You are viewing a plain text version of this content. The canonical link for it is here.
Posted to users@activemq.apache.org by Tiger_ <ya...@163.com> on 2010/06/09 16:02:18 UTC
Why does ActiveMQ's performance on server so poor?
Hi everybody,
I test ActiveMQ on my PC (Core2 E8400, 2G RAM, CentOS 64,
jdk1.6_0_20_x86_64), the throughput is about 1200msgs/sec(persistent) or
7000msgs/sec(Non-persistent).
But on my server (Xeon E7420 * 4, 16G RAM, CentOS 64, jdk1.6_0_20_x86_64),
the throughput is about 90msgs/sec(persistent) or
150msgs/sec(Non-persistent).
And I found I/O blocking on one core.
top - 05:31:12 up 22:30, 5 users, load average: 1.72, 1.77, 1.71
Tasks: 301 total, 1 running, 299 sleeping, 1 stopped, 0 zombie
Cpu0 : 0.7%us, 0.0%sy, 0.0%ni, 99.3%id, 0.0%wa, 0.0%hi, 0.0%si,
0.0%st
Cpu1 : 0.3%us, 0.3%sy, 0.0%ni, 99.3%id, 0.0%wa, 0.0%hi, 0.0%si,
0.0%st
Cpu2 : 0.3%us, 0.0%sy, 0.0%ni, 99.7%id, 0.0%wa, 0.0%hi, 0.0%si,
0.0%st
Cpu3 : 1.0%us, 0.0%sy, 0.0%ni, 99.0%id, 0.0%wa, 0.0%hi, 0.0%si,
0.0%st
Cpu4 : 0.3%us, 0.0%sy, 0.0%ni, 99.7%id, 0.0%wa, 0.0%hi, 0.0%si,
0.0%st
Cpu5 : 0.7%us, 0.3%sy, 0.0%ni, 1.3%id, 97.3%wa, 0.0%hi, 0.3%si,
0.0%st
Cpu6 : 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si,
0.0%st
Cpu7 : 0.3%us, 0.0%sy, 0.0%ni, 99.3%id, 0.0%wa, 0.0%hi, 0.3%si,
0.0%st
Cpu8 : 0.3%us, 0.0%sy, 0.0%ni, 99.7%id, 0.0%wa, 0.0%hi, 0.0%si,
0.0%st
Cpu9 : 0.3%us, 0.0%sy, 0.0%ni, 99.0%id, 0.3%wa, 0.0%hi, 0.3%si,
0.0%st
Cpu10 : 1.0%us, 0.3%sy, 0.0%ni, 98.7%id, 0.0%wa, 0.0%hi, 0.0%si,
0.0%st
Cpu11 : 0.3%us, 0.0%sy, 0.0%ni, 99.7%id, 0.0%wa, 0.0%hi, 0.0%si,
0.0%st
Cpu12 : 0.7%us, 0.0%sy, 0.0%ni, 99.3%id, 0.0%wa, 0.0%hi, 0.0%si,
0.0%st
Cpu13 : 0.3%us, 0.0%sy, 0.0%ni, 99.7%id, 0.0%wa, 0.0%hi, 0.0%si,
0.0%st
Cpu14 : 0.3%us, 0.7%sy, 0.0%ni, 99.0%id, 0.0%wa, 0.0%hi, 0.0%si,
0.0%st
Cpu15 : 2.0%us, 0.7%sy, 0.0%ni, 97.3%id, 0.0%wa, 0.0%hi, 0.0%si,
0.0%st
--
View this message in context: http://old.nabble.com/Why-does-ActiveMQ%27s-performance-on-server-so-poor--tp28830825p28830825.html
Sent from the ActiveMQ - User mailing list archive at Nabble.com.
Re: Why does ActiveMQ's performance on server so poor?
Posted by Gary Tully <ga...@gmail.com>.
difference in fsync behavior? see:
http://old.nabble.com/slow-KahaDB-access-td26172918.html#a26213644
On 9 June 2010 15:02, Tiger_ <ya...@163.com> wrote:
>
> Hi everybody,
> I test ActiveMQ on my PC (Core2 E8400, 2G RAM, CentOS 64,
> jdk1.6_0_20_x86_64), the throughput is about 1200msgs/sec(persistent) or
> 7000msgs/sec(Non-persistent).
