RFR: 8316180: Thread-local backoff for secondary_super_cache updates [v6]
Amit Kumar
amitkumar at openjdk.org
Thu Oct 12 14:04:09 UTC 2023
On Wed, 27 Sep 2023 18:25:02 GMT, Aleksey Shipilev <shade at openjdk.org> wrote:
>> I see the following disclaimer in the description:
>>> Work in progress, submitting for broader attention.
>>
>> What are next steps and, more broadly, what's left to get the PR finalized? Especially, it's not clear how much performance testing it went through so far.
>
>> What are next steps and, more broadly, what's left to get the PR finalized? Especially, it's not clear how much performance testing it went through so far.
>
> I was waiting on Derek White to publish their benchmarks, so that we can decide reasonable defaults. While it seems too early to run larger scale benchmarks, feel free to give it a spin.
Hi @shipilev,
Please include s390 patch from here:
[s390_port.patch](https://github.com/openjdk/jdk/files/12882890/s390_port.patch)
Benchmark: Z15 Machine, with 64 CPUs
-XX:SecondarySuperMissBackoff=0
Benchmark Mode Cnt Score Error Units
SecondarySuperCache.contended avgt 15 10655.113 ? 6148.685 ns/op
SecondarySuperCache.uncontended avgt 15 107.9 ? 54.109 ns/op
-XX:SecondarySuperMissBackoff=10
Benchmark Mode Cnt Score Error Units
SecondarySuperCache.contended avgt 15 2541.671 ? 1048.361 ns/op
SecondarySuperCache.uncontended avgt 15 120.107 ? 63.345 ns/op
-XX:SecondarySuperMissBackoff=100
Benchmark Mode Cnt Score Error Units
SecondarySuperCache.contended avgt 15 662.473 ? 139.208 ns/op
SecondarySuperCache.uncontended avgt 15 79.371 ? 40.232 ns/op
-XX:SecondarySuperMissBackoff=1000
Benchmark Mode Cnt Score Error Units
SecondarySuperCache.contended avgt 15 248.292 ? 77.175 ns/op
SecondarySuperCache.uncontended avgt 15 87.333 ? 35.103 ns/op
-XX:SecondarySuperMissBackoff=10000
Benchmark Mode Cnt Score Error Units
SecondarySuperCache.contended avgt 15 139.901 ? 44.83 ns/op
SecondarySuperCache.uncontended avgt 15 90.872 ? 31.791 ns/op
-------------
PR Comment: https://git.openjdk.org/jdk/pull/15718#issuecomment-1759621237
More information about the hotspot-dev
mailing list