[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[ https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16901482#comment-16901482 ] Joseph Lynch commented on CASSANDRA-15175: -- The analysis so far: [^cassandra_comparative_performance_all_flamegraphs.html] > Evaluate 200 node, compression=on, encryption=all > - > > Key: CASSANDRA-15175 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15175 > Project: Cassandra > Issue Type: Sub-task > Components: Test/benchmark >Reporter: Joseph Lynch >Assignee: Joseph Lynch >Priority: Normal > Attachments: 30x_14400cRPS-14400cWPS.svg, > 30x_LQ_21600cRPS-14400cWPS.svg, ShortbufferExceptions.png, > image-2019-08-06-14-20-25-140.png, odd_netty_jdk_tls_cpu_usage.png, > trunk_14400cRPS-14400cWPS.svg, trunk_187000cRPS-14400cWPS.svg, > trunk_187kcRPS_14kcWPS.png, trunk_22000cRPS-14400cWPS-jdk.svg, > trunk_22000cRPS-14400cWPS-openssl.svg, trunk_220kcRPS_14kcWPS.png, > trunk_252kcRPS-14kcWPS.png, trunk_93500cRPS-14400cWPS.svg, > trunk_LQ_14400cRPS-14400cWPS.svg, trunk_LQ_21600cRPS-14400cWPS.svg, > trunk_Q_21600cRPS-7200cWPS.svg, trunk_allocation_Q_21k_cRPS.svg, > trunk_vs_30x_125kcRPS_14kcWPS.png, trunk_vs_30x_14kRPS_14kcWPS_load.png, > trunk_vs_30x_14kcRPS_14kcWPS.png, > trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png, > trunk_vs_30x_156kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS.png, > trunk_vs_30x_24kcRPS_14kcWPS_load.png, trunk_vs_30x_31kcRPS_14kcWPS.png, > trunk_vs_30x_62kcRPS_14kcWPS.png, trunk_vs_30x_93kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_14kcRPS_14kcWPS.png, trunk_vs_30x_LQ_21kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_64kcRPS_14kcWPS.png, trunk_vs_30x_LQ_jdk_summary.png, > trunk_vs_30x_LQ_openssl_21kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_tcnative_summary.png, trunk_vs_30x_Q_21kcRPS_7200cWPS.png, > trunk_vs_30x_Q_36kcRPS_7200cWPS.png, trunk_vs_30x_Q_tcnative_summary.png, > trunk_vs_30x_summary.png, trunk_vs_30x_wEQ_rLQ_7kcRPS_22kcWPS.png, > trunk_vs_30x_wEQ_rLQ_7kcRPS_58kcWPS.png, > trunk_vs_30x_wEQ_rLQ_7kcRPS_7kcWPS.png, > trunk_vs_30x_write_LO_7kcRPS_108kcWPS.png, > trunk_vs_30x_write_LO_7kcRPS_162kcWPS.png, > trunk_vs_30x_write_LO_7kcRPS_72kcWPS.png, > trunk_vs_30x_write_LO_7kcRPS_7kcWPS.png, write_scaling_local_one_summary.png, > write_scaling_lq_eq_summary.png > > > Tracks evaluating a 192 node cluster with compression and encryption on. > First test is a [read scaling test > |https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053] > > |Test Setup| | > |Baseline|3.0.19 > @d7d00036| > |Candiate|trunk > @abb0e177| > | | | > |Workload| | > |Write size|4kb random| > |Read size|4kb random| > |Per Node Data|110GiB| > |Generator|ndbench| > |Key Distribution|Uniform| > |SSTable Compr|Off| > |Internode TLS|On (jdk)| > |Internode Compr|On| > |Compaction|LCS (320 MiB)| > |Repair|Off| > | | | > |Hardware| | > |Instance Type|i3.xlarge| > |Deployment|96 us-east-1, 96 eu-west-1| > |Region node count|96| > | | | > |OS Settings| | > |IO scheduler|kyber| > |Net qdisc|tc-fq| > |readahead|32kb| > |Java Version|OpenJDK 1.8.0_202 (Zulu)| > | | | > Second test is a [write scaling > test|https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=428858608]: -- This message was sent by Atlassian JIRA (v7.6.14#76016) - To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[ https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16901476#comment-16901476 ] Joseph Lynch commented on CASSANDRA-15175: -- Write scaling test LOCAL_ONE looks good: !write_scaling_local_one_summary.png! Write scaling test at LQ reads + EQ writes looks ok, but not great: !write_scaling_lq_eq_summary.png! > Evaluate 200 node, compression=on, encryption=all > - > > Key: CASSANDRA-15175 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15175 > Project: Cassandra > Issue Type: Sub-task > Components: Test/benchmark >Reporter: Joseph Lynch >Assignee: Joseph Lynch >Priority: Normal > Attachments: 30x_14400cRPS-14400cWPS.svg, > 30x_LQ_21600cRPS-14400cWPS.svg, ShortbufferExceptions.png, > image-2019-08-06-14-20-25-140.png, odd_netty_jdk_tls_cpu_usage.png, > trunk_14400cRPS-14400cWPS.svg, trunk_187000cRPS-14400cWPS.svg, > trunk_187kcRPS_14kcWPS.png, trunk_22000cRPS-14400cWPS-jdk.svg, > trunk_22000cRPS-14400cWPS-openssl.svg, trunk_220kcRPS_14kcWPS.png, > trunk_252kcRPS-14kcWPS.png, trunk_93500cRPS-14400cWPS.svg, > trunk_LQ_14400cRPS-14400cWPS.svg, trunk_LQ_21600cRPS-14400cWPS.svg, > trunk_Q_21600cRPS-7200cWPS.svg, trunk_allocation_Q_21k_cRPS.svg, > trunk_vs_30x_125kcRPS_14kcWPS.png, trunk_vs_30x_14kRPS_14kcWPS_load.png, > trunk_vs_30x_14kcRPS_14kcWPS.png, > trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png, > trunk_vs_30x_156kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS.png, > trunk_vs_30x_24kcRPS_14kcWPS_load.png, trunk_vs_30x_31kcRPS_14kcWPS.png, > trunk_vs_30x_62kcRPS_14kcWPS.png, trunk_vs_30x_93kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_14kcRPS_14kcWPS.png, trunk_vs_30x_LQ_21kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_64kcRPS_14kcWPS.png, trunk_vs_30x_LQ_jdk_summary.png, > trunk_vs_30x_LQ_openssl_21kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_tcnative_summary.png, trunk_vs_30x_Q_21kcRPS_7200cWPS.png, > trunk_vs_30x_Q_36kcRPS_7200cWPS.png, trunk_vs_30x_Q_tcnative_summary.png, > trunk_vs_30x_summary.png, trunk_vs_30x_wEQ_rLQ_7kcRPS_22kcWPS.png, > trunk_vs_30x_wEQ_rLQ_7kcRPS_58kcWPS.png, > trunk_vs_30x_wEQ_rLQ_7kcRPS_7kcWPS.png, > trunk_vs_30x_write_LO_7kcRPS_108kcWPS.png, > trunk_vs_30x_write_LO_7kcRPS_162kcWPS.png, > trunk_vs_30x_write_LO_7kcRPS_72kcWPS.png, > trunk_vs_30x_write_LO_7kcRPS_7kcWPS.png, write_scaling_local_one_summary.png, > write_scaling_lq_eq_summary.png > > > Tracks evaluating a 192 node cluster with compression and encryption