<html><body><p><font size="2"><br></font><font size="2">I don\u2019t currently have any x86 based servers to do that kind of performance testing,<br></font><font size="2"><br></font><font size="2">But the PCI-Gen 4 advantages alone mean that the AMD server options have significant benefits over current Intel processor platforms.<br></font><font size="2"><br></font><font size="2">There are however limited storage controllers and Network adapters that can help utilise the full benefits of PCI-gen4.<br></font><font size="2"><br></font><font size="2">In terms of NSD architecture there are many variables that you also have to take into consideration.<br></font><font size="2"><br></font><font size="2">Are you looking at storage rich servers?<br></font><font size="2">Are you looking at SAN attached Flash<br></font><font size="2">Are you looking at scale ECE type deployment?<br></font><font size="2"><br></font><font size="2">As an IBM employee and someone familiar with ESS 5000, and the differences / benefits of the 5K architecture, <br></font><font size="2">Unless your planning on building a Scale ECE type cluster with AMD processors, storage class memory, and NVMe flash modules. I would seriously consider the ESS 5k over an x86 based NL-SAS storage topology Including AMD.<br></font><font size="2"><br></font><font size="2"><br></font><font size="2">Sent from my iPhone<br></font><font size="2"><br></font><font size="2">> On 3 Sep 2020, at 17:44, Giovanni Bracco <giovanni.bracco@enea.it> wrote:<br></font><font size="2">> <br></font><font size="2">> \ufeffOK from client side, but I would like to know if the same is also for <br></font><font size="2">> NSD servers with AMD EPYC, do they operate with good performance <br></font><font size="2">> compared to Intel CPUs?<br></font><font size="2">> <br></font><font size="2">> Giovanni<br></font><font size="2">> <br></font><font size="2">>> On 03/09/20 00:28, Andrew Beattie wrote:<br></font><font size="2">>> Giovanni,<br></font><font size="2">>> I have clients in Australia that are running AMD ROME processors in <br></font><font size="2">>> their Visualisation nodes connected to scale 5.0.4 clusters with no issues.<br></font><font size="2">>> Spectrum Scale doesn't differentiate between x86 processor technologies <br></font><font size="2">>> -- it only looks at x86_64 (OS support more than anything else)<br></font><font size="2">>> Andrew Beattie<br></font><font size="2">>> File and Object Storage Technical Specialist - A/NZ<br></font><font size="2">>> IBM Systems - Storage<br></font><font size="2">>> Phone: 614-2133-7927<br></font><font size="2">>> E-mail: abeattie@au1.ibm.com <<a href="mailto:abeattie@au1.ibm.com">mailto:abeattie@au1.ibm.com</a>><br></font><font size="2">>> <br></font><font size="2">>> ----- Original message -----<br></font><font size="2">>> From: Giovanni Bracco <giovanni.bracco@enea.it><br></font><font size="2">>> Sent by: gpfsug-discuss-bounces@spectrumscale.org<br></font><font size="2">>> To: gpfsug main discussion list <gpfsug-discuss@spectrumscale.org>,<br></font><font size="2">>> Frederick Stock <stockf@us.ibm.com><br></font><font size="2">>> Cc:<br></font><font size="2">>> Subject: [EXTERNAL] Re: [gpfsug-discuss] tsgskkm stuck---> what<br></font><font size="2">>> about AMD epyc support in GPFS?<br></font><font size="2">>> Date: Thu, Sep 3, 2020 7:29 AM<br></font><font size="2">>> I am curious to know about AMD epyc support by GPFS: what is the status?<br></font><font size="2">>> Giovanni Bracco<br></font><font size="2">>> <br></font><font size="2">>>> On 28/08/20 14:25, Frederick Stock wrote:<br></font><font size="2">>>> Not sure that Spectrum Scale has stated it supports the AMD epyc<br></font><font size="2">>> (Rome?)<br></font><font size="2">>>> processors. You may want to open a help case to determine the<br></font><font size="2">>> cause of<br></font><font size="2">>>> this problem.<br></font><font size="2">>>> Note that Spectrum Scale 4.2.x goes out of service on September<br></font><font size="2">>> 30, 2020<br></font><font size="2">>>> so you may want to consider upgrading your cluster. And should Scale<br></font><font size="2">>>> officially support the AMD epyc processor it would not be on<br></font><font size="2">>> Scale 4.2.x.<br></font><font size="2">>>> <br></font><font size="2">>>> Fred<br></font><font size="2">>>> __________________________________________________<br></font><font size="2">>>> Fred Stock | IBM Pittsburgh Lab | 720-430-8821<br></font><font size="2">>>> stockf@us.ibm.com<br></font><font size="2">>>> <br></font><font size="2">>>> ----- Original message -----<br></font><font size="2">>>> From: Philipp Helo Rehs <Philipp.Rehs@uni-duesseldorf.de><br></font><font size="2">>>> Sent by: gpfsug-discuss-bounces@spectrumscale.org<br></font><font size="2">>>> To: gpfsug main discussion list<br></font><font size="2">>> <gpfsug-discuss@spectrumscale.org><br></font><font size="2">>>> Cc:<br></font><font size="2">>>> Subject: [EXTERNAL] [gpfsug-discuss] tsgskkm stuck<br></font><font