[flink-web] 02/02: regenerate website

[rm...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

rmetzger pushed a commit to branch asf-site
in repository https://gitbox.apache.org/repos/asf/flink-web.git

commit b1d04dcd49804c5b3f073e286e5ca69e3d1726d5
Author: Robert Metzger <rm...@apache.org>
AuthorDate: Thu Oct 15 16:48:42 2020 +0200

    regenerate website
---
 ...om-aligned-to-unaligned-checkpoints-part-1.html | 370 +++++++++++++++++++++
 content/blog/feed.xml                              | 350 +++++++------------
 content/blog/index.html                            |  36 +-
 content/blog/page10/index.html                     |  39 ++-
 content/blog/page11/index.html                     |  38 ++-
 content/blog/page12/index.html                     |  37 ++-
 content/blog/page13/index.html                     |  39 ++-
 content/blog/page14/index.html                     |  25 ++
 content/blog/page2/index.html                      |  36 +-
 content/blog/page3/index.html                      |  36 +-
 content/blog/page4/index.html                      |  38 ++-
 content/blog/page5/index.html                      |  38 ++-
 content/blog/page6/index.html                      |  38 ++-
 content/blog/page7/index.html                      |  40 ++-
 content/blog/page8/index.html                      |  38 ++-
 content/blog/page9/index.html                      |  37 ++-
 ...m-aligned-to-unaligned-checkpoints-part-1-1.png | Bin 0 -> 31754 bytes
 ...m-aligned-to-unaligned-checkpoints-part-1-2.png | Bin 0 -> 335330 bytes
 ...m-aligned-to-unaligned-checkpoints-part-1-3.png | Bin 0 -> 199162 bytes
 ...m-aligned-to-unaligned-checkpoints-part-1-4.png | Bin 0 -> 177701 bytes
 ...m-aligned-to-unaligned-checkpoints-part-1-5.png | Bin 0 -> 75609 bytes
 content/index.html                                 |   6 +-
 content/zh/index.html                              |   6 +-
 23 files changed, 838 insertions(+), 409 deletions(-)

diff --git a/content/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html b/content/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html
new file mode 100644
index 0000000..0cc8662
--- /dev/null
+++ b/content/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html
@@ -0,0 +1,370 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <!-- The above 3 meta tags *must* come first in the head; any other head content must come *after* these tags -->
+    <title>Apache Flink: From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</title>
+    <link rel="shortcut icon" href="/favicon.ico" type="image/x-icon">
+    <link rel="icon" href="/favicon.ico" type="image/x-icon">
+
+    <!-- Bootstrap -->
+    <link rel="stylesheet" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.4.1/css/bootstrap.min.css">
+    <link rel="stylesheet" href="/css/flink.css">
+    <link rel="stylesheet" href="/css/syntax.css">
+
+    <!-- Blog RSS feed -->
+    <link href="/blog/feed.xml" rel="alternate" type="application/rss+xml" title="Apache Flink Blog: RSS feed" />
+
+    <!-- jQuery (necessary for Bootstrap's JavaScript plugins) -->
+    <!-- We need to load Jquery in the header for custom google analytics event tracking-->
+    <script src="/js/jquery.min.js"></script>
+
+    <!-- HTML5 shim and Respond.js for IE8 support of HTML5 elements and media queries -->
+    <!-- WARNING: Respond.js doesn't work if you view the page via file:// -->
+    <!--[if lt IE 9]>
+      <script src="https://oss.maxcdn.com/html5shiv/3.7.2/html5shiv.min.js"></script>
+      <script src="https://oss.maxcdn.com/respond/1.4.2/respond.min.js"></script>
+    <![endif]-->
+  </head>
+  <body>  
+    
+
+    <!-- Main content. -->
+    <div class="container">
+    <div class="row">
+
+      
+     <div id="sidebar" class="col-sm-3">
+        
+
+<!-- Top navbar. -->
+    <nav class="navbar navbar-default">
+        <!-- The logo. -->
+        <div class="navbar-header">
+          <button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#bs-example-navbar-collapse-1">
+            <span class="icon-bar"></span>
+            <span class="icon-bar"></span>
+            <span class="icon-bar"></span>
+          </button>
+          <div class="navbar-logo">
+            <a href="/">
+              <img alt="Apache Flink" src="/img/flink-header-logo.svg" width="147px" height="73px">
+            </a>
+          </div>
+        </div><!-- /.navbar-header -->
+
+        <!-- The navigation links. -->
+        <div class="collapse navbar-collapse" id="bs-example-navbar-collapse-1">
+          <ul class="nav navbar-nav navbar-main">
+
+            <!-- First menu section explains visitors what Flink is -->
+
+            <!-- What is Stream Processing? -->
+            <!--
+            <li><a href="/streamprocessing1.html">What is Stream Processing?</a></li>
+            -->
+
+            <!-- What is Flink? -->
+            <li><a href="/flink-architecture.html">What is Apache Flink?</a></li>
+
+            
+
+            <!-- What is Stateful Functions? -->
+
+            <li><a href="/stateful-functions.html">What is Stateful Functions?</a></li>
+
+            <!-- Use cases -->
+            <li><a href="/usecases.html">Use Cases</a></li>
+
+            <!-- Powered by -->
+            <li><a href="/poweredby.html">Powered By</a></li>
+
+
+            &nbsp;
+            <!-- Second menu section aims to support Flink users -->
+
+            <!-- Downloads -->
+            <li><a href="/downloads.html">Downloads</a></li>
+
+            <!-- Getting Started -->
+            <li class="dropdown">
+              <a class="dropdown-toggle" data-toggle="dropdown" href="#">Getting Started<span class="caret"></span></a>
+              <ul class="dropdown-menu">
+                <li><a href="https://ci.apache.org/projects/flink/flink-docs-release-1.11/getting-started/index.html" target="_blank">With Flink <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
+                <li><a href="https://ci.apache.org/projects/flink/flink-statefun-docs-release-2.2/getting-started/project-setup.html" target="_blank">With Flink Stateful Functions <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
+                <li><a href="/training.html">Training Course</a></li>
+              </ul>
+            </li>
+
+            <!-- Documentation -->
+            <li class="dropdown">
+              <a class="dropdown-toggle" data-toggle="dropdown" href="#">Documentation<span class="caret"></span></a>
+              <ul class="dropdown-menu">
+                <li><a href="https://ci.apache.org/projects/flink/flink-docs-release-1.11" target="_blank">Flink 1.11 (Latest stable release) <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
+                <li><a href="https://ci.apache.org/projects/flink/flink-docs-master" target="_blank">Flink Master (Latest Snapshot) <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
+                <li><a href="https://ci.apache.org/projects/flink/flink-statefun-docs-release-2.2" target="_blank">Flink Stateful Functions 2.2 (Latest stable release) <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
+                <li><a href="https://ci.apache.org/projects/flink/flink-statefun-docs-master" target="_blank">Flink Stateful Functions Master (Latest Snapshot) <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
+              </ul>
+            </li>
+
+            <!-- getting help -->
+            <li><a href="/gettinghelp.html">Getting Help</a></li>
+
+            <!-- Blog -->
+            <li><a href="/blog/"><b>Flink Blog</b></a></li>
+
+
+            <!-- Flink-packages -->
+            <li>
+              <a href="https://flink-packages.org" target="_blank">flink-packages.org <small><span class="glyphicon glyphicon-new-window"></span></small></a>
+            </li>
+            &nbsp;
+
+            <!-- Third menu section aim to support community and contributors -->
+
+            <!-- Community -->
+            <li><a href="/community.html">Community &amp; Project Info</a></li>
+
+            <!-- Roadmap -->
+            <li><a href="/roadmap.html">Roadmap</a></li>
+
+            <!-- Contribute -->
+            <li><a href="/contributing/how-to-contribute.html">How to Contribute</a></li>
+            
+
+            <!-- GitHub -->
+            <li>
