This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/ozone-site.git
The following commit(s) were added to refs/heads/asf-site by this push:
new 4609f800 [auto] Generated docs from Apache Ozone master
1661a9a13ba36c67098134b0644ebef0e572b51e
4609f800 is described below
commit 4609f8000f3a61fed268cf9e940dbde6856193ea
Author: Github Actions <[email protected]>
AuthorDate: Thu Aug 14 12:47:02 2025 +0000
[auto] Generated docs from Apache Ozone master
1661a9a13ba36c67098134b0644ebef0e572b51e
---
docs/edge/en/sitemap.xml | 2 +-
docs/edge/feature/topology.html | 194 +++++++++++++++++++++++++++++++---------
docs/edge/sitemap.xml | 2 +-
3 files changed, 154 insertions(+), 44 deletions(-)
diff --git a/docs/edge/en/sitemap.xml b/docs/edge/en/sitemap.xml
index ad9e7e44..3c93820b 100644
--- a/docs/edge/en/sitemap.xml
+++ b/docs/edge/en/sitemap.xml
@@ -207,7 +207,7 @@
/>
</url><url>
<loc>/feature/topology.html</loc>
- <lastmod>2023-03-29T13:32:17+05:30</lastmod>
+ <lastmod>2025-08-13T18:57:49-07:00</lastmod>
<xhtml:link
rel="alternate"
hreflang="zh"
diff --git a/docs/edge/feature/topology.html b/docs/edge/feature/topology.html
index 477fd239..21afafbd 100644
--- a/docs/edge/feature/topology.html
+++ b/docs/edge/feature/topology.html
@@ -606,59 +606,169 @@ s=d.getElementsByTagName('script')[0];
See the License for the specific language governing permissions and
limitations under the License.
-->
-<p>Ozone can use topology related information (for example rack placement) to
optimize read and write pipelines. To get full rack-aware cluster, Ozone
requires three different configuration.</p>
+<p>Apache Ozone uses topology information (e.g., rack placement) to optimize
data access and improve resilience. A fully rack-aware cluster needs:</p>
<ol>
-<li>The topology information should be configured by Ozone.</li>
-<li>Topology related information should be used when Ozone chooses 3 different
datanodes for a specific pipeline/container. (WRITE)</li>
-<li>When Ozone reads a Key it should prefer to read from the closest node.</li>
+<li>Configured network topology.</li>
+<li>Topology-aware DataNode selection for container replica placement (write
path).</li>
+<li>Prioritized reads from topologically closest DataNodes (read path).</li>
</ol>
-<div class="alert alert-warning" role="alert">
-<p>Ozone uses RAFT replication for Open containers (write), and an async
replication for closed, immutable containers (cold data). As RAFT requires
low-latency network, topology awareness placement is available only for closed
containers. See the <a href="../concept/containers.html">page about
Containers</a> about more information related to Open vs Closed containers.</p>
-</div>
-<h2 id="topology-hierarchy">Topology hierarchy</h2>
-<p>Topology hierarchy can be configured with using
<code>net.topology.node.switch.mapping.impl</code> configuration key. This
configuration should define an implementation of the
<code>org.apache.hadoop.net.CachedDNSToSwitchMapping</code>. As this is a
Hadoop class, the configuration is exactly the same as the Hadoop
Configuration</p>
-<h3 id="static-list">Static list</h3>
-<p>Static list can be configured with the help of
<code>TableMapping</code>:</p>
-<div class="highlight"><pre tabindex="0"
style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code
class="language-XML" data-lang="XML"><span style="display:flex;"><span><span
style="color:#f92672"><property></span>
-</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><name></span>net.topology.node.switch.mapping.impl<span
style="color:#f92672"></name></span>
-</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><value></span>org.apache.hadoop.net.TableMapping<span
style="color:#f92672"></value></span>
+<h2 id="applicability-to-container-types">Applicability to Container Types</h2>
+<p>Ozone’s topology-aware placement strategies vary by container
replication type and state:</p>
+<ul>
+<li><strong>RATIS Replicated Containers:</strong> Ozone uses RAFT replication
for Open containers (write), and an async replication for closed, immutable
containers (cold data). Topology awareness placement is implemented for both
open and closed RATIS containers, ensuring rack diversity and fault tolerance
during both write and re-replication operations. See the <a
href="../concept/containers.html">page about Containers</a> for more
information related to Open vs Closed containers.</li>
+</ul>
+<h2 id="configuring-topology-hierarchy">Configuring Topology Hierarchy</h2>
+<p>Ozone determines DataNode network locations (e.g., racks) using
Hadoop’s rack awareness, configured via
<code>net.topology.node.switch.mapping.impl</code> in
<code>ozone-site.xml</code>. This key specifies a
<code>org.apache.hadoop.net.CachedDNSToSwitchMapping</code> implementation.
