I don't know about your case, but in Zigor response I understood that some part of his code was using just one thread... AFAIK, if you have a single thread, you will use just one processor :-)
2011/10/24 Buğra Çakır <bug...@mobiliz.com.tr> > There is no way to scale on CPU's manually or setting any parameters. > May be I couldn't do that. But as I know and see that regardless of > whatever > you do at application level, JVM decides on the threading and scaling > policy. > > Note: I'm using Mina 1.1.7 with a highly loaded communication setup, > similar > Hardware as Zigor's and same CPU scheduling behaviour as Zigor's top > command > output. > > > -----Original Message----- > From: Zigor Salvador [mailto:zigorsalva...@gmail.com] > Sent: Monday, October 24, 2011 3:34 PM > To: users@mina.apache.org > Subject: Re: Performance (CPU use) > > Yes, I have just realized I won't improve performance until my 'routing > logic' code path is multithreaded. :-/ > > Your suggestion to check CPU utilization was really helpful, indeed. > > Thanks, > > Zigor. > > On 24 Oct 2011, at 14:07, Emmanuel Lecharny wrote: > > > On 10/24/11 2:01 PM, Zigor Salvador wrote: > >> Hi, > >> > >> I'm back with some more results. > >> > >> This is the typical load I'm seeing in the system when communication > throughput with MINA is maxed out. > > > > Strange. It seems like you only have one CPU working at 100% (CPU 9), > like > if it does all the work. > >> > >> I notice I'm only using around 10% of the available processing power. > >> > >> Zigor. > >> > >> top - 13:56:05 up 2:49, 2 users, load average: 0.28, 0.12, 0.14 > >> Tasks: 196 total, 2 running, 194 sleeping, 0 stopped, 0 zombie > >> Cpu0 : 0.3%us, 0.0%sy, 0.0%ni, 98.3%id, 0.0%wa, 0.0%hi, 1.3%si, > 0.0%st > >> Cpu1 : 4.5%us, 4.2%sy, 0.0%ni, 91.3%id, 0.0%wa, 0.0%hi, 0.0%si, > 0.0%st > >> Cpu2 : 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si, > 0.0%st > >> Cpu3 : 3.5%us, 4.1%sy, 0.0%ni, 92.4%id, 0.0%wa, 0.0%hi, 0.0%si, > 0.0%st > >> Cpu4 : 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si, > 0.0%st > >> Cpu5 : 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si, > 0.0%st > >> Cpu6 : 0.3%us, 0.0%sy, 0.0%ni, 99.7%id, 0.0%wa, 0.0%hi, 0.0%si, > 0.0%st > >> Cpu7 : 0.3%us, 0.3%sy, 0.0%ni, 99.4%id, 0.0%wa, 0.0%hi, 0.0%si, > 0.0%st > >> Cpu8 : 0.7%us, 0.0%sy, 0.0%ni, 99.3%id, 0.0%wa, 0.0%hi, 0.0%si, > 0.0%st > >> Cpu9 : 92.7%us, 5.0%sy, 0.0%ni, 1.0%id, 0.0%wa, 0.0%hi, 1.3%si, > 0.0%st > >> Cpu10 : 0.3%us, 0.0%sy, 0.0%ni, 99.7%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 : 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si, > 0.0%st > >> Cpu13 : 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si, > 0.0%st > >> Cpu14 : 14.0%us, 8.5%sy, 0.0%ni, 77.5%id, 0.0%wa, 0.0%hi, 0.0%si, > 0.0%st > >> Cpu15 : 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si, > 0.0%st > >> Mem: 24677232k total, 1123960k used, 23553272k free, 26644k buffers > >> Swap: 25101524k total, 0k used, 25101524k free, 285016k cached > >> > >> PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND > >> 3015 zigor 20 0 16.3g 171m 9808 S 9.2 0.7 17:28.95 java > >> 33 root 20 0 0 0 0 S 0.0 0.0 0:01.04 kworker/9:0 > >> 178 root 20 0 0 0 0 S 0.0 0.0 0:00.09 kworker/6:1 > >> 1571 zigor 20 0 27380 3068 868 S 0.0 0.0 0:03.34 dbus-daemon > >> 1691 zigor 20 0 198m 12m 9500 S 0.0 0.1 0:00.97 metacity > >> 1766 zigor 20 0 374m 19m 10m S 0.0 0.1 0:01.84 > unity-panel-ser > >> 3456 zigor 20 0 21568 1532 1084 R 0.0 0.0 0:01.60 top > >> 1 root 20 0 24184 2276 1344 S 0.0 0.0 0:02.34 init > >> 2 root 20 0 0 0 0 S 0.0 0.0 0:00.00 kthreadd > >> 3 root 20 0 0 0 0 S 0.0 0.0 0:00.20 ksoftirqd/0 > >> 6 root RT 0 0 0 0 S 0.0 0.0 0:00.00 migration/0 > >> 7 root RT 0 0 0 0 S 0.0 0.0 0:00.00 migration/1 > >> 8 root 20 0 0 0 0 S 0.0 0.0 0:00.00 kworker/1:0 > >> 9 root 20 0 0 0 0 S 0.0 0.0 0:00.00 ksoftirqd/1 > >> 10 root 20 0 0 0 0 S 0.0 0.0 0:01.82 kworker/0:1 > >> 11 root RT 0 0 0 0 S 0.0 0.0 0:00.00 migration/2 > > > > > > -- > > Regards, > > Cordialement, > > Emmanuel Lécharny > > www.iktek.com > > > >