+              <a href="https://github.com/apache/flink" target="_blank">Flink on GitHub <small><span class="glyphicon glyphicon-new-window"></span></small></a>
+            </li>
+
+            &nbsp;
+
+            <!-- Language Switcher -->
+            <li>
+              
+                
+                  <a href="/zh/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">中文版</a>
+                
+              
+            </li>
+
+          </ul>
+
+          <ul class="nav navbar-nav navbar-bottom">
+          <hr />
+
+            <!-- Twitter -->
+            <li><a href="https://twitter.com/apacheflink" target="_blank">@ApacheFlink <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
+
+            <!-- Visualizer -->
+            <li class=" hidden-md hidden-sm"><a href="/visualizer/" target="_blank">Plan Visualizer <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
+
+          <hr />
+
+            <li><a href="https://apache.org" target="_blank">Apache Software Foundation <small><span class="glyphicon glyphicon-new-window"></span></small></a></li>
+
+            <li>
+              <style>
+                .smalllinks:link {
+                  display: inline-block !important; background: none; padding-top: 0px; padding-bottom: 0px; padding-right: 0px; min-width: 75px;
+                }
+              </style>
+
+              <a class="smalllinks" href="https://www.apache.org/licenses/" target="_blank">License</a> <small><span class="glyphicon glyphicon-new-window"></span></small>
+
+              <a class="smalllinks" href="https://www.apache.org/security/" target="_blank">Security</a> <small><span class="glyphicon glyphicon-new-window"></span></small>
+
+              <a class="smalllinks" href="https://www.apache.org/foundation/sponsorship.html" target="_blank">Donate</a> <small><span class="glyphicon glyphicon-new-window"></span></small>
+
+              <a class="smalllinks" href="https://www.apache.org/foundation/thanks.html" target="_blank">Thanks</a> <small><span class="glyphicon glyphicon-new-window"></span></small>
+            </li>
+
+          </ul>
+        </div><!-- /.navbar-collapse -->
+    </nav>
+
+      </div>
+      <div class="col-sm-9">
+      <div class="row-fluid">
+  <div class="col-sm-12">
+    <div class="row">
+      <h1>From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</h1>
+      <p><i></i></p>
+
+      <article>
+        <p>15 Oct 2020 Arvid Heise  &amp; Stephan Ewen </p>
+
+<p>Apache Flink’s checkpoint-based fault tolerance mechanism is one of its defining features. Because of that design, Flink unifies batch and stream processing, can easily scale to both <a href="https://hal.inria.fr/hal-02463206/document">very small</a> and <a href="https://102.alibaba.com/detail?id=35">extremely large</a> scenarios and provides support for many operational features like stateful upgrades with <a href="https://ci.apache.org/projects/flink/flink-docs-stable/dev/stream/sta [...]
+
+<p>Despite all these great properties, Flink’s checkpointing method has an Achilles Heel: the speed of a completed checkpoint is determined by the speed at which data flows through the application. When the application backpressures, the processing of checkpoints is backpressured as well (<a href="#appendix-1---on-backpressure">Appendix 1</a> recaps what is backpressure and why it can be a good thing). In such cases, checkpoints may take longer to complete or even time out completely.</p>
+
+<p>In Flink 1.11, the community introduced a first version of a new feature called “<a href="https://ci.apache.org/projects/flink/flink-docs-stable/ops/state/checkpoints.html#unaligned-checkpoints">unaligned checkpoints</a>” that aims at solving this issue, while Flink 1.12 plans to further expand its functionality. In this two-series blog post, we discuss how Flink’s checkpointing mechanism has been modified to support unaligned checkpoints, how unaligned checkpoints work, and how this  [...]
+
+<h1 id="state-in-streaming-applications">State in Streaming Applications</h1>
+
+<p>Simply put, state is the information that you need to remember across events. Even the most trivial streaming applications are typically stateful because of their need to “remember” the exact position they are processing data from, for example in the form of a Kafka Partition Offset or a File Offset.
+In addition, many applications hold state internally as a way to support their internal operations, such as windows, aggregations, joins, or state machines.</p>
+
+<p>For the remainder of this article, we’ll use the following example showing a streaming application consisting of <strong>four operators</strong>, each one holding some state.</p>
+
+<p><span>
+	<center>
+	<img vspace="8" style="width:75%" src="/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-1.png" />
+	</center>
+</span></p>
+
+<h2 id="state-persistence-through-checkpoints">State Persistence through Checkpoints</h2>
+
+<p>Streaming applications are long-lived. They inevitably experience hardware and software failures but should, ideally, look from the outside as if no failure ever happened. Since applications are long-lived — and can potentially accumulate very large state —, recomputing partial results after failures can take quite some time, and so a way to persist and recover this (potentially very large) application state is necessary.</p>
+
+<p>Flink relies on its <strong>state checkpointing and recovery mechanism</strong> to implement such behavior, as shown in the figure below. Periodic checkpoints store a snapshot of the application’s state on some Checkpoint Storage (commonly an Object Store or Distributed File System, like S3, HDFS, GCS, Azure Blob Storage, etc.). When a failure is detected, the affected parts of the application are reset to the state of the latest checkpoint (either by a local reset or by loading the s [...]
+
+<div style="line-height:40%;">
+    <br />
+</div>
+
+<center>
+	<img vspace="8" style="width:90%" src="/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-2.png" />
+</center>
+
+<div style="line-height:60%;">
+    <br />
+</div>
+
+<p>Flink’s checkpoint-based approach differs from the approach taken by other stream processing systems that keep state in a distributed database or write state changes to a log, for example. The checkpoint-based approach has some nice properties, described below, which make it a great option for Flink.</p>
+
+<ul>
+  <li>
+    <p><strong>Checkpointing has very simple external dependencies</strong>: An <em>Object Storage</em> or a <em>Distributed FileSystem</em> are probably the most available and easiest-to-administer services. Because these are available on all public cloud providers and among the first systems to provide on-premises, Flink becomes well-suited for a <em>cloud-native</em> stack. In addition, these storage systems are cheaper by an order of magnitude (GB/month) when compared to distributed  [...]
+  </li>
+  <li>
+    <p><strong>Checkpoints are immutable and versioned</strong>: Together with immutable and versioned inputs (as input streams are, by nature), checkpoints support storing immutable application snapshots that can be used for rollbacks, debugging, testing, or as a cheap alternative to analyze application state outside the production setup.</p>
+  </li>
+  <li>
+    <p><strong>Checkpoints decouple the “stream transport” from the persistence mechanism</strong>: “Stream transport” refers to how data is being exchanged between operators (e.g. during a shuffle). This decoupling is key to Flink’s batch &lt;-&gt; streaming unification in one system, because it allows Flink to implement a data transport that can take the shape of both a low-latency streaming exchange or a decoupled batch data exchange.</p>
+  </li>
+</ul>
+
+<h1 id="the-checkpointing-mechanism">The Checkpointing Mechanism</h1>
+
+<p>The fundamental challenge solved by the checkpointing algorithm (details in <a href="https://pdfs.semanticscholar.org/6fa0/917417d3c213b0e130ae01b7b440b1868dde.pdf">this paper</a>) is drawing a snapshot out of the ever-changing state of a streaming application without suspending the continuous processing of events. Because there are always events in-flight (on the network, in I/O buffers, etc.), up- and downstream operators can be processing events from different times: the sink may w [...]
