Details
-
Bug
-
Resolution: Cannot Reproduce
-
Blocker
-
3.0
-
Security Level: Public
-
3.0.0-943
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
Rebalance after failover, 3 -> 4, 1 bucket x 100M x 2KB, 1 view, 10K mixed ops/sec, 400 queries/sec
Steps:
1. "Failover" one node.
2. Add it back.
3. Wait 20 minutes
4. Trigger cluster rebalance, wait for rebalance to finish.
Rebalance in 2x slower than in beta build, indexing of individual vbuckets takes up to 3.5h:
http://cbmonitor.sc.couchbase.com/reports/movements/?filename=e1175a17dae049d38215d5b25ed46f72
couch_view_group_cleanup crashed 3 times during rebalance: "Segmentation fault".
gdb --ex 't a a bt full' /opt/couchbase/bin/couch_view_group_cleanup /tmp/core.couch_view_grou.113377.leto-s304.1405132791 < /dev/null > gdb.log