hbase-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From lars hofhansl <la...@apache.org>
Subject Re: GC peaks during major compaction
Date Thu, 14 Aug 2014 17:17:51 GMT
Can send you JVM command line arguments (specifically how you tune the GC)?

-- Lars

 From: yanivG <yaniv.yancovich@gmail.com>
To: user@hbase.apache.org 
Sent: Thursday, August 14, 2014 9:01 AM
Subject: GC peaks during major compaction

We are running CDH 4.5, 6 nodes with hbase cluster (0.94.6). 
We configured major compaction to run once a week. During this time we are
getting timeouts while writing to hbase (application level).
When investigating it further more I have noticed that the timeout are being
caused by GC "Stop the world" scenario which takes 3 minutes and not the
actual Major compaction (which takes few hours).    
Is there any GC configuration we can set for relaxing it during Major
Note that we see this GC peak just when the major compaction starts.
We are running with default hbase GC settings.

View this message in context: http://apache-hbase.679495.n3.nabble.com/GC-peaks-during-major-compaction-tp4062704.html
Sent from the HBase User mailing list archive at Nabble.com.
  • Unnamed multipart/alternative (inline, None, 0 bytes)
View raw message