[1]</p>
+<p>Two primary methods exist:</p>
+<h3 id="1-static-list-tablemapping">1. Static List:
<code>TableMapping</code></h3>
+<p>Maps IPs/hostnames to racks using a predefined file.</p>
+<ul>
+<li><strong>Configuration:</strong> Set
<code>net.topology.node.switch.mapping.impl</code> to
<code>org.apache.hadoop.net.TableMapping</code> and
<code>net.topology.table.file.name</code> to the mapping file’s path. [1]
+<div class="highlight"><pre tabindex="0"
style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code
class="language-xml" data-lang="xml"><span style="display:flex;"><span><span
style="color:#f92672"><property></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><name></span>net.topology.node.switch.mapping.impl<span
style="color:#f92672"></name></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><value></span>org.apache.hadoop.net.TableMapping<span
style="color:#f92672"></value></span>
</span></span><span style="display:flex;"><span><span
style="color:#f92672"></property></span>
</span></span><span style="display:flex;"><span><span
style="color:#f92672"><property></span>
-</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><name></span>net.topology.table.file.name<span
style="color:#f92672"></name></span>
-</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><value></span>/opt/hadoop/compose/ozone-topology/network-config<span
style="color:#f92672"></value></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><name></span>net.topology.table.file.name<span
style="color:#f92672"></name></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><value></span>/etc/ozone/topology.map<span
style="color:#f92672"></value></span>
</span></span><span style="display:flex;"><span><span
style="color:#f92672"></property></span>
-</span></span></code></pre></div><p>The second configuration option should
point to a text file. The file format is a two column text file, with columns
separated by whitespace. The first column is IP address and the second column
specifies the rack where the address maps. If no entry corresponding to a host
in the cluster is found, then <code>/default-rack</code> is assumed.</p>
-<h3 id="dynamic-list">Dynamic list</h3>
-<p>Rack information can be identified with the help of an external script:</p>
-<div class="highlight"><pre tabindex="0"
style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code
class="language-XML" data-lang="XML"><span style="display:flex;"><span><span
style="color:#f92672"><property></span>
-</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><name></span>net.topology.node.switch.mapping.impl<span
style="color:#f92672"></name></span>
-</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><value></span>org.apache.hadoop.net.ScriptBasedMapping<span
style="color:#f92672"></value></span>
+</span></span></code></pre></div></li>
+<li><strong>File Format:</strong> A two-column text file (IP/hostname, rack
path per line). Unlisted nodes go to <code>/default-rack</code>. [1]
+Example <code>topology.map</code>:
+<pre tabindex="0"><code>192.168.1.100 /rack1
+datanode101.example.com /rack1
+192.168.1.102 /rack2
+datanode103.example.com /rack2
+</code></pre></li>
+</ul>
+<h3 id="2-dynamic-list-scriptbasedmapping">2. Dynamic List:
<code>ScriptBasedMapping</code></h3>
+<p>Uses an external script to resolve rack locations for IPs.</p>
+<ul>
+<li>
+<p><strong>Configuration:</strong> Set
<code>net.topology.node.switch.mapping.impl</code> to
<code>org.apache.hadoop.net.ScriptBasedMapping</code> and
<code>net.topology.script.file.name</code> to the script’s path. [1]</p>
+<div class="highlight"><pre tabindex="0"
style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code
class="language-xml" data-lang="xml"><span style="display:flex;"><span><span
style="color:#f92672"><property></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><name></span>net.topology.node.switch.mapping.impl<span
style="color:#f92672"></name></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><value></span>org.apache.hadoop.net.ScriptBasedMapping<span
style="color:#f92672"></value></span>
</span></span><span style="display:flex;"><span><span
style="color:#f92672"></property></span>
</span></span><span style="display:flex;"><span><span
style="color:#f92672"><property></span>
-</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><name></span>net.topology.script.file.name<span
style="color:#f92672"></name></span>
-</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><value></span>/usr/local/bin/rack.sh<span
style="color:#f92672"></value></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><name></span>net.topology.script.file.name<span
style="color:#f92672"></name></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><value></span>/etc/ozone/determine_rack.sh<span
style="color:#f92672"></value></span>
</span></span><span style="display:flex;"><span><span
style="color:#f92672"></property></span>
-</span></span></code></pre></div><p>If implementing an external script, it
will be specified with the <code>net.topology.script.file.name</code> parameter
in the configuration files. Unlike the java class, the external topology script
is not included with the Ozone distribution and is provided by the
administrator. Ozone will send multiple IP addresses to ARGV when forking the
topology script. The number of IP addresses sent to the topology script is
controlled with <code>net.topology.sc [...]
