[ https://issues.apache.org/jira/browse/CASSANDRA-20092?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17942283#comment-17942283 ]
Jordan West edited comment on CASSANDRA-20092 at 4/9/25 7:11 PM: ----------------------------------------------------------------- I've been working on the backport for this ticket to 5.0 as discussed on the mailing list. Figure updates are best put here since their isn't a separate tracking ticket. One note is in my backport I have addressed CASSANDRA-20538 as well for 5.0 branch (was planning to treat 20538 solely for trunk but I am happy to split it up) I've also included the fix in CASSANDRA-20396 in the backport [Branch|https://github.com/jrwest/cassandra/tree/jwest/20092-5.0-backport] [Tests|https://app.circleci.com/pipelines/github/jrwest/cassandra/234/workflows/9a1656ca-4e3f-4373-8afa-9e668bbf4a6e] (nothing failing that is related, just two failures in TestBootstrap that I have seen before) was (Author: jrwest): I've been working on the backport for this ticket to 5.0 as discussed on the mailing list. Figure updates are best put here since their isn't a separate tracking ticket. One note is in my backport I have addressed CASSANDRA-20538 as well for 5.0 branch (was planning to treat 20538 solely for trunk but I am happy to split it up) [Branch|https://github.com/jrwest/cassandra/tree/jwest/20092-5.0-backport] [Tests|https://app.circleci.com/pipelines/github/jrwest/cassandra/234/workflows/9a1656ca-4e3f-4373-8afa-9e668bbf4a6e] (nothing failing that is related, just two failures in TestBootstrap that I have seen before) > SSTableScanner can be vastly simplified for compaction > ------------------------------------------------------ > > Key: CASSANDRA-20092 > URL: https://issues.apache.org/jira/browse/CASSANDRA-20092 > Project: Apache Cassandra > Issue Type: Improvement > Components: Local/Compaction > Reporter: Branimir Lambov > Assignee: Branimir Lambov > Priority: Normal > Fix For: 5.1 > > Attachments: ci_summary_thelastpickle_mck-20092-5.0_154.html, > results_details_thelastpickle_mck-20092-5.0_154.tar.xz > > Time Spent: 40m > Remaining Estimate: 0h > > One of the main bottlenecks for compaction performance is its use of the > {{SSTableScanner}} class, whose main purpose is to implement partition range > queries and as such supports filtering by row and column that is not helpful > to compaction. To implement the latter it must rely on the sstable's index, > adding a lot of complexity and inefficiency. > Implementing a simpler version of a scanner that reads off the data file > directly for given spans of offsets would speed up compaction significantly. -- This message was sent by Atlassian Jira (v8.20.10#820010) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@cassandra.apache.org For additional commands, e-mail: commits-h...@cassandra.apache.org