|
@@ -387,16 +387,28 @@
|
|
<para>Failure of another leader</para>
|
|
<para>Failure of another leader</para>
|
|
</listitem>
|
|
</listitem>
|
|
</orderedlist>
|
|
</orderedlist>
|
|
|
|
+ </section>
|
|
|
|
|
|
- <para><figure id="fg_zkPerfReliability">
|
|
|
|
|
|
+ <section>
|
|
|
|
+ <title>Reliability</title>
|
|
|
|
+
|
|
|
|
+ <para>To show the behavior of the system over time as
|
|
|
|
+ failures are injected we ran a ZooKeeper service made up of
|
|
|
|
+ 7 machines. We ran the same saturation benchmark as before,
|
|
|
|
+ but this time we kept the write percentage at a constant
|
|
|
|
+ 30%, which is a conservative ratio of our expected
|
|
|
|
+ workloads.
|
|
|
|
+ </para>
|
|
|
|
+ <para>
|
|
|
|
+ <figure id="fg_zkPerfReliability">
|
|
<title>Reliability in the Presence of Errors</title>
|
|
<title>Reliability in the Presence of Errors</title>
|
|
-
|
|
|
|
<mediaobject>
|
|
<mediaobject>
|
|
<imageobject>
|
|
<imageobject>
|
|
<imagedata fileref="images/zkperfreliability.jpg" />
|
|
<imagedata fileref="images/zkperfreliability.jpg" />
|
|
</imageobject>
|
|
</imageobject>
|
|
</mediaobject>
|
|
</mediaobject>
|
|
- </figure></para>
|
|
|
|
|
|
+ </figure>
|
|
|
|
+ </para>
|
|
|
|
|
|
<para>The are a few important observations from this graph. First, if
|
|
<para>The are a few important observations from this graph. First, if
|
|
followers fail and recover quickly, then ZooKeeper is able to sustain a
|
|
followers fail and recover quickly, then ZooKeeper is able to sustain a
|
|
@@ -411,25 +423,27 @@
|
|
<section>
|
|
<section>
|
|
<title>The ZooKeeper Project</title>
|
|
<title>The ZooKeeper Project</title>
|
|
|
|
|
|
- <para>ZooKeeper has been successfully used in industrial applications.
|
|
|
|
- It is used at Yahoo! as the coordination and failure recovery service
|
|
|
|
- for Yahoo! Message Broker, which is a highly scalable publish-subscribe
|
|
|
|
- system managing thousands of topics for replication and data delivery.
|
|
|
|
- It is used by the Fetching Service for Yahoo! crawler, where it also
|
|
|
|
- manages failure recovery. And it is used by Hadoop On Demand (HOD),
|
|
|
|
- which is an open source implementation of the map-reduce model of
|
|
|
|
- computation. HOD uses Zookeeper as a communications and control channel
|
|
|
|
- between slave and master process. (For more information, see the <ulink
|
|
|
|
- url="http://hadoop.apache.org/core/">Hadoop</ulink> and <ulink
|
|
|
|
- url="http://hadoop.apache.org/core/docs/current/hod.html">Hadoop on
|
|
|
|
- Demand</ulink> open source projects on Apache.)</para>
|
|
|
|
-
|
|
|
|
- <para>ZooKeeper itself is an open source project, under the Apache Open
|
|
|
|
- Source Foundation. It is a subproject of Hadoop. All users and
|
|
|
|
- developers are encourged to join the community and contribute their
|
|
|
|
- expertise. See the <ulink
|
|
|
|
- url="http://hadoop.apache.org/zookeeper/">Zookeeper Project on
|
|
|
|
- Apache</ulink> for more information.</para>
|
|
|
|
|
|
+ <para>ZooKeeper has been
|
|
|
|
+ <ulink url="http://wiki.apache.org/hadoop/ZooKeeper/PoweredBy">
|
|
|
|
+ successfully used
|
|
|
|
+ </ulink>
|
|
|
|
+ in many industrial applications. It is used at Yahoo! as the
|
|
|
|
+ coordination and failure recovery service for Yahoo! Message
|
|
|
|
+ Broker, which is a highly scalable publish-subscribe system
|
|
|
|
+ managing thousands of topics for replication and data
|
|
|
|
+ delivery. It is used by the Fetching Service for Yahoo!
|
|
|
|
+ crawler, where it also manages failure recovery. A number of
|
|
|
|
+ Yahoo! advertising systems also use ZooKeeper to implement
|
|
|
|
+ reliable services.
|
|
|
|
+ </para>
|
|
|
|
+
|
|
|
|
+ <para>All users and developers are encouraged to join the
|
|
|
|
+ community and contribute their expertise. See the
|
|
|
|
+ <ulink url="http://hadoop.apache.org/zookeeper/">
|
|
|
|
+ Zookeeper Project on Apache
|
|
|
|
+ </ulink>
|
|
|
|
+ for more information.
|
|
|
|
+ </para>
|
|
</section>
|
|
</section>
|
|
</chapter>
|
|
</chapter>
|
|
</book>
|
|
</book>
|