* MPI benchmark performance gap between native linux and domU
@ 2005-04-04 22:43 xuehai zhang
0 siblings, 0 replies; 4+ messages in thread
From: xuehai zhang @ 2005-04-04 22:43 UTC (permalink / raw)
To: xen-devel
Hi all,
I did the following experiments to explore the MPI application execution performance
on both native linux machines and inside of unpriviledged Xen user domains. I use 8
machines with identical HW configurations (498.756 MHz dual CPU, 512MB memory, on a
10MB/sec LAN) and I use Pallas MPI Benchmarks (PMB).
Experiment 1: I boot all 8 nodes with native linux (nosmp, kernel 2.4.29) and use all
of them for PMB tests.
Experiment 2: I boot all 8 nodes with Xen running and start a single user domain
(port 2.6.10,using file-backed VBD) on each node with 360MB memory. Then I run the
same PMB tests among these 8 user domains.
The expreiment results show, running a same MPI benchmark in user domains usually
results in a worse (sometimes very bad) performance comparing with on native
linux machines. The following are the results for PMB SendRecv benchmark for both
experiments (table1 and table2 report throughput and latency respectively). As you may
notice, SendRecv can achieve a 14.9MB/sec throughput on native linux machines but can
get a maximum 7.07 MB/sec throughput if running inside of user domains. The latency
results also have big gap.
Clearly, there is difference between the memory used in the native linux machine of
Experiment 1 (512MB) and in the user domain (360MB, can not go higher because dom0
started with 128MB memory) of Experiment 2. However, I don't think it is the main
cause of the performance gap because the tested message sizes are much smaller than
both memory sizes.
I will appreciate your help if you had the similar experience and wanna share your
insights.
BTW, if you are not familar with PMB SendRecv benchmark, you can find a detailed
explaination at http://people.cs.uchicago.edu/~hai/PMB-MPI1.pdf (see section 4.3.1).
Thanks in advance for you help.
Xuehai
P.S. Table 1: SendRecv throughput (MB/sec) performance
Message_Size(bytes) Experiment_1 Experiment_2
0 0 0
1 0 0
2 0 0
4 0 0
8 0.04 0.01
16 0.16 0.01
32 0.34 0.02
64 0.65 0.04
128 1.17 0.09
256 2.15 0.59
512 3.4 1.23
1K 5.29 2.57
2K 7.68 3.5
4K 10.7 4.96
8K 13.35 7.07
16K 14.9 3.77
32K 9.85 3.68
64K 5.06 3.02
128K 7.91 4.94
256K 7.85 5.25
512K 7.93 6.11
1M 7.85 6.5
2M 8.18 5.44
4M 7.55 4.93
Table 2: SendRecv latency (millisec) performance
Message_Size(bytes) Experiment_1 Experiment_2
0 1979.6 3010.96
1 1724.16 3218.88
2 1669.65 3185.3
4 1637.26 3055.67
8 406.77 2966.17
16 185.76 2777.89
32 181.06 2791.06
64 189.12 2940.82
128 210.51 2716.3
256 227.36 843.94
512 287.28 796.71
1K 368.72 758.19
2K 508.65 1144.24
4K 730.59 1612.66
8K 1170.22 2471.65
16K 2096.86 8300.18
32K 6340.45 17017.99
64K 24640.78 41264.5
128K 31709.09 50608.97
256K 63680.67 94918.13
512K 125531.7 162168.47
1M 251566.94 321451.02
2M 477431.32 707981
4M 997768.35 1503987.61
^ permalink raw reply [flat|nested] 4+ messages in thread
* MPI benchmark performance gap between native linux and domU
@ 2005-04-04 23:18 xuehai zhang
2005-04-04 23:37 ` Nivedita Singhvi
0 siblings, 1 reply; 4+ messages in thread
From: xuehai zhang @ 2005-04-04 23:18 UTC (permalink / raw)
To: Xen-devel
Hi all,
I did the following experiments to explore the MPI application execution performance
on both native linux machines and inside of unpriviledged Xen user domains. I use 8
machines with identical HW configurations (498.756 MHz dual CPU, 512MB memory, on a
10MB/sec LAN) and I use Pallas MPI Benchmarks (PMB).
Experiment 1: I boot all 8 nodes with native linux (nosmp, kernel 2.4.29) and use all
of them for PMB tests.
Experiment 2: I boot all 8 nodes with Xen running and start a single user domain
(port 2.6.10,using file-backed VBD) on each node with 360MB memory. Then I run the
same PMB tests among these 8 user domains.
