hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Andrew Purtell (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HBASE-2315) BookKeeper for write-ahead logging
Date Fri, 12 Mar 2010 22:53:27 GMT

    [ https://issues.apache.org/jira/browse/HBASE-2315?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12844736#action_12844736
] 

Andrew Purtell commented on HBASE-2315:
---------------------------------------

@Flavio: Thanks for your kind reply.

bq. In fact, with a previous version of BK, we were able to get 70kwrites/s for writes of
128 bytes

Dedicated hardware, I presume. How many BK nodes would be needed alongside HBase+Hadoop nodes
to achieve 1M ops/sec over 100 concurrent ledgers? HBase WAL has group commit but that can
only batch so much... depends on the order of edits coming from userland. So what amount of
batching? (Average transaction size to BK for example.)

> BookKeeper for write-ahead logging
> ----------------------------------
>
>                 Key: HBASE-2315
>                 URL: https://issues.apache.org/jira/browse/HBASE-2315
>             Project: Hadoop HBase
>          Issue Type: New Feature
>          Components: regionserver
>            Reporter: Flavio Paiva Junqueira
>         Attachments: HBASE-2315.patch, zookeeper-dev-bookkeeper.jar
>
>
> BookKeeper, a contrib of the ZooKeeper project, is a fault tolerant and high throughput
write-ahead logging service. This issue provides an implementation of write-ahead logging
for hbase using BookKeeper. Apart from expected throughput improvements, BookKeeper also has
stronger durability guarantees compared to the implementation currently used by hbase.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message