SAP Knowledge Base Article - Preview

3002704 - Hardware memory corruption logged on OS level

Symptom

- OS logs (/var/log/messages, /var/log/warn, dmesg) contain entries referencing "hardware memory corruption":

Example 1:

2020-12-08T12:21:03.858622+01:00 server3 kernel: [1423822.815742] MCE: Killing <process:PID> due to hardware memory corruption fault at 7fe9bc16fb00

Example 2:

Dec 3 04:44:10 server1 kernel: [5105857.955669] [Hardware Error]: Machine check events logged
Dec 3 04:44:10 server1 kernel: [5105857.955693] Uncorrected hardware memory error in user-access at 48d3259dc0
Dec 3 04:44:10 server1 kernel: [5105857.956108] MCE 0x48d3259: huge page recovery: Delayed
Dec 3 04:44:10 server1 kernel: [5105857.956110] MCE 0x48d3259: huge page still referenced by 1 users
Dec 3 04:44:10 server1 kernel: [5105857.956112] Memory error not recovered
Dec 3 04:44:10 server1 kernel: [5105858.220111] MCE: Killing <process:PID> due to hardware memory corruption fault at 10ab458064

Example 3:

Jan 20 09:39:41 server2 kernel: [106912.808085] Disabling lock debugging due to kernel taint
Jan 20 09:39:41 server2 kernel: [106912.808181] [Hardware Error]: Machine check events logged
Jan 20 09:39:41 server2 kernel: [106912.808264] Uncorrected hardware memory error in user-access at f63ef7d300
Jan 20 09:39:41 server2 kernel: [106912.809617] MCE 0xf63ef7d: Killing <process:PID> due to hardware memory corruption
Jan 20 09:39:41 server2 kernel: [106912.809798] MCE 0xf63ef7d: dirty LRU page recovery: Recovered
Jan 20 09:39:41 server2 kernel: [106912.810001] MCE: Killing JobWrk0222:125751 due to hardware memory corruption fault at 7f4e5eb23330
Jan 20 09:39:53 server2 hpasmlited[3365]: CRITICAL: Uncorrectable Memory Error (Board 7, Memory Module 8)
Jan 20 09:39:53 server2 kernel: [106924.806296] [Hardware Error]: Machine check events logged
Jan 20 09:39:53 server2 kernel: [106924.806313] Uncorrected hardware memory error in user-access at d0e6d11f00
Jan 20 09:39:53 server2 kernel: [106924.806325] MCE 0xd0e6d11: corrupted page was clean: dropped without side effects

- SAP or any other process has crashed at the same time the logs are written


Read more...

Environment

Linux (any distribution)

Keywords

hardware memory corruption, MCE, memory corruption, Linux , KBA , BC-OP-LNX , Linux , Problem

About this page

This is a preview of a SAP Knowledge Base Article. Click more to access the full version on SAP ONE Support launchpad (Login required).

Search for additional results

Visit SAP Support Portal's SAP Notes and KBA Search.