<div dir="ltr"><div><div><div></div><div><br>1) You mention they are on the same host. Are they on separate partitions already?<br>
As you have failover configured I'm assuming that both servers can see
the storage. In which case this will not be too difficult (depending on
your failover software of course) if they have separate partitions.<br>
<br></div><span style="color:rgb(0,0,255)">Yes, they are separate DRBD Devices. So mounting any one of them on the other server is easy.<br></span></div><span style="color:rgb(0,0,255)">But how do I tell the OSS that MGS or MDT has moved to a new IP/Host?<br></span></div><span style="color:rgb(0,0,255)">And how do I reconfigure the failover on the device I move?</span><br><div><div><div><div>
<br>
2) so today Linux clients use the native client? And you are planning on
shifting this to use the NFS service from a gateway node, is that
correct?<br>
How do they connect to the lustre servers today? QDR IB?<br>
How will they reach the gateway nodes after this change? NFS over IB? NFS over RDMA?<br></div><div><span style="color:rgb(0,0,255)"><br></span></div><div><span style="color:rgb(0,0,255)">Yes, the Linux Hosts use Lustre Native Clients. Windows Hosts connect via the Gateway.<br></span></div><div><span style="color:rgb(0,0,255)">The Gateway Nodes uses Infiniband+RDMA to connect to Lustre.<br></span></div><div><span style="color:rgb(0,0,255)">I am thinking of moving the Linux Native Clients to NFS, connecting them through this Gateway.</span><br></div><div><span style="color:rgb(0,0,255)">All client nodes are on 1GbE network.<br></span></div><div><span style="color:rgb(0,0,255)">Infiniband is used only to connect the Gateway to Lustre.<br></span></div><div><br></div><div>Regards,<br><br><br></div><div>Indivar Nair</div><div><br></div></div></div></div></div><div class="gmail_extra"><br><div class="gmail_quote">On Tue, Jul 21, 2015 at 8:29 PM, Wahl, Edward <span dir="ltr"><<a href="mailto:ewahl@osc.edu" target="_blank">ewahl@osc.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div>
<div style="direction:ltr;font-family:Tahoma;color:#000000;font-size:10pt">1) You mention they are on the same host. Are they on separate partitions already?<br>
As you have failover configured I'm assuming that both servers can see the storage. In which case this will not be too difficult (depending on your failover software of course) if they have separate partitions.<br>
<br>
<br>
2) so today Linux clients use the native client? And you are planning on shifting this to use the NFS service from a gateway node, is that correct?<br>
How do they connect to the lustre servers today? QDR IB?<br>
How will they reach the gateway nodes after this change? NFS over IB? NFS over RDMA?<br>
<br>
<br>
Ed<br>
<br>
<div style="font-family:Times New Roman;color:#000000;font-size:16px">
<hr>
<div style="direction:ltr"><font face="Tahoma" size="2" color="#000000"><b>From:</b> lustre-discuss [<a href="mailto:lustre-discuss-bounces@lists.lustre.org" target="_blank">lustre-discuss-bounces@lists.lustre.org</a>] on behalf of Indivar Nair [<a href="mailto:indivar.nair@techterra.in" target="_blank">indivar.nair@techterra.in</a>]<br>
<b>Sent:</b> Tuesday, July 21, 2015 4:27 AM<br>
<b>To:</b> lustre-discuss; hpdd-discuss<br>
<b>Subject:</b> [lustre-discuss] Speeding up recovery<br>
</font><br>
</div><div><div class="h5">
<div></div>
<div>
<div dir="ltr">
<div>
<div>Hi ...,<br>
<br>
</div>
<div>Currently, Failover and Recovery takes a very long long time in our setup; almost 20 Minutes. We would like to make it as fast as possible.<br>
</div>
<div><br>
</div>
<div>I have two queries regarding this -<br>
</div>
<div><br>
1.<br>
===================================================<br>
</div>
<div>The MGS and MDT are on the same host.<br>
</div>
<div><br>
</div>
<div>We do however have a passive stand-by server for the MGS/MDT server, which only mounts these partitions in case of a failure.<br>
<br>
</div>
<div><u>Current Setup</u><br>
</div>
<div>Server A: MGS+MDT<br>
</div>
<div>Server B: Failover MGS+MDT<br>
</div>
<div><br>
</div>
<div>I was wondering whether I can now move the MGS or MDT Partition to the standby server (so that imperative recovery works properly) -
<br>
<br>
</div>
<div><u>New Setup</u><br>
</div>
<div>Server A: MDT & <b>Failover MGS</b><br>
</div>
<div>Server B: <b>MGS</b> & Failover MDT<br>
</div>
<div></div>
<div> <b>OR<br>
</b>
<div>Server A: <b>MGS</b> & Failover MDT<br>
</div>
Server B: MDT & <b>Failover MGS</b><br>
<br>
</div>
<div>i.e. <br>
<b>Can I separate the MDT and MGS partitions on to different machines without formatting or reinstalling Lustre?<br>
</b></div>
<div>===================================================<br>
<br>
2.<br>
===================================================<br>
</div>
<div>This storage is used by around 150 Workstations and 150 Compute (Render) Nodes.<br>
<br>
</div>
<div>Out of these 150 workstations, around 30 - 40 are MS Windows. The MS Windows clients access the storage through a 2-node Samba Gateway Cluster.<br>
<br>
</div>
<div>The Gateway Nodes are connected to the storage through a QDR Infiniband Network.<br>
<br>
</div>
<div>We were thinking of adding NFS Service to the Samba Gateway nodes, and reconfiguring the Linux clients to connect via this gateway.
<br>
<br>
</div>
This will bring down the direct Lustre Clients to just 2 nodes.<br>
</div>
<div>
<div><b>So, will having only 2 clients improve the failover-recovery time?</b><br>
</div>
<div>===================================================<br>
<br>
</div>
<div>Is there anything else we can do to speed up recovery?<br>
</div>
<div><br>
</div>
Regards,<br>
<br>
<br>
</div>
Indivar Nair<br>
</div>
</div>
</div></div></div>
</div>
</div>
</blockquote></div><br></div>