Re: Performance test result between per-vhost kthread disable and enable

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



traffic with same bandwidth.
for example,both 1000 packets per second.


2010/11/23 Huang, Zhiteng <zhiteng.huang@xxxxxxxxx>:
> By same traffic load, do you mean same amount of packets or traffic with same bandwidth or anything else?
>
> Regards,
>
> HUANG, Zhiteng
>
>
>
> -----Original Message-----
> From: lidong chen [mailto:chen.lidong.kernel@xxxxxxxxx]
> Sent: Tuesday, November 23, 2010 2:53 PM
> To: Huang, Zhiteng
> Cc: tj@xxxxxxxxxx; sri@xxxxxxxxxx; mst@xxxxxxxxxx; Avi Kivity; kvm@xxxxxxxxxxxxxxx
> Subject: Re: Performance test result between per-vhost kthread disable and enable
>
> I used a special tool, this tool can send and receive packets parallelly.
> I set the tool to use the same traffic load.
> then i use the tool to test different version of kvm.
>
>
>
> 2010/11/23 Huang, Zhiteng <zhiteng.huang@xxxxxxxxx>:
>> Hi Lidong,
>>
>> What do you mean by 'send the same traffic load between...' ?
>>
>> See if my understanding is correct:
>> You have two identical physical machines (CPU/Memory/NIC...), one(A) runs RHEL6 Beta2(2.6.32-60) and the other one (B) runs RHEL6 (2.6.32-71).
>> Each machine booted 5 identical VMs and then VMs on machine A (pool A) paired up with VMs on machine B (pool B).  Sending packets between two VM pools yielded 20% utilization difference.
>>
>> Did you test bi-direction traffic, i.e. first pool A sends and pool B receives then vice versa?
>>
>> Regards,
>>
>> HUANG, Zhiteng
>>
>>
>>
>> -----Original Message-----
>> From: kvm-owner@xxxxxxxxxxxxxxx [mailto:kvm-owner@xxxxxxxxxxxxxxx] On
>> Behalf Of lidong chen
>> Sent: Tuesday, November 23, 2010 10:14 AM
>> To: tj@xxxxxxxxxx; sri@xxxxxxxxxx; mst@xxxxxxxxxx; Avi Kivity;
>> kvm@xxxxxxxxxxxxxxx
>> Subject: Performance test result between per-vhost kthread disable and
>> enable
>>
>> I test the performance between per-vhost kthread disable and enable.
>>
>> Test method:
>> Send the same traffic load between per-vhost kthread disable and enable, and compare the cpu rate of host os.
>> I run five vm on kvm, each of them have five nic.
>> the vhost version which per-vhost kthread disable we used is rhel6 beta 2(2.6.32.60).
>> the vhost version which per-vhost kthread enable we used is rhel6 (2.6.32-71).
>>
>> Test result:
>> with per-vhost kthread disable, the cpu rate of host os is 110%.
>> with per-vhost kthread enable, the cpu rate of host os is 130%.
>>
>> In 2.6.32.60,the whole system only have a kthread.
>> [root@rhel6-kvm1 ~]# ps -ef | grep vhost root       973     2  0 Nov22
>> ?        00:00:00 [vhost]
>>
>> In 2.6.32.71,the whole system have 25 kthread.
>> [root@kvm-4slot ~]# ps -ef | grep vhost- root     12896     2  0 10:26
>> ?        00:00:00 [vhost-12842] root     12897     2  0 10:26 ?
>> 00:00:00 [vhost-12842] root     12898     2  0 10:26 ?        00:00:00
>> [vhost-12842] root     12899     2  0 10:26 ?        00:00:00
>> [vhost-12842] root     12900     2  0 10:26 ?        00:00:00
>> [vhost-12842]
>>
>> root     13022     2  0 10:26 ?        00:00:00 [vhost-12981] root
>> 13023     2  0 10:26 ?        00:00:00 [vhost-12981] root     13024
>> 2  0 10:26 ?        00:00:00 [vhost-12981] root     13025     2  0
>> 10:26 ?        00:00:00 [vhost-12981] root     13026     2  0 10:26 ?
>> 00:00:00 [vhost-12981]
>>
>> root     13146     2  0 10:26 ?        00:00:00 [vhost-13088] root
>> 13147     2  0 10:26 ?        00:00:00 [vhost-13088] root     13148
>> 2  0 10:26 ?        00:00:00 [vhost-13088] root     13149     2  0
>> 10:26 ?        00:00:00 [vhost-13088] root     13150     2  0 10:26 ?
>> 00:00:00 [vhost-13088] ...
>>
>> Code difference:
>> In 2.6.32.60,in function vhost_init, create the kthread for vhost.
>> vhost_workqueue = create_singlethread_workqueue("vhost");
>>
>> In 2.6.32.71,in function vhost_dev_set_owner, create the kthread for each nic interface.
>> dev->wq = create_singlethread_workqueue(vhost_name);
>>
>> Conclusion:
>> with per-vhost kthread enable, the system can more throughput.
>> but deal the same traffic load with per-vhost kthread enable, it waste more cpu resource.
>>
>> In my application scene, the cpu resource is more important, and one kthread for deal with traffic load is enough.
>>
>> So i think we should add a param to control this.
>> for the CPU-bound system, this param disable per-vhost kthread.
>> for the I/O-bound system, this param enable per-vhost kthread.
>> the default value of this param is enable.
>>
>> If my opinion is right, i will give a patch for this.
>> --
>> To unsubscribe from this list: send the line "unsubscribe kvm" in the
>> body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at  http://vger.kernel.org/majordomo-info.html
>>
>
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html


[Index of Archives]     [KVM ARM]     [KVM ia64]     [KVM ppc]     [Virtualization Tools]     [Spice Development]     [Libvirt]     [Libvirt Users]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite Questions]     [Linux Kernel]     [Linux SCSI]     [XFree86]
  Powered by Linux