+
+<p>To achieve that, Flink injects <em>checkpoint barriers</em> into the streams at the sources, which travel through the entire topology and eventually reach the sinks. These barriers divide the stream into a <em>pre-checkpoint epoch</em> (all events that are persisted in state or emitted into sinks) and a <em>post-checkpoint epoch</em> (events not reflected in the state, to be re-processed when resuming from the checkpoint).</p>
+
+<p>The following figure shows what happens when a barrier reaches an operator.</p>
+
+<p><span>
+	<center>
+	<img vspace="8" style="width:100%" src="/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-3.png" />
+	</center>
+</span></p>
+
+<p>Operators need to make sure that they take the checkpoint exactly when all pre-checkpoint events are processed and no post-checkpoint events have yet been processed. When the first barrier reaches the head of the input buffer queue and is consumed by the operator, the operator starts the so-called <em>alignment phase</em>. During that phase, the operator will not consume any data from the channels where it already received a barrier, until it has received a barrier from all input chan [...]
+
+<p>Once all barriers are received, the operator snapshots its state, forwards the barrier to the output, and ends the alignment phase, which unblocks all inputs. An operator state snapshot is written into the checkpoint storage, typically asynchronously while data processing continues. Once all operators have successfully written their state snapshot to the checkpoint storage, the checkpoint is successfully completed and can be used for recovery.</p>
+
+<p>One important thing to note here is that the barriers flow with the events, strictly in line. In a healthy setup without backpressure, barriers flow and align in milliseconds. The checkpoint duration is dominated by the time it takes to write the state snapshots to the checkpoint storage, which becomes faster with <a href="https://ci.apache.org/projects/flink/flink-docs-stable/ops/state/large_state_tuning.html#incremental-checkpoints">incremental checkpoints</a>. If the events flow sl [...]
+
+<h2 id="recovery">Recovery</h2>
+
+<p>When operators restart from a checkpoint (automatically during recovery or manually during deployment from a savepoint), the operators first restore their state from the checkpoint storage before resuming the event stream processing.</p>
+
+<p><span>
+	<center>
+	<img vspace="8" style="width:100%" src="/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-4.png" />
+	</center>
+</span></p>
+
+<p>Since sources are bound to the offsets persisted in the checkpoint, recovery time is often calculated as the sum of the time of the recovery process — outlined in the previous figure — and any additional time needed to process any remaining data up to the point right before the system failure. When an application experiences backpressure, recovery time can also include the total time from the very start of the recovery process until backpressure is fully eliminated.</p>
+
+<h2 id="consistency-guarantees">Consistency Guarantees</h2>
+
+<p>The alignment phase is only necessary for checkpoints with <strong>exactly-once</strong> processing semantics, which is the default setting in Flink. If an application runs with <strong>at-least-once</strong> processing semantics, checkpoints will not block any channels with barriers during alignment, which has an additional cost from the duplication of the then-not-blocked events when recovering the operator.</p>
+
+<p>This is not to be confused with having at-least-once semantics only in the sinks — something that many Flink users choose over transactional sinks — because many sink operations are idempotent or converge to the same result (like inputs/outputs to key/value stores). Having at-least-once semantics in an intermediate operator state is often not idempotent (for example a simple count aggregation) and hence using exactly-once checkpoints is advisable for the majority of Flink users.</p>
+
+<h1 id="conclusion">Conclusion</h1>
+
+<p>This blog post recaps how Flink’s fault tolerance mechanism (based on aligned checkpoints) works, and why checkpointing is a fitting mechanism for a fault-tolerant stream processor. The checkpointing mechanism has been optimized over time to make checkpoints faster and cheaper (with both asynchronous and incremental checkpoints) and faster-to-recover (local caching), but the basic concepts (barriers, alignment, operator state snapshots) are still the same as in the original version.</p>
+
+<p>The next part will dig into a major break with the original mechanism that avoids the alignment phase — the recently-introduced “unaligned checkpoints”. Stay tuned for the second part, which explains how unaligned checkpoints work and how they guarantee consistent checkpointing times under backpressure.</p>
+
+<hr />
+
+<h2 id="appendix-1---on-backpressure">Appendix 1 - On Backpressure</h2>
+
+<p>Backpressure refers to the behavior where a slow receiver (e.g. of data/requests) makes the senders slow down in order to not overwhelm the receiver, something that can result in possibly dropping some of the processed data or requests. This is a crucial and very much desirable behavior for systems where completeness/correctness is important. Backpressure is implicitly implemented in many of the most basic building blocks of distributed communication, such as TCP Flow Control, bounded [...]
+
+<p>Apache Flink implements backpressure across the entire data flow graph. A sink that (temporarily) cannot keep up with the data rate will result in the source connectors slowing down and pulling data out of the source systems more slowly. We believe that this is a good and desirable behavior, because backpressure is not only necessary in order to avoid overwhelming the memory of a receiver (thread), but can also prevent different stages of the streaming application from drifting apart  [...]
+
+<p>Consider the example below:
+- We have a source (let’s say reading data from Apache Kafka), parsing data, grouping and aggregating data by a key, and writing it to a sink system (some database).
+- The application needs to re-group data by key between the parsing and the grouping/aggregation step.</p>
+
+<p><span>
+	<center>
+	<img vspace="8" style="width:75%" src="/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-5.png" />
+	</center>
+</span></p>
+
+<p>Let’s assume we use a <strong>non-backpressure approach</strong>, like writing the data to a log/MQ for the data re-grouping over the network (the approach used by <a href="https://docs.confluent.io/current/streams/architecture.html#backpressure">Kafka Streams</a>). If the sink is now slower than the remaining parts of the streaming application (which can easily happen), the first stage (source and parse) will still work as fast as possible to pull data out of the source, parse it, an [...]
+
+<p><strong>With backpressure</strong>, the source/parse stage slows down to match the speed of the sink, keeping both parts of the application closer together in their progress through the data, and avoiding the need to provision a lot of intermediate storage capacity.</p>
+
+<hr />
+
+<p>We’d like to thank Marta Paes Moreira and Markos Sfikas for the wonderful review process.</p>
+
+      </article>
+    </div>
+
+    <div class="row">
+      <div id="disqus_thread"></div>
+      <script type="text/javascript">
+        /* * * CONFIGURATION VARIABLES: EDIT BEFORE PASTING INTO YOUR WEBPAGE * * */
+        var disqus_shortname = 'stratosphere-eu'; // required: replace example with your forum shortname
+
+        /* * * DON'T EDIT BELOW THIS LINE * * */
+        (function() {
+            var dsq = document.createElement('script'); dsq.type = 'text/javascript'; dsq.async = true;
+            dsq.src = '//' + disqus_shortname + '.disqus.com/embed.js';
+             (document.getElementsByTagName('head')[0] || document.getElementsByTagName('body')[0]).appendChild(dsq);
+        })();
+      </script>
+    </div>
+  </div>
+</div>
+      </div>
+    </div>
+
+    <hr />
+
+    <div class="row">
+      <div class="footer text-center col-sm-12">
+        <p>Copyright © 2014-2019 <a href="http://apache.org">The Apache Software Foundation</a>. All Rights Reserved.</p>
+        <p>Apache Flink, Flink®, Apache®, the squirrel logo, and the Apache feather logo are either registered trademarks or trademarks of The Apache Software Foundation.</p>
+        <p><a href="/privacy-policy.html">Privacy Policy</a> &middot; <a href="/blog/feed.xml">RSS feed</a></p>
+      </div>
+    </div>
+    </div><!-- /.container -->
+
+    <!-- Include all compiled plugins (below), or include individual files as needed -->
+    <script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.4/js/bootstrap.min.js"></script>
+    <script src="https://cdnjs.cloudflare.com/ajax/libs/jquery.matchHeight/0.7.0/jquery.matchHeight-min.js"></script>
+    <script src="/js/codetabs.js"></script>
+    <script src="/js/stickysidebar.js"></script>
+
+    <!-- Google Analytics -->
+    <script>
+      (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
+      (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),
+      m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
+      })(window,document,'script','//www.google-analytics.com/analytics.js','ga');
+
+      ga('create', 'UA-52545728-1', 'auto');
+      ga('send', 'pageview');
+    </script>
+  </body>
+</html>
diff --git a/content/blog/feed.xml b/content/blog/feed.xml
index 7667b62..65c275a 100644
--- a/content/blog/feed.xml
+++ b/content/blog/feed.xml
@@ -7,6 +7,134 @@
 <atom:link href="https://flink.apache.org/blog/feed.xml" rel="self" type="application/rss+xml" />
 
 <item>
+<title>From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</title>
+<description>&lt;p&gt;Apache Flink’s checkpoint-based fault tolerance mechanism is one of its defining features. Because of that design, Flink unifies batch and stream processing, can easily scale to both &lt;a href=&quot;https://hal.inria.fr/hal-02463206/document&quot;&gt;very small&lt;/a&gt; and &lt;a href=&quot;https://102.alibaba.com/detail?id=35&quot;&gt;extremely large&lt;/a&gt; scenarios and provides support for many operational features like stateful upgrades with &lt;a href=&quo [...]
