Description
Some users of HDFS cache opened HDFS file handles to avoid repeated roundtrips to the NameNode. For example, Impala caches up to 20,000 HDFS file handles by default. Recent tests on erasure coded files show that the open file handles can consume a large amount of memory when not in use.
For example, here is output from Impala's JMX endpoint when 608 file handles are cached
{
"name": "java.nio:type=BufferPool,name=direct",
"modelerType": "sun.management.ManagementFactoryHelper$1",
"Name": "direct",
"TotalCapacity": 1921048960,
"MemoryUsed": 1921048961,
"Count": 633,
"ObjectName": "java.nio:type=BufferPool,name=direct"
},
This shows direct buffer memory usage of 3MB per DFSStripedInputStream. Attached is output from Eclipse MAT showing that the direct buffers come from DFSStripedInputStream objects. Both Impala and HBase call unbuffer() when a file handle is being cached and potentially unused for significant chunks of time, yet this shows that the memory remains in use.
To support caching file handles on erasure coded files, DFSStripedInputStream should avoid holding buffers after the unbuffer() call. See HDFS-7694. "unbuffer()" is intended to move an input stream to a lower memory state to support these caching use cases. In particular, the curStripeBuf seems to be allocated from the BUFFER_POOL on a resetCurStripeBuffer(true) call. It is not freed until close().
Attachments
Attachments
Issue Links
- relates to
-
IMPALA-9485 Enable file handle cache for EC files
-
- Resolved
-
-
HBASE-24051 When the data directory is set to EC,the amount of storefiles reaches a relatively high level,heap Occupancy Percent is above heap occupancy alarm watermark,resulting in frequent gc and eventual failure
-
- Reopened
-
-
-
- Resolved
-
- links to