Last week in scylladb.git master (issue #167; 2023-02-12)

This short report brings to light some interesting commits to scylladb.git master from the last week. Commits in the 61dfc9c10f…ca4db9bb72 range are covered.

There were 129 non-merge commits from 18 authors in that period. Some notable commits:

The row cache and memtables now hold rows and range tombstones in a unified data structure, rather than in separate data structures. This solves performance problems (throughput and latency) when a large partition had many range tombstones.

A recently-introduced bug, where a prepared statement with named bind variables was executed without providing a value for one of the variables was fixed.

Repair-based node operations was made the default. However, after problems surfaced in continuous integration, it was reverted again.

The port option in SSTableLoader was fixed.

The check for whether a user defined function is in use by a user defined aggregate before dropping it has been improved.

A crash duing cql3 aggregation, for the case the query returned no results, has been fixed.

ScyllaDB will now treat running out of disk quota (EDQUOT) in the same way it treats running out of disk space (ENOSPC).

An edge case where a vnode token boundary coincided with a range scan boundary, but inclusiveness/exclusiveness of the token (< vs <=) did not agree, has been fixed.

Some minor bugs in the cql transport server error handling have been corrected.

Repair will now ignore local keyspaces.

See you in the next issue of last week in scylladb.git master!