on. > First test is a [read scaling test > |https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053] > > |Test Setup| | > |Baseline|3.0.19 > @d7d00036| > |Candiate|trunk > @abb0e177| > | | | > |Workload| | > |Write size|4kb random| > |Read size|4kb random| > |Per Node Data|110GiB| > |Generator|ndbench| > |Key Distribution|Uniform| > |SSTable Compr|Off| > |Internode TLS|On (jdk)| > |Internode Compr|On| > |Compaction|LCS (320 MiB)| > |Repair|Off| > | | | > |Hardware| | > |Instance Type|i3.xlarge| > |Deployment|96 us-east-1, 96 eu-west-1| > |Region node count|96| > | | | > |OS Settings| | > |IO scheduler|kyber| > |Net qdisc|tc-fq| > |readahead|32kb| > |Java Version|OpenJDK 1.8.0_202 (Zulu)| > | | | > Second test is a [write scaling > test|https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=428858608]: -- This message was sent by Atlassian JIRA (v7.6.14#76016) - To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[ https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16878164#comment-16878164 ] Joseph Lynch commented on CASSANDRA-15175: -- The QUORUM test is completed, results look pretty good on the read side: !trunk_vs_30x_Q_tcnative_summary.png! > Evaluate 200 node, compression=on, encryption=all > - > > Key: CASSANDRA-15175 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15175 > Project: Cassandra > Issue Type: Sub-task > Components: Test/benchmark >Reporter: Joseph Lynch >Assignee: Joseph Lynch >Priority: Normal > Attachments: 30x_14400cRPS-14400cWPS.svg, > 30x_LQ_21600cRPS-14400cWPS.svg, ShortbufferExceptions.png, > odd_netty_jdk_tls_cpu_usage.png, trunk_14400cRPS-14400cWPS.svg, > trunk_187000cRPS-14400cWPS.svg, trunk_187kcRPS_14kcWPS.png, > trunk_22000cRPS-14400cWPS-jdk.svg, trunk_22000cRPS-14400cWPS-openssl.svg, > trunk_220kcRPS_14kcWPS.png, trunk_252kcRPS-14kcWPS.png, > trunk_93500cRPS-14400cWPS.svg, trunk_LQ_14400cRPS-14400cWPS.svg, > trunk_LQ_21600cRPS-14400cWPS.svg, trunk_Q_21600cRPS-7200cWPS.svg, > trunk_allocation_Q_21k_cRPS.svg, trunk_vs_30x_125kcRPS_14kcWPS.png, > trunk_vs_30x_14kRPS_14kcWPS_load.png, trunk_vs_30x_14kcRPS_14kcWPS.png, > trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png, > trunk_vs_30x_156kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS.png, > trunk_vs_30x_24kcRPS_14kcWPS_load.png, trunk_vs_30x_31kcRPS_14kcWPS.png, > trunk_vs_30x_62kcRPS_14kcWPS.png, trunk_vs_30x_93kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_14kcRPS_14kcWPS.png, trunk_vs_30x_LQ_21kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_64kcRPS_14kcWPS.png, trunk_vs_30x_LQ_jdk_summary.png, > trunk_vs_30x_LQ_openssl_21kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_tcnative_summary.png, trunk_vs_30x_Q_21kcRPS_7200cWPS.png, > trunk_vs_30x_Q_36kcRPS_7200cWPS.png, trunk_vs_30x_Q_tcnative_summary.png, > trunk_vs_30x_summary.png, trunk_vs_30x_write_LO_7kcRPS_7kcWPS.png > > > Tracks evaluating a 192 node cluster with compression and encryption on. > Test setup at (reproduced below) > [https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053] > > |Test Setup| | > |Baseline|3.0.19 > @d7d00036| > |Candiate|trunk > @abb0e177| > | | | > |Workload| | > |Write size|4kb random| > |Read size|4kb random| > |Per Node Data|110GiB| > |Generator|ndbench| > |Key Distribution|Uniform| > |SSTable Compr|Off| > |Internode TLS|On (jdk)| > |Internode Compr|On| > |Compaction|LCS (320 MiB)| > |Repair|Off| > | | | > |Hardware| | > |Instance Type|i3.xlarge| > |Deployment|96 us-east-1, 96 eu-west-1| > |Region node count|96| > | | | > |OS Settings| | > |IO scheduler|kyber| > |Net qdisc|tc-fq| > |readahead|32kb| > |Java Version|OpenJDK 1.8.0_202 (Zulu)| > | | | -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[ https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16875587#comment-16875587 ] Joseph Lynch commented on CASSANDRA-15175: -- [~norman] Yes, I think we have enough evidence that the latency regression was probably not Netty TLS (although I am somewhat surprised CPU time with tcnative is about the same as pre-netty jdk TLS) and probably in how we're using it instead. It is possible that the default cipher choice for netty on Java 8 may want to be revised, or at least noted somewhere in the documentation that Java 8 has a performance limitation with GCM ciphers? > Evaluate 200 node, compression=on, encryption=all > - > > Key: CASSANDRA-15175 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15175 > Project: Cassandra > Issue Type: Sub-task > Components: Test/benchmark >Reporter: Joseph Lynch >Assignee: Joseph Lynch >Priority: Normal > Attachments: 30x_14400cRPS-14400cWPS.svg, > 30x_LQ_21600cRPS-14400cWPS.svg, ShortbufferExceptions.png, > odd_netty_jdk_tls_cpu_usage.png, trunk_14400cRPS-14400cWPS.svg, > trunk_187000cRPS-14400cWPS.svg, trunk_187kcRPS_14kcWPS.png, > trunk_22000cRPS-14400cWPS-jdk.svg, trunk_22000cRPS-14400cWPS-openssl.svg, > trunk_220kcRPS_14kcWPS.png, trunk_252kcRPS-14kcWPS.png, > trunk_93500cRPS-14400cWPS.svg, trunk_LQ_14400cRPS-14400cWPS.svg, > trunk_LQ_21600cRPS-14400cWPS.svg, trunk_Q_21600cRPS-7200cWPS.svg, > trunk_allocation_Q_21k_cRPS.svg, trunk_vs_30x_125kcRPS_14kcWPS.png, > trunk_vs_30x_14kRPS_14kcWPS_load.png, trunk_vs_30x_14kcRPS_14kcWPS.png, > trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png, > trunk_vs_30x_156kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS.png, > trunk_vs_30x_24kcRPS_14kcWPS_load.png, trunk_vs_30x_31kcRPS_14kcWPS.png, > trunk_vs_30x_62kcRPS_14kcWPS.png, trunk_vs_30x_93kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_14kcRPS_14kcWPS.png, trunk_vs_30x_LQ_21kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_64kcRPS_14kcWPS.png, trunk_vs_30x_LQ_jdk_summary.png, > trunk_vs_30x_LQ_openssl_21kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_tcnative_summary.png, trunk_vs_30x_Q_21kcRPS_7200cWPS.png, > trunk_vs_30x_Q_36kcRPS_7200cWPS.png, trunk_vs_30x_summary.png > > > Tracks evaluating a 192 node cluster with compression and encryption on. > Test setup at (reproduced below) > [https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053] > > |Test Setup| | > |Baseline|3.0.19 > @d7d00036| > |Candiate|trunk > @abb0e177| > | | | > |Workload| | > |Write size|4kb random| > |Read size|4kb random| > |Per Node Data|110GiB| > |Generator|ndbench| > |Key Distribution|Uniform| > |SSTable Compr|Off| > |Internode TLS|On (jdk)| > |Internode Compr|On| > |Compaction|LCS (320 MiB)| > |Repair|Off| > | | | > |Hardware| | > |Instance Type|i3.xlarge| > |Deployment|96 us-east-1, 96 eu-west-1| > |Region node count|96| > | | | > |OS Settings| | > |IO scheduler|kyber| > |Net qdisc|tc-fq| > |readahead|32kb| > |Java Version|OpenJDK 1.8.0_202 (Zulu)| > | | | -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[ https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16874475#comment-16874475 ] Norman Maurer commented on CASSANDRA-15175: --- [~jolynch] so is it fair to say that there is nothing for me to investigate for now on the Netty side ? > Evaluate 200 node, compression=on, encryption=all > - > > Key: CASSANDRA-15175 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15175 > Project: Cassandra > Issue Type: Sub-task > Components: Test/benchmark >Reporter: Joseph Lynch >Assignee: Joseph Lynch >Priority: Normal > Attachments: 30x_14400cRPS-14400cWPS.svg, > 30x_LQ_21600cRPS-14400cWPS.svg, ShortbufferExceptions.png, > odd_netty_jdk_tls_cpu_usage.png, trunk_14400cRPS-14400cWPS.svg, > trunk_187000cRPS-14400cWPS.svg, trunk_187kcRPS_14kcWPS.png, > trunk_22000cRPS-14400cWPS-jdk.svg, trunk_22000cRPS-14400cWPS-openssl.svg, > trunk_220kcRPS_14kcWPS.png, trunk_252kcRPS-14kcWPS.png, > trunk_93500cRPS-14400cWPS.svg, trunk_LQ_14400cRPS-14400cWPS.svg, > trunk_LQ_21600cRPS-14400cWPS.svg, trunk_vs_30x_125kcRPS_14kcWPS.png, > trunk_vs_30x_14kRPS_14kcWPS_load.png, trunk_vs_30x_14kcRPS_14kcWPS.png, > trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png, > trunk_vs_30x_156kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS.png, > trunk_vs_30x_24kcRPS_14kcWPS_load.png, trunk_vs_30x_31kcRPS_14kcWPS.png, > trunk_vs_30x_62kcRPS_14kcWPS.png, trunk_vs_30x_93kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_14kcRPS_14kcWPS.png, trunk_vs_30x_LQ_21kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_64kcRPS_14kcWPS.png, trunk_vs_30x_LQ_jdk_summary.png, > trunk_vs_30x_LQ_openssl_21kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_tcnative_summary.png, trunk_vs_30x_summary.png > > > Tracks evaluating a 192 node cluster with compression and encryption on. > Test setup at (reproduced below) > [https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053] > > |Test Setup| | > |Baseline|3.0.19 > @d7d00036| > |Candiate|trunk > @abb0e177| > | | | > |Workload| | > |Write size|4kb random| > |Read size|4kb random| > |Per Node Data|110GiB| > |Generator|ndbench| > |Key Distribution|Uniform| > |SSTable Compr|Off| > |Internode TLS|On (jdk)| > |Internode Compr|On| > |Compaction|LCS (320 MiB)| > |Repair|Off| > | | | > |Hardware| | > |Instance Type|i3.xlarge| > |Deployment|96 us-east-1, 96 eu-west-1| > |Region node count|96| > | | | > |OS Settings| | > |IO scheduler|kyber| > |Net qdisc|tc-fq| > |readahead|32kb| > |Java Version|OpenJDK 1.8.0_202 (Zulu)| > | | | -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[
https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16874410#comment-16874410
]
Joseph Lynch commented on CASSANDRA-15175:
--
Alright, I've run the scaling test with both (jdk) TLS and (openssl) TLS (I
dropped the statically linked boringssl jar).
With jdk TLS after switching the default cipher to
{{TLS_RSA_WITH_AES_128_CBC_SHA}}:
!trunk_vs_30x_LQ_jdk_summary.png!
With openssl TLS again with the default cipher the same as 30x:
!trunk_vs_30x_LQ_tcnative_summary.png!
So the summary is, we have a minor regression in average performance for
LOCAL_QUORUM. Flamegraphs are attached for root cause. The good news is that
the tail is significantly better.
Action items:
* Make sure that cipher we use isn't GCM by default
* Determine why writes got slower, still outstanding
I am now moving on to a QUORUM test.
> Evaluate 200 node, compression=on, encryption=all
> -
>
> Key: CASSANDRA-15175
> URL: https://issues.apache.org/jira/browse/CASSANDRA-15175
> Project: Cassandra
> Issue Type: Sub-task
> Components: Test/benchmark
>Reporter: Joseph Lynch
>Assignee: Joseph Lynch
>Priority: Normal
> Attachments: 30x_14400cRPS-14400cWPS.svg,
> 30x_LQ_21600cRPS-14400cWPS.svg, ShortbufferExceptions.png,
> odd_netty_jdk_tls_cpu_usage.png, trunk_14400cRPS-14400cWPS.svg,
> trunk_187000cRPS-14400cWPS.svg, trunk_187kcRPS_14kcWPS.png,
> trunk_22000cRPS-14400cWPS-jdk.svg, trunk_22000cRPS-14400cWPS-openssl.svg,
> trunk_220kcRPS_14kcWPS.png, trunk_252kcRPS-14kcWPS.png,
> trunk_93500cRPS-14400cWPS.svg, trunk_LQ_14400cRPS-14400cWPS.svg,
> trunk_LQ_21600cRPS-14400cWPS.svg, trunk_vs_30x_125kcRPS_14kcWPS.png,
> trunk_vs_30x_14kRPS_14kcWPS_load.png, trunk_vs_30x_14kcRPS_14kcWPS.png,
> trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png,
> trunk_vs_30x_156kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS.png,
> trunk_vs_30x_24kcRPS_14kcWPS_load.png, trunk_vs_30x_31kcRPS_14kcWPS.png,
> trunk_vs_30x_62kcRPS_14kcWPS.png, trunk_vs_30x_93kcRPS_14kcWPS.png,
> trunk_vs_30x_LQ_14kcRPS_14kcWPS.png, trunk_vs_30x_LQ_21kcRPS_14kcWPS.png,
> trunk_vs_30x_LQ_64kcRPS_14kcWPS.png, trunk_vs_30x_LQ_jdk_summary.png,
> trunk_vs_30x_LQ_openssl_21kcRPS_14kcWPS.png,
> trunk_vs_30x_LQ_tcnative_summary.png, trunk_vs_30x_summary.png
>
>
> Tracks evaluating a 192 node cluster with compression and encryption on.