The expreiment results show, running a same MPI benchmark in user domains usually
results in a worse (sometimes very bad) performance comparing with on native
linux machines. The following are the results for PMB SendRecv benchmark for both
experiments (table1 and table2 report throughput and latency respectively). As you may
notice, SendRecv can achieve a 14.9MB/sec throughput on native linux machines but can
get a maximum 7.07 MB/sec throughput if running inside of user domains. The latency
results also have big gap.
Clearly, there is difference between the memory used in the native linux machine of
Experiment 1 (512MB) and in the user domain (360MB, can not go higher because dom0
started with 128MB memory) of Experiment 2. However, I don't think it is the main
cause of the performance gap because the tested message sizes are much smaller than
both memory sizes.
I will appreciate your help if you had the similar experience and wanna share your
insights.
BTW, if you are not familar with PMB SendRecv benchmark, you can find a detailed
explaination at http://people.cs.uchicago.edu/~hai/PMB-MPI1.pdf (see section 4.3.1).
Thanks in advance for you help.
Xuehai
P.S. Table 1: SendRecv throughput (MB/sec) performance
Message_Size(bytes) Experiment_1 Experiment_2
0 0 0
1 0 0
2 0 0
4 0 0
8 0.04 0.01
16 0.16 0.01
32 0.34 0.02
64 0.65 0.04
128 1.17 0.09
256 2.15 0.59
512 3.4 1.23
1K 5.29 2.57
2K 7.68 3.5
4K 10.7 4.96
8K 13.35 7.07
16K 14.9 3.77
32K 9.85 3.68
64K 5.06 3.02
128K 7.91 4.94
256K 7.85 5.25
512K 7.93 6.11
1M 7.85 6.5
2M 8.18 5.44
4M 7.55 4.93
Table 2: SendRecv latency (millisec) performance
Message_Size(bytes) Experiment_1 Experiment_2
0 1979.6 3010.96
1 1724.16 3218.88
2 1669.65 3185.3
4 1637.26 3055.67
8 406.77 2966.17
16 185.76 2777.89
32 181.06 2791.06
64 189.12 2940.82
128 210.51 2716.3
256 227.36 843.94
512 287.28 796.71
1K 368.72 758.19
2K 508.65 1144.24
4K 730.59 1612.66
8K 1170.22 2471.65
16K 2096.86 8300.18
32K 6340.45 17017.99
64K 24640.78 41264.5
128K 31709.09 50608.97
256K 63680.67 94918.13
512K 125531.7 162168.47
1M 251566.94 321451.02
2M 477431.32 707981
4M 997768.35 1503987.61
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: MPI benchmark performance gap between native linux and domU
2005-04-04 23:18 MPI benchmark performance gap between native linux and domU xuehai zhang
@ 2005-04-04 23:37 ` Nivedita Singhvi
2005-04-05 4:49 ` xuehai zhang
0 siblings, 1 reply; 4+ messages in thread
From: Nivedita Singhvi @ 2005-04-04 23:37 UTC (permalink / raw)
To: xuehai zhang; +Cc: Xen-devel
xuehai zhang wrote:
> Experiment 1: I boot all 8 nodes with native linux (nosmp, kernel
> 2.4.29) and use all
> Experiment 2: I boot all 8 nodes with Xen running and start a single
> user domain
> (port 2.6.10,using file-backed VBD) on each node with 360MB memory. Then
What do you get when you compare 2.4.29 native Linux
against 2.6.10 native Linux, without Xen involved at
all?
thanks,
Nivedita
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: MPI benchmark performance gap between native linux and domU
2005-04-04 23:37 ` Nivedita Singhvi
@ 2005-04-05 4:49 ` xuehai zhang
0 siblings, 0 replies; 4+ messages in thread
From: xuehai zhang @ 2005-04-05 4:49 UTC (permalink / raw)
To: Nivedita Singhvi; +Cc: Xen-devel
Nivedita Singhvi wrote:
> xuehai zhang wrote:
>
>
>> Experiment 1: I boot all 8 nodes with native linux (nosmp, kernel
>> 2.4.29) and use all
>
>
>> Experiment 2: I boot all 8 nodes with Xen running and start a single
>> user domain
>> (port 2.6.10,using file-backed VBD) on each node with 360MB memory. Then
>
>
>
> What do you get when you compare 2.4.29 native Linux
> against 2.6.10 native Linux, without Xen involved at
> all?
2.6.10 is not for native Linux but for domU (Xen is running on the machine).
Xuehai
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2005-04-05 4:49 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2005-04-04 23:18 MPI benchmark performance gap between native linux and domU xuehai zhang
2005-04-04 23:37 ` Nivedita Singhvi
2005-04-05 4:49 ` xuehai zhang
-- strict thread matches above, loose matches on Subject: below --
2005-04-04 22:43 xuehai zhang
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.