Hi Zhengyu,
On 2/02/2019 11:38 pm, [email protected] wrote:
On Sat, 2019-02-02 at 11:01 +1000, David Holmes wrote:
On 2/02/2019 4:27 am, [email protected] wrote:
After FastTLABRefill was removed, let's cleanup related perf
counters.
I removed perf counters for fast refill, and renamed perf counters
for
slow refill.
I am not all clear what implication of renaming/removing exported
symbols, and have no idea what aliasmap is for. So I ran all tests
I
think could be affected, showed no problem.
Will need to check how perfcounters may be accessed before removing
them. I don't know if external tools may access them as jvmstat does.
Yep, but It is hard to find out. I can not image this is the first one,
how we dealt with before?
Removing "_reserve_for_allocation_prefetch" breaks JDK8 tools, how it
was communicated?
I don't know what you are referring to. _reserve_for_allocation_prefetch
was moved in 9 from Abstract_VM_Version to ThreadLocalAllocBuffer.
http://hg.openjdk.java.net/jdk9/jdk9/hotspot/rev/6525e4ba82a1
It still exists there. And it is a plain int not a perf counter/variable.
That aside we have in threadLocalAllocBuffer.cpp:
320 return PerfDataManager::create_variable(SUN_GC,
PerfDataManager::counter_name("tlab", name), unit, THREAD);
So these are in the SUN_GC namespace and anything in the sun namespace
is unstable and unsupported:
hotspot/share/runtime/perfData.cpp
const char* PerfDataManager::_name_spaces[] = {
// top level name spaces
"java", // stable and supported name space
"com.sun", // unstable but supported name space
"sun", // unstable and unsupported name space
So this should be okay.
Thanks,
David
-----
Thanks,
-Zhengyu
David
-----
Bug: https://bugs.openjdk.java.net/browse/JDK-8212127
Webrev: http://cr.openjdk.java.net/~zgu/JDK-8212127/webrev.00/
Test:
hotspot_runtime, hotspot_serviceability,
vmTestbase_nsk_monitoring,
vmTestbase_nsk_jdi, vmTestbase_nsk_jvmti, vmTestbase_vm_jdwp
on Linux x64
Eyeball output of jsnap
Thanks,
-Zhengyu
