Details
-
Bug
-
Resolution: Fixed
-
Blocker
-
3.0
-
Security Level: Public
-
Platform = Physical
OS = CentOS 6.5
CPU = Intel Xeon E5-2630 (24 vCPU)
Memory = 64 GB
Disk = 2 x SSD
-
Untriaged
-
Centos 64-bit
-
Yes
-
June 30 - July 18
Description
1 bucket x 20M x 2KB, non-DGM, 4 ddocs x 1 view, 10K ops/sec (read-heavy), 400 queries/sec
It's possible to measure latency in simple cases like MB-11386. But in more complicated scenarios latency is extremely high.
Most likely the issue is caused by timeout / retry logic in UPR client. Though I'm not really aware about current status of view engine.
Attachments
Issue Links
- depends on
-
MB-11486 Erlang memory usage increases to 50GB in 10 minutes after "unexpected_binary", node obviously fails afterwards
- Closed
- is duplicated by
-
MB-11386 Latency of stale=false queries is 50% higher in 3.0 (light workloads)
- Closed
- relates to
-
MB-11325 {UPR}:: Rebalance hanging during View Query + Rebalance tests
- Closed