[
https://issues.apache.org/jira/browse/CASSANDRA-21533?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18098988#comment-18098988
]
Yuqi Yan commented on CASSANDRA-21533:
--------------------------------------
Thanks [~smiklosovic] - yes i think we should support compression option, as
Zstd has compression level option and this will give more flexibility if we
hope to use different compression level (or other option). I'll update the PR
I was also thinking for this option we might want to target `!=
OperationType.FLUSH` instead, otherwise it's probably weird if we have some
single sstable compaction not using this per level compression settings. wdyt?
> Configurable compression algorithm for each LCS level
> -----------------------------------------------------
>
> Key: CASSANDRA-21533
> URL: https://issues.apache.org/jira/browse/CASSANDRA-21533
> Project: Apache Cassandra
> Issue Type: Improvement
> Components: Local/Compaction
> Reporter: Yuqi Yan
> Assignee: Yuqi Yan
> Priority: Normal
> Fix For: 4.1.x, trunk
>
>
> Allow an LCS table to use a different sstable compressor per level. The most
> useful case: keep the high-churn L0 tier on a fast codec (LZ4) while deeper
> levels retain a high-ratio codec (Zstd). L0 is repeatedly rewritten by
> STCS-in-L0 and L0→L1 compactions, so paying full Zstd cost there wastes
> compaction CPU for data that is short-lived at that level; the ratio only
> matters once data settles into the deeper, stable levels.
> *Motivation*
> This generalizes the idea already accepted in CASSANDRA-15379
> ({{{}flush_compression{}}}), which flushes with fast LZ4 and lets compaction
> re-compress to the table codec. Today there is no way to keep the churny
> compaction tier on a fast codec — the table's single compressor applies to
> every level.
> *Proposed change*
> * New LCS compaction sub-option {{{}per_level_compression{}}}: a
> comma-separated {{level:CompressorClass}} list (e.g.
> {{{}'0:LZ4Compressor'{}}}). Levels not listed inherit the table
> {{{}compression{}}}.
> * Only the compressor _class_ is overridden; {{chunk_length_in_kb}} and
> {{min_compress_ratio}} are inherited from the table compression so chunk
> sizing stays consistent.
> * Applied in the compaction write path, keyed on the target sstable level.
>
> I'll share a patch for 4.1 targeting LCS and will create a trunk PR targeting
> both UCS / LCS. Not very sure how UCS handles the "level" concept if
> configured with size tiered like "T4" but I think the idea of using faster
> compression in shallow level for "L10" like setup still make sense
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