-<h2 id="write-path">Write path</h2>
-<p>Placement of the closed containers can be configured with
<code>ozone.scm.container.placement.impl</code> configuration key. The
available container placement policies can be found in the
<code>org.apache.hdds.scm.container.placement</code> <a
href="https://github.com/apache/ozone/tree/master/hadoop-hdds/server-scm/src/main/java/org/apache/hadoop/hdds/scm/container/placement/algorithms";>package</a>.</p>
-<p>By default the <code>SCMContainerPlacementRandom</code> is used for
topology-awareness the <code>SCMContainerPlacementRackAware</code> can be
used:</p>
-<div class="highlight"><pre tabindex="0"
style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code
class="language-XML" data-lang="XML"><span style="display:flex;"><span><span
style="color:#f92672"><property></span>
-</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><name></span>ozone.scm.container.placement.impl<span
style="color:#f92672"></name></span>
-</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><value></span>org.apache.hadoop.hdds.scm.container.placement.algorithms.SCMContainerPlacementRackAware<span
style="color:#f92672"></value></span>
+</span></span></code></pre></div></li>
+<li>
+<p><strong>Script:</strong> Admin-provided, executable script. Ozone passes
IPs (up to <code>net.topology.script.number.args</code>, default 100) as
arguments; script outputs rack paths (one per line).
+Example <code>determine_rack.sh</code>:</p>
+<div class="highlight"><pre tabindex="0"
style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code
class="language-bash" data-lang="bash"><span style="display:flex;"><span><span
style="color:#75715e">#!/bin/bash
+</span></span></span><span style="display:flex;"><span><span
style="color:#75715e"></span><span style="color:#75715e"># This is a simplified
example. A real script might query a CMDB or use other logic.</span>
+</span></span><span style="display:flex;"><span><span
style="color:#66d9ef">while</span> <span style="color:#f92672">[</span> $# -gt
<span style="color:#ae81ff">0</span> <span style="color:#f92672">]</span> ;
<span style="color:#66d9ef">do</span>
+</span></span><span style="display:flex;"><span> nodeAddress<span
style="color:#f92672">=</span>$1
+</span></span><span style="display:flex;"><span> <span
style="color:#66d9ef">if</span> <span style="color:#f92672">[[</span> <span
style="color:#e6db74">"</span>$nodeAddress<span
style="color:#e6db74">"</span> <span style="color:#f92672">==</span> <span
style="color:#e6db74">"192.168.1.100"</span> <span
style="color:#f92672">||</span> <span
style="color:#e6db74">"</span>$nodeAddress<span
style="color:#e6db74">"</span> <span style="color:#f92672">==</span> <span
s [...]
+</span></span><span style="display:flex;"><span> echo <span
style="color:#e6db74">"/rack1"</span>
+</span></span><span style="display:flex;"><span> <span
style="color:#66d9ef">elif</span> <span style="color:#f92672">[[</span> <span
style="color:#e6db74">"</span>$nodeAddress<span
style="color:#e6db74">"</span> <span style="color:#f92672">==</span> <span
style="color:#e6db74">"192.168.1.102"</span> <span
style="color:#f92672">||</span> <span
style="color:#e6db74">"</span>$nodeAddress<span
style="color:#e6db74">"</span> <span style="color:#f92672">==</span> <span
[...]
