[
https://issues.apache.org/jira/browse/CASSANDRA-1765?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12964417#action_12964417
]
Eric Evans commented on CASSANDRA-1765:
---------------------------------------
The Avro tests are unnecessarily serializing and deserializing their own schema
as part of the messages. In real life both reader and writer would have the
schema, readers/writers would store it (once)/read it, to/from the file format,
or handshake it (once) on an RPC session.
The attached patch (v1-0001-CASSANDRA-1765-don-t-ser-dser-schema-string.txt)
fixes this.
Results run on my laptop here: https://gist.github.com/2f5d00d87c77260bcaac
These results are averages of the 5 tests ran. One thing interesting about the
Avro results is the high/low swing on the serialization times that make up the
average. About half the runs are ~2175, and about half ~1200. It'd be
interesting to find out why that is, 2175 would make it the slowest by a wide
margin, and 1200 the fastest by a wide margin.
> Compare serialization metrics between a few frameworks.
> -------------------------------------------------------
>
> Key: CASSANDRA-1765
> URL: https://issues.apache.org/jira/browse/CASSANDRA-1765
> Project: Cassandra
> Issue Type: Task
> Reporter: Gary Dusbabek
> Assignee: Gary Dusbabek
> Priority: Minor
> Fix For: 0.8
>
> Attachments:
> 0001-inserts-codes-for-properly-calling-full-GC-into-Mess.patch,
> v1-0001-CASSANDRA-1765-don-t-ser-dser-schema-string.txt,
> v1-0001-IDL-and-RangeSliceCommand-alteration.txt,
> v1-0002-msgpack-dependencies.txt, v1-0003-serialization-tests.txt,
> v1-0004-jvm-warmup-and-other-improvements.-by-Muga-Nishizawa.txt
>
>
> Compare serialization performance of Cassandra (ICompactSerializer), Thrift,
> Avro and Messagepack.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
