[CASSANDRA-15306] Investigate why we are allocating 8MiB chunks and reaching the maximum BufferPool size

• Type: Bug
• Status: Resolved
• Priority: Normal
• Resolution: Cannot Reproduce
• Fix Version/s: 4.0-alpha4, 4.0
• Component/s: Observability/Logging, Test/benchmark
• Platform: All
• Assignee: Unassigned
• Reporter: Joey Lynch
• Created: 06/Sep/19 15:28
• Updated: 15/May/20 08:53
• Resolved: 01/Apr/20 12:19

Description

While throwing some light traffic at 4.0-alpha1 I saw a lot of the following in the logs

INFO  [CompactionExecutor:8] 2019-09-06 11:40:31,419 NoSpamLogger.java:91 - Maximum memory usage reached (512.000MiB), cannot allocate chunk of 8.000MiB

INFO  [CompactionExecutor:8] 2019-09-06 11:55:31,419 NoSpamLogger.java:91 - Maximum memory usage reached (512.000MiB), cannot allocate chunk of 8.000MiB

INFO  [CompactionExecutor:15] 2019-09-06 12:10:31,419 NoSpamLogger.java:91 - Maximum memory usage reached (512.000MiB), cannot allocate chunk of 8.000MiB

INFO  [CompactionExecutor:18] 2019-09-06 12:25:31,421 NoSpamLogger.java:91 - Maximum memory usage reached (512.000MiB), cannot allocate chunk of 8.000MiB 

This was with about 150 WPS against a LCS table containing 4kib partitions. It seemed that compaction proceeded just fine but I don't remember seeing this in previous testing runs and I'd like to make sure it's not a bug (otherwise we may want to reduce the logging).