+</span></span><span style="display:flex;"><span> echo <span
style="color:#e6db74">"/rack2"</span>
+</span></span><span style="display:flex;"><span> <span
style="color:#66d9ef">else</span>
+</span></span><span style="display:flex;"><span> echo <span
style="color:#e6db74">"/default-rack"</span>
+</span></span><span style="display:flex;"><span> <span
style="color:#66d9ef">fi</span>
+</span></span><span style="display:flex;"><span> shift
+</span></span><span style="display:flex;"><span><span
style="color:#66d9ef">done</span>
+</span></span></code></pre></div><p>Ensure the script is executable
(<code>chmod +x /etc/ozone/determine_rack.sh</code>).</p>
+<p><strong>Note:</strong> For production environments, implement robust error
handling and validation in your script. This should include handling network
timeouts, invalid inputs, CMDB query failures, and logging errors
appropriately. The example above is simplified for illustration purposes
only.</p>
+</li>
+</ul>
+<p><strong>Topology Mapping Best Practices:</strong></p>
+<ul>
+<li><strong>Accuracy:</strong> Mappings must be accurate and current.</li>
+<li><strong>Static Mapping:</strong> Simpler for small, stable clusters;
requires manual updates.</li>
+<li><strong>Dynamic Mapping:</strong> Flexible for large/dynamic clusters.
Script performance, correctness, and reliability are vital; ensure it’s
idempotent and handles batch lookups efficiently.</li>
+</ul>
+<h2 id="pipeline-choosing-policies">Pipeline Choosing Policies</h2>
+<p>Ozone supports several policies for selecting a pipeline when placing
containers. The policy for Ratis containers is configured by the property
<code>hdds.scm.pipeline.choose.policy.impl</code> for SCM. The policy for EC
(Erasure Coded) containers is configured by the property
<code>hdds.scm.ec.pipeline.choose.policy.impl</code>. For both, the default
value is
<code>org.apache.hadoop.hdds.scm.pipeline.choose.algorithms.RandomPipelineChoosePolicy</code>.</p>
+<p>These policies help optimize for different goals such as load balancing,
health, or simplicity:</p>
+<ul>
+<li>
+<p><strong>RandomPipelineChoosePolicy</strong> (Default): Selects a pipeline
at random from the available list, without considering utilization or health.
This policy is simple and does not optimize for any particular metric.</p>
+</li>
+<li>
+<p><strong>CapacityPipelineChoosePolicy</strong>: Picks two random pipelines
and selects the one with lower utilization, favoring pipelines with more
available capacity and helping to balance the load across the cluster.</p>
+</li>
+<li>
+<p><strong>RoundRobinPipelineChoosePolicy</strong>: Selects pipelines in a
round-robin order. This policy is mainly used for debugging and testing,
ensuring even distribution but not considering health or capacity.</p>
+</li>
+<li>
+<p><strong>HealthyPipelineChoosePolicy</strong>: Randomly selects pipelines
but only returns a healthy one. If no healthy pipeline is found, it returns the
last tried pipeline as a fallback.</p>
+</li>
+</ul>
+<p>These policies can be configured to suit different deployment needs and
workloads.</p>
+<h2
id="container-placement-policies-for-replicated-ratis-containers">Container
Placement Policies for Replicated (RATIS) Containers</h2>
+<p>SCM uses a pluggable policy to place additional replicas of <em>closed</em>
RATIS-replicated containers. This is configured using the
<code>ozone.scm.container.placement.impl</code> property in
<code>ozone-site.xml</code>. Available policies are found in the
<code>org.apache.hadoop.hdds.scm.container.placement.algorithms</code> package
[1, 3].</p>
+<p>These policies are applied when SCM needs to re-replicate containers, such
as during container balancing.</p>
+<h3 id="1-scmcontainerplacementrackaware-default">1.
