That one long GC aside, look at the timings of the others as well. Even
the smaller GCs are taking up the majority of each second.
For a heap that size you might want to try a java version over java7u60 and
use the G1GC. Otherwise there are a bunch of resources on the web
including in the
Is there any reason for 27G heap? It seems you run M/R job? If yes, then I
would recommend you trying M/R over snapshots. Combination of large HBase
heap and M/R is very hard to tune if possible at all
You can also try reducing number of map tasks and check your MR job
resource consumption
On May
2014-08-14 21:35:16,740 WARN org.apache.hadoop.hbase.util.Sleeper: We
slept
14912ms instead of 3000ms, this is likely due to a long garbage collecting
pause and it's usually bad, see
http://hbase.apache.org/book.html#trouble.rs.runtime.zkexpired
I would check your gc logs for long gc
This is a sample from gc log file. At the end I see long gc pauses. Is
there a way I can tune this ?
2015-04-29T22:46:12.387+: 98061.660: [GC2015-04-29T22:46:12.387+:
98061.661: [ParNew: 572757K-63867K(580608K), 0.6549550 secs]
13294553K-12811090K(20001132K), 0.6551600 secs] [Times:
Hi All,
In our cluster region server logs are filled with response too slow
message. This is causing jobs to slow down. How can I debug what is the
reason for this slowness.
We have enabled short circuit reads and region server has 27GB RAM.
Here is a trace when regionserver starts.
Thu Aug 14
Yes we are running MR on hbase. I tried running MR on snapshot but the data
in our HBase changes very frequently and we end up occupying twice the
space and end up running into full disks.
I think we are hitting large HBase heap and M/R problem. I will try to add
some more space to our cluster