You should unmount the MGS from both filesystems immediately and run e2fsck. For some reason, the MMP feature was not enabled on your MGS (it is done automatically at mkfs.lustre time only if you specify failover options. You can enable it manually before remounting with: tune2fs -O mmp /dev/{mgsdev} I believe the MMP feature will print a console message at mount time if enabled. You can also check your other target filesystems to verify it is enabled: dumpe2fs -h /dev/{OST or MDT} | grep -i feature And it should list the MMP feature. Cheers, Andreas On 2013-10-18, at 5:41, "Thomas Roth" <t.roth(a)gsi.de&gt; wrote: > Hi all, > > we have a test system where the metadata part consists of two servers connected via Fibre Channel to > one storage box. > We are running CentOS 6.4 (Lustre 2.4) and can access the storage device using multipathd: > I have created a partition for the MGS, one for the MDT, both of which I can see on both servers as > /dev/mapper/mdsp1, /dev/mapper/mdsp2 > > Lustre works fine, I have just tested failing over from one metadata server to the other, and back, > all o.k. > > For the fun of it I wanted to test the MMP feature, and mounted the partitions on the inactive one of > the two servers. > The MDT-mount refused all right, but I was surprised to see the MGS mounting cleanly, without so much > as a single log entry! > > If both servers are running an MGS, which one is being addressed by the clients? Round-robin? Did I > discover an active-active scenario I was not aware of? > > More importantly: the MGS holds the configuration of my system, correct? What if I add an OST now? > Which server gets to write this to the MGS disk? Isn't it possible to mess up big time in this way? > > Regards, > Thomas > _______________________________________________ > HPDD-discuss mailing list > HPDD-discuss(a)lists.01.org > https://lists.01.org/mailman/listinfo/hpdd-discuss