Hello Experts,
Does GPFS start "down" disks in a filesystem automatically? For instance, when
connection to NSD is recovered, but it the meantime disk was put in "down"
state by GPFS. Will GPFS in such case start the disk?
With best regards / Mit freundlichen Grüßen / Pozdrawiam
Tomasz Wolski
Hello we have a half day (afternoon) usergroup next week. Please check out the
event registration link below for tickets, speakers and topics.
https://goo.gl/za8g3r
Regards,
Chris Schlipalius
Lead Organiser Spectrum Scale Usergroups Australia
Senior Storage Infrastucture Specialist,
The Pawsey
By default, GPFS does not automatically start down disks. You could add a
callback “downdisk” via mmaddcallback that could trigger a “mmchdisk start” if
you wanted. If a disk is marked down, it’s better to determine why before
trying to start it as it may involve other issues that need investiga
If you do a "mmchconfig restripeOnDiskFailure=yes", such a callback will be
added for node-join events. That can be quite useful for stretched
clusters, where you want to replicate all blocks to both locations, and
this way recover automatically.
-jf
On Wed, Aug 9, 2017 at 2:14 PM, Oesterlin,
Be careful here, as this does:
“When a disk experiences a failure and becomes unavailable, the recovery
procedure will first attempt to restart the disk and if this fails, the disk is
suspended and its data moved to other disks. “
Which may not be what you want to happen. :-) If you have disks
For non-stretch clusters, I think best practice would be to have an
administrator analyze the situation and understand why the NSD was considered
unavailable before attempting to start the disks back in the file system. Down
NSDs are usually indicative of a serious issue.
However I have seen a