Search before asking

• I searched in the issues and found nothing similar.

Fluss version

0.7.0 (latest release)

Please describe the bug 🐞

Under large-scale data testing, every tabletServer in the Fluss cluster exhibited excessive mmap memory usage, as shown in the figure below Almost 300GB):

Using pmap -x <PID> to show the mmap usage, found that there are too many deleted index or timeIndex file refs stale in mmap as follow:

Only when the G1 Mixed GC is triggered will these objects be reclaimed.

Solution

No response

Are you willing to submit a PR?

• I'm willing to submit a PR!