This post is more than 5 years old
5 Posts
0
3341
scini volume I/O error - failed getting LB-Info
Hello!
I'm currently testing ScaleIO with version R2_0.14000.231 on CentOS 7.2.
I have 12 SDS in one storage pool, 1 protection domain and 4 fault sets with 3 SDS in each fault set.
Each SDS have two network interface: 1 Gb/s Ethernet for management traffic and 56 Gb/s InfiniBand for Data traffic.
MDM cluster running on 5-node mode.
Yesterday my test scini volume observe some I/O errors in /var/log/messages:
May 6 21:00:02 hostname kernel: ScaleIO R2_0 mapVolIO_ReportIOErrorIfNeeded:361 :[24173965336] IO-ERROR comb: 0. offsetInComb 0. SizeInLB 0. SDS_ID 0. Comb Gen 0. Head Gen 1477.
May 6 21:00:02 hostname kernel: ScaleIO R2_0 mapVolIO_ReportIOErrorIfNeeded:374 :Vol ID 0xf5dea3500000042. Last fault Status SUCCESS(65).Last error Status SUCCESS(65) Reason (failed getting LB-Info) Retry count (0) chan (0)
May 6 21:00:02 hostname kernel: blk_update_request: 9 callbacks suppressed
May 6 21:00:02 hostname kernel: blk_update_request: I/O error, dev scinif, sector 0
MDM cluster doesn't report any failure from MDM or SDS nodes. I/O erors was appeared for 1 second, and then disappears.
What I should check? What mean this error - failed getting LB-Info?
RHasleton1
73 Posts
0
May 23rd, 2018 08:00
Hi iemmanuylov,
In a case like this, it would be difficult to give a complete answer without logs to review. The LB-Info error you are referencing is basically saying that it could not get the logical block information, in this case because the SDS_ID came back as 0. Meaning, there was IO (read/write) that was attempted and it could not be completed because there was no valid SDS to fulfill the request.
What you would be looking for is in the MDM/SDS logs, something to correlate to the timestamps above as to what was going on at the time. If you can't find anything or need root cause, the suggestion after that would be to open a support ticket and let the ScaleIO engineers take a look.
Hope that helps,
Rick
iemmanuylov
5 Posts
0
May 24th, 2018 08:00
RickH, thank you for reply!
Unfortunately, I can't find something correlated in MDM/SDS logs by myself.
If issue will repeat, I will open a support ticket for ScaleIO engineers.