I’ve got a 6 node test cluster running 3.0.1 with 5 buckets. I ran a rebalance to try to remove one node last night and left it over night. This morning all nodes said 100% and one node said 99.7% complete after 12 hours. I’ve added additional nodes and tried to rebalance them in but can’t get the rebalance to complete. It stalls between 80% and 100% every time. I’m looking for a little guidance on how to identify the problem and fix it.
Average item waited time - Poor ep-engine key performance indicators
Symptom in opensips bucket on cblab01:8091:
Average waiting time ‘860 us’ for items serviced by dispatcher is slower than '500 us’
Server performance is below expectation.
Please contact firstname.lastname@example.org