Sorry I missed the anniversary of your conception (announcement letter)
back on August 26th, so I hope you'll accept my belated congratulations on
this long and exciting journey!
https://www-01.ibm.com/common/ssi/cgi-bin/ssialias?subtype=ca=an=iSource=897=ENUS297-318
I remember your parent,
hi all,
what is the expected behaviour of a mixed verbsRdmaSend setup: some
nodes enabled, most disabled.
we have some nodes that have a very high iops workload, but most of the
cluster of 500+ nodes do not have such usecase.
we enabled verbsRdmaSend on the managers/quorum nodes (<10) and on the
Hello Venkateswara, Edward,
Thank you for the comments on how to speed up AFM prefetch with small files. We
run 4.2.2-3 and the AFM mode is RO and we have just a single gateway, i.e. no
parallel reads for large files. We will try to increase the value of
afmNumFlushThreads. It wasn’t clear to
Hi,
you still need both of them, but they are both on the list to be removed,
the first is already integrated for the next major release, the 2nd we
still work on.
Sven
On Wed, Sep 6, 2017 at 4:55 AM Kenneth Waegeman
wrote:
> Hi Sven,
>
> I see two parameters that
Hello Damir,
the files that belong to your fileset "backup" has a separate quota, it is
not related to the quota in "b1000".
There is no cumulative quota.
Fileset Nesting may need other considerations as well, in some cases
filesets behave different than simple directories.
-> For NFSV4 ACLs,
Filesets in filesets are fine. BUT if you use scoped backups with TSM... Er
Spectrum Protect, then there are restrictions on creating an IFS inside an IFS
...
Simon
From:
>
on behalf of
The 2017 Supercomputing conference is only 2 months away, and here’s a reminder
to come early and attend the GPFS user group meeting. The meeting is
tentatively scheduled from the afternoon of Sunday, November 12th. Exact
location and times are still being discussed.
If you have an interest in
Hi Sven,
I see two parameters that we have set to non-default values that are not
in your list of options still to configure.
verbsRdmasPerConnection (256) and
socketMaxListenConnections (1024)
I remember we had to set socketMaxListenConnections because our cluster
consist of +550 nodes.