instead.
Were there VM changes that could be responsible?
--Lee Hetherington
-
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.tux.org/lkml/
This archive was generated by hypermail 2b29 : Fri Jun 23 2000 - 21:00:26 EST