HP G6 ML350 Locks Up

[tech_guy]

We've got a bit of a headscratcher. One of our servers with Windows 2008 R2 - a HP G6 ML350 has randomly crashed twice now. The first time it simply restarted itself and the second time it completely locked up and needed a hard reset.

 

There's nothing in the logs except that the previous shutdown was unexpected.

 

All the latest updates are on.

 

HP USA have the diagnostic logs but so far haven't come up with anything.

 

A second machine that is almost identical and is in the same rack, connected to the same switch and UPS, is unaffected.

 

It's started in December where we saw laggy behaviour at first on the network.

 

We don't know if it's related but on three successive Thursdays now we've had slowness on that network. We can't see anything that happens on that day that might cause it. Thursdays are no different to any other day of the week for us.

 

Thoughts and ideas much appreciated!

[chazzy2501]

Have you done any firmware updates on the G6 ML350? I've done 2 sets in 4 years.

 

(VMware recommended before new ESXi updates)

 

August Update did a few things:

 

Problems Fixed:

 

Addressed a processor issue under which a rare and complex sequence of internal processor microarchitecture events that occur in specific operating environments could cause a server system to experience unexpected page faults, general protection faults, or machine check exceptions or other unpredictable system behavior. While all processors supported by this server have this issue, to be affected by this issue the server must be operating in a virtualized environment, have Intel Hyperthreading enabled, have a hypervisor that enables Intel VT FlexPriority and Extended Page Tables, and have a guest OS utilizing 32-bit PAE Paging Mode. This issue is not unique to HP ProLiant servers and could impact any system utilizing affected processors operating with the conditions listed above. This revision of the System ROM contains an updated version of Intel's microcode that addresses this issue. Due to the potential severity of the issue addressed in this revision of the System ROM, this System ROM upgrade is considered a critical fix.

Resolved an issue with the Intel Xeon Processor X5675, Intel Xeon Processor X5690, and Intel Xeon Processor X5687 where a rare and complex combination of data and environmental conditions may result in some instructions not executing properly causing unpredictable system behavior. This issue is not unique to HP ProLiant servers and could impact any system using the affected processors listed above. This revision of the System ROM contains and updated version of Intel's microcode that addresses this issue. This System ROM upgrade is considered a critical fix for customers utilizing the affected processors. This issue does not impact any processors that are not listed above.

 

Addressed an issue where the platform may experience networking issues under heavy workloads with Operating Systems, such as Linux RedHat 6.2, and IRQ Balancing enabled in the Operating System. As a result of this issue, software may lose interrupts, receive spurious interrupts or cause a network disconnect.

Edited January 31, 2014 by chazzy2501
more info