[Qemu-devel] Performance Profiling 2 VMs

[kalyan tata]

Hi All,

I am new to qemu development.

Sorry If this is not the correct forum for this question, it would be great if you could direct me to correct forum.

I am seeing very low virtio network throughput on an older (2.6.18) linux guest  vs another newer guest (3.10) both running on the same host. (same config 2 vcpus, no multi Q etc.)  I see very high CPU usage on the 2.6.18 guest at very low network throughput and want to profile to find bottleneck. 

I tried to use "perf kvm" but the analysis  shows overhead as  max .25 % where as top in VM shows 100% cpu. (I used following as a guide https://access.redhat.com/documentation/en-US/Red_Hat_Enterprise_Linux/6/html-single/Virtualization_Tuning_and_Optimization_Guide/index.html#sect-Virtualization_Tuning_Optimization_Guide-Monitoring_Tools-perf_kvm)

     0.25%  :5235    [uhci_hcd]        [g] 0xffffffff80182236

     0.24%  :5235    [uhci_hcd]        [g] 0xffffffff8018226a

     0.23%  :5235    [virtio_ring]     [g] vring_new_virtqueue

     0.20%  :5236    [uhci_hcd]        [g] 0xffffffff80182236

     0.18%  :5236    [uhci_hcd]        [g] 0xffffffff8018226a

     0.18%  :5235    [uhci_hcd]        [g] 0xffffffff8016f385

     0.14%  :5236    [uhci_hcd]        [g] 0xffffffff802fbe0f

     0.14%  :5235    [uhci_hcd]        [g] 0xffffffff8001161a

     0.14%  :5235    [virtio_ring]     [g] virtqueue_is_broken

My basic question is - Is there a way I can profile the older version of linux guest so i can see the bottleneck (where the guest is spending CPU cycles) My aim is to see if i can patch the older version in the critical path with improvements made in newer version

Thanks 

Kal