cassandra-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From aiva...@iponweb.net
Subject Bootstrapping new node overloads cpu on existing nodes
Date Sat, 25 Oct 2014 12:36:29 GMT
‎Dear all,

‎So, here is our setup so far:

 - Ubuntu 12.04
 - Cassandra 2.0.10, JDK 1.7.0_65-b17
 - 6 nodes (EC2 c3.8xlarge/ 32 cores/60GB RAM, EBS disks for data,
   ephemeral SSD for commit logs etc)
 - pretty heavy write load - 100Ks/second
 - RF=2, one dc, 2 racks
 - everything works just fine with low CPU consumption - load average tends to be around
4-10

Now, we are trying to add a node. This cases a heavy load on existing nodes - like over 100
load average. The cluster becomes unresponsive, writes and reads mostly fail. 

The weird observations are that:
 - without adding new node CPU is low
 - if we turn off writes while adding a new node load average on existing nodes drops back
to 4-10 and the new node just fine

I've checked VisualVM sampling and basically all the CPU on existing nodes is consumed by
org.jboss.netty.channel.socket.nio.SelectorUtil.select(). 

What we tried so far:

 - throttling streaming - no impact
 - disabling internode compression - no impact
 - disabling autocompaction on existing nodes - no impact
 - even running with -Dorg.jboss.netty.epollBugWorkaround=true - no impact

And as of now we are somewhat desperate as this behavior is a blocker for us - we can't afford
losing writes and we will need to expand C* dynamically.

Anyone has encountered something similar? Any ideas/hints? Thanks 





Mime
View raw message