RFR: JDK-8055845 - Add trace event for promoted objects

Thu Aug 28 09:27:16 UTC 2014

Hi Staffan,

thanks for the patch, looks like a useful event!

A few initial comments:
- Aren't the events for promotion to the tenured generation (SerialOld)
   and the CMS generation missing?
- We try to keep the trace dependency (the header file) in
   gcTraceSend.cpp, see the pattern for all the other events in
   gcTrace.cpp (they all have a "report" and a "send" function).
- Would it make sense to differentiate, either by separate events or by
   a field in a event, between promotions to to-space and to the old
   generation?
- The are two events for TLAB allocations,
   java/object_alloc_in_new_TLAB and java/object_alloc_outside_TLAB.
   What do you think about using two events for PLAB allocations as well:
   - java/object_alloc_in_new_PLAB
   - java/object_alloc_outside_PLAB
- In PSPromotionManager, instead of utilizing the C++ friendship with
   PSScavenge, should we add a getter function for the gc_tracer?

Thanks,
Erik

On 2014-08-27 16:28, Bengt Rutisson wrote:
>
>
> Hi Staffan,
>
> Overall I think this change looks fine. I know that Erik Helin has some
> thoughts on the naming of the events. I'll let him communicate those
> thoughts.
>
> Apart from Erik's comments and the missing test case (that I know you
> are working on) I think the change looks good.
>
> Thanks,
> Bengt
>
> On 8/26/14 10:50 AM, Bengt Rutisson wrote:
>>
>> Hi all,
>>
>> Staffan sent me an updated webrev based on Erik's comments. I uploaded
>> it here:
>> http://cr.openjdk.java.net/~brutisso/8055845/webrev.01/
>>
>> Thanks,
>> Bengt
>>
>>
>> On 2014-08-25 19:32, Staffan Friberg wrote:
>>> Hi Erik,
>>>
>>> No issue with naming the field class, since the event is similar to
>>> the Allocation event I used that as a starting point and it also uses
>>> class as name together with a couple of other events.
>>>
>>> Will go through the descriptions and remove periods.
>>>
>>> Object age is basically the how many times an object has been kept in
>>> survivor region, it is incremented each time a YC happens and the
>>> object is aged.
>>> Will see how I can update the description to make it clearer. Calling
>>> the field tenuringAge might help?
>>>
>>>> From the documentation,
>>>> http://docs.oracle.com/javase/8/docs/technotes/tools/unix/java.html
>>>>
>>>> -XX:MaxTenuringThreshold=/threshold/
>>>>
>>>>     Sets the maximum tenuring threshold for use in adaptive GC
>>>>     sizing. The largest value is 15. The default value is 15 for the
>>>>     parallel (throughput) collector, and 6 for the CMS collector.
>>>>
>>>>     The following example shows how to set the maximum tenuring
>>>>     threshold to 10:
>>>>
>>>>     -XX:MaxTenuringThreshold=10
>>>>
>>>>
>>>> -XX:+PrintTenuringDistribution
>>>>
>>>>     Enables printing of tenuring age information. The following is
>>>>     an example of the output:
>>>>
>>>>     Desired survivor size 48286924 bytes, new threshold 10 (max 10)
>>>>     - age 1: 28992024 bytes, 28992024 total
>>>>     - age 2: 1366864 bytes, 30358888 total
>>>>     - age 3: 1425912 bytes, 31784800 total
>>>>     ...
>>>>
>>>>     Age 1 objects are the youngest survivors (they were created
>>>>     after the previous scavenge, survived the latest scavenge, and
>>>>     moved from eden to survivor space). Age 2 objects have survived
>>>>     two scavenges (during the second scavenge they were copied from
>>>>     one survivor space to the next). And so on.
>>>>
>>>>     In the preceding example, 28 992 024 bytes survived one scavenge
>>>>     and were copied from eden to survivor space, 1 366 864 bytes are
>>>>     occupied by age 2 objects, etc. The third value in each row is
>>>>     the cumulative size of objects of age n or less.
>>>>
>>>>     By default, this option is disabled.
>>>>
>>>
>>> Thanks for the comments,
>>> Staffan
>>>
>>> On 08/25/2014 09:55 AM, Erik Gahlin wrote:
>>>> Did you manage to call the field "class"? It's a reserved word in
>>>> C++, so we had to use "klass" in the past
>>>>
>>>> Descriptions with only one sentence shouldn't end with "."
>>>>
>>>> How is "Object Age" measured?
>>>>
>>>> As a user, I would expect the number to be in seconds/minutes/hours,
>>>> but that is not the case. Perhaps an explanation in the description
>>>> and/or a field name that better reflects what we really mean with age.
>>>>
>>>> Otherwise trace.xml looks good!
>>>>
>>>> Erik
>>>>
>>>> Staffan Friberg skrev 25/08/14 18:28:
>>>>> Hi,
>>>>>
>>>>> Could I please get reviews for this RFE that adds a trace event for
>>>>> aging and promotion for young collections in G1, CMS and Parallel GC.
>>>>> It works similarly to allocation events, and generates the event on
>>>>> the slow path when either a direct copy occurs or a new PLAB is
>>>>> request.
>>>>>
>>>>> Since I'm adding an event I cc:ed the serviceability list in case
>>>>> anyone has any comments on the event and changes to trace.xml.
>>>>>
>>>>> RFE: https://bugs.openjdk.java.net/browse/JDK-8055845
>>>>> Webrev: http://cr.openjdk.java.net/~brutisso/8055845/webrev.00
>>>>>
>>>>> Bengt has been kind and agreed to both sponsor and host the the
>>>>> webrev.
>>>>>
>>>>> Thanks,
>>>>> Staffan
>>>>>
>>>>
>>>
>>
>