You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@kafka.apache.org by "Jay Kreps (JIRA)" <ji...@apache.org> on 2012/11/05 22:14:12 UTC
[jira] [Updated] (KAFKA-545) Add a Performance Suite for the Log
subsystem
[ https://issues.apache.org/jira/browse/KAFKA-545?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Jay Kreps updated KAFKA-545:
----------------------------
Attachment: KAFKA-545.patch
- Improve the existing TestLinearWriteSpeed.scala that does linear writes to a file. Now this prints latency/throughput info at a configurable period and allows writing to many files at once as well as using either mmap or write. This is a great test because it gives a bound on fs performance without any Kafka code involved.
- Added a test program that drives the LogManager level. Can write to any number of partitions and controls various configs.
- Add three test programs to test read and write locking in the OS. These are a bit hacky and I am fine leaving them on my machine too though they may come in handy again. (TestFileChannelLocking.scala, TestFileChannelReadLocking.scala, TestMmapLocking.scala)
Misc things
- Remove the reference to flushInterval in many tests. Lots of tests were setting this to 1 to commit messages immediately. That is no longer necessary in 0.8.
- Added a new configuration replica.highwatermark.checkpoint.ms to control the checkpointing of hwm. Previously we used the config for log sync, but that doesn't make sense.
- Added Log.toString method for convenience
- Added explicit check for maxSize < 0 and startOffset > endOffset in LogSegment.read
> Add a Performance Suite for the Log subsystem
> ---------------------------------------------
>
> Key: KAFKA-545
> URL: https://issues.apache.org/jira/browse/KAFKA-545
> Project: Kafka
> Issue Type: New Feature
> Affects Versions: 0.8
> Reporter: Jay Kreps
> Priority: Blocker
> Labels: features
> Attachments: KAFKA-545-draft.patch, KAFKA-545.patch
>
>
> We have had several performance concerns or potential improvements for the logging subsystem. To conduct these in a data-driven way, it would be good to have a single-machine performance test that isolated the performance of the log.
> The performance optimizations we would like to evaluate include
> - Special casing appends in a follower which already have the correct offset to avoid decompression and recompression
> - Memory mapping either all or some of the segment files to improve the performance of small appends and lookups
> - Supporting multiple data directories and avoiding RAID
> Having a standalone tool is nice to isolate the component and makes profiling more intelligible.
> This test would drive load against Log/LogManager controlled by a set of command line options. These command line program could then be scripted up into a suite of tests that covered variations in message size, message set size, compression, number of partitions, etc.
> Here is a proposed usage for the tool:
> ./bin/kafka-log-perf-test.sh
> Option Description
> ------ -----------
> --partitions The number of partitions to write to
> --dir The directory in which to write the log
> --message-size The size of the messages
> --set-size The number of messages per write
> --compression Compression alg
> --messages The number of messages to write
> --readers The number of reader threads reading the data
> The tool would capture latency and throughput for the append() and read() operations.
--
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