cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Ariel Weisberg (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (CASSANDRA-13530) GroupCommitLogService
Date Thu, 06 Jul 2017 17:44:00 GMT

    [ https://issues.apache.org/jira/browse/CASSANDRA-13530?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16076956#comment-16076956
] 

Ariel Weisberg commented on CASSANDRA-13530:
--------------------------------------------

You shouldn't set commitlog_sync_batch_window_in_ms and that might be hurting performance.
It's not meant to be a small number. The batch commit log syncs as soon as the first entry
arrives always. That's why at low concurrency it does well.

Can you increase the test to do a few million operations, and then run a warmup (in the same
client JVM) first? It really does take hotspot a long time to warm up at both client and server.
Basically put the test into a method you can call and then call it twice and report the values
from the second.

I don't need to see a huge matrix. Just UPDATE with batch and group at whatever value performs
best on your hardware. If that doesn't close the gap enough then there is a case to be made
that maybe you are better off using group commit log service to match the fsync frequency
your device supports with your workload.

> GroupCommitLogService
> ---------------------
>
>                 Key: CASSANDRA-13530
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-13530
>             Project: Cassandra
>          Issue Type: Improvement
>            Reporter: Yuji Ito
>            Assignee: Yuji Ito
>             Fix For: 2.2.x, 3.0.x, 3.11.x
>
>         Attachments: groupCommit22.patch, groupCommit30.patch, groupCommit3x.patch, groupCommitLog_result.xlsx,
GuavaRequestThread.java, MicroRequestThread.java
>
>
> I propose a new CommitLogService, GroupCommitLogService, to improve the throughput when
lots of requests are received.
> It improved the throughput by maximum 94%.
> I'd like to discuss about this CommitLogService.
> Currently, we can select either 2 CommitLog services; Periodic and Batch.
> In Periodic, we might lose some commit log which hasn't written to the disk.
> In Batch, we can write commit log to the disk every time. The size of commit log to write
is too small (< 4KB). When high concurrency, these writes are gathered and persisted to
the disk at once. But, when insufficient concurrency, many small writes are issued and the
performance decreases due to the latency of the disk. Even if you use SSD, processes of many
IO commands decrease the performance.
> GroupCommitLogService writes some commitlog to the disk at once.
> The patch adds GroupCommitLogService (It is enabled by setting `commitlog_sync` and `commitlog_sync_group_window_in_ms`
in cassandra.yaml).
> The difference from Batch is just only waiting for the semaphore.
> By waiting for the semaphore, some writes for commit logs are executed at the same time.
> In GroupCommitLogService, the latency becomes worse if the there is no concurrency.
> I measured the performance with my microbench (MicroRequestThread.java) by increasing
the number of threads.The cluster has 3 nodes (Replication factor: 3). Each nodes is AWS EC2
m4.large instance + 200IOPS io1 volume.
> The result is as below. The GroupCommitLogService with 10ms window improved update with
Paxos by 94% and improved select with Paxos by 76%.
> h6. SELECT / sec
> ||\# of threads||Batch 2ms||Group 10ms||
> |1|192|103|
> |2|163|212|
> |4|264|416|
> |8|454|800|
> |16|744|1311|
> |32|1151|1481|
> |64|1767|1844|
> |128|2949|3011|
> |256|4723|5000|
> h6. UPDATE / sec
> ||\# of threads||Batch 2ms||Group 10ms||
> |1|45|26|
> |2|39|51|
> |4|58|102|
> |8|102|198|
> |16|167|213|
> |32|289|295|
> |64|544|548|
> |128|1046|1058|
> |256|2020|2061|



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

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


Mime
View raw message