Hi everyone,
Matt and I finished running all the tests for V2 with the bug fixes from CASSANDRA-18086 <https://issues.apache.org/jira/browse/CASSANDRA-18086> and the results for the 100 partitions are definitely better than V1. For the larger partitions (1000, 10000), the results for V2 are comparable and overall V2 did not have any performance regression. On Tue, Dec 6, 2022 at 4:49 PM Marianne Lyne Manaog < marianne.man...@ieee.org> wrote: > Here is CASSANDRA-18097 > <https://issues.apache.org/jira/browse/CASSANDRA-18097> with the bug fix > for the performance regression encountered with 100 partitions in V2. > > On Mon, Dec 5, 2022 at 2:05 PM Marianne Lyne Manaog < > marianne.man...@ieee.org> wrote: > >> Following on what Matt said: >> >> - Here is the link to the Cassandra repo with the bugfix of wait time >> from ms to ns: >> https://github.com/apache/cassandra/compare/trunk...marianne-manaog:cassandra:bugfix/wait-from-ms-to-ns >> >> - the Paxos configuration used is: >> >> paxos_contention_wait_randomizer: uniform >> >> paxos_contention_min_wait: 0 >> >> paxos_contention_max_wait: 100ms >> >> - V1 and V2 have the same configurations except for paxos_variant: which >> changes accordingly >> >> *Results: V1 (100 partitions)* >> >> - Average read: 28948 >> >> - Standard Deviation: 416.271 >> >> - Coefficient of variance: 1.44% >> >> - Average write: 19248 >> >> - Standard Deviation:158.595 >> >> - Coefficient of variance:0.82% >> >> *Results: V2 (100 partitions)* >> >> - Average read: 12307 >> >> - Standard Deviation: 2367.473 >> >> - Coefficient of variance: 19.24% >> >> - Average write: 5780 >> >> - Standard Deviation: 1154.261 >> >> - Coefficient of variance: 19.97% >> >> >> On Mon, Dec 5, 2022 at 1:50 PM Matt Fleming <m...@codeblueprint.co.uk> >> wrote: >> >>> Me and Marianne are also still chasing a performance issue with Paxos v2 >>> when compared with v1. We >>> see way more contention on v2 for a LOCAL_SERIALIZABLE workload that >>> writes/reads to only 100 >>> partitions (v2 performs better for higher partition counts). We're still >>> investigating what's going >>> on. >>> >>> Should that be a -1 vote? I'm not sure :) >>> >>> On Mon, 5 Dec 2022 at 11:37, Benedict <bened...@apache.org> wrote: >>> >>>> -0 >>>> >>>> CASSANDRA-18086 should probably be fixed and merged first, as Paxos v2 >>>> will be unlikely to work well for users without it. Either that or we need >>>> to update NEWS.txt to mention it. >>>> >>>> On 5 Dec 2022, at 11:01, Aleksey Yeshchenko <alek...@apple.com> wrote: >>>> >>>> +1 >>>> >>>> On 5 Dec 2022, at 10:17, Benjamin Lerer <ble...@apache.org> wrote: >>>> >>>> +1 >>>> >>>> Le lun. 5 déc. 2022 à 11:02, Berenguer Blasi <berenguerbl...@gmail.com> >>>> a écrit : >>>> >>>>> +1 >>>>> On 5/12/22 10:53, guo Maxwell wrote: >>>>> >>>>> +1 >>>>> >>>>> Mick Semb Wever <m...@apache.org>于2022年12月5日 周一下午5:33写道： >>>>> >>>>>> >>>>>> Proposing the test build of Cassandra 4.1.0 GA for release. >>>>>> >>>>>> sha1: b807f97b37933fac251020dbd949ee8ef245b158 >>>>>> Git: >>>>>> https://gitbox.apache.org/repos/asf?p=cassandra.git;a=shortlog;h=refs/tags/4.1.0-tentative >>>>>> Maven Artifacts: >>>>>> https://repository.apache.org/content/repositories/orgapachecassandra-1281/org/apache/cassandra/cassandra-all/4.1.0/ >>>>>> >>>>>> The Source and Build Artifacts, and the Debian and RPM packages and >>>>>> repositories, are available here: >>>>>> https://dist.apache.org/repos/dist/dev/cassandra/4.1.0/ >>>>>> >>>>>> The vote will be open for 72 hours (longer if needed). Everyone who >>>>>> has tested the build is invited to vote. Votes by PMC members are >>>>>> considered binding. A vote passes if there are at least three binding +1s >>>>>> and no -1's. >>>>>> >>>>>> [1]: CHANGES.txt: >>>>>> https://gitbox.apache.org/repos/asf?p=cassandra.git;a=blob_plain;f=CHANGES.txt;hb=refs/tags/4.1.0-tentative >>>>>> [2]: NEWS.txt: >>>>>> https://gitbox.apache.org/repos/asf?p=cassandra.git;a=blob_plain;f=NEWS.txt;hb=refs/tags/4.1.0-tentative >>>>>> >>>>> -- >>>>> you are the apple of my eye ! >>>>> >>>>> >>>>
