>>> Update #3

Dear Expanse User,

We have remounted the Lustre filesystem on Expanse excluding the OST that is having problems. This should prevent the hung tasks that were causing higher loads on the login nodes. We continue to work on the OST with issues and will update once it is returned to service. In the interim any old files that were striped onto the OST will fail on reads. New I/O to the filesystem will target healthy OSTs. 

Thanks

SDSC User Services Staff

>>> Update #2

Dear Expanse User,

We are still working on the one OST from the Expanse Lustre filesystem that is failing to mount. This is making all files/directories that are striped onto this OST unavailable. Please note that this will also cause full file listings to hang so please refrain from doing full metadata listings on Lustre directories. All other OSTs on the filesystem are usable and new I/O will automatically avoid the problem OST. We will update once the OST with issues is restored.

Thanks

SDSC User Services Staff

>>> Update 

Dear Expanse User,

We brought the two OSSs online last night but there is still one storage target on one of them that needs more work to recover. We are continuing to look at the issue and will update again once the filesystem is back.

Thanks

SDSC User Services

>>>

Dear Expanse User,

We are currently seeing problems with two object storage servers (OSSs) that are part of the Expanse Lustre filesystem. This is causing access issues on files that are striped on these servers. Please refrain from doing full metadata listings on Lustre directories as chances are you will access a file that is on one of the OSSs and the commands might hang. We are working on resolving the problem and will update once the OSSs are back in service.

Thanks

SDSC User Services Staff