> Test setup at (reproduced below)
> [https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053]
>
> |Test Setup| |
> |Baseline|3.0.19
> @d7d00036|
> |Candiate|trunk
> @abb0e177|
> | | |
> |Workload| |
> |Write size|4kb random|
> |Read size|4kb random|
> |Per Node Data|110GiB|
> |Generator|ndbench|
> |Key Distribution|Uniform|
> |SSTable Compr|Off|
> |Internode TLS|On (jdk)|
> |Internode Compr|On|
> |Compaction|LCS (320 MiB)|
> |Repair|Off|
> | | |
> |Hardware| |
> |Instance Type|i3.xlarge|
> |Deployment|96 us-east-1, 96 eu-west-1|
> |Region node count|96|
> | | |
> |OS Settings| |
> |IO scheduler|kyber|
> |Net qdisc|tc-fq|
> |readahead|32kb|
> |Java Version|OpenJDK 1.8.0_202 (Zulu)|
> | | |
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
-
To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org
For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[ https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16871894#comment-16871894 ] Joseph Lynch commented on CASSANDRA-15175: -- I switched to the same cipher that 3.0 is running and saw a reduction of on CPU time to 12.9% (compared to 3.0's 8.5%). This is a significant improvement but still not quite equal. Interestingly with that improvement average latency is now on par with 3.0 in the local quorum test. [^trunk_LQ_21600cRPS-14400cWPS.svg] [^30x_LQ_21600cRPS-14400cWPS.svg] I'm going to finish off this round of jdk TLS testing and then switch to tcnative tomorrow and test that. > Evaluate 200 node, compression=on, encryption=all > - > > Key: CASSANDRA-15175 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15175 > Project: Cassandra > Issue Type: Sub-task > Components: Test/benchmark >Reporter: Joseph Lynch >Assignee: Joseph Lynch >Priority: Normal > Attachments: 30x_14400cRPS-14400cWPS.svg, > 30x_LQ_21600cRPS-14400cWPS.svg, ShortbufferExceptions.png, > odd_netty_jdk_tls_cpu_usage.png, trunk_14400cRPS-14400cWPS.svg, > trunk_187000cRPS-14400cWPS.svg, trunk_187kcRPS_14kcWPS.png, > trunk_22000cRPS-14400cWPS-jdk.svg, trunk_22000cRPS-14400cWPS-openssl.svg, > trunk_220kcRPS_14kcWPS.png, trunk_252kcRPS-14kcWPS.png, > trunk_93500cRPS-14400cWPS.svg, trunk_LQ_14400cRPS-14400cWPS.svg, > trunk_LQ_21600cRPS-14400cWPS.svg, trunk_vs_30x_125kcRPS_14kcWPS.png, > trunk_vs_30x_14kRPS_14kcWPS_load.png, trunk_vs_30x_14kcRPS_14kcWPS.png, > trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png, > trunk_vs_30x_156kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS.png, > trunk_vs_30x_24kcRPS_14kcWPS_load.png, trunk_vs_30x_31kcRPS_14kcWPS.png, > trunk_vs_30x_62kcRPS_14kcWPS.png, trunk_vs_30x_93kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_14kcRPS_14kcWPS.png, trunk_vs_30x_summary.png > > > Tracks evaluating a 192 node cluster with compression and encryption on. > Test setup at (reproduced below) > [https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053] > > |Test Setup| | > |Baseline|3.0.19 > @d7d00036| > |Candiate|trunk > @abb0e177| > | | | > |Workload| | > |Write size|4kb random| > |Read size|4kb random| > |Per Node Data|110GiB| > |Generator|ndbench| > |Key Distribution|Uniform| > |SSTable Compr|Off| > |Internode TLS|On (jdk)| > |Internode Compr|On| > |Compaction|LCS (320 MiB)| > |Repair|Off| > | | | > |Hardware| | > |Instance Type|i3.xlarge| > |Deployment|96 us-east-1, 96 eu-west-1| > |Region node count|96| > | | | > |OS Settings| | > |IO scheduler|kyber| > |Net qdisc|tc-fq| > |readahead|32kb| > |Java Version|OpenJDK 1.8.0_202 (Zulu)| > | | | -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[ https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16871778#comment-16871778 ] Norman Maurer commented on CASSANDRA-15175: --- [~jolynch] Yes please use a non GCM cipher and report back :) > Evaluate 200 node, compression=on, encryption=all > - > > Key: CASSANDRA-15175 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15175 > Project: Cassandra > Issue Type: Sub-task > Components: Test/benchmark >Reporter: Joseph Lynch >Assignee: Joseph Lynch >Priority: Normal > Attachments: 30x_14400cRPS-14400cWPS.svg, ShortbufferExceptions.png, > odd_netty_jdk_tls_cpu_usage.png, trunk_14400cRPS-14400cWPS.svg, > trunk_187000cRPS-14400cWPS.svg, trunk_187kcRPS_14kcWPS.png, > trunk_22000cRPS-14400cWPS-jdk.svg, trunk_22000cRPS-14400cWPS-openssl.svg, > trunk_220kcRPS_14kcWPS.png, trunk_252kcRPS-14kcWPS.png, > trunk_93500cRPS-14400cWPS.svg, trunk_LQ_14400cRPS-14400cWPS.svg, > trunk_vs_30x_125kcRPS_14kcWPS.png, trunk_vs_30x_14kRPS_14kcWPS_load.png, > trunk_vs_30x_14kcRPS_14kcWPS.png, > trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png, > trunk_vs_30x_156kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS.png, > trunk_vs_30x_24kcRPS_14kcWPS_load.png, trunk_vs_30x_31kcRPS_14kcWPS.png, > trunk_vs_30x_62kcRPS_14kcWPS.png, trunk_vs_30x_93kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_14kcRPS_14kcWPS.png, trunk_vs_30x_summary.png > > > Tracks evaluating a 192 node cluster with compression and encryption on. > Test setup at (reproduced below) > [https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053] > > |Test Setup| | > |Baseline|3.0.19 > @d7d00036| > |Candiate|trunk > @abb0e177| > | | | > |Workload| | > |Write size|4kb random| > |Read size|4kb random| > |Per Node Data|110GiB| > |Generator|ndbench| > |Key Distribution|Uniform| > |SSTable Compr|Off| > |Internode TLS|On (jdk)| > |Internode Compr|On| > |Compaction|LCS (320 MiB)| > |Repair|Off| > | | | > |Hardware| | > |Instance Type|i3.xlarge| > |Deployment|96 us-east-1, 96 eu-west-1| > |Region node count|96| > | | | > |OS Settings| | > |IO scheduler|kyber| > |Net qdisc|tc-fq| > |readahead|32kb| > |Java Version|OpenJDK 1.8.0_202 (Zulu)| > | | | -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[
https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16871774#comment-16871774
]
Joseph Lynch commented on CASSANDRA-15175:
--
[~norman] yeah sadly I don't see any exceptions in the C* code that correlate
with that exception, but I can try enabling more verbose logging on particular
netty modules if you think it will help? Also fwiw I think that the 3.0 branch
in this test is using {{TLS_RSA_WITH_AES_128_CBC_SHA}} as the default cipher
instead of {{TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384}}. I don't really know
what I'm talking about when it comes to TLS cipher suites but it appears from
my reading of https://bugs.openjdk.java.net/browse/JDK-8046943 that {{GCM}} is
very slow in Java 8 (apparently fixed in Java 9). That might explain why we're
spending so much CPU time in GaloisCountMode (which I assume is GCM). I can try
using {{TLS_RSA_WITH_AES_256_CBC_SHA}} with both as a fair test?
