As detailed in the parent task, db1112 has recently had some errors on dimm B1, and hung hard yesterday.
https://phabricator.wikimedia.org/T294295#7456670:
This host is obviously out of warranty, but maybe we can get a spare DIMM somewhere and replace B1?
(Making this a dedicated dc-ops subtask so we can manage the service-level stuff in the parent task)
| Status | Subtype | Assigned | Task | ||
|---|---|---|---|---|---|
| Resolved | • Marostegui | T294295 db1112 (s3 contribs/rc replica) is down | |||
| Resolved | Cmjohnson | T294345 db1112 - DIMM replacement | |||
| Unknown Object (Task) |
This is the DIMM information. I am not sure if we have one in a spare server but I will spot a check a few. @wiki_willy
we may want to purchase a DIMM.
emory Device
Array Handle: 0x1000
Error Information Handle: Not Provided
Total Width: 72 bits
Data Width: 64 bits
Size: 32 GB
Form Factor: DIMM
Set: 4
Locator: B1
Bank Locator: Not Specified
Type: DDR4
Type Detail: Synchronous Registered (Buffered)
Speed: 2400 MT/s
Manufacturer: 00AD00B300AD
Serial Number: 11A54A33
Asset Tag: 00173830
Part Number: HMA84GR7MFR4N-UH
Rank: 2
Configured Memory Speed: 2400 MT/s
Minimum Voltage: 1.2 V
Maximum Voltage: 1.2 V
Configured Voltage: 1.2 V
Let me know if you're able to find a spare @Cmjohnson. If not, we can order one with @RobH. Thanks, Willy
Please coordinate with us before changing the DIMM as this host has MySQL up and running (although it is nos serving production it can still get corrupted if powered off without gracefully stopping mysql first).
Thank you!