size="2">>>> Date: Fri, Aug 28, 2020 5:52 AM<br></font><font size="2">>>> Hello,<br></font><font size="2">>>> <br></font><font size="2">>>> we have a gpfs v4 cluster running with 4 nsds and i am trying<br></font><font size="2">>> to add<br></font><font size="2">>>> some clients:<br></font><font size="2">>>> <br></font><font size="2">>>> mmaddnode -N hpc-storage-1-ib:client:hpc-storage-1<br></font><font size="2">>>> <br></font><font size="2">>>> this commands hangs and do not finish<br></font><font size="2">>>> <br></font><font size="2">>>> When i look into the server, i can see the following<br></font><font size="2">>> processes which<br></font><font size="2">>>> never finish:<br></font><font size="2">>>> <br></font><font size="2">>>> root 38138 0.0 0.0 123048 10376 ? Ss 11:32 0:00<br></font><font size="2">>>> /usr/lpp/mmfs/bin/mmksh /usr/lpp/mmfs/bin/mmremote<br></font><font size="2">>> checkNewClusterNode3<br></font><font size="2">>>> lc/setupClient<br></font><font size="2">>>> <br></font><font size="2">>> %%9999%%:00_VERSION_LINE::1709:3:1::lc:gpfs3.hilbert.hpc.uni-duesseldorf.de::0:/bin/ssh:/bin/scp:5362040003754711198:lc2:1597757602::HPCStorage.hilbert.hpc.uni-duesseldorf.de:2:1:1:2:A:::central:0.0:<br></font><font size="2">>>> %%home%%:20_MEMBER_NODE::5:20:hpc-storage-1<br></font><font size="2">>>> root 38169 0.0 0.0 123564 10892 ? S 11:32 0:00<br></font><font size="2">>>> /usr/lpp/mmfs/bin/mmksh /usr/lpp/mmfs/bin/mmremote ccrctl<br></font><font size="2">>> setupClient 2<br></font><font size="2">>>> 21479<br></font><font size="2">>>> <br></font><font size="2">>> 1=gpfs3-ib.hilbert.hpc.uni-duesseldorf.de:1191,2=gpfs4-ib.hilbert.hpc.uni-duesseldorf.de:1191,4=gpfs6-ib.hilbert.hpc.uni-duesseldorf.de:1191,3=gpfs5-ib.hilbert.hpc.uni-duesseldorf.de:1191<br></font><font size="2">>>> 0 1191<br></font><font size="2">>>> root 38212 100 0.0 35544 5752 ? R 11:32 9:40<br></font><font size="2">>>> /usr/lpp/mmfs/bin/tsgskkm store --cert<br></font><font size="2">>>> /var/mmfs/ssl/stage/tmpKeyData.mmremote.38169.cert --priv<br></font><font size="2">>>> /var/mmfs/ssl/stage/tmpKeyData.mmremote.38169.priv --out<br></font><font size="2">>>> /var/mmfs/ssl/stage/tmpKeyData.mmremote.38169.keystore --fips off<br></font><font size="2">>>> <br></font><font size="2">>>> The node is an AMD epyc.<br></font><font size="2">>>> <br></font><font size="2">>>> Any idea what could cause the issue?<br></font><font size="2">>>> <br></font><font size="2">>>> ssh is possible in both directions and firewall is disabled.<br></font><font size="2">>>> <br></font><font size="2">>>> <br></font><font size="2">>>> Kind regards<br></font><font size="2">>>> <br></font><font size="2">>>> Philipp Rehs<br></font><font size="2">>>> <br></font><font size="2">>>> <br></font><font size="2">>>> _______________________________________________<br></font><font size="2">>>> gpfsug-discuss mailing list<br></font><font size="2">>>> gpfsug-discuss at spectrumscale.org<br></font><font size="2">>>> <a href="http://gpfsug.org/mailman/listinfo/gpfsug-discuss">http://gpfsug.org/mailman/listinfo/gpfsug-discuss</a> <br></font><font size="2">>>> <br></font><font size="2">>>> <br></font><font size="2">>>> <br></font><font size="2">>>> _______________________________________________<br></font><font size="2">>>> gpfsug-discuss mailing list<br></font><font size="2">>>> gpfsug-discuss at spectrumscale.org<br></font><font size="2">>>> <a href="http://gpfsug.org/mailman/listinfo/gpfsug-discuss">http://gpfsug.org/mailman/listinfo/gpfsug-discuss</a> <br></font><font size="2">>>> <br></font><font size="2">>> <br></font><font size="2">>> --<br></font><font size="2">>> Giovanni Bracco<br></font><font size="2">>> phone +39 351 8804788<br></font><font size="2">>> E-mail giovanni.bracco@enea.it<br></font><font size="2">>> WWW <a href="http://www.afs.enea.it/bracco">http://www.afs.enea.it/bracco</a> <br></font><font size="2">>> _______________________________________________<br></font><font size="2">>> gpfsug-discuss mailing list<br></font><font size="2">>> gpfsug-discuss at spectrumscale.org<br></font><font size="2">>> <a href="http://gpfsug.org/mailman/listinfo/gpfsug-discuss">http://gpfsug.org/mailman/listinfo/gpfsug-discuss</a> <br></font><font size="2">>> <br></font><font size="2">>> <br></font><font size="2">>> <br></font><font size="2">>> _______________________________________________<br></font><font size="2">>> gpfsug-discuss mailing list<br></font><font size="2">>> gpfsug-discuss at spectrumscale.org<br></font><font size="2">>> <a href="http://gpfsug.org/mailman/listinfo/gpfsug-discuss">http://gpfsug.org/mailman/listinfo/gpfsug-discuss</a> <br></font><font size="2">>> <br></font><font size="2">> <br></font><font size="2">> -- <br></font><font size="2">> Giovanni Bracco<br></font><font size="2">> phone +39 351 8804788<br></font><font size="2">> E-mail giovanni.bracco@enea.it<br></font><font size="2">> WWW <a href="http://www.afs.enea.it/bracco">http://www.afs.enea.it/bracco</a> <br></font><font size="2">> <br></font><BR>
</body></html>