Hi Frederic, hi Alex,
thank you for your comments.
I think it is better to have a fresh implementation in fieldStreams.hpp.
This way, other functionality can be addressed separately (and
fieldStreams.hpp is a more appropriate place imo).
I agree that the FieldStream implementation should be
Hi Hannes,
Thank you for the analysis and the proposed solution.
The changes look reasonable to me, and I agree with Alex that we should
either fix or get rid of the old FieldStream implementation. If we keep
it, this kind of performance issue will happen again.
Regards,
Fred
On 10/2/2
cc'ing hotspot-runtime-dev and Fred. :)
Cheers,
David
On 3/10/2023 4:49 am, Hannes Greule wrote:
Hi,
recently, a performance regression of jcmd GC.heap_dump was brought to
my attention. I investigated the regression and tracked down
https://bugs.openjdk.org/browse/JDK-8292818 as the source o
Hi Hannes,
The change looks very reasonable to me.
Field order is not important in the heap dump (the order just should be
the same in class and instance subrecords).
And I think it would be better to fix original FieldStream (or introduce
new HierarchicalFieldStream and use in for heap dumpi
Hi,
recently, a performance regression of jcmd GC.heap_dump was brought to
my attention. I investigated the regression and tracked down
https://bugs.openjdk.org/browse/JDK-8292818 as the source of it.
For reproduction, I used the code at [1] and ran it with `java -Xmx2G
CountPrimes`.
In Java 1
