Dear Ilene,
thanks for the feedback.
While entering data for these supercomputers, I found the problem is complex.
There might be storage systems that are shared between some
supercomputers but not all supercomputers on the site.
At the moment the aggregation on this list works as follows:
* Actually sites are ranked, not supercomputers or storage systems
* By default a metrics is aggregated across the site, i.e., multiple
storage systems add their performance, capacity, ....
It is also possible to pick the min, max, or mean. (have a look at the
pickers below the list), that way one could ask the question what is
the best performant storage system?
Maybe measuring a single site-wide file system could be possible by
utilizing two supercomputers at the same time...
In particular, people do this with their data archive that may remain
with little change over several generations of supercomputers.
The text of the HPSL should allow people to at least document the
topology on the site page and to document the execution of the
benchmark on the storage page, e.g., saying the best value was
achieved using Supercomputer X or Y.
I believe still having the supercomputers on the list is mandatory as
we understand how the storage resource is used.
Maybe there are sites that have 4 supercomputers on a single shared
file system or two.
What counts is the cluster characteristics memory throughput,
bisection bandwidth, connection to storage and so on.
Hopefully, they build overall a balanced cluster with storage.
I can imagine, to slightly change the storage systems allowing to
define which supercomputers they actually serve. Not sure if this
really will resolve the problem.
Resolving this would be nice though,
Julian
2017-04-06 19:59 GMT+02:00 Carpenter, Ilene <Ilene.Carpenter(a)nrel.gov>:
Thanks Julian! If for site-wide file systems the table would just not
have
entries in the middle section (Supercomputer) then this is resolved.
--
Ilene Carpenter, Ph.D.
ilene.carpenter(a)nrel.gov
Computational Science Center
National Renewable Energy Laboratory
15013 Denver West Pkwy, MS ESIF 301
Golden, CO 80401-3305
Office: (303)275-3947
Mobile: (612)810-9322
Fax: (303)275-4007
On 4/6/17, 11:49 AM, "Julian Kunkel" <juliankunkel(a)googlemail.com>
wrote:
>Dear all,
>this is a side thread only regarding the naming conventions, please
>have a look here:
>https://www.vi4io.org/hpsl/start
>
>From my perspective this is resolved:
>The HPSL currently supports site (facility), supercomputer and storage
>system in a component fashion.
>A site can have multiple supercomputers and storage systems.
>An identifier is <site>/<supercomputer | storage>.
>
>A storage system and supercomputer can have a name.
>Most storage names provided in the list so far are dull names like
>"Lustre" or "Lustre work" but this could be improved if the names
of
>file systems would be available / easy to find.
>
>@Ilene and Andreas:
>Please let me hear, if this resolves the issues or if some
>modifications to the current scheme would be necessary.
>
>The performance values of Top500, Graph500 etc. are also part of the
>respective supercomputer.
>
>Regards,
>Julian
>
>
>--
>http://wr.informatik.uni-hamburg.de/people/julian_kunkel
--
http://wr.informatik.uni-hamburg.de/people/julian_kunkel