> Evaluate 200 node, compression=on, encryption=all
> -
>
> Key: CASSANDRA-15175
> URL: https://issues.apache.org/jira/browse/CASSANDRA-15175
> Project: Cassandra
> Issue Type: Sub-task
> Components: Test/benchmark
>Reporter: Joseph Lynch
>Assignee: Joseph Lynch
>Priority: Normal
> Attachments: 30x_14400cRPS-14400cWPS.svg, ShortbufferExceptions.png,
> odd_netty_jdk_tls_cpu_usage.png, trunk_14400cRPS-14400cWPS.svg,
> trunk_187000cRPS-14400cWPS.svg, trunk_187kcRPS_14kcWPS.png,
> trunk_22000cRPS-14400cWPS-jdk.svg, trunk_22000cRPS-14400cWPS-openssl.svg,
> trunk_220kcRPS_14kcWPS.png, trunk_252kcRPS-14kcWPS.png,
> trunk_93500cRPS-14400cWPS.svg, trunk_LQ_14400cRPS-14400cWPS.svg,
> trunk_vs_30x_125kcRPS_14kcWPS.png, trunk_vs_30x_14kRPS_14kcWPS_load.png,
> trunk_vs_30x_14kcRPS_14kcWPS.png,
> trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png,
> trunk_vs_30x_156kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS.png,
> trunk_vs_30x_24kcRPS_14kcWPS_load.png, trunk_vs_30x_31kcRPS_14kcWPS.png,
> trunk_vs_30x_62kcRPS_14kcWPS.png, trunk_vs_30x_93kcRPS_14kcWPS.png,
> trunk_vs_30x_LQ_14kcRPS_14kcWPS.png, trunk_vs_30x_summary.png
>
>
> Tracks evaluating a 192 node cluster with compression and encryption on.
> Test setup at (reproduced below)
> [https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053]
>
> |Test Setup| |
> |Baseline|3.0.19
> @d7d00036|
> |Candiate|trunk
> @abb0e177|
> | | |
> |Workload| |
> |Write size|4kb random|
> |Read size|4kb random|
> |Per Node Data|110GiB|
> |Generator|ndbench|
> |Key Distribution|Uniform|
> |SSTable Compr|Off|
> |Internode TLS|On (jdk)|
> |Internode Compr|On|
> |Compaction|LCS (320 MiB)|
> |Repair|Off|
> | | |
> |Hardware| |
> |Instance Type|i3.xlarge|
> |Deployment|96 us-east-1, 96 eu-west-1|
> |Region node count|96|
> | | |
> |OS Settings| |
> |IO scheduler|kyber|
> |Net qdisc|tc-fq|
> |readahead|32kb|
> |Java Version|OpenJDK 1.8.0_202 (Zulu)|
> | | |
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
-
To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org
For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[ https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16871727#comment-16871727 ] Norman Maurer commented on CASSANDRA-15175: --- [~jolynch] yeah that is why I ask... From the OpenJDK code it seems like `ShortBufferException` should really "never happen". That is why I ask about errors. > Evaluate 200 node, compression=on, encryption=all > - > > Key: CASSANDRA-15175 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15175 > Project: Cassandra > Issue Type: Sub-task > Components: Test/benchmark >Reporter: Joseph Lynch >Assignee: Joseph Lynch >Priority: Normal > Attachments: 30x_14400cRPS-14400cWPS.svg, ShortbufferExceptions.png, > odd_netty_jdk_tls_cpu_usage.png, trunk_14400cRPS-14400cWPS.svg, > trunk_187000cRPS-14400cWPS.svg, trunk_187kcRPS_14kcWPS.png, > trunk_22000cRPS-14400cWPS-jdk.svg, trunk_22000cRPS-14400cWPS-openssl.svg, > trunk_220kcRPS_14kcWPS.png, trunk_252kcRPS-14kcWPS.png, > trunk_93500cRPS-14400cWPS.svg, trunk_LQ_14400cRPS-14400cWPS.svg, > trunk_vs_30x_125kcRPS_14kcWPS.png, trunk_vs_30x_14kRPS_14kcWPS_load.png, > trunk_vs_30x_14kcRPS_14kcWPS.png, > trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png, > trunk_vs_30x_156kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS.png, > trunk_vs_30x_24kcRPS_14kcWPS_load.png, trunk_vs_30x_31kcRPS_14kcWPS.png, > trunk_vs_30x_62kcRPS_14kcWPS.png, trunk_vs_30x_93kcRPS_14kcWPS.png, > trunk_vs_30x_LQ_14kcRPS_14kcWPS.png, trunk_vs_30x_summary.png > > > Tracks evaluating a 192 node cluster with compression and encryption on. > Test setup at (reproduced below) > [https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053] > > |Test Setup| | > |Baseline|3.0.19 > @d7d00036| > |Candiate|trunk > @abb0e177| > | | | > |Workload| | > |Write size|4kb random| > |Read size|4kb random| > |Per Node Data|110GiB| > |Generator|ndbench| > |Key Distribution|Uniform| > |SSTable Compr|Off| > |Internode TLS|On (jdk)| > |Internode Compr|On| > |Compaction|LCS (320 MiB)| > |Repair|Off| > | | | > |Hardware| | > |Instance Type|i3.xlarge| > |Deployment|96 us-east-1, 96 eu-west-1| > |Region node count|96| > | | | > |OS Settings| | > |IO scheduler|kyber| > |Net qdisc|tc-fq| > |readahead|32kb| > |Java Version|OpenJDK 1.8.0_202 (Zulu)| > | | | -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[
https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16871714#comment-16871714
]
Joseph Lynch commented on CASSANDRA-15175:
--
{quote}
[~jolynch] one question... when using JDK TLS do you see any errors at all or
you just see more CPU usage and thats it ?
{quote}
I don't see any errors in our logs but we are spending more CPU handling
{{ShortBufferExceptions}} internally to Netty then may make sense. I took the
following screenshots from the [^trunk_LQ_14400cRPS-14400cWPS.svg] flamegraph.
!odd_netty_jdk_tls_cpu_usage.png!
