tech-kern archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

Re: netbsd-4 vs -current web server performance



On Wed, Sep 3, 2008 at 3:08 PM, Jeff Rizzo <riz%netbsd.org@localhost> wrote:
> Thor Lancelot Simon wrote:
>> On Tue, Sep 02, 2008 at 02:52:33PM -0700, Jeff Rizzo wrote:
>>
>>> Jeff Rizzo wrote:
>>>
>>>> Looking at both machines, the one running 4 was at its normal load -
>>>> between 4 and 5 - but the machine running -current had a load of about
>>>> 12, and many of the httpd processes were showing as 'parked' in top, and
>>>> there were no idle cpus. Restarting apache on the affected machine seems
>>>> to have brought things back to normal - both machines have a load just
>>>> under 3, and all CPUs (8 per box) have ~80% idle.
>>>>
>>>>
>>> By way of following up to myself, I just had to pull the -current
>>> machine out of the rotation for unrelated reasons (forgot to install an
>>> important package on it), and the load dropped away *except* for three
>>> httpd processes:
>>>
>>>   PID USERNAME PRI NICE   SIZE   RES STATE      TIME   WCPU    CPU COMMAND
>>>  4742 www       42    0    17M  314M parked/2 233:14 99.02% 99.02% httpd
>>>  3265 www       39    0    17M  266M parked/0 164:34 99.02% 99.02% httpd
>>>  8844 www       40    0    17M  298M parked/0 158:27 99.02% 99.02% httpd
>>>
>>
>> Parked *and* 100% of a CPU?
>>
>> That seems just wrong.
>>
>> Thor
>>
>
> I would tend to agree - but I don't know all that much about the new
> states.  This issue is fairly reproducible (within a few hours) - and
> also seems to go away (for a few hours) after restarting apache.  I have
> a couple weeks to get this fixed, since even at it's worst it's not too
> bad, and in any event I have multiple webservers.
>


Do the httpd's slowly increase until they get parked at 99% or do they
suddenly spike?

If it's a slow increase, could you start monitoring various stats like
the number of threads/PID, memory growth, etc?

If it's a sudden spike, is there a way you can run ktrace or something
until you can start to isolate the trigger?


Home | Main Index | Thread Index | Old Index