Page MenuHomePhabricator

Broken disk on analytics1039
Closed, DuplicatePublic

Description

analytics1039 has a broken disk, throwing errors like

[11049762.269483] blk_update_request: I/O error, dev sdb, sector 7812937712
[11049762.277031] sd 0:2:1:0: [sdb] tag#0 FAILED Result: hostbyte=DID_BAD_TARGET driverbyte=DRIVER_OK
[11049762.277036] sd 0:2:1:0: [sdb] tag#0 CDB: Read(16) 88 00 00 00 00 00 00 00 08 00 00 00 00 08 00 00

It's out-of-warranty, but those servers are used for the Hadoop test cluster, if we can't snatch a replacement disk from a decommed server we could maybe decom the server and repurpose one of the Hadoop workers from the test cluster as the new Hadoop UI server Let's check with @elukey when he's back.

Event Timeline