<code>SCMContainerPlacementRackAware</code> (Default)</h3>
+<ul>
+<li><strong>Function:</strong> Distributes replicas across racks for fault
tolerance (e.g., for 3 replicas, aims for at least two racks). Similar to HDFS
placement. [1]</li>
+<li><strong>Use Cases:</strong> Production clusters needing rack-level fault
tolerance.</li>
+<li><strong>Configuration:</strong>
+<div class="highlight"><pre tabindex="0"
style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code
class="language-xml" data-lang="xml"><span style="display:flex;"><span><span
style="color:#f92672"><property></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><name></span>ozone.scm.container.placement.impl<span
style="color:#f92672"></name></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><value></span>org.apache.hadoop.hdds.scm.container.placement.algorithms.SCMContainerPlacementRackAware<span
style="color:#f92672"></value></span>
+</span></span><span style="display:flex;"><span><span
style="color:#f92672"></property></span>
+</span></span></code></pre></div></li>
+<li><strong>Best Practices:</strong> Requires accurate topology mapping.</li>
+<li><strong>Limitations:</strong> Designed for single-layer rack topologies
(e.g., <code>/rack/node</code>). Not recommended for multi-layer hierarchies
(e.g., <code>/dc/row/rack/node</code>) as it may not interpret deeper levels
correctly. [1]</li>
+</ul>
+<h3 id="2-scmcontainerplacementrandom">2.
<code>SCMContainerPlacementRandom</code></h3>
+<ul>
+<li><strong>Function:</strong> Randomly selects healthy, available DataNodes
meeting basic criteria (space, no existing replica), ignoring rack topology.
[1, 4]</li>
+<li><strong>Use Cases:</strong> Small/dev/test clusters, or if rack fault
tolerance for closed replicas isn’t critical.</li>
+<li><strong>Configuration:</strong>
+<div class="highlight"><pre tabindex="0"
style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code
class="language-xml" data-lang="xml"><span style="display:flex;"><span><span
style="color:#f92672"><property></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><name></span>ozone.scm.container.placement.impl<span
style="color:#f92672"></name></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><value></span>org.apache.hadoop.hdds.scm.container.placement.algorithms.SCMContainerPlacementRandom<span
style="color:#f92672"></value></span>
+</span></span><span style="display:flex;"><span><span
style="color:#f92672"></property></span>
+</span></span></code></pre></div></li>
+<li><strong>Best Practices:</strong> Not for production needing rack failure
resilience.</li>
+</ul>
+<h3 id="3-scmcontainerplacementcapacity">3.
<code>SCMContainerPlacementCapacity</code></h3>
+<ul>
+<li><strong>Function:</strong> Selects DataNodes by available capacity (favors
lower disk utilization) to balance disk usage. [5, 6]</li>
+<li><strong>Use Cases:</strong> Heterogeneous storage clusters or where even
disk utilization is key.</li>
+<li><strong>Configuration:</strong>
+<div class="highlight"><pre tabindex="0"
style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code
class="language-xml" data-lang="xml"><span style="display:flex;"><span><span
style="color:#f92672"><property></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><name></span>ozone.scm.container.placement.impl<span
style="color:#f92672"></name></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><value></span>org.apache.hadoop.hdds.scm.container.placement.algorithms.SCMContainerPlacementCapacity<span
style="color:#f92672"></value></span>
</span></span><span style="display:flex;"><span><span
style="color:#f92672"></property></span>
-</span></span></code></pre></div><p>This placement policy complies with the
algorithm used in HDFS. With default 3 replica, two replicas will be on the
same rack, the third one will on a different rack.</p>
-<p>This implementation applies to network topology like
“/rack/node”. Don’t recommend to use this if the network
topology has more layers.</p>
-<h2 id="read-path">Read path</h2>
-<p>Finally the read path also should be configured to read the data from the
closest pipeline.</p>
-<div class="highlight"><pre tabindex="0"
style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code
class="language-XML" data-lang="XML"><span style="display:flex;"><span><span
style="color:#f92672"><property></span>
-</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><name></span>ozone.network.topology.aware.read<span
style="color:#f92672"></name></span>
-</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><value></span>true<span
style="color:#f92672"></value></span>
