cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Sylvain Lebresne (JIRA)" <>
Subject [jira] [Commented] (CASSANDRA-6689) Partially Off Heap Memtables
Date Fri, 21 Mar 2014 10:35:02 GMT


Sylvain Lebresne commented on CASSANDRA-6689:

bq. Reviewing under the assumption that 1-3 will go in 2.1 and the rest into 3.0

So at the risk of adding more debate, I do think one of the point of separating things is
also that we can evaluate things separately. Typically, I would be happy to see a quick evaluation
of what #1+#2 gives us, and what #3 adds to the table. If 1+2 is borderline unusable without
3 (and if that's the case, it should be easy to cook up simple graph that shows it), then
fine, let's do 3 in 2.1. But if it turns out that the difference is no that big, I would personally
be keen to move #3 to 3.0, cause we're shoving enough big patches in 2.1 post beta1 as it
is imo. To put it another way, if we're making steps, let's try to be true to them, and not
make too strong assumptions about what goes where, because as far as I'm concerned, nothing
should never be set in stone until it's committed (and even then really).

> Partially Off Heap Memtables
> ----------------------------
>                 Key: CASSANDRA-6689
>                 URL:
>             Project: Cassandra
>          Issue Type: New Feature
>          Components: Core
>            Reporter: Benedict
>            Assignee: Benedict
>              Labels: performance
>             Fix For: 2.1 beta2
>         Attachments: CASSANDRA-6689-small-changes.patch
> Move the contents of ByteBuffers off-heap for records written to a memtable.
> (See comments for details)

This message was sent by Atlassian JIRA

View raw message