Mark Kirkwood wrote:
Pieter de Goeje wrote:
It would be more interesting to see how random access to a (cached)
file performs in Linux vs FreeBSD, which seems a more logical pattern
for a database.
Agreed, and good point, I'll knock up a simple program to do random
and/or sequential access of a file and see what we get!
Here's a (very) simple program that does block reads sequentially or
randomly. It probably needs a little polishing, but seems to work ok for
the size of files we are interested in: i.e < a few GB (see attached):
Results:
========
Compiled with CFLAGS=-O2 -march=i686
Gentoo - 2.6.18-gentoo-r3:
-----------------------
$ ./readtest /data0/dump/file 8192 0
random reads: 100000 elapsed: 1.2646 io rate 647805551 bytes/s
$ ./readtest /data0/dump/file 8192 1
sequential reads: 100000 elapsed: 1.1267 io rate 727075854 bytes/s
FreeBSD - 6.2-PRERELEASE #7: Mon Nov 27 19:32:33 NZDT 2006 :
------------------------------------------------------------
./readtest /data0/dump/file 8192 0
random reads: 100000 elapsed: 4.3669 io rate 187594060 bytes/s
$ ./readtest /data0/dump/file 8192 1
sequential reads: 100000 elapsed: 1.9679 io rate 416283642 bytes/s
So looks like we get faster overall results than dd (I guess not needing
to send output anywhere helps)...also we seem to be slower in the random
case too :-(. I ran these programs several times, typical results shown.
Cheers
Mark
_______________________________________________
[email protected] mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-stable
To unsubscribe, send any mail to "[EMAIL PROTECTED]"
