Details
-
Bug
-
Resolution: Duplicate
-
Critical
-
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
Description
Following up our performance meeting.
We saw 3-4x faster rebalance after Erlang->C rewrite, but with DCP everything as slow as in 2.5.x.
Rebalance-out:
http://cbmonitor.sc.couchbase.com/reports/html/?snapshot=leto_ssd_251-1083_1f4_rebalance&snapshot=leto_ssd_300-1121_19f_rebalance
Rebalance-swap:
http://cbmonitor.sc.couchbase.com/reports/html/?snapshot=leto_ssd_251-1083_515_rebalance&snapshot=leto_ssd_300-1121_98e_rebalance
ShowFast has more reports and master events profiles.
Attachments
Issue Links
- depends on
-
MB-11589 Sliding endseqno during initial index build or upr reading from disk snapshot results in longer stale=false query latency and index startup time
- Closed