+
+&lt;p&gt;Despite all these great properties, Flink’s checkpointing method has an Achilles Heel: the speed of a completed checkpoint is determined by the speed at which data flows through the application. When the application backpressures, the processing of checkpoints is backpressured as well (&lt;a href=&quot;#appendix-1---on-backpressure&quot;&gt;Appendix 1&lt;/a&gt; recaps what is backpressure and why it can be a good thing). In such cases, checkpoints may take longer to complete or  [...]
+
+&lt;p&gt;In Flink 1.11, the community introduced a first version of a new feature called “&lt;a href=&quot;https://ci.apache.org/projects/flink/flink-docs-stable/ops/state/checkpoints.html#unaligned-checkpoints&quot;&gt;unaligned checkpoints&lt;/a&gt;” that aims at solving this issue, while Flink 1.12 plans to further expand its functionality. In this two-series blog post, we discuss how Flink’s checkpointing mechanism has been modified to support unaligned checkpoints, how unaligned che [...]
+
+&lt;h1 id=&quot;state-in-streaming-applications&quot;&gt;State in Streaming Applications&lt;/h1&gt;
+
+&lt;p&gt;Simply put, state is the information that you need to remember across events. Even the most trivial streaming applications are typically stateful because of their need to “remember” the exact position they are processing data from, for example in the form of a Kafka Partition Offset or a File Offset.
+In addition, many applications hold state internally as a way to support their internal operations, such as windows, aggregations, joins, or state machines.&lt;/p&gt;
+
+&lt;p&gt;For the remainder of this article, we’ll use the following example showing a streaming application consisting of &lt;strong&gt;four operators&lt;/strong&gt;, each one holding some state.&lt;/p&gt;
+
+&lt;p&gt;&lt;span&gt;
+	&lt;center&gt;
+	&lt;img vspace=&quot;8&quot; style=&quot;width:75%&quot; src=&quot;/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-1.png&quot; /&gt;
+	&lt;/center&gt;
+&lt;/span&gt;&lt;/p&gt;
+
+&lt;h2 id=&quot;state-persistence-through-checkpoints&quot;&gt;State Persistence through Checkpoints&lt;/h2&gt;
+
+&lt;p&gt;Streaming applications are long-lived. They inevitably experience hardware and software failures but should, ideally, look from the outside as if no failure ever happened. Since applications are long-lived — and can potentially accumulate very large state —, recomputing partial results after failures can take quite some time, and so a way to persist and recover this (potentially very large) application state is necessary.&lt;/p&gt;
+
+&lt;p&gt;Flink relies on its &lt;strong&gt;state checkpointing and recovery mechanism&lt;/strong&gt; to implement such behavior, as shown in the figure below. Periodic checkpoints store a snapshot of the application’s state on some Checkpoint Storage (commonly an Object Store or Distributed File System, like S3, HDFS, GCS, Azure Blob Storage, etc.). When a failure is detected, the affected parts of the application are reset to the state of the latest checkpoint (either by a local reset o [...]
+
+&lt;div style=&quot;line-height:40%;&quot;&gt;
+    &lt;br /&gt;
+&lt;/div&gt;
+
+&lt;center&gt;
+	&lt;img vspace=&quot;8&quot; style=&quot;width:90%&quot; src=&quot;/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-2.png&quot; /&gt;
+&lt;/center&gt;
+
+&lt;div style=&quot;line-height:60%;&quot;&gt;
+    &lt;br /&gt;
+&lt;/div&gt;
+
+&lt;p&gt;Flink’s checkpoint-based approach differs from the approach taken by other stream processing systems that keep state in a distributed database or write state changes to a log, for example. The checkpoint-based approach has some nice properties, described below, which make it a great option for Flink.&lt;/p&gt;
+
+&lt;ul&gt;
+  &lt;li&gt;
+    &lt;p&gt;&lt;strong&gt;Checkpointing has very simple external dependencies&lt;/strong&gt;: An &lt;em&gt;Object Storage&lt;/em&gt; or a &lt;em&gt;Distributed FileSystem&lt;/em&gt; are probably the most available and easiest-to-administer services. Because these are available on all public cloud providers and among the first systems to provide on-premises, Flink becomes well-suited for a &lt;em&gt;cloud-native&lt;/em&gt; stack. In addition, these storage systems are cheaper by an order [...]
+  &lt;/li&gt;
+  &lt;li&gt;
+    &lt;p&gt;&lt;strong&gt;Checkpoints are immutable and versioned&lt;/strong&gt;: Together with immutable and versioned inputs (as input streams are, by nature), checkpoints support storing immutable application snapshots that can be used for rollbacks, debugging, testing, or as a cheap alternative to analyze application state outside the production setup.&lt;/p&gt;
+  &lt;/li&gt;
+  &lt;li&gt;
+    &lt;p&gt;&lt;strong&gt;Checkpoints decouple the “stream transport” from the persistence mechanism&lt;/strong&gt;: “Stream transport” refers to how data is being exchanged between operators (e.g. during a shuffle). This decoupling is key to Flink’s batch &amp;lt;-&amp;gt; streaming unification in one system, because it allows Flink to implement a data transport that can take the shape of both a low-latency streaming exchange or a decoupled batch data exchange.&lt;/p&gt;
+  &lt;/li&gt;
+&lt;/ul&gt;
+
+&lt;h1 id=&quot;the-checkpointing-mechanism&quot;&gt;The Checkpointing Mechanism&lt;/h1&gt;
+
+&lt;p&gt;The fundamental challenge solved by the checkpointing algorithm (details in &lt;a href=&quot;https://pdfs.semanticscholar.org/6fa0/917417d3c213b0e130ae01b7b440b1868dde.pdf&quot;&gt;this paper&lt;/a&gt;) is drawing a snapshot out of the ever-changing state of a streaming application without suspending the continuous processing of events. Because there are always events in-flight (on the network, in I/O buffers, etc.), up- and downstream operators can be processing events from dif [...]
+
+&lt;p&gt;To achieve that, Flink injects &lt;em&gt;checkpoint barriers&lt;/em&gt; into the streams at the sources, which travel through the entire topology and eventually reach the sinks. These barriers divide the stream into a &lt;em&gt;pre-checkpoint epoch&lt;/em&gt; (all events that are persisted in state or emitted into sinks) and a &lt;em&gt;post-checkpoint epoch&lt;/em&gt; (events not reflected in the state, to be re-processed when resuming from the checkpoint).&lt;/p&gt;
+
+&lt;p&gt;The following figure shows what happens when a barrier reaches an operator.&lt;/p&gt;
+
+&lt;p&gt;&lt;span&gt;
+	&lt;center&gt;
+	&lt;img vspace=&quot;8&quot; style=&quot;width:100%&quot; src=&quot;/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-3.png&quot; /&gt;
+	&lt;/center&gt;
+&lt;/span&gt;&lt;/p&gt;
+
+&lt;p&gt;Operators need to make sure that they take the checkpoint exactly when all pre-checkpoint events are processed and no post-checkpoint events have yet been processed. When the first barrier reaches the head of the input buffer queue and is consumed by the operator, the operator starts the so-called &lt;em&gt;alignment phase&lt;/em&gt;. During that phase, the operator will not consume any data from the channels where it already received a barrier, until it has received a barrier f [...]