+</span></span></code></pre></div></li>
+<li><strong>Best Practices:</strong> Prevents uneven node filling.</li>
+<li><strong>Interaction:</strong> This container placement policy selects
datanodes by randomly picking two nodes from a pool of healthy, available nodes
and then choosing the one with lower utilization (more free space). This
approach aims to distribute containers more evenly across the cluster over
time, favoring less utilized nodes without overwhelming newly added nodes.</li>
+</ul>
+<h2 id="optimizing-read-paths">Optimizing Read Paths</h2>
+<p>Enable by setting <code>ozone.network.topology.aware.read</code> to
<code>true</code> in <code>ozone-site.xml</code>. [1]</p>
+<div class="highlight"><pre tabindex="0"
style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code
class="language-xml" data-lang="xml"><span style="display:flex;"><span><span
style="color:#f92672"><property></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><name></span>ozone.network.topology.aware.read<span
style="color:#f92672"></name></span>
+</span></span><span style="display:flex;"><span> <span
style="color:#f92672"><value></span>true<span
style="color:#f92672"></value></span>
</span></span><span style="display:flex;"><span><span
style="color:#f92672"></property></span>
-</span></span></code></pre></div><h2 id="references">References</h2>
+</span></span></code></pre></div><p>This directs clients (replicated data) to
read from topologically closest DataNodes, reducing latency and cross-rack
traffic. Recommended with accurate topology.</p>
+<h2 id="summary-of-best-practices">Summary of Best Practices</h2>
<ul>
-<li>Hadoop documentation about
<code>net.topology.node.switch.mapping.impl</code>: <a
href="https://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-common/RackAwareness.html";>https://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-common/RackAwareness.html</a></li>
-<li><a href="../design/topology.html">Design doc</a></li>
+<li>
+<p><strong>Accurate Topology:</strong> Maintain an accurate, up-to-date
topology map (static or dynamic script); this is foundational.</p>
+</li>
+<li>
+<p><strong>Replicated (RATIS) Containers:</strong> For production rack fault
tolerance, use <code>SCMContainerPlacementRackAware</code> (mindful of its
single-layer topology limitation) or <code>SCMContainerPlacementCapacity</code>
(verify rack interaction) over <code>SCMContainerPlacementRandom</code>.</p>
+</li>
+<li>
+<p><strong>Read Operations:</strong> Enable
<code>ozone.network.topology.aware.read</code> with accurate topology.</p>
+</li>
+<li>
+<p><strong>Monitor & Validate:</strong> Regularly monitor placement and
balance; use tools like Recon to verify topology awareness.</p>
+</li>
</ul>
+<h2 id="references">References</h2>
+<ol>
+<li><a
href="https://hadoop.apache.org/docs/stable/hadoop-project-dist/hadoop-common/RackAwareness.html";>Hadoop
Documentation: Rack Awareness</a>.</li>
+<li><a
href="https://github.com/apache/ozone/tree/master/hadoop-hdds/server-scm/src/main/java/org/apache/hadoop/hdds/scm/container/placement/algorithms";>Ozone
Source Code: container placement policies</a>. (For implementations of
pluggable placement policies).</li>
+<li><a
href="https://github.com/apache/ozone/blob/master/hadoop-hdds/server-scm/src/main/java/org/apache/hadoop/hdds/scm/container/placement/algorithms/SCMContainerPlacementRandom.java";>Ozone
Source Code: SCMContainerPlacementRandom.java</a>.</li>
+<li><a
href="https://github.com/apache/ozone/blob/master/hadoop-hdds/server-scm/src/main/java/org/apache/hadoop/hdds/scm/container/placement/algorithms/SCMContainerPlacementCapacity.java";>Ozone
Source Code: SCMContainerPlacementCapacity.java</a>.</li>
+</ol>
@@ -678,7 +788,7 @@ s=d.getElementsByTagName('script')[0];
<footer class="footer">
<div class="container">
<span class="small text-muted">
- Version: 2.1.0-SNAPSHOT, Last Modified: March 29, 2023 <a
class="hide-child link primary-color"
href="https://github.com/apache/ozone/commit/cce3c7ea79ec19657d10f011ddeaf3067a2f83bd";>cce3c7ea79</a>
+ Version: 2.1.0-SNAPSHOT, Last Modified: August 13, 2025 <a
class="hide-child link primary-color"
href="https://github.com/apache/ozone/commit/cc2a42d80cabcf29ae60a87096fe59ef369a5d4a";>cc2a42d80c</a>
</span>
</div>
</footer>
diff --git a/docs/edge/sitemap.xml b/docs/edge/sitemap.xml
index 2553c4c8..458f80c7 100644
--- a/docs/edge/sitemap.xml
+++ b/docs/edge/sitemap.xml
@@ -4,7 +4,7 @@
<sitemap>
<loc>/en/sitemap.xml</loc>
- <lastmod>2025-08-12T14:24:23-04:00</lastmod>
+ <lastmod>2025-08-13T18:57:49-07:00</lastmod>
</sitemap>
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
