[ https://issues.apache.org/jira/browse/CASSANDRA-10407?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14941719#comment-14941719 ]
Alan Boudreault edited comment on CASSANDRA-10407 at 10/2/15 9:48 PM: ---------------------------------------------------------------------- [~Stefania] Here are all the graphs from our tests yesterday. I tested the 3.0.0-rc1 this morning. As you already know, I've not been able to clearly demonstrate the improvement. All tests have been run on a single node cluster (ec2, i2.4xlarge) using ONLY non-striped ssd disk (so the other disks had been removed from the data_directory setting of cstar_perf) Revisions: * without path: a59be2693e33e899264bc29b37b669d4bb645a74 * with path: 6422e34769e42b4eef5d9c073301c9791e9ca8b2 without path - 64k readahead: http://riptano.github.io/cassandra_performance/graph_v5/graph.html?stats=10407%2Ftiny-readahead-64k.log&metric=op_rate&operation=2_user&smoothing=1&show_aggregates=true&xmin=0&xmax=209.11&ymin=0&ymax=74949.6 without patch - readhead disabled: http://riptano.github.io/cassandra_performance/graph_v5/graph.html?stats=10407%2Ftiny-no-readahead.log&metric=op_rate&operation=2_user&smoothing=1&show_aggregates=true&xmin=0&xmax=209.11&ymin=0&ymax=74949.6 with path - 64k readahead: http://riptano.github.io/cassandra_performance/graph_v5/graph.html?stats=10407%2Ftiny-with-path-64k-readahead.log&metric=op_rate&operation=2_user&smoothing=1&show_aggregates=true&xmin=0&xmax=209.11&ymin=0&ymax=74949.6 witht path - readahead disabled: http://riptano.github.io/cassandra_performance/graph_v5/graph.html?stats=10407%2Ftiny-with-path-no-readahead.log&metric=op_rate&operation=2_user&smoothing=1&show_aggregates=true&xmin=0&xmax=209.11&ymin=0&ymax=74949.6 3.0.0-rc1 64k readahead: http://riptano.github.io/cassandra_performance/graph_v5/graph.html?stats=10407%2Ftiny-3.0.0-rc1-64k-readahead.log&metric=op_rate&operation=2_user&smoothing=1&show_aggregates=true&xmin=0&xmax=209.11&ymin=0&ymax=74949.6 3.0.0-rc1 readahead disabled: http://riptano.github.io/cassandra_performance/graph_v5/graph.html?stats=10407%2Ftiny-3.0.0-rc1-no-readahead.log&metric=op_rate&operation=2_user&smoothing=1&show_aggregates=true&xmin=0&xmax=209.11&ymin=0&ymax=74949.6 was (Author: aboudreault): [~Stefania] Here are all the graphs from our tests yesterday. I tested the 3.0.0-rc1 this morning. As you already know, I've not been able to clearly demonstrate the improvement. All tests have been run on a single node cluster (ec2, i2.4xlarge) Revisions: * without path: a59be2693e33e899264bc29b37b669d4bb645a74 * with path: 6422e34769e42b4eef5d9c073301c9791e9ca8b2 without path - 64k readahead: http://riptano.github.io/cassandra_performance/graph_v5/graph.html?stats=10407%2Ftiny-readahead-64k.log&metric=op_rate&operation=2_user&smoothing=1&show_aggregates=true&xmin=0&xmax=209.11&ymin=0&ymax=74949.6 without patch - readhead disabled: http://riptano.github.io/cassandra_performance/graph_v5/graph.html?stats=10407%2Ftiny-no-readahead.log&metric=op_rate&operation=2_user&smoothing=1&show_aggregates=true&xmin=0&xmax=209.11&ymin=0&ymax=74949.6 with path - 64k readahead: http://riptano.github.io/cassandra_performance/graph_v5/graph.html?stats=10407%2Ftiny-with-path-64k-readahead.log&metric=op_rate&operation=2_user&smoothing=1&show_aggregates=true&xmin=0&xmax=209.11&ymin=0&ymax=74949.6 witht path - readahead disabled: http://riptano.github.io/cassandra_performance/graph_v5/graph.html?stats=10407%2Ftiny-with-path-no-readahead.log&metric=op_rate&operation=2_user&smoothing=1&show_aggregates=true&xmin=0&xmax=209.11&ymin=0&ymax=74949.6 3.0.0-rc1 64k readahead: http://riptano.github.io/cassandra_performance/graph_v5/graph.html?stats=10407%2Ftiny-3.0.0-rc1-64k-readahead.log&metric=op_rate&operation=2_user&smoothing=1&show_aggregates=true&xmin=0&xmax=209.11&ymin=0&ymax=74949.6 3.0.0-rc1 readahead disabled: http://riptano.github.io/cassandra_performance/graph_v5/graph.html?stats=10407%2Ftiny-3.0.0-rc1-no-readahead.log&metric=op_rate&operation=2_user&smoothing=1&show_aggregates=true&xmin=0&xmax=209.11&ymin=0&ymax=74949.6 > Benchmark and evaluate CASSANDRA-8894 improvements > -------------------------------------------------- > > Key: CASSANDRA-10407 > URL: https://issues.apache.org/jira/browse/CASSANDRA-10407 > Project: Cassandra > Issue Type: Test > Reporter: Aleksey Yeschenko > Assignee: Alan Boudreault > Fix For: 3.0.0 rc2 > > Attachments: 8894_tiny.yaml, flight-recordings.tar.gz, > test-with-8894-tiny.json, test-without-8894-tiny.json > > > The original ticket (CASSANDRA-8894) was committed to 3.0 alpha1 two months > ago. We need to get proper performance tests before GA. > See [~benedict]'s > [comment|https://issues.apache.org/jira/browse/CASSANDRA-8894?focusedCommentId=14631203&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-14631203] > for more details. -- This message was sent by Atlassian JIRA (v6.3.4#6332)