[Bioclusters] Tool to benchmark disk IO?

[Dan Bolser]

On Fri, 24 Sep 2004, James Cuff wrote:

>On Fri, 2004-09-24 at 14:32, James Cuff wrote:
>> On Fri, 2004-09-24 at 14:21, Dan Bolser wrote:
>> > On Fri, 24 Sep 2004, elijah wright wrote:
>> 
>> > Seeker 1...Seeker 3...Seeker 2...start 'em...done...done...done...
>> >               -------Sequential Output-------- ---Sequential Input--
>> > --Random--
>> >               -Per Char- --Block--- -Rewrite-- -Per Char- --Block---
>> > --Seeks---
>> > Machine    MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU  /sec %CPU
>> >           100  4240 25.9  5437  2.1  4780  2.4 19595 100.1 566942 99.7 2023.0 10.1
>> > 
>> > With default file size (104857600). The CPU is 'amazingly high' during
>> > reads.
>> 
>> I think your file size is to small - 100MB will fit in the UBC.  Once
>> written according to these figures you are seeing ca 600MB/s reads for
>> getchar ops.  The block ops must not be htting the buffer cache
>> correctly so go back down to 2MB/s.  This seems pretty poor even for
>
>Doh!  That should have been 20MB/s for getchar and 566MB/s for blocks. 
>Sorry - I said I had too much coffee :-)  Anyway the take home message
>is still the same - make the file size at least 2x the amount of memory
>in your server.


I don't know why I just deleted the results from a much bigger
file... Perhaps too much caffine has a lot to answer for.. (it is the
biggest single cause of a anxiety in the UK).

I am re-running the tests on my local SCSI and on the NFS (from a 'farm'
machine)...

I will post the results when they come in.



>
>Cheers,
>
>j.
>
>
>_______________________________________________
>Bioclusters maillist  -  Bioclusters@bioinformatics.org
>https://bioinformatics.org/mailman/listinfo/bioclusters
>