!ShortbufferExceptions.png!
Other than the flamegraph and degraded latency in {{LOCAL_QUORUM}} mode (where
C* nodes actually have to talk to each other through the internode messaging
framework), things appear about the same (no errors that I can see).
> Evaluate 200 node, compression=on, encryption=all
> -
>
> Key: CASSANDRA-15175
> URL: https://issues.apache.org/jira/browse/CASSANDRA-15175
> Project: Cassandra
> Issue Type: Sub-task
> Components: Test/benchmark
>Reporter: Joseph Lynch
>Assignee: Joseph Lynch
>Priority: Normal
> Attachments: 30x_14400cRPS-14400cWPS.svg, ShortbufferExceptions.png,
> odd_netty_jdk_tls_cpu_usage.png, trunk_14400cRPS-14400cWPS.svg,
> trunk_187000cRPS-14400cWPS.svg, trunk_187kcRPS_14kcWPS.png,
> trunk_22000cRPS-14400cWPS-jdk.svg, trunk_22000cRPS-14400cWPS-openssl.svg,
> trunk_220kcRPS_14kcWPS.png, trunk_252kcRPS-14kcWPS.png,
> trunk_93500cRPS-14400cWPS.svg, trunk_LQ_14400cRPS-14400cWPS.svg,
> trunk_vs_30x_125kcRPS_14kcWPS.png, trunk_vs_30x_14kRPS_14kcWPS_load.png,
> trunk_vs_30x_14kcRPS_14kcWPS.png,
> trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png,
> trunk_vs_30x_156kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS.png,
> trunk_vs_30x_24kcRPS_14kcWPS_load.png, trunk_vs_30x_31kcRPS_14kcWPS.png,
> trunk_vs_30x_62kcRPS_14kcWPS.png, trunk_vs_30x_93kcRPS_14kcWPS.png,
> trunk_vs_30x_LQ_14kcRPS_14kcWPS.png, trunk_vs_30x_summary.png
>
>
> Tracks evaluating a 192 node cluster with compression and encryption on.
> Test setup at (reproduced below)
> [https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053]
>
> |Test Setup| |
> |Baseline|3.0.19
> @d7d00036|
> |Candiate|trunk
> @abb0e177|
> | | |
> |Workload| |
> |Write size|4kb random|
> |Read size|4kb random|
> |Per Node Data|110GiB|
> |Generator|ndbench|
> |Key Distribution|Uniform|
> |SSTable Compr|Off|
> |Internode TLS|On (jdk)|
> |Internode Compr|On|
> |Compaction|LCS (320 MiB)|
> |Repair|Off|
> | | |
> |Hardware| |
> |Instance Type|i3.xlarge|
> |Deployment|96 us-east-1, 96 eu-west-1|
> |Region node count|96|
> | | |
> |OS Settings| |
> |IO scheduler|kyber|
> |Net qdisc|tc-fq|
> |readahead|32kb|
> |Java Version|OpenJDK 1.8.0_202 (Zulu)|
> | | |
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
-
To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org
For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[ https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16871684#comment-16871684 ] Norman Maurer commented on CASSANDRA-15175: --- [~jolynch] one question... when using JDK TLS do you see any errors at all or you just see more CPU usage and thats it ? > Evaluate 200 node, compression=on, encryption=all > - > > Key: CASSANDRA-15175 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15175 > Project: Cassandra > Issue Type: Sub-task > Components: Test/benchmark >Reporter: Joseph Lynch >Assignee: Joseph Lynch >Priority: Normal > Attachments: 30x_14400cRPS-14400cWPS.svg, > trunk_14400cRPS-14400cWPS.svg, trunk_187000cRPS-14400cWPS.svg, > trunk_187kcRPS_14kcWPS.png, trunk_22000cRPS-14400cWPS-jdk.svg, > trunk_22000cRPS-14400cWPS-openssl.svg, trunk_220kcRPS_14kcWPS.png, > trunk_252kcRPS-14kcWPS.png, trunk_93500cRPS-14400cWPS.svg, > trunk_vs_30x_125kcRPS_14kcWPS.png, trunk_vs_30x_14kRPS_14kcWPS_load.png, > trunk_vs_30x_14kcRPS_14kcWPS.png, > trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png, > trunk_vs_30x_156kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS.png, > trunk_vs_30x_24kcRPS_14kcWPS_load.png, trunk_vs_30x_31kcRPS_14kcWPS.png, > trunk_vs_30x_62kcRPS_14kcWPS.png, trunk_vs_30x_93kcRPS_14kcWPS.png, > trunk_vs_30x_summary.png > > > Tracks evaluating a 192 node cluster with compression and encryption on. > Test setup at (reproduced below) > [https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053] > > |Test Setup| | > |Baseline|3.0.19 > @d7d00036| > |Candiate|trunk > @abb0e177| > | | | > |Workload| | > |Write size|4kb random| > |Read size|4kb random| > |Per Node Data|110GiB| > |Generator|ndbench| > |Key Distribution|Uniform| > |SSTable Compr|Off| > |Internode TLS|On (jdk)| > |Internode Compr|On| > |Compaction|LCS (320 MiB)| > |Repair|Off| > | | | > |Hardware| | > |Instance Type|i3.xlarge| > |Deployment|96 us-east-1, 96 eu-west-1| > |Region node count|96| > | | | > |OS Settings| | > |IO scheduler|kyber| > |Net qdisc|tc-fq| > |readahead|32kb| > |Java Version|OpenJDK 1.8.0_202 (Zulu)| > | | | -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[
https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16871656#comment-16871656
]
Joseph Lynch commented on CASSANDRA-15175:
--
I have completed the {{LOCAL_ONE}} scaling test. I have summarized the test in
the following graph:
!trunk_vs_30x_summary.png!
As we can see, even with the extra TLS CPU requirements, trunk was able to
significantly outperform the status quo 3.0.x cluster across the load spectrum
for this consistency level
I am proceeding with other consistency levels and gathering additional data.
So far I have noticed the following issues during these tests which I will
gather more data on and follow up with in other tickets (and edit here with
ticket numbers once I have them):
# JDK Netty TLS appears significantly more CPU intensive than the previous
Java Sockets implementation. [~norman] is taking a look from the Netty side and
we can follow up and make sure we're not creating improperly (looking at the
flamegraphs it looks like we may have a buffer sizing issue)
# When a node was terminated and replaced, the new node appeared to sit for a
very long time waiting for schema pulls to complete (I think it was waiting on
the node it was replacing but I haven't fully debugged this).
# Nodetool netstats doesn't report progress properly for the file count
(percent, single file, and size still seem right; this is probably
CASSANDRA-14192
# When we re-load NTS keyspaces from disk we throw warnings about "Ignoring
Unrecognized strategy option" for datacenters that we are not in
# After a node shuts down there is a burst of re-connections on the urgent
port prior to actual shutdown (I _think_ this is pre-existing and I'm just
noticing it because of the new logging)
Also while setting up the {{LOCAL_QUORUM}} test I found the following trying to
understand why I was seeing a higher number of blocking read repairs on the
trunk cluster than the 30x cluster:
# When I stop and start nodes, it appears that hints may not always playback.
In particular the high blocking read repairs were coming from neighbors of the
node I had restarted a few times to test tcnative openssl integration. I
checked the neighbor's hints directories and sure enough there were pending
hints there that were not playing at all (they had been there for over 8 hours
and still not played).
