Tsz-Wo, I would like to invite Hongbing to share their experience about this sometime later in the community meeting. Will let you know the time once it's confirmed.
Sammi On Tue, 29 Oct 2024 at 01:21, Tsz Wo Sze <szets...@gmail.com> wrote: > > Follower reader feature is used in production environment with a bit of > customization. > > Weiming/Weiming/Jianghua, That is great! Could you submit a pull request > for https://issues.apache.org/jira/browse/HDDS-9279 ? Thank you in > advance. > > Tsz-Wo > > > On Mon, Oct 28, 2024 at 9:15 AM Wei-Chiu Chuang <weic...@apache.org> > wrote: > > > ZGC in JDK17 is stable. According to the various reports, ZGC achieves > > better throughput, latency than G1. > > If someone in the community would like to give it a try, I know some > HBase > > community members opted in ZGC for HBase and it turned out better than > > other choices. > > > > We don't support JDK21 yet. But JDK21 has a new ZGC mode > > > > > > > https://medium.com/@roopa.kushtagi/netflixs-journey-from-g1gc-to-zgc-tackling-tail-latencies-66ee75681d49 > > > > > > > https://kstefanj.github.io/2023/12/13/jdk-21-the-gcs-keep-getting-better.html > > > > On Sun, Oct 27, 2024 at 8:50 PM Sammi Chen <sammic...@apache.org> wrote: > > > > > Attenders: Hao, Weiming, Conway, Jianghua, Sammi > > > > > > Sammi：The new OM HA prototype shows times of improvement of OM > > throughput. > > > Weiming/Weiming/Jianghua: > > > - Follower reader feature is used in production environment with a bit > of > > > customization. > > > - Tencent Kona JDK 17 is used with G1 GC to replace the Open JDK 17 on > > OM, > > > which welly solve the OM GC problem triggered by threadLocal usage. > > > GuoHao: > > > - Found EC pipeline creation lock contention which causes P99 latency > > > higher than expected, when there is intensive block allocation > requests. > > > Will investigate a) EC pipeline pre-allocation pool, and b) code > refactor > > > to reduce the lock scope, two solutions next. > > > - Proposed a key deleting service optimization, instead of iterating > from > > > first key of the table, save last key of last iterator as the start key > > of > > > next iterator, to skip the tombstones of already deleted record. > > > - Found one issue that the block delete request exceeds the SCM raft > log > > > max message size when there are big MPU files involved. Should control > > the > > > block delete request size under the SCM raft log max message size. > > > > > >
