[
https://issues.apache.org/jira/browse/HBASE-20786?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16603944#comment-16603944
]
stack commented on HBASE-20786:
-------------------------------
Here is a little bottleneck where we single-threaded spin through all regions
-- even if hundreds of thousands -- doing updates on location. I see startups
stall here.
{code}
"Thread-20" #98 daemon prio=5 os_prio=0 tid=0x00007faa4c6a7000 nid=0x48a9
waiting on condition [0x00007faa26e13000]
java.lang.Thread.State: WAITING (parking)
at sun.misc.Unsafe.park(Native Method)
- parking to wait for <0x00000006517d3a48> (a
org.apache.hbase.thirdparty.com.google.common.util.concurrent.TrustedListenableFutureTask)
at java.util.concurrent.locks.LockSupport.park(LockSupport.java:175)
at
org.apache.hbase.thirdparty.com.google.common.util.concurrent.AbstractFuture.get(AbstractFuture.java:472)
at
org.apache.hbase.thirdparty.com.google.common.util.concurrent.AbstractFuture$TrustedFuture.get(AbstractFuture.java:79)
at
org.apache.hadoop.hbase.master.balancer.RegionLocationFinder.refreshAndWait(RegionLocationFinder.java:311)
at
org.apache.hadoop.hbase.master.balancer.BaseLoadBalancer.postMasterStartupInitialize(BaseLoadBalancer.java:1160)
at
org.apache.hadoop.hbase.master.HMaster.finishActiveMasterInitialization(HMaster.java:1098)
at
org.apache.hadoop.hbase.master.HMaster.startActiveMasterManager(HMaster.java:2157)
at org.apache.hadoop.hbase.master.HMaster.lambda$run$0(HMaster.java:567)
at
org.apache.hadoop.hbase.master.HMaster$$Lambda$42/249833322.run(Unknown Source)
at java.lang.Thread.run(Thread.java:748)
{code}
> Table create with thousands of regions takes too long
> -----------------------------------------------------
>
> Key: HBASE-20786
> URL: https://issues.apache.org/jira/browse/HBASE-20786
> Project: HBase
> Issue Type: Sub-task
> Components: Performance
> Reporter: stack
> Priority: Major
>
> Internal testing has create of a table with 33k regions taking 18 minutes.
> Let me provide more info below. We have an executor with default ten threads
> handling the creation of the regions in HDFS which helps distribute out the
> load but its not enough. This cluster had >600 servers. Let me add detail.
> Need to spend some time on speeding up create/assigns. Made this an umbrella
> issue so can pick off pieces of the problem as subtasks.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