# Repair appears to fail on the default system_traces when run with {{-full}}
and \{{-os}
{noformat}
cass-perf-trunk-14746--useast1c-i-00a32889835534b75:~$ nodetool repair -os
-full -local
[2019-06-23 23:29:30,210] Starting repair command #1
(bfbc7ba0-960e-11e9-b238-77fd1c2e9b1c), repairing keyspace perftest with repair
options (parallelism: parallel, primary range: false, incremental: false, job
threads: 1, ColumnFamilies: [], dataCenters: [us-east-1], hosts: [],
previewKind: NONE, # of ranges: 6, pull repair: false, force repair: false,
optimise streams: true)
[2019-06-23 23:52:08,248] Repair session c0573500-960e-11e9-b238-77fd1c2e9b1c
for range [(384307168575030403,384307170010857891],
(192153585909716729,384307168575030403]] finished (progress: 10%)
[2019-06-23 23:52:26,393] Repair session c0307320-960e-11e9-b238-77fd1c2e9b1c
for range [(1808575567,192153584473889241],
(192153584473889241,192153585909716729]] finished (progress: 20%)
[2019-06-23 23:52:28,298] Repair session c059f420-960e-11e9-b238-77fd1c2e9b1c
for range [(576460752676171565,576460754111999053],
(384307170010857891,576460752676171565]] finished (progress: 30%)
[2019-06-23 23:52:28,302] Repair completed successfully
[2019-06-23 23:52:28,310] Repair command #1 finished in 22 minutes 58 seconds
[2019-06-23 23:52:28,331] Replication factor is 1. No repair is needed for
keyspace 'system_auth'
[2019-06-23 23:52:28,350] Starting repair command #2
(f52c1c70-9611-11e9-b238-77fd1c2e9b1c), repairing keyspace system_traces with
repair options (parallelism: parallel, primary range: false, incremental:
false, job threads: 1, ColumnFamilies: [], dataCenters: [us-east-1], hosts: [],
previewKind: NONE, # of ranges: 2, pull repair: false, force repair: false,
optimise streams: true)
[2019-06-23 23:52:28,351] Repair command #2 failed with error Endpoints can not
be empty
[2019-06-23 23:52:28,351] Repair command #2 finished with error
error: Repair job has failed with the error message: [2019-06-23 23:52:28,351]
Repair command #2 failed with error Endpoints can not be empty. Check the logs
on the repair participants for further details
-- StackTrace --
java.lang.RuntimeException: Repair job has failed with the error message:
[2019-06-23 23:52:28,351] Repair command #2 failed with error Endpoints can not
be empty. Check the logs on the repair participants for further details
at
org.apache.cassandra.tools.RepairRunner.progress(RepairRunner.java:122)
at
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[
https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16870615#comment-16870615
]
Joseph Lynch commented on CASSANDRA-15175:
--
We just use the default protocol and cipher suite via netty's
SslContextBuilder. I believe that means
{{TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384}} if I understand the following
logging properly:
{noformat}
$ grep "Default cipher " debug.log -C 2
DEBUG [main] 2019-06-23 18:24:31,158 Slf4JLogger.java:71 - netty-tcnative not
in the classpath; OpenSslEngine will be unavailable.
DEBUG [main] 2019-06-23 18:24:31,735 Slf4JLogger.java:76 - Default protocols
(JDK): [TLSv1.2, TLSv1.1, TLSv1]
DEBUG [main] 2019-06-23 18:24:31,736 Slf4JLogger.java:76 - Default cipher
suites (JDK): [TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,
TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256, TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,
TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA, TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA,
TLS_RSA_WITH_AES_128_GCM_SHA256, TLS_RSA_WITH_AES_128_CBC_SHA,
TLS_RSA_WITH_AES_256_CBC_SHA]
{noformat}
> Evaluate 200 node, compression=on, encryption=all
> -
>
> Key: CASSANDRA-15175
> URL: https://issues.apache.org/jira/browse/CASSANDRA-15175
> Project: Cassandra
> Issue Type: Sub-task
> Components: Test/benchmark
>Reporter: Joseph Lynch
>Assignee: Joseph Lynch
>Priority: Normal
> Attachments: 30x_14400cRPS-14400cWPS.svg,
> trunk_14400cRPS-14400cWPS.svg, trunk_187000cRPS-14400cWPS.svg,
> trunk_187kcRPS_14kcWPS.png, trunk_93500cRPS-14400cWPS.svg,
> trunk_vs_30x_125kcRPS_14kcWPS.png, trunk_vs_30x_14kRPS_14kcWPS_load.png,
> trunk_vs_30x_14kcRPS_14kcWPS.png,
> trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png,
> trunk_vs_30x_156kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS.png,
> trunk_vs_30x_24kcRPS_14kcWPS_load.png, trunk_vs_30x_31kcRPS_14kcWPS.png,
> trunk_vs_30x_62kcRPS_14kcWPS.png, trunk_vs_30x_93kcRPS_14kcWPS.png
>
>
> Tracks evaluating a 192 node cluster with compression and encryption on.
