cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Jay Zhuang (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (CASSANDRA-9067) BloomFilter serialization format should not change byte ordering
Date Tue, 16 Jan 2018 03:34:00 GMT

    [ https://issues.apache.org/jira/browse/CASSANDRA-9067?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16326721#comment-16326721
] 

Jay Zhuang commented on CASSANDRA-9067:
---------------------------------------

Here is the patch, please review:
| Branch | uTest |
| [9067|https://github.com/cooldoger/cassandra/tree/9067] | [!https://circleci.com/gh/cooldoger/cassandra/tree/9067.svg?style=svg!|https://circleci.com/gh/cooldoger/cassandra/tree/9067]
|

Here is the microbench test result (Score number is the running time, smaller is better):
{noformat}
     [java] Benchmark                                     (numElemsInK)  (oldBfFormat)  Mode
 Cnt      Score       Error  Units
     [java] BloomFilterSerializerBench.serializationTest              1           true  avgt
   4    143.170 ?    35.566  us/op
     [java] BloomFilterSerializerBench.serializationTest              1          false  avgt
   4     95.692 ?    61.473  us/op
     [java] BloomFilterSerializerBench.serializationTest             10           true  avgt
   4    662.022 ?   202.386  us/op
     [java] BloomFilterSerializerBench.serializationTest             10          false  avgt
   4    186.326 ?    87.105  us/op
     [java] BloomFilterSerializerBench.serializationTest            100           true  avgt
   4   6312.909 ?  2090.136  us/op
     [java] BloomFilterSerializerBench.serializationTest            100          false  avgt
   4   1125.158 ?   553.381  us/op
     [java] BloomFilterSerializerBench.serializationTest           1024           true  avgt
   4  60436.370 ? 16174.150  us/op
     [java] BloomFilterSerializerBench.serializationTest           1024          false  avgt
   4  10781.518 ?  6975.222  us/op
{noformat}

> BloomFilter serialization format should not change byte ordering
> ----------------------------------------------------------------
>
>                 Key: CASSANDRA-9067
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-9067
>             Project: Cassandra
>          Issue Type: Improvement
>            Reporter: Benedict
>            Assignee: Jay Zhuang
>            Priority: Minor
>             Fix For: 4.x
>
>
> As a follow-up to CASSANDRA-9066 and CASSANDRA-9060, it appears we do some unnecessary
byte swapping during the serialization of bloom filters, which makes the logic slower and
harder to follow. We should either perform them more efficiently (using Long.reverseBytes)
or, preferably, eliminate the conversion altogether since it does not appear to serve any
purpose.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@cassandra.apache.org
For additional commands, e-mail: commits-help@cassandra.apache.org


Mime
View raw message