[
https://issues.apache.org/jira/browse/HAMA-559?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Suraj Menon updated HAMA-559:
-----------------------------
Attachment: spilling_buffer_profile_timesplit_text_write.png
spilling_buffer_profile_cpu_graph_test_write.png
spilling_buffer_cpu_usage_text_write.png
The result for profiling with the following code. I am writing a file close to
4GB size. With Text.write it took close to half hour.
{noformat}
SpillingBuffer buffer = new SpillingBuffer();
// super(new SpillingStream(2, 1 << 24, 1 << 24, true,
// //super(new SpillingStream( 2, 1 << 20, 1 << 8, true,
// System.getProperty("java.io.tmpdir") + File.separatorChar
// + new BigInteger(128, new SecureRandom()).toString(32)));
Text t = new Text("Testing the spillage of spilling buffer");
for (int i = 0; i < 100000000; ++i)
t.write(buffer);
buffer.close();
{noformat}
> Add a spilling message queue
> ----------------------------
>
> Key: HAMA-559
> URL: https://issues.apache.org/jira/browse/HAMA-559
> Project: Hama
> Issue Type: Sub-task
> Components: bsp core
> Affects Versions: 0.5.0
> Reporter: Thomas Jungblut
> Assignee: Suraj Menon
> Priority: Minor
> Fix For: 0.7.0
>
> Attachments: HAMA-559.patch-v1,
> spilling_buffer_cpu_usage_text_write.png,
> spilling_buffer_profile_cpu_graph_test_write.png,
> spilling_buffer_profile_timesplit_text_write.png
>
>
> After HAMA-521 is done, we can add a spilling queue which just holds the
> messages in RAM that fit into the heap space. The rest can be flushed to disk.
> We may call this a HybridQueue or something like that.
> The benefits should be that we don't have to flush to disk so often and get
> faster. However we may have more GC so it is always overall faster.
> The requirements for this queue also include:
> - The message object once written to the queue (after returning from the
> write call) could be modified, but the changes should not be reflected in the
> messages stored in the queue.
> - For now let's implement a queue that does not support concurrent reading
> and writing. This feature is needed when we implement asynchronous
> communication.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
