And if you increase beyond 4 threads?  How does the parallel collector
do by comparison?

On Thu, May 6, 2010 at 1:38 PM, Matt Fowles <[email protected]> wrote:
> Andrew~
>
> Absolutely.
>
> 1+2) I have not done anything.  So they should be on the defaults.
> 3) The system is a 16-core (4 quad-core cpus) with an insane amount of
> ram (~128g)
>
> Matt
>
> On Thu, May 6, 2010 at 12:57 PM, Andrew Oliver <[email protected]> wrote:
>> Some quick stupid questions:
>>
>> 1. You haven't disabled TLAB (mainly this is not YG)?
>> 2. You have enabled the biased locking?
>> 3. You either have the cores for parallel (and don't have any silly
>> thing taking up the extra cores) or have switched to single or reduced
>> the number of threads?
>>
>> -Andy
>>
>> On Thu, May 6, 2010 at 12:23 PM, Matt Fowles <[email protected]> wrote:
>>> Charles~
>>>
>>> I have tried tweaking young gen sizes, both above and below the 4g I
>>> settled on.  Basically what you expect happens, as you increase young
>>> gen sizes you get less frequent longer runs.  As you decrease young
>>> gen you get more frequent shorter runs.  However, the decrease in
>>> sweep time from 4g to 2g is approximately 400ms to 300ms for the
>>> initial steady state, but they both display the growing GC times.
>>>
>>> We don't do anything with finalizers or soft references.
>>>
>>> Also, I have tried just letting the GC ergonomics let it decide all
>>> the sizes with a 50ms latency budget.  It ends up destroying itself
>>> continuously running GC.
>>>
>>> Matt
>>>
>>> On Wed, May 5, 2010 at 2:28 PM, Charles Oliver Nutter
>>> <[email protected]> wrote:
>>>> Ok, my next thought would be that your young generation is perhaps too
>>>> big? I'm sure you've probably tried choking it down and letting GC run
>>>> more often against a smaller young heap?
>>>>
>>>> If GC times for young gen are getting longer, something has to be
>>>> changing. Finalizers? Weak/SoftReferences? You say you're not getting
>>>> to the point of CMS running, but a large young gen can still take a
>>>> long time to collect. Do less more often?
>>>>
>>>> On Wed, May 5, 2010 at 9:25 AM, Matt Fowles <[email protected]> wrote:
>>>>> Charles~
>>>>>
>>>>> I settled on that after having run experiments varying the survivor
>>>>> ratio and tenuring threshold.  In the end, I discovered that >99.9% of
>>>>> the young garbage got caught with this and each extra young gen run
>>>>> only reclaimed about 1% of the previously surviving objects.  So it
>>>>> seemed like the trade off just wasn't winning me anything.
>>>>>
>>>>> Matt
>>>>>
>>>>> On Tue, May 4, 2010 at 6:50 PM, Charles Oliver Nutter
>>>>> <[email protected]> wrote:
>>>>>> Why are you using -XX:MaxTenuringThreshold=0? That's basically forcing
>>>>>> all objects that survive one collection to immediately be promoted,
>>>>>> even if they just happen to be a slightly longer-lived young object.
>>>>>> Using 0 seems like a bad idea.
>>>>>>
>>>>>> On Tue, May 4, 2010 at 4:46 PM, Matt Fowles <[email protected]> 
>>>>>> wrote:
>>>>>>> All~
>>>>>>>
>>>>>>> I have a large app that produces ~4g of garbage every minute and am
>>>>>>> trying to reduce the size of gc outliers.  About 99% of this data is
>>>>>>> garbage, but almost anything that survives one collection survives for
>>>>>>> an indeterminately long amount of time.  We are currently using the
>>>>>>> following VM and options
>>>>>>>
>>>>>>>
>>>>>>> java version "1.6.0_16"
>>>>>>> Java(TM) SE Runtime Environment (build 1.6.0_16-b01)
>>>>>>> Java HotSpot(TM) 64-Bit Server VM (build 14.2-b01, mixed mode)
>>>>>>>
>>>>>>> -verbose:gc
>>>>>>> -Xms32g -Xmx32g -Xmn4g
>>>>>>> -XX:+UseParNewGC
>>>>>>> -XX:ParallelGCThreads=4
>>>>>>> -XX:+UseConcMarkSweepGC
>>>>>>> -XX:ParallelCMSThreads=4
>>>>>>> -XX:MaxTenuringThreshold=0
>>>>>>> -XX:SurvivorRatio=20000
>>>>>>> -XX:CMSInitiatingOccupancyFraction=60
>>>>>>> -XX:+UseCMSInitiatingOccupancyOnly
>>>>>>> -XX:+CMSParallelRemarkEnabled
>>>>>>> -XX:MaxGCPauseMillis=50
>>>>>>> -Xloggc:gc.log
>>>>>>>
>>>>>>>
>>>>>>>
>>>>>>> As you can see from the GC log, we never actually reach the point
>>>>>>> where the CMS kicks in (after app startup).  But our young gens seem
