[ https://issues.apache.org/jira/browse/CASSANDRA-17240?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17620908#comment-17620908 ]
Branimir Lambov commented on CASSANDRA-17240: --------------------------------------------- Is the answer above not satisfactory? The additional counted bytes are at most a {{ByteBuffer}} (32 or 48 bytes) per partition plus a reference (4 bytes) per column in the partition. Given that the total per-partition size is in the high hundreds of bytes, and that the cell instance and reference are at least 32 + 4, the increase in calculated size in the worst case (hundreds of columns in a key-value table) cannot be over 1/9 (assuming a compressed-pointer JVM), and will be much lower in practice. > CEP-19: Trie memtable implementation > ------------------------------------ > > Key: CASSANDRA-17240 > URL: https://issues.apache.org/jira/browse/CASSANDRA-17240 > Project: Cassandra > Issue Type: Improvement > Components: Local/Memtable > Reporter: Branimir Lambov > Assignee: Branimir Lambov > Priority: Normal > Attachments: SkipListMemtable-OSS.png, TrieMemtable-OSS.png, > density_SG.html.gz, density_test_with_sharding.html.gz, latency-1_1-95.png, > latency-9_1-95.png, throughput_SG.png, throughput_apache.png > > Time Spent: 13h 20m > Remaining Estimate: 0h > > Trie-based memtable implementation as described in CEP-19, built on top of > CASSANDRA-17034 and CASSANDRA-6936. > The implementation is available in this > [branch|https://github.com/blambov/cassandra/tree/CASSANDRA-17240]. -- 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