[ https://issues.apache.org/jira/browse/CASSANDRA-5932?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13779994#comment-13779994 ]
Ryan McGuire commented on CASSANDRA-5932: ----------------------------------------- The good news is that speculative read has improved across the board. However, this new batch of testing introduces some new mysteries. !5933-7a87fc11.png! This is all of the runs from 7a87fc1186f39678382cf9b3e1dd224d9c71aead. All of the speculative retry runs are better than with 2.0.0-rc1. However, I can't explain why sr=NONE did better than ALWAYS and 95percentile. There is no visible indication that a node went down for sr=NONE. I have double checked the logs, and it did, in fact, go down. Compare this to the baseline of 1.2.8 and 2.0.0-rc1 (redone last night on same hardware as above): !5933-128_and_200rc1.png! All of these have clear indications of the node going down. You can [see all the data here|http://ryanmcguire.info/ds/graph/graph.html?stats=stats.5933.node_killed.json&metric=interval_op_rate&operation=stress-read&smoothing=1] - you can double click the colored squares to toggle the visibility of the lines, as they do overlap. I've uploaded logs from all these runs as !5933-logs.tar.gz!. > Speculative read performance data show unexpected results > --------------------------------------------------------- > > Key: CASSANDRA-5932 > URL: https://issues.apache.org/jira/browse/CASSANDRA-5932 > Project: Cassandra > Issue Type: Bug > Reporter: Ryan McGuire > Assignee: Aleksey Yeschenko > Fix For: 2.0.2 > > Attachments: 5932.txt, 5933-128_and_200rc1.png, 5933-7a87fc11.png, > 5933-logs.tar.gz, compaction-makes-slow.png, compaction-makes-slow-stats.png, > eager-read-looks-promising.png, eager-read-looks-promising-stats.png, > eager-read-not-consistent.png, eager-read-not-consistent-stats.png, > node-down-increase-performance.png > > > I've done a series of stress tests with eager retries enabled that show > undesirable behavior. I'm grouping these behaviours into one ticket as they > are most likely related. > 1) Killing off a node in a 4 node cluster actually increases performance. > 2) Compactions make nodes slow, even after the compaction is done. > 3) Eager Reads tend to lessen the *immediate* performance impact of a node > going down, but not consistently. > My Environment: > 1 stress machine: node0 > 4 C* nodes: node4, node5, node6, node7 > My script: > node0 writes some data: stress -d node4 -F 30000000 -n 30000000 -i 5 -l 2 -K > 20 > node0 reads some data: stress -d node4 -n 30000000 -o read -i 5 -K 20 > h3. Examples: > h5. A node going down increases performance: > !node-down-increase-performance.png! > [Data for this test > here|http://ryanmcguire.info/ds/graph/graph.html?stats=stats.eager_retry.node_killed.just_20.json&metric=interval_op_rate&operation=stress-read&smoothing=1] > At 450s, I kill -9 one of the nodes. There is a brief decrease in performance > as the snitch adapts, but then it recovers... to even higher performance than > before. > h5. Compactions make nodes permanently slow: > !compaction-makes-slow.png! > !compaction-makes-slow-stats.png! > The green and orange lines represent trials with eager retry enabled, they > never recover their op-rate from before the compaction as the red and blue > lines do. > [Data for this test > here|http://ryanmcguire.info/ds/graph/graph.html?stats=stats.eager_retry.compaction.2.json&metric=interval_op_rate&operation=stress-read&smoothing=1] > h5. Speculative Read tends to lessen the *immediate* impact: > !eager-read-looks-promising.png! > !eager-read-looks-promising-stats.png! > This graph looked the most promising to me, the two trials with eager retry, > the green and orange line, at 450s showed the smallest dip in performance. > [Data for this test > here|http://ryanmcguire.info/ds/graph/graph.html?stats=stats.eager_retry.node_killed.json&metric=interval_op_rate&operation=stress-read&smoothing=1] > h5. But not always: > !eager-read-not-consistent.png! > !eager-read-not-consistent-stats.png! > This is a retrial with the same settings as above, yet the 95percentile eager > retry (red line) did poorly this time at 450s. > [Data for this test > here|http://ryanmcguire.info/ds/graph/graph.html?stats=stats.eager_retry.node_killed.just_20.rc1.try2.json&metric=interval_op_rate&operation=stress-read&smoothing=1] -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira