Mailing-List: contact dev-help@giraph.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@giraph.apache.org
Content-Type: multipart/alternative;
 boundary="===============1050193215551512021=="
MIME-Version: 1.0
Subject: Re: Review Request: Move part of the graph out-of-core when memory is
 low
From: "Alessandro Presta" <alessandro@fb.com>
To: "Avery Ching" <avery.ching@gmail.com>
Cc: "Maja Kabiljo" <majakabiljo@fb.com>,
 "Eli Reisman" <initialcontext@gmail.com>, "giraph" <dev@giraph.apache.org>,
 "Alessandro Presta" <alessandro@fb.com>
Date: Wed, 22 Aug 2012 12:36:44 -0000
Message-ID: <20120822123644.15256.12033@reviews.apache.org>
Auto-Submitted: auto-generated
Sender: "Alessandro Presta" <noreply@reviews.apache.org>
References: <20120822103429.15256.92727@reviews.apache.org>
In-Reply-To: <20120822103429.15256.92727@reviews.apache.org>
Reply-To: "Alessandro Presta" <alessandro@fb.com>

--===============1050193215551512021==
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable


-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/5987/
-----------------------------------------------------------

(Updated Aug. 22, 2012, 12:36 p.m.)


Review request for giraph and Avery Ching.


Changes
-------

Iterate over messages by partition in prepareSuperstep().


Description
-------

I gave this another shot. This time it plays nicely with input superstep: I=
 replaced both the temporary partitions and the worker partition map with a=
 common data structure, PartitionStore, held in ServerData. This is similar=
 to what we now have for messages.

Partition is now thread-safe so that we can have concurrent calls to putVer=
tex().

SimplePartitionStore is backed by a concurrent hash map (nothing new here, =
except that we skip copying partitions to the worker).

DiskBackedPartitionStore can hold up to a user-defined number of partitions=
 in memory, and spill the remaining ones to disk. Each partition is stored =
in a separate file.
Adding vertices to an out-of-core partition consists in appending them to t=
he file, which makes processing vertex requests relatively fast.
We use a ReadWriteLock for each partition: performing operations on a parti=
tion held in memory only requires a read-lock (since Partition is thread-sa=
fe), while creating a new partition, moving it in and out of core or append=
ing vertices requires a write-lock (we can't have concurrent writes).

Also note that this breaks Hadoop RPC: I preferred to keep it clean (this a=
lso shows what code we get rid of) instead of working around it. I suppose =
the Netty security patch will be completed soon. If not, I will restore RPC=
 compatibility.

More here: https://issues.apache.org/jira/browse/GIRAPH-249?focusedCommentI=
d=3D13435280&page=3Dcom.atlassian.jira.plugin.system.issuetabpanels:comment=
-tabpanel#comment-13435280


This addresses bug GIRAPH-249.
    https://issues.apache.org/jira/browse/GIRAPH-249


Diffs (updated)
-----

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/bsp/CentralizedServiceWorker.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/comm/BasicRPCCommunications.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/comm/NettyWorkerClientServer.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/comm/NettyWorkerServer.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/comm/SendVertexRequest.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/comm/ServerData.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/comm/WorkerServer.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/graph/BspServiceWorker.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/graph/GiraphJob.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/graph/GraphMapper.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/graph/partition/DiskBackedPartitionStore.java PRE-CREATION =

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/graph/partition/HashWorkerPartitioner.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/graph/partition/Partition.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/graph/partition/PartitionStore.java PRE-CREATION =

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/graph/partition/SimplePartitionStore.java PRE-CREATION =

  http://svn.apache.org/repos/asf/giraph/trunk/src/main/java/org/apache/gir=
aph/graph/partition/WorkerGraphPartitioner.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/test/java/org/apache/gir=
aph/TestMutateGraphVertex.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/test/java/org/apache/gir=
aph/comm/ConnectionTest.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/test/java/org/apache/gir=
aph/comm/RequestFailureTest.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/test/java/org/apache/gir=
aph/comm/RequestTest.java 1375843 =

  http://svn.apache.org/repos/asf/giraph/trunk/src/test/java/org/apache/gir=
aph/graph/partition/TestPartitionStores.java PRE-CREATION =


Diff: https://reviews.apache.org/r/5987/diff/


Testing
-------

mvn verify and pseudo-distributed mode tests with both SimplePartitionStore=
 and DiskBackedPartitionStore


Thanks,

Alessandro Presta


--===============1050193215551512021==--