Differences

This shows you the differences between two versions of the page.

--- technical:generic:caviness-lustre-rebalance [2021-02-23 16:48] – frey
+++ technical:generic:caviness-lustre-rebalance [2021-02-23 16:54] – frey
@@ Line 67: / Line 67: @@
   - Finally, all directories under ''/lustre/scratch/altroot'' will be moved back to being under ''/lustre/scratch'' as before.
 With the metadata of the new copies being striped across all MDTs, and the Lustre metadata subsystem spreading the copies across the new and old OSTs, the net effect will be to rebalance MDT and OST usage across all devices.
+===== Testing =====
+All aspects of this workflow were tested using VirtualBox on a Mac laptop.  A CentOS 7 VM (of the same version as is in-use on Caviness) was provisioned with Lustre 2.10.3 patchless server kernel modules installed.  This VM was diff-cloned to create three additional VMs: mds0, mds1, oss1, oss2.  The following VDIs were created:
+  * 50 GB - mgt
+  * 250 GB - mdt0, mdt1
+  * 1000 GB - ost0, ost1
+The mgt and mdt0 VDIs were attached to mds0 and formatted:
+<code bash>
+$ mkfs.lustre --mgs --reformat \
+    --servicenode=mds0@tcp --mgsnode=mds1@tcp \
+    --backfstype=ldiskfs \
+    /dev/sdb
+$ mkfs.lustre --mdt --reformat \
+    --mgsnode=mds0@tcp --mgsnode=mds1@tcp \
+    --servicenode=mds0@tcp --mgsnode=mds1@tcp \
+    --backfstype=ldiskfs --fsname=demo \
+    /dev/sdc1
+</code>
+The ost0 VDI was attached to oss0 and formatted:
+<code bash>
+$ mkfs.lustre --ost --reformat --index=0 \
+    --mgsnode=mds0@tcp --mgsnode=mds1@tcp \
+    --servicenode=oss0@tcp --mgsnode=oss1@tcp \
+    --backfstype=ldiskfs --fsname=demo \
+    /dev/sdb
+</code>