http://www.couchbase.com/issues This file is an XML representation of an issue en-us 5.2.4 845 26-12-2012 http://www.couchbase.com/issues/browse/MB-7552 Couchbase Server 15-node-cluster with HHD 8GB RAM and 4 core CPU. During initial loading, I have 1 k &quot;sets&quot; ops/ per sec for each node. Some of the nodes in cluster consume all the CPU resources <br/> Memcached (200%~250%), beam.smp (100%~150%). We only have compaction running, no views, rebalance. It&#39;s just a Key-Value load. <br/> <br/> I am using couchbase-python-client to do the multi-set loading. <br/> <br/> I attach the log from the node which suffers from this issue. couchbase-server-community_x86_64_2.0.1-129-rel on Centos MB-7552

CPU usage of beam.smp is too high during initial loading of system test for 2.0.1 build

Bug Major Closed Incomplete Public Chisheng Hong Chisheng Hong Thu, 17 Jan 2013 16:30:49 -0600 Mon, 4 Feb 2013 11:42:48 -0600 Wed, 30 Jan 2013 23:08:21 -0600 2.0.1 2.0.1 ns_server 0 3 Per previous discussion, please try to reproduce with the latest build. It is reproduced in build 2.0.1-139 with R 15 on the same cluster with the same load. I ran measure-sched-delays program on one of the machines while it was experiencing high cpu load: <br/> <br/> 1358816552.787212133 7704073 <br/> 1358816553.781080246 1571073 <br/> 1358816554.851312160 71804073 <br/> 1358816556.044983149 265474073 <br/> 1358816556.781110048 1602073 <br/> 1358816557.781501055 1993073 <br/> <br/> So sometimes it doesn&#39;t get a cpu share for more than two seconds. This is most likely an indication of environment problems. Talked with Farshid and he&#39;ll be working Chisheng to understand if this is really a virtualization issue. last update: <br/> we changed VMware setting to avoid oversubscribing cpu utilization to any vm more than others and only use as much CPU available in the host. <br/> <br/> Chisheng however is still seeing same behavior and we will have to investigate this further on system test. will assign this ticket back to engineering if we find out more about the environment. the specific test is now moved to EC2 <br/> <br/> will reopen if this is observed on EC2 environment Can not repro it on EC2 environment. After disable memory ballooning on the previous cluster which cause this issue, CPU usage of beam.smp is back to normal. Date of First Response Mon, 21 Jan 2013 13:50:08 -0600 Rank 2908 Time In Status