Issue Details (XML | Word | Printable)

Key: HADOOP-4802
Type: Bug Bug
Status: Open Open
Priority: Major Major
Assignee: Unassigned
Reporter: stack
Votes: 0
Watchers: 6
Operations

If you were logged in you would be able to see more operations.
Hadoop Common

RPC Server send buffer retains size of largest response ever sent

Created: 07/Dec/08 07:45 PM   Updated: 13/Jan/09 07:47 PM
Return to search
Component/s: ipc
Affects Version/s: 0.18.2, 0.19.0
Fix Version/s: None

Time Tracking:
Not Specified

Issue Links:
Reference
 


 Description  « Hide
The stack-based ByteArrayOutputStream in Server.Hander is reset each time through the run loop. This will set the BAOS 'size' back to zero but the allocated backing buffer is unaltered. If during an Handlers' lifecycle, any particular RPC response was fat – Megabytes, even – the buffer expands during the write to accommodate the particular response but then never shrinks subsequently. If a hosting Server has had more than one 'fat payload' occurrence, the resultant occupied heap can provoke memory woes (See https://issues.apache.org/jira/browse/HBASE-900?focusedCommentId=12654009#action_12654009 for an extreme example; occasional payloads of 20-50MB with 30 handlers robbed the heap of 700MB).

 All   Comments   Work Log   Change History   Subversion Commits      Sort Order: Ascending order - Click to sort in descending order
No work has yet been logged on this issue.