>/dev/hdb
>Kernel Block write Block read Kernel compile time
> K/sec %CPU K/sec %CPU dep bzImage
>2.2.10 7958 16.8 5891 8.7 1:06.89 8:45.87
>2.3.7 6006 11.6 5946 8.6 1:09.02 8:46.99
>2.3.8-pre2 6077 10.8 6069 9.0 1:10.11 8:57.25
>2.3.7-andrea1 7217 13.6 6165 8.9 0:49.38 8:42.29
Could you give a try also to:
ftp://ftp.suse.com/pub/people/andrea/kernel-patches/2.2.10_andrea-VM9.gz
This one is against 2.2.10 and it's a "stable" release. You may consider
it the equivalent of 2.3.7_andrea1, but against 2.2.10 and really stable.
>The interesting part is the block write. 2.3.8-pre2 performs the same
>as 2.3.7 and 2.3.7-andrea1 is a lot faster on /dev/hdb. 2.3.8-pre2
>performs the same as 2.3.7-andrea1 on /dev/hdc. Why is that? I would
>expect the same differences/rates in the above combinations.
The difference are not so high in the bonnie numbers though. Also bonnie
runs over a filesystem so a different layout on disk may change the
profile. Probably bonnie is not an optimal test (at least with normal HD)
since the I/O bandwith seems just pretty much handled. It's interesting
that the >2.3.7 has a less CPU power involved in the operations and that
in turn means that we'll be able to handle higher I/O bandwith with faster
HD.
I think the interesting difference is shown from the make dep test. Also
the make bzImage would probably show interesting differences but you
should only look at the system time and ignore the user-time otherwise the
difference will be hided from gcc.
Andrea Arcangeli
-
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/