-
Notifications
You must be signed in to change notification settings - Fork 119
Closed
Labels
Description
What happened?
When creating an index over 1B+ records I'm seeing memory usage increase linearly, seemingly unbounded. Is this expected/is there a way to control memory usage?
pgvectorscale extension affected
No response
PostgreSQL version used
17.4
What operating system did you use?
Ubuntu 24.04
What installation method did you use?
Docker
What platform did you run on?
On prem/Self-hosted
Relevant log output and stack trace
How can we reproduce the bug?
Run `CREATE INDEX` over a very large corpus of vectors and monitor the memory consumption.Are you going to work on the bugfix?
None