OOM in Elasticsearch 1.6

I use Elasticsearch for log search. And already has doc_values settings for a long while.
But my cluster begin OOM after I upgrade to ES 1.6, even delete some shard:

[2015-07-23 01:32:06,096][WARN ][index.merge.scheduler    ] [10.19.0.43] [logstash-mweibo-2015.07.22][24] failed to merge
org.apache.lucene.store.AlreadyClosedException: refusing to delete any files: this IndexWriter hit an unrecoverable exception
        at org.apache.lucene.index.IndexFileDeleter.ensureOpen(IndexFileDeleter.java:354)
        at org.apache.lucene.index.IndexFileDeleter.deleteFile(IndexFileDeleter.java:719)
        at org.apache.lucene.index.IndexFileDeleter.refresh(IndexFileDeleter.java:451)
        at org.apache.lucene.index.IndexWriter.merge(IndexWriter.java:3826)
        at org.apache.lucene.index.ConcurrentMergeScheduler.doMerge(ConcurrentMergeScheduler.java:409)
        at org.apache.lucene.index.TrackingConcurrentMergeScheduler.doMerge(TrackingConcurrentMergeScheduler.java:107)
        at org.apache.lucene.index.ConcurrentMergeScheduler$MergeThread.run(ConcurrentMergeScheduler.java:486)
Caused by: java.lang.OutOfMemoryError: Java heap space

...

[2015-07-23 01:37:03,324][WARN ][index.engine             ] [10.19.0.43] [logstash-mweibo-2015.07.22][24] failed engine [out of memory]
java.lang.OutOfMemoryError: Java heap space
[2015-07-23 01:37:03,327][WARN ][action.bulk              ] [10.19.0.43] Failed to send response for indices:data/write/bulk[s]
java.lang.OutOfMemoryError: Java heap space
[2015-07-23 01:37:03,327][WARN ][action.bulk              ] [10.19.0.43] Failed to send response for indices:data/write/bulk[s]
java.lang.OutOfMemoryError: Java heap space
[2015-07-23 01:37:03,343][WARN ][indices.cluster          ] [10.19.0.43] [[logstash-mweibo-2015.07.22][24]] marking and sending shard failed due to [engine failure, reason [out of memory]]
java.lang.OutOfMemoryError: Java heap space

...

[2015-07-23 01:37:11,337][WARN ][transport.netty          ] [10.19.0.43] Actual Exception
org.elasticsearch.index.IndexShardMissingException: [logstash-mweibo-2015.07.22][24] missing
        at org.elasticsearch.index.IndexService.shardSafe(IndexService.java:210)
        at org.elasticsearch.action.admin.indices.stats.TransportIndicesStatsAction.shardOperation(TransportIndicesStatsAction.java:138)
        at org.elasticsearch.action.admin.indices.stats.TransportIndicesStatsAction.shardOperation(TransportIndicesStatsAction.java:56)
        at org.elasticsearch.action.support.broadcast.TransportBroadcastOperationAction$ShardTransportHandler.messageReceived(TransportBroadcastOperationAction.java:338)
        at org.elasticsearch.action.support.broadcast.TransportBroadcastOperationAction$ShardTransportHandler.messageReceived(TransportBroadcastOperationAction.java:324)
        at org.elasticsearch.transport.netty.MessageChannelHandler$RequestHandler.doRun(MessageChannelHandler.java:279)
        at org.elasticsearch.common.util.concurrent.AbstractRunnable.run(AbstractRunnable.java:36)
        at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
        at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
        at java.lang.Thread.run(Thread.java:745)

And the first OOM message is my es.log as follow:

[2015-07-23 01:27:39,042][WARN ][indices.ttl              ] [10.19.0.43] failed to execute ttl purge
java.lang.OutOfMemoryError: Java heap space
[2015-07-23 01:27:45,672][WARN ][transport.netty          ] [10.19.0.43] exception caught on transport layer [[id: 0x4de40b8a, /10.19.0.68:38330 => /10.19.0.43:9300]], closi
ng connection
java.lang.OutOfMemoryError: Java heap space
[2015-07-23 01:27:42,044][WARN ][transport.netty          ] [10.19.0.43] exception caught on transport layer [[id: 0xc84f6826, /10.19.0.81:41486 => /10.19.0.43:9300]], closi
ng connection
java.lang.OutOfMemoryError: Java heap space
[2015-07-23 01:27:42,042][WARN ][netty.channel.socket.nio.AbstractNioSelector] Unexpected exception in the selector loop.
java.lang.OutOfMemoryError: Java heap space
[2015-07-23 01:27:39,042][WARN ][netty.channel.socket.nio.AbstractNioSelector] Unexpected exception in the selector loop.
java.lang.OutOfMemoryError: Java heap space
[2015-07-23 01:28:13,656][WARN ][netty.channel.socket.nio.AbstractNioSelector] Unexpected exception in the selector loop.
java.lang.OutOfMemoryError: Java heap space
[2015-07-23 01:28:13,655][WARN ][netty.channel.socket.nio.AbstractNioSelector] Unexpected exception in the selector loop.
java.lang.OutOfMemoryError: Java heap space
[2015-07-23 01:28:13,655][WARN ][netty.channel.socket.nio.AbstractNioSelector] Unexpected exception in the selector loop.
java.lang.OutOfMemoryError: Java heap space
[2015-07-23 01:28:10,786][WARN ][netty.channel.socket.nio.AbstractNioSelector] Unexpected exception in the selector loop.
java.lang.OutOfMemoryError: Java heap space

What's these messages mean? seems I didn't see something like these before ES 1.6.

How much data do you have in your cluster, how many nodes, what is the heap size?

30TB in 26 datanodes with each 25 GB heap.