[ 
https://issues.apache.org/jira/browse/GEODE-8349?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17155591#comment-17155591
 ] 

ASF GitHub Bot commented on GEODE-8349:
---------------------------------------

bschuchardt edited a comment on pull request #5363:
URL: https://github.com/apache/geode/pull/5363#issuecomment-656401747


   ```
    org.apache.geode.benchmark.tests.PartitionedGetBenchmark
                 average ops/second  Baseline:    331221.55  Test:    342201.08 
 Difference:   +3.3%
          ops/second standard error  Baseline:       521.34  Test:       555.60 
 Difference:   +6.6%
      ops/second standard deviation  Baseline:      9014.73  Test:      9607.16 
 Difference:   +6.6%
         YS 99th percentile latency  Baseline:     20071.00  Test:     20071.00 
 Difference:   +0.0%
                     median latency  Baseline:    362239.00  Test:    361471.00 
 Difference:   -0.2%
            90th percentile latency  Baseline:   7036927.00  Test:   6995967.00 
 Difference:   -0.6%
            99th percentile latency  Baseline:  24428543.00  Test:  23085055.00 
 Difference:   -5.5%
          99.9th percentile latency  Baseline:  34963455.00  Test:  33259519.00 
 Difference:   -4.9%
                    average latency  Baseline:   2171050.56  Test:   2101421.48 
 Difference:   -3.2%
         latency standard deviation  Baseline:   5334288.43  Test:   5076754.60 
 Difference:   -4.8%
             latency standard error  Baseline:       535.20  Test:       501.11 
 Difference:   -6.4%
   
   
   org.apache.geode.benchmark.tests.PartitionedPutBenchmark
                 average ops/second  Baseline:    178773.53  Test:    182095.99 
 Difference:   +1.9%
          ops/second standard error  Baseline:       599.58  Test:       835.58 
 Difference:  +39.4%
      ops/second standard deviation  Baseline:     10367.72  Test:     14448.49 
 Difference:  +39.4%
         YS 99th percentile latency  Baseline:     20083.00  Test:     20082.80 
 Difference:   -0.0%
                     median latency  Baseline:    765951.00  Test:    767999.00 
 Difference:   +0.3%
            90th percentile latency  Baseline:  13459455.00  Test:  13107199.00 
 Difference:   -2.6%
            99th percentile latency  Baseline:  28983295.00  Test:  27787263.00 
 Difference:   -4.1%
          99.9th percentile latency  Baseline: 107151359.00  Test: 109379583.00 
 Difference:   +2.1%
                    average latency  Baseline:   4024484.55  Test:   3951012.79 
 Difference:   -1.8%
         latency standard deviation  Baseline:   9229899.71  Test:   8986494.06 
 Difference:   -2.6%
             latency standard error  Baseline:      1260.59  Test:      1216.02 
 Difference:   -3.5%
   
   
   org.apache.geode.benchmark.tests.ReplicatedGetBenchmark
                 average ops/second  Baseline:    339091.57  Test:    351035.30 
 Difference:   +3.5%
          ops/second standard error  Baseline:       450.59  Test:       371.17 
 Difference:  -17.6%
      ops/second standard deviation  Baseline:      7791.42  Test:      6418.07 
 Difference:  -17.6%
         YS 99th percentile latency  Baseline:     20071.00  Test:     20071.33 
 Difference:   +0.0%
                     median latency  Baseline:    355839.00  Test:    357375.00 
 Difference:   +0.4%
            90th percentile latency  Baseline:   6524927.00  Test:   5992447.00 
 Difference:   -8.2%
            99th percentile latency  Baseline:  24526847.00  Test:  23691263.00 
 Difference:   -3.4%
          99.9th percentile latency  Baseline:  34013183.00  Test:  32948223.00 
 Difference:   -3.1%
                    average latency  Baseline:   2120692.40  Test:   2048843.90 
 Difference:   -3.4%
         latency standard deviation  Baseline:   5263600.14  Test:   5054339.01 
 Difference:   -4.0%
             latency standard error  Baseline:       521.94  Test:       492.61 
 Difference:   -5.6%
   
   
   org.apache.geode.benchmark.tests.ReplicatedPutBenchmark
                 average ops/second  Baseline:    192443.22  Test:    194403.34 
 Difference:   +1.0%
          ops/second standard error  Baseline:       726.17  Test:       788.60 
 Difference:   +8.6%
      ops/second standard deviation  Baseline:     12556.67  Test:     13636.14 
 Difference:   +8.6%
         YS 99th percentile latency  Baseline:     20060.00  Test:     20072.00 
 Difference:   +0.1%
                     median latency  Baseline:    809471.00  Test:    781823.00 
 Difference:   -3.4%
            90th percentile latency  Baseline:  10690559.00  Test:  11599871.00 
 Difference:   +8.5%
            99th percentile latency  Baseline:  23724031.00  Test:  24379391.00 
 Difference:   +2.8%
          99.9th percentile latency  Baseline: 106692607.00  Test: 110166015.00 
 Difference:   +3.3%
                    average latency  Baseline:   3739364.07  Test:   3701351.14 
 Difference:   -1.0%
         latency standard deviation  Baseline:   8255312.29  Test:   8420063.75 
 Difference:   +2.0%
             latency standard error  Baseline:      1086.76  Test:      1102.91 
 Difference:   +1.5%
   ```


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


> reinstate use of SSLSocket for cluster communication
> ----------------------------------------------------
>
>                 Key: GEODE-8349
>                 URL: https://issues.apache.org/jira/browse/GEODE-8349
>             Project: Geode
>          Issue Type: Bug
>          Components: membership, messaging
>            Reporter: Bruce J Schuchardt
>            Assignee: Bruce J Schuchardt
>            Priority: Major
>
> We've found problems with "new IO"'s SSLEngine with respect to support for 
> TLSV1.  We've also seen anomalous performance using that secure 
> communications mechanism.  The introduction of the use of the "new IO" 
> SSLEngine was originally to 1) reduce code complexity in the 
> org.apache.geode.internal.tcp package and 2) to set the stage for its use in 
> client/server communications so that selectors could be used in c/s 
> communications.
> This ticket aims to reintroduce the use of SSLSocket in cluster 
> communications without restoring the old, poorly tested SSL code paths.  The 
> new implementation should have as good or better performance than the 
> previous"old IO" implementation and the more recent "new IO" SSLEngine 
> implementation as well.  This should be apparent in the CI benchmark jobs.
>  
>  



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

Reply via email to