<span style=" font-size:10pt;font-family:sans-serif">When using this method
of replication, you need to either issue "mmfsctl suspend or suspend-write"
command before replication or setup a single consistency group for all
LUNs. This is needed to ensure replica contain a consistent
copy of GPFS data. </span><br><span style=" font-size:10pt;font-family:sans-serif"><br>Steve Y. Xiao<br></span><br><tt><span style=" font-size:10pt">gpfsug-discuss-bounces@spectrumscale.org
wrote on 01/26/2018 03:21:23 PM:<br><br>> From: gpfsug-discuss-request@spectrumscale.org</span></tt><br><tt><span style=" font-size:10pt">> To: gpfsug-discuss@spectrumscale.org</span></tt><br><tt><span style=" font-size:10pt">> Date: 01/26/2018 03:21 PM</span></tt><br><tt><span style=" font-size:10pt">> Subject: gpfsug-discuss Digest,
Vol 72, Issue 69</span></tt><br><tt><span style=" font-size:10pt">> Sent by: gpfsug-discuss-bounces@spectrumscale.org</span></tt><br><tt><span style=" font-size:10pt">> <br>> Send gpfsug-discuss mailing list submissions to<br>> gpfsug-discuss@spectrumscale.org<br>> <br>> To subscribe or unsubscribe via the World Wide Web, visit<br>> </span></tt><a href=https://urldefense.proofpoint.com/v2/url?><tt><span style=" font-size:10pt">https://urldefense.proofpoint.com/v2/url?</span></tt></a><tt><span style=" font-size:10pt"><br>> u=http-3A__gpfsug.org_mailman_listinfo_gpfsug-2Ddiscuss&d=DwICAg&c=jf_iaSHvJObTbx-<br>> siA1ZOg&r=ck4PYlaRFvCcNKlfHMPhoA&m=ddkAIwRPQmQKBLLh6nBzhdt-<br>> OKoJwOucQ8oaQet8mkE&s=Emkr3VzCYTecA6E61hAk1AeB6ka34dGAYip6fGaKuwU&e=<br>> or, via email, send a message with subject or body 'help' to<br>> gpfsug-discuss-request@spectrumscale.org<br>> <br>> You can reach the person managing the list at<br>> gpfsug-discuss-owner@spectrumscale.org<br>> <br>> When replying, please edit your Subject line so it is more specific<br>> than "Re: Contents of gpfsug-discuss digest..."<br>> <br>> <br>> Today's Topics:<br>> <br>> 1. Re: storage-based replication for Spectrum Scale (Harold
Morales)<br>> 2. Re: storage-based replication for Spectrum Scale (Glen
Corneau)<br>> <br>> <br>> ----------------------------------------------------------------------<br>> <br>> Message: 1<br>> Date: Fri, 26 Jan 2018 13:29:09 -0500<br>> From: Harold Morales <hmorales@optimizeit.co><br>> To: gpfsug main discussion list <gpfsug-discuss@spectrumscale.org><br>> Subject: Re: [gpfsug-discuss] storage-based replication for Spectrum<br>> Scale<br>> Message-ID:<br>> <CAGQnKWaAJAuFxYT2PzjMW47vuOsMg4evUAT8+SV49rrVkkQLBg@mail.gmail.com><br>> Content-Type: text/plain; charset="utf-8"<br>> <br>> Hi Alex, This set up seems close to what I am trying to achieve.<br>> <br>> With regards to this kind of replication: any prereqs need to be met
in the<br>> target environment for this to work? for example, should disk devices<br>> naming on AIX be the same as in the source environment? when importing
the<br>> mmsdrfs file, how is Scale going to know which disks should it assign
to<br>> the cluster? by their hdisk name alone?<br>> <br>> Thanks again,<br>> <br>> <br>> <br>> 2018-01-24 2:30 GMT-05:00 Alex Levin <alevin@gmail.com>:<br>> <br>> > Hi,<br>> ><br>> > We are using a similar type of replication.<br>> > I assume the site B is the cold site prepared for DR<br>> ><br>> > The storage layer is EMC VMAX and the LUNs are replicated with
SRDF.<br>> > All LUNs ( NSDs ) of the gpfs filesystem are in the same VMAX
replication<br>> > group to ensure consistency.<br>> ><br>> > The cluster name, IP addresses , hostnames of the cluster
nodes are<br>> > different on another site - it can be a pre-configured cluster
