true,
 
if I get a chance I will, but I was hammering the system at the time with lots 
of inserts so I am kind of not all that surprised.



> Date: Wed, 30 Jul 2008 13:22:20 -0400> From: [EMAIL PROTECTED]> To: 
> [email protected]> Subject: Re: [Sequoia] Sequoia process 
> CPU too big in Load Tests> > Adam Purkiss wrote:> > I too have seen this kind 
> of cpu load from sequoia (with mysql running > > at about 80%)> It would be 
> interesting to run the profiling as well in that case.> There are a number of 
> reasons that could be the cause for a high cpu usage:> - improper JVM memory 
> settings leading to GC hyperactivity> - bad caching settings> - problems in 
> network stack configuration (group communication, Nagle > algorithm on some 
> platforms...)> - problems in the database JDBC driver> - operating system 
> scheduler with a large number of threads> > Without more information about 
> the setup and some basic profiling it > will hard to diagnose what is exactly 
> going on.> > Thanks for your interest in Sequoia,> Emmanuel> > >> > 
> ------------------------------------------------------------------------> > > 
> Date: Wed, 30 Jul 2008 12:37:58 -0400> > > From: [EMAIL PROTECTED]> > > To: 
> [email protected]> > > Subject: Re: [Sequoia] Sequoia 
> process CPU too big in Load Tests> > > CC: [EMAIL PROTECTED]; > > [EMAIL 
> PROTECTED]; > > [EMAIL PROTECTED]; > > [EMAIL PROTECTED]; > > [EMAIL 
> PROTECTED]; > > [EMAIL PROTECTED]> > >> > > Hi Toni,> > >> > > It would be 
> interesting to know where Sequoia actually spends its time.> > > Could you 
> turn the CPU profiling in the JVM to get an idea of what is> > > going on?> > 
> > Also what does your configuration look like?> > >> > > Thanks for the 
> feedback,> > > Emmanuel> > > >> > > > We are doing some load test of on 
> product using JBOSS, Sequoia and> > > > MySQL, and in our test we have notice 
> that sequoia get a very big,> > > > big, big quantity of CPU...> > > >> > > > 
> Look top in machine where the service is processes ( nearly > > 150%cpu ),> > 
> > > we are talking about servers with 2 CPUS :> > > >> > > >> > > > top - 
> 14:36:31 up 25 days, 22:28, 2 users, load average: 6.87, 6.53,> > > > 3.66> > 
> > > Tasks: 104 total, 1 running, 103 sleeping, 0 stopped, 0 zombie> > > > 
> Cpu(s): 59.0% us, 8.1% sy, 0.0% ni, 29.6% id, 0.7% wa, 0.3% hi,> > > > 2.3% 
> si> > > > Mem: 8164704k total, 5899548k used, 2265156k free, 387168k buffers> 
> > > > Swap: 8385920k total, 0k used, 8385920k free, 3190788k cached> > > >> > 
> > > PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+> > > > COMMAND> > > > 26562 
> sequoia 17 0 2010m 366m 14m S 150 4.6 16:28.59> > > > java> > > > 5809 jboss 
> 25 0 2049m 1.1g 73m S 89 14.7 11:55.62> > > > java> > > > 21342 mysql 16 0 
> 544m 371m 4872 S 37 4.7 43:01.14> > > > mysqld> > > >> > > > And this in the 
> BE which is not processing any traffic :> > > >> > > > top - 14:42:00 up 25 
> days, 22:33, 2 users, load average: 3.99, 4.57,> > > > 3.67> > > > Tasks: 104 
> total, 1 running, 103 sleeping, 0 stopped, 0 zombie> > > > Cpu(s): 36.8% us, 
> 5.2% sy, 0.0% ni, 54.9% id, 0.4% wa, 0.3% hi,> > > > 2.3% si> > > > Mem: 
> 8164704k total, 5968124k used, 2196580k free, 387396k buffers> > > > Swap: 
> 8385920k total, 0k used, 8385920k free, 3262028k cached> > > >> > > > PID 
> USER PR NI VIRT RES SHR S %CPU %MEM TIME+> > > > COMMAND> > > > 26562 sequoia 
> 17 0 1966m 365m 14m S 141 4.6 22:42.70> > > > java> > > > 21342 mysql 16 0 
> 545m 371m 4872 S 35 4.7 44:32.83 mysqld> > > >> > > -- > Emmanuel Cecchet> 
> FTO @ Frog Thinker > Open Source Development & Consulting> --> Web: 
> http://www.frogthinker.org> email: [EMAIL PROTECTED]> Skype: 
> emmanuel_cecchet> > _______________________________________________> Sequoia 
> mailing list> [email protected]> 
> https://forge.continuent.org/mailman/listinfo/sequoia
_________________________________________________________________
If you like crossword puzzles, then you'll love Flexicon, a game which combines 
four overlapping crossword puzzles into one!
http://g.msn.ca/ca55/208
_______________________________________________
Sequoia mailing list
[email protected]
https://forge.continuent.org/mailman/listinfo/sequoia

Reply via email to