[CASSANDRA-4710] High key hashing overhead for index scans when using RandomPartitioner

• Type: Improvement
• Status: Resolved
• Priority: Low
• Resolution: Fixed
• Fix Version/s: 1.2.0 beta 2
• Assignee: Daniel Norberg
• Reporter: Daniel Norberg

Authors

Daniel Norberg

Reviewers

Jonathan Ellis

• Created: 24/Sep/12 14:31
• Updated: 16/Apr/19 09:32
• Resolved: 05/Oct/12 08:25

Description

For a workload where the dataset is completely in ram, the md5 hashing of the keys during index scans becomes a bottleneck for reads when using RandomPartitioner, according to profiling.

Instead performing a raw key equals check in SSTableReader.getPosition() for EQ operations improves throughput by some 30% for my workload (moving the bottleneck elsewhere).