Could it be related to
https://issues.apache.org/jira/browse/CASSANDRA-14096 ?
On 28/07/2021 13:55, Amandeep Srivastava wrote:
Hi team,
My Cluster configs: DC1 - 9 nodes, DC2 - 4 nodes
Node configs: 12 core x 96GB ram x 1 TB HDD
Repair params: -full -pr -local
Cassandra version: 3.11.4
I'm running a full repair on DC2 nodes - one node and one keyspace at
a time. During the repair, ram usage on all 4 nodes spike up to 95%.
Have tried setting xmx to 24GB, 31GB, 32GB, and 64GB but all show the
same behavior. Could you please advise what might be consuming such
high levels of off-heap memory and what can be done to cap/limit its use?
We run no other process apart from Cassandra daemon on these nodes.
Regards,
Aman