+
+&lt;p&gt;Once all barriers are received, the operator snapshots its state, forwards the barrier to the output, and ends the alignment phase, which unblocks all inputs. An operator state snapshot is written into the checkpoint storage, typically asynchronously while data processing continues. Once all operators have successfully written their state snapshot to the checkpoint storage, the checkpoint is successfully completed and can be used for recovery.&lt;/p&gt;
+
+&lt;p&gt;One important thing to note here is that the barriers flow with the events, strictly in line. In a healthy setup without backpressure, barriers flow and align in milliseconds. The checkpoint duration is dominated by the time it takes to write the state snapshots to the checkpoint storage, which becomes faster with &lt;a href=&quot;https://ci.apache.org/projects/flink/flink-docs-stable/ops/state/large_state_tuning.html#incremental-checkpoints&quot;&gt;incremental checkpoints&lt;/ [...]
+
+&lt;h2 id=&quot;recovery&quot;&gt;Recovery&lt;/h2&gt;
+
+&lt;p&gt;When operators restart from a checkpoint (automatically during recovery or manually during deployment from a savepoint), the operators first restore their state from the checkpoint storage before resuming the event stream processing.&lt;/p&gt;
+
+&lt;p&gt;&lt;span&gt;
+	&lt;center&gt;
+	&lt;img vspace=&quot;8&quot; style=&quot;width:100%&quot; src=&quot;/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-4.png&quot; /&gt;
+	&lt;/center&gt;
+&lt;/span&gt;&lt;/p&gt;
+
+&lt;p&gt;Since sources are bound to the offsets persisted in the checkpoint, recovery time is often calculated as the sum of the time of the recovery process — outlined in the previous figure — and any additional time needed to process any remaining data up to the point right before the system failure. When an application experiences backpressure, recovery time can also include the total time from the very start of the recovery process until backpressure is fully eliminated.&lt;/p&gt;
+
+&lt;h2 id=&quot;consistency-guarantees&quot;&gt;Consistency Guarantees&lt;/h2&gt;
+
+&lt;p&gt;The alignment phase is only necessary for checkpoints with &lt;strong&gt;exactly-once&lt;/strong&gt; processing semantics, which is the default setting in Flink. If an application runs with &lt;strong&gt;at-least-once&lt;/strong&gt; processing semantics, checkpoints will not block any channels with barriers during alignment, which has an additional cost from the duplication of the then-not-blocked events when recovering the operator.&lt;/p&gt;
+
+&lt;p&gt;This is not to be confused with having at-least-once semantics only in the sinks — something that many Flink users choose over transactional sinks — because many sink operations are idempotent or converge to the same result (like inputs/outputs to key/value stores). Having at-least-once semantics in an intermediate operator state is often not idempotent (for example a simple count aggregation) and hence using exactly-once checkpoints is advisable for the majority of Flink users. [...]
+
+&lt;h1 id=&quot;conclusion&quot;&gt;Conclusion&lt;/h1&gt;
+
+&lt;p&gt;This blog post recaps how Flink’s fault tolerance mechanism (based on aligned checkpoints) works, and why checkpointing is a fitting mechanism for a fault-tolerant stream processor. The checkpointing mechanism has been optimized over time to make checkpoints faster and cheaper (with both asynchronous and incremental checkpoints) and faster-to-recover (local caching), but the basic concepts (barriers, alignment, operator state snapshots) are still the same as in the original vers [...]
+
+&lt;p&gt;The next part will dig into a major break with the original mechanism that avoids the alignment phase — the recently-introduced “unaligned checkpoints”. Stay tuned for the second part, which explains how unaligned checkpoints work and how they guarantee consistent checkpointing times under backpressure.&lt;/p&gt;
+
+&lt;hr /&gt;
+
+&lt;h2 id=&quot;appendix-1---on-backpressure&quot;&gt;Appendix 1 - On Backpressure&lt;/h2&gt;
+
+&lt;p&gt;Backpressure refers to the behavior where a slow receiver (e.g. of data/requests) makes the senders slow down in order to not overwhelm the receiver, something that can result in possibly dropping some of the processed data or requests. This is a crucial and very much desirable behavior for systems where completeness/correctness is important. Backpressure is implicitly implemented in many of the most basic building blocks of distributed communication, such as TCP Flow Control, b [...]
+
+&lt;p&gt;Apache Flink implements backpressure across the entire data flow graph. A sink that (temporarily) cannot keep up with the data rate will result in the source connectors slowing down and pulling data out of the source systems more slowly. We believe that this is a good and desirable behavior, because backpressure is not only necessary in order to avoid overwhelming the memory of a receiver (thread), but can also prevent different stages of the streaming application from drifting  [...]
+
+&lt;p&gt;Consider the example below:
+- We have a source (let’s say reading data from Apache Kafka), parsing data, grouping and aggregating data by a key, and writing it to a sink system (some database).
+- The application needs to re-group data by key between the parsing and the grouping/aggregation step.&lt;/p&gt;
+
+&lt;p&gt;&lt;span&gt;
+	&lt;center&gt;
+	&lt;img vspace=&quot;8&quot; style=&quot;width:75%&quot; src=&quot;/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-5.png&quot; /&gt;
+	&lt;/center&gt;
+&lt;/span&gt;&lt;/p&gt;
+
+&lt;p&gt;Let’s assume we use a &lt;strong&gt;non-backpressure approach&lt;/strong&gt;, like writing the data to a log/MQ for the data re-grouping over the network (the approach used by &lt;a href=&quot;https://docs.confluent.io/current/streams/architecture.html#backpressure&quot;&gt;Kafka Streams&lt;/a&gt;). If the sink is now slower than the remaining parts of the streaming application (which can easily happen), the first stage (source and parse) will still work as fast as possible to p [...]
+
+&lt;p&gt;&lt;strong&gt;With backpressure&lt;/strong&gt;, the source/parse stage slows down to match the speed of the sink, keeping both parts of the application closer together in their progress through the data, and avoiding the need to provision a lot of intermediate storage capacity.&lt;/p&gt;
+
+&lt;hr /&gt;
+
+&lt;p&gt;We’d like to thank Marta Paes Moreira and Markos Sfikas for the wonderful review process.&lt;/p&gt;
+</description>
+<pubDate>Thu, 15 Oct 2020 05:00:00 +0200</pubDate>
+<link>https://flink.apache.org/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html</link>
+<guid isPermaLink="true">/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html</guid>
+</item>
+
+<item>
 <title>Stateful Functions Internals: Behind the scenes of Stateful Serverless</title>
 <description>&lt;p&gt;Stateful Functions (StateFun) simplifies the building of distributed stateful applications by combining the best of two worlds:
 the strong messaging and state consistency guarantees of stateful stream processing, and the elasticity and serverless experience of today’s cloud-native architectures and
@@ -17866,227 +17994,5 @@ enable the joining of a main, high-throughput stream with one more more inputs w
 <guid isPermaLink="true">/news/2016/08/11/release-1.1.1.html</guid>
 </item>
 
-<item>
-<title>Announcing Apache Flink 1.1.0</title>
-<description>&lt;div class=&quot;alert alert-success&quot;&gt;&lt;strong&gt;Important&lt;/strong&gt;: The Maven artifacts published with version 1.1.0 on Maven central have a Hadoop dependency issue. It is highly recommended to use &lt;strong&gt;1.1.1&lt;/strong&gt; or &lt;strong&gt;1.1.1-hadoop1&lt;/strong&gt; as the Flink version.&lt;/div&gt;
-
-&lt;p&gt;The Apache Flink community is pleased to announce the availability of Flink 1.1.0.&lt;/p&gt;
-
-&lt;p&gt;This release is the first major release in the 1.X.X series of releases, which maintains API compatibility with 1.0.0. This means that your applications written against stable APIs of Flink 1.0.0 will compile and run with Flink 1.1.0. 95 contributors provided bug fixes, improvements, and new features such that in total more than 450 JIRA issues could be resolved. See the &lt;a href=&quot;/blog/release_1.1.0-changelog.html&quot;&gt;complete changelog&lt;/a&gt; for more details.&l [...]
