[
https://issues.apache.org/jira/browse/GIRAPH-256?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13431242#comment-13431242
]
Jakob Homan commented on GIRAPH-256:
------------------------------------
bq. I see some code where the constants are localized, other code where its all
in GiraphJob (and soon in GiraphConf.) I can see a point to both
Putting everything in GiraphJob doesn't scale and makes it hard to find stuff
when you need it. Please put the conf variables where they're used.
bq. hey not seeing the spurious whitespace in the patch, where did you mean?
For example, lines 40 and 41 in the latest patch (6).
> Partitioning outgoing graph data during INPUT_SUPERSTEP by # of vertices
> results in wide variance in RPC message sizes
> ----------------------------------------------------------------------------------------------------------------------
>
> Key: GIRAPH-256
> URL: https://issues.apache.org/jira/browse/GIRAPH-256
> Project: Giraph
> Issue Type: Improvement
> Components: bsp, graph
> Affects Versions: 0.2.0
> Reporter: Eli Reisman
> Assignee: Eli Reisman
> Labels: patch
> Fix For: 0.2.0
>
> Attachments: GIRAPH-256-1.patch, GIRAPH-256-2.patch,
> GIRAPH-256-3.patch, GIRAPH-256-4.patch, GIRAPH-256-5.patch, GIRAPH-256-6.patch
>
>
> This relates to GIRAPH-247. The unfortunately named
> "MAX_VERTICES_PER_PARTITION" fooled me into thinking this value was
> regulating the size of initial Partition objects as they were composed during
> INPUT_SUPERSTEP from InputSplits each worker reads.
> In fact this configuration option only regulates the size of the outgoing RPC
> messages, stored locally in Partition objects but decomposed into Collections
> of BasicVertex for transfer to their eventual homes on another (or this)
> worker. There they are combined into the actual Partitions they will exist in
> for the job run.
> By partitioning these outgoing messages by # of vertices, metrics load tests
> have shown the size of the average message is not well regulated and can
> create overloads on either side of these transfers. This is important because:
> 1. Throughput and memory are at a premium during INPUT_SUPERSTEP.
> 2. Only one crashed worker in a Giraph job causes cascading job failure, even
> in an otherwise healthy workflow.
> This JIRA renames the offending variables/config options and further
> regulates outgoing graph data in INPUT_SUPERSTEP by the # of edges and THEN
> the # of vertices in a candidate for transfer. This much more effectively
> regulates message size for typical social graph data and has been show in
> testing to greatly improve the amount of load-in data Giraph can handle
> without failure given fixed memory and worker limits.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