> Test setup at (reproduced below)
> [https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053]
>
> |Test Setup| |
> |Baseline|3.0.19
> @d7d00036|
> |Candiate|trunk
> @abb0e177|
> | | |
> |Workload| |
> |Write size|4kb random|
> |Read size|4kb random|
> |Per Node Data|110GiB|
> |Generator|ndbench|
> |Key Distribution|Uniform|
> |SSTable Compr|Off|
> |Internode TLS|On|
> |Internode Compr|On|
> |Compaction|LCS (320 MiB)|
> |Repair|Off|
> | | |
> |Hardware| |
> |Instance Type|i3.xlarge|
> |Deployment|96 us-east-1, 96 eu-west-1|
> |Region node count|96|
> | | |
> |OS Settings| |
> |IO scheduler|kyber|
> |Net qdisc|tc-fq|
> |readahead|32kb|
> |Java Version|OpenJDK 1.8.0_202 (Zulu)|
> | | |
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
-
To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org
For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[ https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16870444#comment-16870444 ] Norman Maurer commented on CASSANDRA-15175: --- Los please include the cipher that is used > Evaluate 200 node, compression=on, encryption=all > - > > Key: CASSANDRA-15175 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15175 > Project: Cassandra > Issue Type: Sub-task > Components: Test/benchmark >Reporter: Joseph Lynch >Assignee: Joseph Lynch >Priority: Normal > Attachments: 30x_14400cRPS-14400cWPS.svg, > trunk_14400cRPS-14400cWPS.svg, trunk_187000cRPS-14400cWPS.svg, > trunk_93500cRPS-14400cWPS.svg, trunk_vs_30x_125kcRPS_14kcWPS.png, > trunk_vs_30x_14kRPS_14kcWPS_load.png, trunk_vs_30x_14kcRPS_14kcWPS.png, > trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png, > trunk_vs_30x_156kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS.png, > trunk_vs_30x_24kcRPS_14kcWPS_load.png, trunk_vs_30x_31kcRPS_14kcWPS.png, > trunk_vs_30x_62kcRPS_14kcWPS.png, trunk_vs_30x_93kcRPS_14kcWPS.png > > > Tracks evaluating a 192 node cluster with compression and encryption on. > Test setup at (reproduced below) > [https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053] > > |Test Setup| | > |Baseline|3.0.19 > @d7d00036| > |Candiate|trunk > @abb0e177| > | | | > |Workload| | > |Write size|4kb random| > |Read size|4kb random| > |Per Node Data|110GiB| > |Generator|ndbench| > |Key Distribution|Uniform| > |SSTable Compr|Off| > |Internode TLS|On| > |Internode Compr|On| > |Compaction|LCS (320 MiB)| > |Repair|Off| > | | | > |Hardware| | > |Instance Type|i3.xlarge| > |Deployment|96 us-east-1, 96 eu-west-1| > |Region node count|96| > | | | > |OS Settings| | > |IO scheduler|kyber| > |Net qdisc|tc-fq| > |readahead|32kb| > |Java Version|OpenJDK 1.8.0_202 (Zulu)| > | | | -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[
https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16870303#comment-16870303
]
Joseph Lynch commented on CASSANDRA-15175:
--
[~norman] thanks for helping out!. We're running OpenJDK 1.8.0_202 (Azul Zulu
builds) and this is using jdk SSL. I'll re-run the tests with OpenSSL as well
to see if that has different results as well.
{noformat}
$ java -version
openjdk version "1.8.0_202"
OpenJDK Runtime Environment (Zulu 8.36.0.2-SA-linux64) (build 1.8.0_202-b05)
OpenJDK 64-Bit Server VM (Zulu 8.36.0.2-SA-linux64) (build 25.202-b05, mixed
mode)
{noformat}
We've got a bunch more tests we need to run with this cluster but we can likely
re-produce on a smaller cluster if you want us to test something.
> Evaluate 200 node, compression=on, encryption=all
> -
>
> Key: CASSANDRA-15175
> URL: https://issues.apache.org/jira/browse/CASSANDRA-15175
> Project: Cassandra
> Issue Type: Sub-task
> Components: Test/benchmark
>Reporter: Joseph Lynch
>Assignee: Joseph Lynch
>Priority: Normal
> Attachments: 30x_14400cRPS-14400cWPS.svg,
> trunk_14400cRPS-14400cWPS.svg, trunk_vs_30x_14kRPS_14kcWPS_load.png,
> trunk_vs_30x_14kcRPS_14kcWPS.png,
> trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png,
> trunk_vs_30x_24kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS_load.png
>
>
> Tracks evaluating a 192 node cluster with compression and encryption on.
> Test setup at (reproduced below)
> [https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053]
>
> |Test Setup| |
> |Baseline|3.0.19
> @d7d00036|
> |Candiate|trunk
> @abb0e177|
> | | |
> |Workload| |
> |Write size|4kb random|
> |Read size|4kb random|
> |Per Node Data|110GiB|
> |Generator|ndbench|
> |Key Distribution|Uniform|
> |SSTable Compr|Off|
> |Internode TLS|On|
> |Internode Compr|On|
> |Compaction|LCS (320 MiB)|
> |Repair|Off|
> | | |
> |Hardware| |
> |Instance Type|i3.xlarge|
> |Deployment|96 us-east-1, 96 eu-west-1|
> |Region node count|96|
> | | |
> |OS Settings| |
> |IO scheduler|kyber|
> |Net qdisc|tc-fq|
> |readahead|32kb|
> |Java Version|OpenJDK 1.8.0_202 (Zulu)|
> | | |
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
-
To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org
For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[ https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16870256#comment-16870256 ] Norman Maurer commented on CASSANDRA-15175: --- Can you provide the full JDK version as well ? > Evaluate 200 node, compression=on, encryption=all > - > > Key: CASSANDRA-15175 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15175 > Project: Cassandra > Issue Type: Sub-task > Components: Test/benchmark >Reporter: Joseph Lynch >Assignee: Joseph Lynch >Priority: Normal > Attachments: 30x_14400cRPS-14400cWPS.svg, > trunk_14400cRPS-14400cWPS.svg, trunk_vs_30x_14kRPS_14kcWPS_load.png, > trunk_vs_30x_14kcRPS_14kcWPS.png, > trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png, > trunk_vs_30x_24kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS_load.png > > > Tracks evaluating a 192 node cluster with compression and encryption on. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[ https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16870255#comment-16870255 ] Norman Maurer commented on CASSANDRA-15175: --- I will have a Look > Evaluate 200 node, compression=on, encryption=all > - > > Key: CASSANDRA-15175 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15175 > Project: Cassandra > Issue Type: Sub-task > Components: Test/benchmark >Reporter: Joseph Lynch >Assignee: Joseph Lynch >Priority: Normal > Attachments: 30x_14400cRPS-14400cWPS.svg, > trunk_14400cRPS-14400cWPS.svg, trunk_vs_30x_14kRPS_14kcWPS_load.png, > trunk_vs_30x_14kcRPS_14kcWPS.png, > trunk_vs_30x_14kcRPS_14kcWPS_schedstat_delays.png, > trunk_vs_30x_24kcRPS_14kcWPS.png, trunk_vs_30x_24kcRPS_14kcWPS_load.png > > > Tracks evaluating a 192 node cluster with compression and encryption on. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org
[jira] [Commented] (CASSANDRA-15175) Evaluate 200 node, compression=on, encryption=all
[ https://issues.apache.org/jira/browse/CASSANDRA-15175?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16869939#comment-16869939 ] Joseph Lynch commented on CASSANDRA-15175: -- Test methedology is recorded in the data spreadsheet [https://docs.google.com/spreadsheets/d/1Vq_wC2q-rcG7UWim-t2leZZ4GgcuAjSREMFbG0QGy20/edit#gid=1336583053] I'm continuing the tests and seeing where we can get to, but we will likely want to debug why TLS is taking relatively more CPU time on trunk vs 3.0.x (although latencies appear better regardless). > Evaluate 200 node, compression=on, encryption=all > - > > Key: CASSANDRA-15175 > URL: https://issues.apache.org/jira/browse/CASSANDRA-15175 > Project: Cassandra > Issue Type: Sub-task > Components: Test/benchmark >Reporter: Joseph Lynch >Assignee: Joseph Lynch >Priority: Normal > Attachments: 30x_14400cRPS-14400cWPS.svg, > trunk_14400cRPS-14400cWPS.svg, trunk_vs_30x_14kcRPS_14kcWPS.png > > > Tracks evaluating a 192 node cluster with compression and encryption on. -- This message was sent by Atlassian JIRA (v7.6.3#76005) - To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org
