Hanisha Koneru created HDDS-1528:
------------------------------------
Summary: Buffer Pool in BlockInputStream
Key: HDDS-1528
URL: https://issues.apache.org/jira/browse/HDDS-1528
Project: Hadoop Distributed Data Store
Issue Type: Improvement
Reporter: Hanisha Koneru
In BlockInputStream, when a new chunk is being read, the data in old buffers is
thrown away. So, if we want to read data in chunk1 and then chunk2 and then go
back to reading chunk1, we would have to fetch chunk1 again from the DNs.
Reads can be optimized if we maintain a buffer pool instead instead of only one
buffer. This way, we can cache chunk data for re-reads.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-dev-unsubscr...@hadoop.apache.org
For additional commands, e-mail: hdfs-dev-h...@hadoop.apache.org