without<br>> > gpfs filesystems or with another filesystem.<br>> > Same names and addresses shouldn't be a problem.<br>> ><br>> > Additionally to the replicated LUNs/NSDs you need to deliver
copy<br>> > of /var/mmfs/gen/mmsdrfs file from A to B site.<br>> > There is no need to replicate it in real-time, only after the
change of<br>> > the cluster configuration.<br>> ><br>> > To activate site B - present replicated LUNs to the nodes
in the DR<br>> > cluster and run mmimportfs as "mmimportfs fs_name
-i copy_of_mmsdrfs"<br>> ><br>> > Tested with multiples LUNs and filesystems on various workloads
- seems<br>> > to be working<br>> ><br>> > --Alex<br>> ><br>> ><br>> > On Wed, Jan 24, 2018 at 1:33 AM, Harold Morales <hmorales@optimizeit.co><br>> > wrote:<br>> ><br>> >> Thanks for answering.<br>> >><br>> >> Essentially, the idea being explored is to replicate LUNs
between<br>> >> identical storage hardware (HP 3PAR volumesrein) on both
sites. There is an<br>> >> IP connection between storage boxes but not between servers
on both sites,<br>> >> there is a dark fiber connecting both sites. Here they dont
want to explore<br>> >> the idea of a scaled-based.<br>> >><br>> >><br>> >> _______________________________________________<br>> >> gpfsug-discuss mailing list<br>> >> gpfsug-discuss at spectrumscale.org<br>> >> </span></tt><a href=https://urldefense.proofpoint.com/v2/url?><tt><span style=" font-size:10pt">https://urldefense.proofpoint.com/v2/url?</span></tt></a><tt><span style=" font-size:10pt"><br>> u=http-3A__gpfsug.org_mailman_listinfo_gpfsug-2Ddiscuss&d=DwICAg&c=jf_iaSHvJObTbx-<br>> siA1ZOg&r=ck4PYlaRFvCcNKlfHMPhoA&m=ddkAIwRPQmQKBLLh6nBzhdt-<br>> OKoJwOucQ8oaQet8mkE&s=Emkr3VzCYTecA6E61hAk1AeB6ka34dGAYip6fGaKuwU&e=<br>> >><br>> >><br>> ><br>> > _______________________________________________<br>> > gpfsug-discuss mailing list<br>> > gpfsug-discuss at spectrumscale.org<br>> > </span></tt><a href=https://urldefense.proofpoint.com/v2/url?><tt><span style=" font-size:10pt">https://urldefense.proofpoint.com/v2/url?</span></tt></a><tt><span style=" font-size:10pt"><br>> u=http-3A__gpfsug.org_mailman_listinfo_gpfsug-2Ddiscuss&d=DwICAg&c=jf_iaSHvJObTbx-<br>> siA1ZOg&r=ck4PYlaRFvCcNKlfHMPhoA&m=ddkAIwRPQmQKBLLh6nBzhdt-<br>> OKoJwOucQ8oaQet8mkE&s=Emkr3VzCYTecA6E61hAk1AeB6ka34dGAYip6fGaKuwU&e=<br>> ><br>> ><br>> -------------- next part --------------<br>> An HTML attachment was scrubbed...<br>> URL: <</span></tt><a href=https://urldefense.proofpoint.com/v2/url?><tt><span style=" font-size:10pt">https://urldefense.proofpoint.com/v2/url?</span></tt></a><tt><span style=" font-size:10pt"><br>> u=http-3A__gpfsug.org_pipermail_gpfsug-2Ddiscuss_attachments_20180126_1503995b_attachment-2D0001.html&d=DwICAg&c=jf_iaSHvJObTbx-<br>> siA1ZOg&r=ck4PYlaRFvCcNKlfHMPhoA&m=ddkAIwRPQmQKBLLh6nBzhdt-<br>> OKoJwOucQ8oaQet8mkE&s=SKdMmQae8uzHNWZq3vuRTp5UVwYFeeusLAxtbaposX0&e=><br>> <br>> ------------------------------<br>> <br>> Message: 2<br>> Date: Fri, 26 Jan 2018 14:21:15 -0600<br>> From: "Glen Corneau" <gcorneau@us.ibm.com><br>> To: gpfsug main discussion list <gpfsug-discuss@spectrumscale.org><br>> Subject: Re: [gpfsug-discuss] storage-based replication for Spectrum<br>> Scale<br>> Message-ID:<br>> <OFEAC48C60.2890CAEF-ON86258221.006F3F43-86258221.<br>> 006FCEEE@notes.na.collabserv.com><br>> <br>> Content-Type: text/plain; charset="us-ascii"<br>> <br>> Scale will walk across all discovered disks upon start time and attempt
to <br>> read the NSD identifiers from the disks. Once it finds them,
it makes a <br>> local map file that correlates the NSD id and the hdiskX identifier.
