[
https://issues.apache.org/jira/browse/CASSANDRA-17021?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18028461#comment-18028461
]
Jon Haddad commented on CASSANDRA-17021:
----------------------------------------
I like the high level approach. I don't object to a list of SSTables, but I
don't think it should be required, it seems a bit overkill for regular users.
I don't think you even need to read through the entire SSTable. Since murmur
gives us effectively random partition sorting, we could probably get by just
from reading <some number of chunk> at the head of the table. How much data do
we need to sample to be effective?
What do you think?
> Enhance Zstd support in Cassandra with dictionaries
> ---------------------------------------------------
>
> Key: CASSANDRA-17021
> URL: https://issues.apache.org/jira/browse/CASSANDRA-17021
> Project: Apache Cassandra
> Issue Type: Improvement
> Components: Feature/Compression
> Reporter: Dinesh Joshi
> Assignee: Yifan Cai
> Priority: Normal
> Time Spent: 4h 50m
> Remaining Estimate: 0h
>
> Currently Cassandra supports zstd compression. However, Zstd also supports
> dictionaries to enhance not only the compression ratio but also the speed.
> Dictionaries can show 3-4x savings. We should add support to train
> dictionaries, ideally per SSTable this will yield the maximum gains.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
