We are using an Aerospike cluster of 7 nodes in Disk mode since the last 6 months.
Since the last 1 month, we have started observing an increase in Aerospike latencies (all APIs) from client side (40% increase in time).
We are suspecting that some of our Aerospike queries are taking too long (may be their data size is large) and because of this all queries are getting stuck in Aerospike queues thereby affecting all calls.
Do we have any way to measure queue time and actual query processing time in Aerospike at individual query level ? In other words, do we have any way to figure out slow query log in Aerospike ?
This will help us identify those bad queries and fix the issue.
Also, is there a way to list all Aerospike keys and their sizes so as to identify large keys in Aerospike ?