The <br>> names do not have to be the same as either the source cluster or even
from <br>> node-to-node.<br>> <br>> The main thing to keep in mind is to keep the file system definitions
in <br>> sync between the source and destination clusters. The "syncFSconfig"
user <br>> exit is the best way to do it because it's automatic. You generally
<br>> shouldn't be shuffling the mmsdrfs file between sites, that's what
the <br>> "mmfsctl syncFSconfig" does for you, on a per-file system
basis.<br>> <br>> GPFS+AIX customers have been using this kind of storage replication
for <br>> over 10 years, it's business as usual.<br>> <br>> ------------------<br>> Glen Corneau<br>> Power Systems<br>> Washington Systems Center<br>> gcorneau@us.ibm.com<br>> <br>> <br>> <br>> <br>> <br>> From: Harold Morales <hmorales@optimizeit.co><br>> To: gpfsug main discussion list <gpfsug-discuss@spectrumscale.org><br>> Date: 01/26/2018 12:30 PM<br>> Subject: Re: [gpfsug-discuss] storage-based
replication for <br>> Spectrum Scale<br>> Sent by: gpfsug-discuss-bounces@spectrumscale.org<br>> <br>> <br>> <br>> Hi Alex, This set up seems close to what I am trying to achieve.<br>> <br>> With regards to this kind of replication: any prereqs need to be met
in <br>> the target environment for this to work? for example, should disk
devices <br>> naming on AIX be the same as in the source environment? when importing
the <br>> mmsdrfs file, how is Scale going to know which disks should it assign
to <br>> the cluster? by their hdisk name alone?<br>> <br>> Thanks again,<br>> <br>> <br>> <br>> 2018-01-24 2:30 GMT-05:00 Alex Levin <alevin@gmail.com>:<br>> Hi, <br>> <br>> We are using a similar type of replication.<br>> I assume the site B is the cold site prepared for DR<br>> <br>> The storage layer is EMC VMAX and the LUNs are replicated with SRDF.<br>> All LUNs ( NSDs ) of the gpfs filesystem are in the same VMAX replication
<br>> group to ensure consistency.<br>> <br>> The cluster name, IP addresses , hostnames of the cluster nodes
are <br>> different on another site - it can be a pre-configured cluster without
<br>> gpfs filesystems or with another filesystem.<br>> Same names and addresses shouldn't be a problem.<br>> <br>> Additionally to the replicated LUNs/NSDs you need to deliver copy
<br>> of /var/mmfs/gen/mmsdrfs file from A to B site.<br>> There is no need to replicate it in real-time, only after the change
of <br>> the cluster configuration.<br>> <br>> To activate site B - present replicated LUNs to the nodes in
the DR <br>> cluster and run mmimportfs as "mmimportfs fs_name
-i copy_of_mmsdrfs"<br>> <br>> Tested with multiples LUNs and filesystems on various workloads
- seems <br>> to be working <br>> <br>> --Alex<br>> <br>> <br>> <br>> On Wed, Jan 24, 2018 at 1:33 AM, Harold Morales <hmorales@optimizeit.co>
<br>> wrote:<br>> Thanks for answering.<br>> <br>> Essentially, the idea being explored is to replicate LUNs between
<br>> identical storage hardware (HP 3PAR volumesrein) on both sites. There
is <br>> an IP connection between storage boxes but not between servers on
both <br>> sites, there is a dark fiber connecting both sites. Here they dont