-
-&lt;p&gt;&lt;strong&gt;We encourage everyone to &lt;a href=&quot;http://flink.apache.org/downloads.html&quot;&gt;download the release&lt;/a&gt; and &lt;a href=&quot;https://ci.apache.org/projects/flink/flink-docs-release-1.1/&quot;&gt;check out the documentation&lt;/a&gt;. Feedback through the Flink &lt;a href=&quot;http://flink.apache.org/community.html#mailing-lists&quot;&gt;mailing lists&lt;/a&gt; is, as always, very welcome!&lt;/strong&gt;&lt;/p&gt;
-
-&lt;p&gt;Some highlights of the release are listed in the following sections.&lt;/p&gt;
-
-&lt;h2 id=&quot;connectors&quot;&gt;Connectors&lt;/h2&gt;
-
-&lt;p&gt;The &lt;a href=&quot;https://ci.apache.org/projects/flink/flink-docs-release-1.1/apis/streaming/connectors/index.html&quot;&gt;streaming connectors&lt;/a&gt; are a major part of Flink’s DataStream API. This release adds support for new external systems and further improves on the available connectors.&lt;/p&gt;
-
-&lt;h3 id=&quot;continuous-file-system-sources&quot;&gt;Continuous File System Sources&lt;/h3&gt;
-
-&lt;p&gt;A frequently requested feature for Flink 1.0 was to be able to monitor directories and process files continuously. Flink 1.1 now adds support for this via &lt;code&gt;FileProcessingMode&lt;/code&gt;s:&lt;/p&gt;
-
-&lt;div class=&quot;highlight&quot;&gt;&lt;pre&gt;&lt;code class=&quot;language-java&quot;&gt;&lt;span class=&quot;n&quot;&gt;DataStream&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;&amp;lt;&lt;/span&gt;&lt;span class=&quot;n&quot;&gt;String&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;&amp;gt;&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;stream&lt;/span&gt; &lt;span class=&quot;o&quot;&gt;=&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;env&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;.&lt;/ [...]
-  &lt;span class=&quot;n&quot;&gt;textInputFormat&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;,&lt;/span&gt;
-  &lt;span class=&quot;s&quot;&gt;&amp;quot;hdfs:///file-path&amp;quot;&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;,&lt;/span&gt;
-  &lt;span class=&quot;n&quot;&gt;FileProcessingMode&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;.&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;PROCESS_CONTINUOUSLY&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;,&lt;/span&gt;
-  &lt;span class=&quot;mi&quot;&gt;5000&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;,&lt;/span&gt; &lt;span class=&quot;c1&quot;&gt;// monitoring interval (millis)&lt;/span&gt;
-  &lt;span class=&quot;n&quot;&gt;FilePathFilter&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;.&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;createDefaultFilter&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;());&lt;/span&gt; &lt;span class=&quot;c1&quot;&gt;// file path filter&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;
-
-&lt;p&gt;This will monitor &lt;code&gt;hdfs:///file-path&lt;/code&gt; every &lt;code&gt;5000&lt;/code&gt; milliseconds. Check out the &lt;a href=&quot;https://ci.apache.org/projects/flink/flink-docs-release-1.1/apis/streaming/index.html#data-sources&quot;&gt;DataSource documentation for more details&lt;/a&gt;.&lt;/p&gt;
-
-&lt;h3 id=&quot;kinesis-source-and-sink&quot;&gt;Kinesis Source and Sink&lt;/h3&gt;
-
-&lt;p&gt;Flink 1.1 adds a Kinesis connector for both consuming (&lt;code&gt;FlinkKinesisConsumer&lt;/code&gt;) from and producing (&lt;code&gt;FlinkKinesisProduer&lt;/code&gt;) to &lt;a href=&quot;https://aws.amazon.com/kinesis/&quot;&gt;Amazon Kinesis Streams&lt;/a&gt;, which is a managed service purpose-built to make it easy to work with streaming data on AWS.&lt;/p&gt;
-
-&lt;div class=&quot;highlight&quot;&gt;&lt;pre&gt;&lt;code class=&quot;language-java&quot;&gt;&lt;span class=&quot;n&quot;&gt;DataStream&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;&amp;lt;&lt;/span&gt;&lt;span class=&quot;n&quot;&gt;String&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;&amp;gt;&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;kinesis&lt;/span&gt; &lt;span class=&quot;o&quot;&gt;=&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;env&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;.&lt; [...]
-  &lt;span class=&quot;k&quot;&gt;new&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;FlinkKinesisConsumer&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;&amp;lt;&amp;gt;(&lt;/span&gt;&lt;span class=&quot;s&quot;&gt;&amp;quot;stream-name&amp;quot;&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;,&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;schema&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;,&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;config&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;));&lt;/sp [...]
-
-&lt;p&gt;Check out the &lt;a href=&quot;https://ci.apache.org/projects/flink/flink-docs-release-1.1/apis/streaming/connectors/kinesis.html&quot;&gt;Kinesis connector documentation for more details&lt;/a&gt;.&lt;/p&gt;
-
-&lt;h3 id=&quot;cassandra-sink&quot;&gt;Cassandra Sink&lt;/h3&gt;
-
-&lt;p&gt;The &lt;a href=&quot;http://wiki.apache.org/cassandra/GettingStarted&quot;&gt;Apache Cassandra&lt;/a&gt; sink allows you to write from Flink to Cassandra. Flink can provide exactly-once guarantees if the query is idempotent, meaning it can be applied multiple times without changing the result.&lt;/p&gt;
-
-&lt;div class=&quot;highlight&quot;&gt;&lt;pre&gt;&lt;code class=&quot;language-java&quot;&gt;&lt;span class=&quot;n&quot;&gt;CassandraSink&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;.&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;addSink&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;(&lt;/span&gt;&lt;span class=&quot;n&quot;&gt;input&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;)&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;
-
-&lt;p&gt;Check out the &lt;a href=&quot;https://ci.apache.org/projects/flink/flink-docs-release-1.1/apis/streaming/connectors/cassandra.html&quot;&gt;Cassandra Sink documentation for more details&lt;/a&gt;.&lt;/p&gt;
-
-&lt;h2 id=&quot;table-api-and-sql&quot;&gt;Table API and SQL&lt;/h2&gt;
-
-&lt;p&gt;The Table API is a SQL-like expression language for relational stream and batch processing that can be easily embedded in Flink’s DataSet and DataStream APIs (for both Java and Scala).&lt;/p&gt;
-
-&lt;div class=&quot;highlight&quot;&gt;&lt;pre&gt;&lt;code class=&quot;language-java&quot;&gt;&lt;span class=&quot;n&quot;&gt;Table&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;custT&lt;/span&gt; &lt;span class=&quot;o&quot;&gt;=&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;tableEnv&lt;/span&gt;
