[mpich2-dev] Another romio performance question

[Bob Cernohous]

mpich2-dev-bounces at mcs.anl.gov wrote on 08/21/2009 11:38:17 AM:
> 
> When the workload is as you describe, ROMIO normally looks at the
> accesses and if there is any overlap, it decides it would be better
> served with independent access (in ad_write_coll.c there's a check for
> interleaved accesses).  Contiguous data like your customer's falls
> under the non-interleaved category.
> 
> However, on BlueGene, the romio_cb_read and romio_cb_write hints are
> set to 'enable' instead of 'automatic'.  This is usually the right
> thing, since aggregation works great on bluegene for workloads that
> are non-overlapping, but also non-contiguous.

Ok, so I tried hinting romio_cb_read/write to automatic and it doesn't do 
the aggregation and performs much better.  I like that even better than 
hinting cb_buffer_size. 

I think we're ok.   Like you said, we might want to look at our defaults 
and selection logic eventually, but I think I'm happy with my answer for 
now.

Thanks

Bob Cernohous:  (T/L 553) 507-253-6093

BobC at us.ibm.com
IBM Rochester, Building 030-2(C335), Department 61L
3605 Hwy 52 North, Rochester,  MN 55901-7829

> Chaos reigns within.
> Reflect, repent, and reboot.
> Order shall return.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/mpich2-dev/attachments/20090821/c90193b9/attachment.htm>