God,,, That was my mistake. Node1 Memory is not pinned well in the machine’s board.
From: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx [mailto:xen-devel-bounces@xxxxxxxxxxxxxxxxxxx] On Behalf Of Chulmin Kim
Sent: Thursday, February 10, 2011 3:36 PM
To: xen-devel@xxxxxxxxxxxxxxxxxxx
Subject: [Xen-devel] Problem with Memory Throughput Difference between Two Nodes(sockets)
Hi all,
I installed xen4.0.1-rc3 & 2.6.18.8 (dom0) on my machine (INTEL Xeon X5650, Westemere, 12cores, 6cores per socket, 2sockets, 12MB L3,.. )
I figured out after running SPECCPU 2006 Libquantum benchmark that two nodes have different throughput.
I set up 6vm on each node, and ran the workload in each VM.
VM in node1 got 1500sec exec time while VM in node2 got 1990sec exec time.
Previously, I also installed same xen version with 2.6.31 (dom0) pvops linux kernel. At that time, there was no such problem in same exp configuration.
Currently, I’m suspecting underutilization of LLC cache since the lowered dom0 kernel version.
Thanks for your attention!