Re: Hint benchmark reaches memory size limit on 4gb box

rwhron@earthlink.net
Mon, 23 Sep 2002 19:55:58 -0400


>>Should the bench be adjusted, or should I boot 2.5.36-mm1?

> Both, sorry.

Lorenzo did an update to qsbench. qsbench is much faster
than hint for a ram shortage simulation.

Current lineup:
qsbench with 2 process = 120% TotalMem

1) qsbench alone
2) qsbench with ed compile loop
3) qsbench + very small chat bench loop (5 clients, 1 room)
4) qsbench + postmark loop with ~ 40000 small files

Hm, guess i should also time 2, 3, and 4 without qsbench
for comparison. 2, 3, 4 run in less than 10 seconds
on quad xeon. The idea is to count the loops that complete
during the time for qsbench to do it's thing.

The first run on 2.5.38 got overwritten during a mkfs. :(

Any suggestions before i lose the next batch of data ;)

-- 
Randy Hron
http://home.earthlink.net/~rwhron/kernel/bigbox.html

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/