Different changefeeds on the same node may have different requirements: some may need low latency, while others are not latency-sensitive at all. It would be nice if users could specify the relative priority between rangefeeds in case of resource contention. This would involve:
Scheduler priority.
Mux stream priority.
Memory budget priority.
gRPC/TCP connection priority.
It would probably also need higher-level prioritization of the writing workload, e.g. in AC and other systems.
Different changefeeds on the same node may have different requirements: some may need low latency, while others are not latency-sensitive at all. It would be nice if users could specify the relative priority between rangefeeds in case of resource contention. This would involve:
It would probably also need higher-level prioritization of the writing workload, e.g. in AC and other systems.
Jira issue: CRDB-31509
Epic CRDB-39959