[Lustre-discuss] Errors after restarting: start index not found?

[Jon Yeargers]

Working with a set of test systems.

4 OST machines / 1 MDT MGT
all running 2.6.32-279.2.1.el6_lustre.gc46c389.x86_64 kernel on CentOS 6.3

The systems lost power due to a UFU. When they were brought back up the IP for the MDT changed. In order to get them working I did the steps listed on: http://wiki.lustre.org/manual/LustreManual20_HTML/LustreMaintenance.html

The MDT reported everyone up and happy.  ‘lctl dl’ shows what I would suspect is ok.

Mounting a client seems to work in that pre-existing files are folders are found.

*but* when I try to ‘touch tmp’ I get ‘touch: setting times of ‘tmp’ : no such file or directory

When I look at ‘dmesg’ on the MDT machine I see these errors:

LustreError: 2937:0:(lov_qos.c:721:alloc_specific()) Start index 0 not found in pool ''


There weren’t any pools setup prior to the reboot / rebuild.

Did I miss a step in fixing things? Is there something I can do to fix this now?

Im preparing to deploy a much larger setup so Im hoping to get the various processes understood soon.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20121220/ddfe9716/attachment.htm>