>>>>>>> to take increasingly long to collect as time goes by.
>>>>>>>
>>>>>>> One of the major metrics we have for measuring this system is latency
>>>>>>> as measured from connected clients and as measured internally.  You
>>>>>>> can see an attached graph of latency vs time for the clients.  It is
>>>>>>> not surprising the the internal latency (green and labeled 'sb') is
>>>>>>> not as large as the network latency.  I assume this is in part because
>>>>>>> VM safe points are less likely to occur within our internal timing
>>>>>>> markers.  But, one can easily see how the external latency
>>>>>>> measurements (blue and labeled 'network') display the same steady
>>>>>>> increase in times.
>>>>>>>
>>>>>>> My hope is to be able to tweak young gen size and trade off GC
>>>>>>> frequency with pause length; however, the steadily increasing GC times
>>>>>>> are proving to persist regardless of the size that I make the young
>>>>>>> generation.
>>>>>>>
>>>>>>> Has anyone seen this sort of behavior before?  Are there more switches
>>>>>>> that I should try running with?
>>>>>>>
>>>>>>> Obviously, I am working to profile the app and reduce the garbage load
>>>>>>> in parallel.  But if I still see this sort of problem, it is only a
>>>>>>> question of how long must the app run before I see unacceptable
>>>>>>> latency spikes.
>>>>>>>
>>>>>>> Matt
>>>>>>>
>>>>>>> --
>>>>>>> You received this message because you are subscribed to the Google 
>>>>>>> Groups "JVM Languages" group.
>>>>>>> To post to this group, send email to [email protected].
>>>>>>> To unsubscribe from this group, send email to 
>>>>>>> [email protected].
>>>>>>> For more options, visit this group at 
>>>>>>> http://groups.google.com/group/jvm-languages?hl=en.
>>>>>>>
>>>>>>>
>>>>>>
>>>>>> --
>>>>>> You received this message because you are subscribed to the Google 
>>>>>> Groups "JVM Languages" group.
>>>>>> To post to this group, send email to [email protected].
>>>>>> To unsubscribe from this group, send email to 
>>>>>> [email protected].
>>>>>> For more options, visit this group at 
>>>>>> http://groups.google.com/group/jvm-languages?hl=en.
>>>>>>
>>>>>>
>>>>>
>>>>> --
>>>>> You received this message because you are subscribed to the Google Groups 
>>>>> "JVM Languages" group.
>>>>> To post to this group, send email to [email protected].
>>>>> To unsubscribe from this group, send email to 
>>>>> [email protected].
>>>>> For more options, visit this group at 
>>>>> http://groups.google.com/group/jvm-languages?hl=en.
>>>>>
>>>>>
>>>>
>>>> --
>>>> You received this message because you are subscribed to the Google Groups 
>>>> "JVM Languages" group.
>>>> To post to this group, send email to [email protected].
>>>> To unsubscribe from this group, send email to 
>>>> [email protected].
>>>> For more options, visit this group at 
>>>> http://groups.google.com/group/jvm-languages?hl=en.
>>>>
>>>>
>>>
>>> --
>>> You received this message because you are subscribed to the Google Groups 
>>> "JVM Languages" group.
>>> To post to this group, send email to [email protected].
>>> To unsubscribe from this group, send email to 
>>> [email protected].
>>> For more options, visit this group at 
>>> http://groups.google.com/group/jvm-languages?hl=en.
>>>
>>>
>>
>> --
>> You received this message because you are subscribed to the Google Groups 
>> "JVM Languages" group.
>> To post to this group, send email to [email protected].
>> To unsubscribe from this group, send email to 
>> [email protected].
>> For more options, visit this group at 
>> http://groups.google.com/group/jvm-languages?hl=en.
>>
>>
>
> --
> You received this message because you are subscribed to the Google Groups 
> "JVM Languages" group.
> To post to this group, send email to [email protected].
> To unsubscribe from this group, send email to 
> [email protected].
> For more options, visit this group at 
> http://groups.google.com/group/jvm-languages?hl=en.
>
>

-- 
You received this message because you are subscribed to the Google Groups "JVM 
Languages" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to 
[email protected].
For more options, visit this group at 
http://groups.google.com/group/jvm-languages?hl=en.

Reply via email to