Home / server / Questions / 245361
Accepted
Josh
Asked: 2011-03-10 11:33:00 +0800 CST

How can I correct the NUMA setup of the memory on my server?

  • 772

I am trying to install VMware ESXi onto a new dedicated server. However, when I boot from the VMware ESXi Installer CD, I am given the following error:

The BIOS reports that NUMA node 1 has no memory.

The system has found a problem on your machine and cannot continue.

The BIOS reports that NUMA node 1 has no memory. This problem is either caused by a bad BIOS or a very unbalanced distribution of memory modules.

How can I resolve this error? Here are the specs of the machine:

  • Custom hardware assembled by my datacenter (I.E. not name brand like Dell, etc)
  • AMD Quad Opteron(tm) Processor 6128 8-core (32 total cores)
  • Supermicro H8QG6/H8QGi
  • 24GB DDR3 RAM
  • 4 physical CPUs
  • Most likely 4x 6GB DIMMs, could be different.

Here's some more info I can obtain from the commandline:

 [root@host ~]# cat /proc/cpuinfo 
 processor  : 0
 vendor_id  : AuthenticAMD
 cpu family : 16
 model      : 9
 model name : AMD Opteron(tm) Processor 6128
 stepping   : 1
 cpu MHz        : 800.000
 cache size : 512 KB
 physical id    : 1
 siblings   : 8
 core id        : 0
 cpu cores  : 8
 apicid     : 16
 fpu        : yes
 fpu_exception  : yes
 cpuid level    : 5
 wp     : yes
 flags      : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc nonstop_tsc pni cx16 popcnt lahf_lm cmp_legacy svm extapic cr8_legacy altmovcr8 abm sse4a misalignsse 3dnowprefetch osvw
 bogomips   : 4000.05
 TLB size   : 1024 4K pages
 clflush size   : 64
 cache_alignment    : 64
 address sizes  : 48 bits physical, 48 bits virtual
 power management: ts ttp tm stc 100mhzsteps hwpstate [8]

 processor  : 1
 vendor_id  : AuthenticAMD
 cpu family : 16
 model      : 9
 model name : AMD Opteron(tm) Processor 6128
 stepping   : 1
 cpu MHz        : 800.000
 cache size : 512 KB
 physical id    : 1
 siblings   : 8
 core id        : 1
 cpu cores  : 8
 apicid     : 17
 fpu        : yes
 fpu_exception  : yes
 cpuid level    : 5
 wp     : yes
 flags      : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc nonstop_tsc pni cx16 popcnt lahf_lm cmp_legacy svm extapic cr8_legacy altmovcr8 abm sse4a misalignsse 3dnowprefetch osvw
 bogomips   : 4000.04
 TLB size   : 1024 4K pages
 clflush size   : 64
 cache_alignment    : 64
 address sizes  : 48 bits physical, 48 bits virtual
 power management: ts ttp tm stc 100mhzsteps hwpstate [8]

 ...

 processor  : 31
 vendor_id  : AuthenticAMD
 cpu family : 16
 model      : 9
 model name : AMD Opteron(tm) Processor 6128
 stepping   : 1
 cpu MHz        : 800.000
 cache size : 512 KB
 physical id    : 4
 siblings   : 8
 core id        : 3
 cpu cores  : 8
 apicid     : 71
 fpu        : yes
 fpu_exception  : yes
 cpuid level    : 5
 wp     : yes
 flags      : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc nonstop_tsc pni cx16 popcnt lahf_lm cmp_legacy svm extapic cr8_legacy altmovcr8 abm sse4a misalignsse 3dnowprefetch osvw
 bogomips   : 3999.74
 TLB size   : 1024 4K pages
 clflush size   : 64
 cache_alignment    : 64
 address sizes  : 48 bits physical, 48 bits virtual
 power management: ts ttp tm stc 100mhzsteps hwpstate [8]
memory vmware-esxi numa

1 Answers

  1. Best Answer

    With all four CPU sockets full you have to be careful you you load out the memory modules.

    HERE is a link to the mobo's memory loadout guideslines, as you can see in table 3 you need to have either 16 or 32 DIMMS in that configuration, so given you have 24GB in there currently you basically you need to either add or remove 8 x 1GB modules, or move things around to fix that model.

    • 8