This method is synchronized, meaning that in your case another thread is waiting on globalMemStoreLimit getting smaller by flushing. Most of the time, this takes a very long time because the regions that are forced flushed also have too many store files... and the requested compaction is far behind in the compaction queue. This is best described here: https://issues.apache.org/jira/browse/HBASE-2646
J-D On Thu, Oct 7, 2010 at 11:48 PM, Tao Xie <[email protected]> wrote: > I use hadoop CDH3 and hbase 0.89. When I doing heavy puts, I see the > following thread dump in one RS. > And the puts throughput drops to zero in a long time. Is this a bug? Anybody > see this before? > Thanks for any response. > > "IPC Server handler 73 on 60020" tid=118 daemon=true priority=5 > state=BLOCKED > at > org.apache.hadoop.hbase.regionserver.MemStoreFlusher.reclaimMemStoreMemory > at org.apache.hadoop.hbase.regionserver.HRegionServer.put > at org.apache.hadoop.hbase.regionserver.HRegionServer.multiPut > at sun.reflect.GeneratedMethodAccessor11.invoke > at sun.reflect.DelegatingMethodAccessorImpl.invoke > at java.lang.reflect.Method.invoke > at org.apache.hadoop.hbase.ipc.HBaseRPC$Server.call > at org.apache.hadoop.hbase.ipc.HBaseServer$Handler.run > > "IPC Server handler 81 on 60020" tid=126 daemon=true priority=5 > state=BLOCKED > at > org.apache.hadoop.hbase.regionserver.MemStoreFlusher.reclaimMemStoreMemory > at org.apache.hadoop.hbase.regionserver.HRegionServer.put > at org.apache.hadoop.hbase.regionserver.HRegionServer.multiPut > at sun.reflect.GeneratedMethodAccessor11.invoke > at sun.reflect.DelegatingMethodAccessorImpl.invoke > at java.lang.reflect.Method.invoke > at org.apache.hadoop.hbase.ipc.HBaseRPC$Server.call > at org.apache.hadoop.hbase.ipc.HBaseServer$Handler.run > > "IPC Server handler 91 on 60020" tid=136 daemon=true priority=5 > state=BLOCKED > at > org.apache.hadoop.hbase.regionserver.MemStoreFlusher.reclaimMemStoreMemory > at org.apache.hadoop.hbase.regionserver.HRegionServer.put > at org.apache.hadoop.hbase.regionserver.HRegionServer.multiPut > at sun.reflect.GeneratedMethodAccessor11.invoke > at sun.reflect.DelegatingMethodAccessorImpl.invoke > at java.lang.reflect.Method.invoke > at org.apache.hadoop.hbase.ipc.HBaseRPC$Server.call > at org.apache.hadoop.hbase.ipc.HBaseServer$Handler.run > > "IPC Server handler 8 on 60020" tid=53 daemon=true priority=5 state=BLOCKED > at > org.apache.hadoop.hbase.regionserver.MemStoreFlusher.reclaimMemStoreMemory > at org.apache.hadoop.hbase.regionserver.HRegionServer.put > at org.apache.hadoop.hbase.regionserver.HRegionServer.multiPut > at sun.reflect.GeneratedMethodAccessor11.invoke > at sun.reflect.DelegatingMethodAccessorImpl.invoke > at java.lang.reflect.Method.invoke > at org.apache.hadoop.hbase.ipc.HBaseRPC$Server.call > at org.apache.hadoop.hbase.ipc.HBaseServer$Handler.run >