-  &lt;span class=&quot;o&quot;&gt;.&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;toTable&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;(&lt;/span&gt;&lt;span class=&quot;n&quot;&gt;custDs&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;,&lt;/span&gt; &lt;span class=&quot;s&quot;&gt;&amp;quot;name, zipcode&amp;quot;&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;)&lt;/span&gt;
-  &lt;span class=&quot;o&quot;&gt;.&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;where&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;(&lt;/span&gt;&lt;span class=&quot;s&quot;&gt;&amp;quot;zipcode = &amp;#39;12345&amp;#39;&amp;quot;&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;)&lt;/span&gt;
-  &lt;span class=&quot;o&quot;&gt;.&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;select&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;(&lt;/span&gt;&lt;span class=&quot;s&quot;&gt;&amp;quot;name&amp;quot;&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;)&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;
-
-&lt;p&gt;An initial version of this API was already available in Flink 1.0. For Flink 1.1, the community put a lot of work into reworking the architecture of the Table API and integrating it with &lt;a href=&quot;https://calcite.apache.org&quot;&gt;Apache Calcite&lt;/a&gt;.&lt;/p&gt;
-
-&lt;p&gt;In this first version, SQL (and Table API) queries on streams are limited to selection, filter, and union operators. Compared to Flink 1.0, the revised Table API supports many more scalar functions and is able to read tables from external sources and write them back to external sinks.&lt;/p&gt;
-
-&lt;div class=&quot;highlight&quot;&gt;&lt;pre&gt;&lt;code class=&quot;language-java&quot;&gt;&lt;span class=&quot;n&quot;&gt;Table&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;result&lt;/span&gt; &lt;span class=&quot;o&quot;&gt;=&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;tableEnv&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;.&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;sql&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;(&lt;/span&gt;
-  &lt;span class=&quot;s&quot;&gt;&amp;quot;SELECT STREAM product, amount FROM Orders WHERE product LIKE &amp;#39;%Rubber%&amp;#39;&amp;quot;&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;);&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;
-&lt;p&gt;A more detailed introduction can be found in the &lt;a href=&quot;http://flink.apache.org/news/2016/05/24/stream-sql.html&quot;&gt;Flink blog&lt;/a&gt; and the &lt;a href=&quot;https://ci.apache.org/projects/flink/flink-docs-release-1.1/apis/table.html&quot;&gt;Table API documentation&lt;/a&gt;.&lt;/p&gt;
-
-&lt;h2 id=&quot;datastream-api&quot;&gt;DataStream API&lt;/h2&gt;
-
-&lt;p&gt;The DataStream API now exposes &lt;strong&gt;session windows&lt;/strong&gt; and &lt;strong&gt;allowed lateness&lt;/strong&gt; as first-class citizens.&lt;/p&gt;
-
-&lt;h3 id=&quot;session-windows&quot;&gt;Session Windows&lt;/h3&gt;
-
-&lt;p&gt;Session windows are ideal for cases where the window boundaries need to adjust to the incoming data. This enables you to have windows that start at individual points in time for each key and that end once there has been a &lt;em&gt;certain period of inactivity&lt;/em&gt;. The configuration parameter is the session gap that specifies how long to wait for new data before considering a session as closed.&lt;/p&gt;
-
-&lt;center&gt;
-&lt;img src=&quot;/img/blog/session-windows.svg&quot; style=&quot;height:400px&quot; /&gt;
-&lt;/center&gt;
-
-&lt;div class=&quot;highlight&quot;&gt;&lt;pre&gt;&lt;code class=&quot;language-java&quot;&gt;&lt;span class=&quot;n&quot;&gt;input&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;.&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;keyBy&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;(&amp;lt;&lt;/span&gt;&lt;span class=&quot;n&quot;&gt;key&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;selector&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;&amp;gt;)&lt;/span&gt;
-    &lt;span class=&quot;o&quot;&gt;.&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;window&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;(&lt;/span&gt;&lt;span class=&quot;n&quot;&gt;EventTimeSessionWindows&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;.&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;withGap&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;(&lt;/span&gt;&lt;span class=&quot;n&quot;&gt;Time&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;.&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;min [...]
-    &lt;span class=&quot;o&quot;&gt;.&amp;lt;&lt;/span&gt;&lt;span class=&quot;n&quot;&gt;windowed&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;transformation&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;&amp;gt;(&amp;lt;&lt;/span&gt;&lt;span class=&quot;n&quot;&gt;window&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;function&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;&amp;gt;);&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;
-
-&lt;h3 id=&quot;support-for-late-elements&quot;&gt;Support for Late Elements&lt;/h3&gt;
-
-&lt;p&gt;You can now specify how a windowed transformation should deal with late elements and how much lateness is allowed. The parameter for this is called &lt;em&gt;allowed lateness&lt;/em&gt;. This specifies by how much time elements can be late.&lt;/p&gt;
-
-&lt;div class=&quot;highlight&quot;&gt;&lt;pre&gt;&lt;code class=&quot;language-java&quot;&gt;&lt;span class=&quot;n&quot;&gt;input&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;.&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;keyBy&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;(&amp;lt;&lt;/span&gt;&lt;span class=&quot;n&quot;&gt;key&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;selector&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;&amp;gt;).&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;window& [...]
-    &lt;span class=&quot;o&quot;&gt;.&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;allowedLateness&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;(&amp;lt;&lt;/span&gt;&lt;span class=&quot;n&quot;&gt;time&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;&amp;gt;)&lt;/span&gt;
-    &lt;span class=&quot;o&quot;&gt;.&amp;lt;&lt;/span&gt;&lt;span class=&quot;n&quot;&gt;windowed&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;transformation&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;&amp;gt;(&amp;lt;&lt;/span&gt;&lt;span class=&quot;n&quot;&gt;window&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;function&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;&amp;gt;);&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;
-
