[
https://issues.apache.org/jira/browse/SAMZA-543?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14368329#comment-14368329
]
Jay Kreps commented on SAMZA-543:
---------------------------------
Yeah quite apart from this settings change it is surprising that you see lower
throughput in MB/sec with larger messages. You should see much higher
throughput. I wonder if maybe the issue is that the test is small enough that
with the smaller messages you aren't really hitting disk?
> Disable WAL in RocksDB KV store
> -------------------------------
>
> Key: SAMZA-543
> URL: https://issues.apache.org/jira/browse/SAMZA-543
> Project: Samza
> Issue Type: Bug
> Components: kv
> Affects Versions: 0.9.0
> Reporter: Chris Riccomini
> Assignee: Navina Ramesh
> Fix For: 0.9.0
>
> Attachments: DisableWAL.diff, SAMZA-543-0.patch, SAMZA-543-2.patch
>
>
> RocksDB uses a write-ahead log by default. This is unnecessary in Samza,
> since we have full durability from a state store's changelog topic. We should
> [disable the
> WAL|https://github.com/facebook/rocksdb/wiki/Basic-Operations#asynchronous-writes]
> in the RocksDB KV store.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
