Process & threads - Karmic vs past kernels
peter.matulis at canonical.com
Fri Mar 12 15:20:57 UTC 2010
Tim Gardner wrote:
> On 03/12/2010 07:17 AM, Peter Matulis wrote:
>> Chase Douglas wrote:
>>> On Wed, Mar 10, 2010 at 3:45 PM, Peter Matulis
>>> <peter.matulis at canonical.com> wrote:
>>>> Can anyone tell me whether the Karmic kernel has implemented a
>>>> way of what it considers a process (as opposed to threads)?
>>>> I have a situation where CPU load is zero on Karmic but considerably
>>>> higher in Jaunty and earlier.
>>>> The scenario is a single java process with many threads. The system
>>>> 4 cores and only one java process should logically produce a negligible
>>>> CPU load but why was this not the case with earlier kernels? Has
>>>> something changed in Karmic that would explain what I'm seeing?
>>> I doubt that to be the case. Have you been able to get more data for
>>> your bug ?
>>>  https://bugs.launchpad.net/ubuntu/+source/linux/+bug/513848
>> Yes, but I couldn't get as much CPU usage out of the Karmic test. My
>> 'top' results show the following:
>> Cpu1 : 0.3%us, 0.6%sy
>> Cpu2 : 2.4%us, 0.6%sy
>> Cpu3 : 9.1%us, 1.8%sy
>> Cpu4 : 16.0%us, 7.4%sy
>> With a load of 0.00 across the board.
>> Now since CPU1 has such a low usage it makes sense that load is
>> negligible since that CPU is always available. It seems that the
>> question is now:
>> Why the CPU usage is so much different between Karmic and Jaunty in this
>> (single process/multiple thread) scenario.
> There was a pretty major change in the process and I/O schedulers
> between Jaunty and Karmic. Lucid is different yet again.
Thanks Tim. Are you saying that the Karmic kernel is more efficient or
it's just a matter of how usage/load is reported (process/threads)?
Could you point me to the details concerning this change?
Peter Matulis | GPG 34F740E8
Ubuntu Support Team | Canonical Ltd. (canonical.com)
More information about the kernel-team