Dear John,
would move find and (any) concurrent benchmark or other application
specific mode to the extended benchmark.
Makes it easier to rollout the initial version.
Cheers,
Julian
2017-06-24 2:05 GMT+02:00 John Bent <John.Bent(a)seagategov.com>:
> On Jun 23, 2017, at 6:02 PM, Andreas Dilger <adilger(a)dilger.ca> wrote:
>
> On Jun 23, 2017, at 4:57 PM, John Bent <John.Bent(a)seagategov.com> wrote:
>>
>> All,
>>
>> We had a great session at ISC (about 30 people I think) and made great progress
in the weeks leading up to it as well. Thanks to Satoshi we even got the two attached
slides added into the official slides being released from the Top 500 session! We had 6
people sign up at the BOF saying that they’ll run the benchmark when it is finalized.
>>
>> I know I always say that we have ‘almost’ finalized the benchmark. But we really
are getting much closer; it helped so much that Nathan combined the benchmarks and George
worked on the script.
>>
>> I think we only have two open questions right now:
>>
>> 1. do 47K random IO in the IOR-hard or do 47K simple strided? My original
thinking was strided but someone pointed out that the idea is to create the bounding box
and random is harder than strided. Also random might be increasingly prevalent these days
with more analytics and machine learning and graph analytics, etc. So I propose that we
do random unless there are objections here.
>
> May as well go random at that point.
>
>> 2. Should we do some sort of mixed IO workload in addition to running the 4 tests
serially? I like the idea but am not sure how exactly to do it. Do we need to merely mix
IOR-hard and IOR-easy or md-hard and md-easy or both or mix all 4 at once? Do we just
launch multiple command lines in the background and hope that the mpirun launch times are
fast enough that they overlap? Do we need to modify IOR/mdtest to split the ranks in half
and do different workloads with the two halves? Thoughts?
>
> This would be a bit of a dog's breakfast, and very hard to specify the test
parameters. Do all of the loads need to be running for the whole duration? How does this
work if some jobs finish early? What if, for example, there was a workload scheduler in
the storage that (automatically?) segregated the IO of each workload and they actually ran
serially and didn't contend at all? Would that be considered an improvement, since
this could help real-world jobs as well?
>
Agree about the scheduler. But what about a modified IOR that split the ranks in two and
half did easy and the other half did hard?
Thanks,
John
> Maybe something for V2?
>
>> We also made some procedural decisions. The initial steering committee will be
Jay Lofstead, Julian Kunkle, and myself. That steering committee membership will last
until IO500 is up and running and stable at which point the community can nominate new
members. All decisions will be discussed first on the mailing list and we will try for as
much consensus as possible. The VI4IO organization will host the IO500.
>>
>> Thanks very much,
>>
>> John
>> <io500_two_slides.pdf>_______________________________________________
>> IO-500 mailing list
>> IO-500(a)vi4io.org
>>
https://www.vi4io.org/cgi-bin/mailman/listinfo/io-500
>
>
> Cheers, Andreas
>
>
>
>
>
_______________________________________________
IO-500 mailing list
IO-500(a)vi4io.org
https://www.vi4io.org/cgi-bin/mailman/listinfo/io-500