>
> But on my server (Xeon E7420 * 4, 16G RAM, CentOS 64, jdk1.6_0_20_x86_64),
> the throughput is about 90msgs/sec(persistent) or
> 150msgs/sec(Non-persistent).
>
> And I found I/O blocking on one core.
>
> top - 05:31:12 up 22:30, 5 users, load average: 1.72, 1.77, 1.71
> Tasks: 301 total, 1 running, 299 sleeping, 1 stopped, 0 zombie
> Cpu0 : 0.7%us, 0.0%sy, 0.0%ni, 99.3%id, 0.0%wa, 0.0%hi, 0.0%si,
> 0.0%st
> Cpu1 : 0.3%us, 0.3%sy, 0.0%ni, 99.3%id, 0.0%wa, 0.0%hi, 0.0%si,
> 0.0%st
> Cpu2 : 0.3%us, 0.0%sy, 0.0%ni, 99.7%id, 0.0%wa, 0.0%hi, 0.0%si,
> 0.0%st
> Cpu3 : 1.0%us, 0.0%sy, 0.0%ni, 99.0%id, 0.0%wa, 0.0%hi, 0.0%si,
> 0.0%st
> Cpu4 : 0.3%us, 0.0%sy, 0.0%ni, 99.7%id, 0.0%wa, 0.0%hi, 0.0%si,
> 0.0%st
> Cpu5 : 0.7%us, 0.3%sy, 0.0%ni, 1.3%id, 97.3%wa, 0.0%hi, 0.3%si,
> 0.0%st
> Cpu6 : 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si,
> 0.0%st
> Cpu7 : 0.3%us, 0.0%sy, 0.0%ni, 99.3%id, 0.0%wa, 0.0%hi, 0.3%si,
> 0.0%st
> Cpu8 : 0.3%us, 0.0%sy, 0.0%ni, 99.7%id, 0.0%wa, 0.0%hi, 0.0%si,
> 0.0%st
> Cpu9 : 0.3%us, 0.0%sy, 0.0%ni, 99.0%id, 0.3%wa, 0.0%hi, 0.3%si,
> 0.0%st
> Cpu10 : 1.0%us, 0.3%sy, 0.0%ni, 98.7%id, 0.0%wa, 0.0%hi, 0.0%si,
> 0.0%st
> Cpu11 : 0.3%us, 0.0%sy, 0.0%ni, 99.7%id, 0.0%wa, 0.0%hi, 0.0%si,
> 0.0%st
> Cpu12 : 0.7%us, 0.0%sy, 0.0%ni, 99.3%id, 0.0%wa, 0.0%hi, 0.0%si,
> 0.0%st
> Cpu13 : 0.3%us, 0.0%sy, 0.0%ni, 99.7%id, 0.0%wa, 0.0%hi, 0.0%si,
> 0.0%st
> Cpu14 : 0.3%us, 0.7%sy, 0.0%ni, 99.0%id, 0.0%wa, 0.0%hi, 0.0%si,
> 0.0%st
> Cpu15 : 2.0%us, 0.7%sy, 0.0%ni, 97.3%id, 0.0%wa, 0.0%hi, 0.0%si,
> 0.0%st
> --
> View this message in context:
> http://old.nabble.com/Why-does-ActiveMQ%27s-performance-on-server-so-poor--tp28830825p28830825.html
> Sent from the ActiveMQ - User mailing list archive at Nabble.com.
>
>
--
http://blog.garytully.com
Open Source Integration
http://fusesource.com
Re: Why does ActiveMQ's performance on server so poor?
Posted by Tiger_ <ya...@163.com>.
When I benchmark my server I'm seeing this:
Writes:
511997 writes of size 4096 written in 10.945 seconds.
46779.08 writes/second.
182.73077 megs/second.
Sync Writes:
1642 writes of size 4096 written in 10.004 seconds.
164.13435 writes/second.
0.6411498 megs/second.
Reads:
2518572 reads of size 4096 read in 10.001 seconds.
251832.02 writes/second.
983.7188 megs/second.
But on my pc, the sync writes is about 50 times of on the server.
--
View this message in context: http://old.nabble.com/Why-does-ActiveMQ%27s-performance-on-server-so-poor--tp28830825p28838954.html
Sent from the ActiveMQ - User mailing list archive at Nabble.com.