want to <br>> explore the idea of a scaled-based.<br>> <br>> <br>> _______________________________________________<br>> gpfsug-discuss mailing list<br>> gpfsug-discuss at spectrumscale.org<br>> </span></tt><a href=https://urldefense.proofpoint.com/v2/url?><tt><span style=" font-size:10pt">https://urldefense.proofpoint.com/v2/url?</span></tt></a><tt><span style=" font-size:10pt"><br>> u=http-3A__gpfsug.org_mailman_listinfo_gpfsug-2Ddiscuss&d=DwICAg&c=jf_iaSHvJObTbx-<br>> siA1ZOg&r=ck4PYlaRFvCcNKlfHMPhoA&m=ddkAIwRPQmQKBLLh6nBzhdt-<br>> OKoJwOucQ8oaQet8mkE&s=Emkr3VzCYTecA6E61hAk1AeB6ka34dGAYip6fGaKuwU&e=<br>> <br>> <br>> <br>> _______________________________________________<br>> gpfsug-discuss mailing list<br>> gpfsug-discuss at spectrumscale.org<br>> </span></tt><a href=https://urldefense.proofpoint.com/v2/url?><tt><span style=" font-size:10pt">https://urldefense.proofpoint.com/v2/url?</span></tt></a><tt><span style=" font-size:10pt"><br>> u=http-3A__gpfsug.org_mailman_listinfo_gpfsug-2Ddiscuss&d=DwICAg&c=jf_iaSHvJObTbx-<br>> siA1ZOg&r=ck4PYlaRFvCcNKlfHMPhoA&m=ddkAIwRPQmQKBLLh6nBzhdt-<br>> OKoJwOucQ8oaQet8mkE&s=Emkr3VzCYTecA6E61hAk1AeB6ka34dGAYip6fGaKuwU&e=<br>> <br>> _______________________________________________<br>> gpfsug-discuss mailing list<br>> gpfsug-discuss at spectrumscale.org<br>> </span></tt><a href=https://urldefense.proofpoint.com/v2/url?><tt><span style=" font-size:10pt">https://urldefense.proofpoint.com/v2/url?</span></tt></a><tt><span style=" font-size:10pt"><br>> u=http-3A__gpfsug.org_mailman_listinfo_gpfsug-2Ddiscuss&d=DwICAg&c=jf_iaSHvJObTbx-<br>> siA1ZOg&r=d-<br>> vphLEe_UlGazP6RdYAyyAA3Qv5S9IRVNuO1i9vjJc&m=VbfWaftYSVjx8fMb2vHGBi6XUhDJOsKf_dKOX3J8s1A&s=p2mGvPrlPLO1oyEh-<br>> GeVJiVS49opBwwCFs-FKQrQ7rc&e=<br>> <br>> <br>> <br>> <br>> <br>> -------------- next part --------------<br>> An HTML attachment was scrubbed...<br>> URL: <</span></tt><a href=https://urldefense.proofpoint.com/v2/url?><tt><span style=" font-size:10pt">https://urldefense.proofpoint.com/v2/url?</span></tt></a><tt><span style=" font-size:10pt"><br>> u=http-3A__gpfsug.org_pipermail_gpfsug-2Ddiscuss_attachments_20180126_e291af63_attachment.html&d=DwICAg&c=jf_iaSHvJObTbx-<br>> siA1ZOg&r=ck4PYlaRFvCcNKlfHMPhoA&m=ddkAIwRPQmQKBLLh6nBzhdt-<br>> OKoJwOucQ8oaQet8mkE&s=bYnf-7v0CxYUkGth-QaVeUQdIlG8f1Gro-hwOxok7Qw&e=><br>> -------------- next part --------------<br>> A non-text attachment was scrubbed...<br>> Name: not available<br>> Type: image/jpeg<br>> Size: 26117 bytes<br>> Desc: not available<br>> URL: <</span></tt><a href=https://urldefense.proofpoint.com/v2/url?><tt><span style=" font-size:10pt">https://urldefense.proofpoint.com/v2/url?</span></tt></a><tt><span style=" font-size:10pt"><br>> u=http-3A__gpfsug.org_pipermail_gpfsug-2Ddiscuss_attachments_20180126_e291af63_attachment.jpe&d=DwICAg&c=jf_iaSHvJObTbx-<br>> siA1ZOg&r=ck4PYlaRFvCcNKlfHMPhoA&m=ddkAIwRPQmQKBLLh6nBzhdt-<br>> OKoJwOucQ8oaQet8mkE&s=jYdnqhQBlnpf58oxunzBcTs9XdcbeOtLDQdgnASidDA&e=><br>> <br>> ------------------------------<br>> <br>> _______________________________________________<br>> gpfsug-discuss mailing list<br>> gpfsug-discuss at spectrumscale.org<br>> </span></tt><a href=https://urldefense.proofpoint.com/v2/url?><tt><span style=" font-size:10pt">https://urldefense.proofpoint.com/v2/url?</span></tt></a><tt><span style=" font-size:10pt"><br>> u=http-3A__gpfsug.org_mailman_listinfo_gpfsug-2Ddiscuss&d=DwICAg&c=jf_iaSHvJObTbx-<br>> siA1ZOg&r=ck4PYlaRFvCcNKlfHMPhoA&m=ddkAIwRPQmQKBLLh6nBzhdt-<br>> OKoJwOucQ8oaQet8mkE&s=Emkr3VzCYTecA6E61hAk1AeB6ka34dGAYip6fGaKuwU&e=<br>> <br>> <br>> End of gpfsug-discuss Digest, Vol 72, Issue 69<br>> **********************************************<br>> <br></span></tt><BR>