-&lt;p&gt;Elements that arrive within the allowed lateness are still put into windows and are considered when computing window results. If elements arrive after the allowed lateness they will be dropped. Flink will also make sure that any state held by the windowing operation is garbage collected once the watermark passes the end of a window plus the allowed lateness.&lt;/p&gt;
-
-&lt;p&gt;Check out the &lt;a href=&quot;https://ci.apache.org/projects/flink/flink-docs-release-1.1/apis/streaming/windows.html&quot;&gt;Windows documentation for more details&lt;/a&gt;.&lt;/p&gt;
-
-&lt;h2 id=&quot;scala-api-for-complex-event-processing-cep&quot;&gt;Scala API for Complex Event Processing (CEP)&lt;/h2&gt;
-
-&lt;p&gt;Flink 1.0 added the initial version of the CEP library. The core of the library is a Pattern API, which allows you to easily specify patterns to match against in your event stream. While in Flink 1.0 this API was only available for Java, Flink 1.1. now exposes the same API for Scala, allowing you to specify your event patterns in a more concise manner.&lt;/p&gt;
-
-&lt;p&gt;A more detailed introduction can be found in the &lt;a href=&quot;http://flink.apache.org/news/2016/04/06/cep-monitoring.html&quot;&gt;Flink blog&lt;/a&gt; and the &lt;a href=&quot;https://ci.apache.org/projects/flink/flink-docs-release-1.1/apis/streaming/libs/cep.html&quot;&gt;CEP documentation&lt;/a&gt;.&lt;/p&gt;
-
-&lt;h2 id=&quot;graph-generators-and-new-gelly-library-algorithms&quot;&gt;Graph generators and new Gelly library algorithms&lt;/h2&gt;
-
-&lt;p&gt;This release includes many enhancements and new features for graph processing. Gelly now provides a collection of scalable graph generators for common graph types, such as complete, cycle, grid, hypercube, and RMat graphs. A variety of new graph algorithms have been added to the Gelly library, including Global and Local Clustering Coefficient, HITS, and similarity measures (Jaccard and Adamic-Adar).&lt;/p&gt;
-
-&lt;p&gt;For a full list of new graph processing features, check out the &lt;a href=&quot;https://ci.apache.org/projects/flink/flink-docs-release-1.1/apis/batch/libs/gelly.html&quot;&gt;Gelly documentation&lt;/a&gt;.&lt;/p&gt;
-
-&lt;h2 id=&quot;metrics&quot;&gt;Metrics&lt;/h2&gt;
-
-&lt;p&gt;Flink’s new metrics system allows you to easily gather and expose metrics from your user application to external systems. You can add counters, gauges, and histograms to your application via the runtime context:&lt;/p&gt;
-
-&lt;div class=&quot;highlight&quot;&gt;&lt;pre&gt;&lt;code class=&quot;language-java&quot;&gt;&lt;span class=&quot;n&quot;&gt;Counter&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;counter&lt;/span&gt; &lt;span class=&quot;o&quot;&gt;=&lt;/span&gt; &lt;span class=&quot;n&quot;&gt;getRuntimeContext&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;()&lt;/span&gt;
-  &lt;span class=&quot;o&quot;&gt;.&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;getMetricGroup&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;()&lt;/span&gt;
-  &lt;span class=&quot;o&quot;&gt;.&lt;/span&gt;&lt;span class=&quot;na&quot;&gt;counter&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;(&lt;/span&gt;&lt;span class=&quot;s&quot;&gt;&amp;quot;my-counter&amp;quot;&lt;/span&gt;&lt;span class=&quot;o&quot;&gt;);&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;
-
-&lt;p&gt;All registered metrics will be exposed via reporters. Out of the box, Flinks comes with support for JMX, Ganglia, Graphite, and statsD. In addition to your custom metrics, Flink exposes many internal metrics like checkpoint sizes and JVM stats.&lt;/p&gt;
-
-&lt;p&gt;Check out the &lt;a href=&quot;https://ci.apache.org/projects/flink/flink-docs-release-1.1/apis/metrics.html&quot;&gt;Metrics documentation for more details&lt;/a&gt;.&lt;/p&gt;
-
-&lt;h2 id=&quot;list-of-contributors&quot;&gt;List of Contributors&lt;/h2&gt;
-
-&lt;p&gt;The following 95 people contributed to this release:&lt;/p&gt;
-
-&lt;ul&gt;
-  &lt;li&gt;Abdullah Ozturk&lt;/li&gt;
-  &lt;li&gt;Ajay Bhat&lt;/li&gt;
-  &lt;li&gt;Alexey Savartsov&lt;/li&gt;
-  &lt;li&gt;Aljoscha Krettek&lt;/li&gt;
-  &lt;li&gt;Andrea Sella&lt;/li&gt;
-  &lt;li&gt;Andrew Palumbo&lt;/li&gt;
-  &lt;li&gt;Chenguang He&lt;/li&gt;
-  &lt;li&gt;Chiwan Park&lt;/li&gt;
-  &lt;li&gt;David Moravek&lt;/li&gt;
-  &lt;li&gt;Dominik Bruhn&lt;/li&gt;
-  &lt;li&gt;Dyana Rose&lt;/li&gt;
-  &lt;li&gt;Fabian Hueske&lt;/li&gt;
-  &lt;li&gt;Flavio Pompermaier&lt;/li&gt;
-  &lt;li&gt;Gabor Gevay&lt;/li&gt;
-  &lt;li&gt;Gabor Horvath&lt;/li&gt;
-  &lt;li&gt;Geoffrey Mon&lt;/li&gt;
-  &lt;li&gt;Gordon Tai&lt;/li&gt;
-  &lt;li&gt;Greg Hogan&lt;/li&gt;
-  &lt;li&gt;Gyula Fora&lt;/li&gt;
-  &lt;li&gt;Henry Saputra&lt;/li&gt;
-  &lt;li&gt;Ignacio N. Lucero Ascencio&lt;/li&gt;
-  &lt;li&gt;Igor Berman&lt;/li&gt;
-  &lt;li&gt;Ismaël Mejía&lt;/li&gt;
-  &lt;li&gt;Ivan Mushketyk&lt;/li&gt;
-  &lt;li&gt;Jark Wu&lt;/li&gt;
-  &lt;li&gt;Jiri Simsa&lt;/li&gt;
-  &lt;li&gt;Jonas Traub&lt;/li&gt;
-  &lt;li&gt;Josh&lt;/li&gt;
-  &lt;li&gt;Joshi&lt;/li&gt;
-  &lt;li&gt;Joshua Herman&lt;/li&gt;
-  &lt;li&gt;Ken Krugler&lt;/li&gt;
-  &lt;li&gt;Konstantin Knauf&lt;/li&gt;
-  &lt;li&gt;Lasse Dalegaard&lt;/li&gt;
-  &lt;li&gt;Li Fanxi&lt;/li&gt;
-  &lt;li&gt;MaBiao&lt;/li&gt;
-  &lt;li&gt;Mao Wei&lt;/li&gt;
-  &lt;li&gt;Mark Reddy&lt;/li&gt;
-  &lt;li&gt;Martin Junghanns&lt;/li&gt;
-  &lt;li&gt;Martin Liesenberg&lt;/li&gt;
-  &lt;li&gt;Maximilian Michels&lt;/li&gt;
-  &lt;li&gt;Michal Fijolek&lt;/li&gt;
-  &lt;li&gt;Márton Balassi&lt;/li&gt;
-  &lt;li&gt;Nathan Howell&lt;/li&gt;
-  &lt;li&gt;Niels Basjes&lt;/li&gt;
-  &lt;li&gt;Niels Zeilemaker&lt;/li&gt;
-  &lt;li&gt;Phetsarath, Sourigna&lt;/li&gt;
-  &lt;li&gt;Robert Metzger&lt;/li&gt;
-  &lt;li&gt;Scott Kidder&lt;/li&gt;
-  &lt;li&gt;Sebastian Klemke&lt;/li&gt;
-  &lt;li&gt;Shahin&lt;/li&gt;
-  &lt;li&gt;Shannon Carey&lt;/li&gt;
-  &lt;li&gt;Shannon Quinn&lt;/li&gt;
-  &lt;li&gt;Stefan Richter&lt;/li&gt;
-  &lt;li&gt;Stefano Baghino&lt;/li&gt;
-  &lt;li&gt;Stefano Bortoli&lt;/li&gt;
-  &lt;li&gt;Stephan Ewen&lt;/li&gt;
-  &lt;li&gt;Steve Cosenza&lt;/li&gt;
-  &lt;li&gt;Sumit Chawla&lt;/li&gt;
-  &lt;li&gt;Tatu Saloranta&lt;/li&gt;
-  &lt;li&gt;Tianji Li&lt;/li&gt;
-  &lt;li&gt;Till Rohrmann&lt;/li&gt;
-  &lt;li&gt;Todd Lisonbee&lt;/li&gt;
-  &lt;li&gt;Tony Baines&lt;/li&gt;
-  &lt;li&gt;Trevor Grant&lt;/li&gt;
-  &lt;li&gt;Ufuk Celebi&lt;/li&gt;
-  &lt;li&gt;Vasudevan&lt;/li&gt;
-  &lt;li&gt;Yijie Shen&lt;/li&gt;
-  &lt;li&gt;Zack Pierce&lt;/li&gt;
-  &lt;li&gt;Zhai Jia&lt;/li&gt;
-  &lt;li&gt;chengxiang li&lt;/li&gt;
-  &lt;li&gt;chobeat&lt;/li&gt;
-  &lt;li&gt;danielblazevski&lt;/li&gt;
-  &lt;li&gt;dawid&lt;/li&gt;
-  &lt;li&gt;dawidwys&lt;/li&gt;
-  &lt;li&gt;eastcirclek&lt;/li&gt;
-  &lt;li&gt;erli ding&lt;/li&gt;
-  &lt;li&gt;gallenvara&lt;/li&gt;
-  &lt;li&gt;kl0u&lt;/li&gt;
-  &lt;li&gt;mans2singh&lt;/li&gt;
-  &lt;li&gt;markreddy&lt;/li&gt;
-  &lt;li&gt;mjsax&lt;/li&gt;
-  &lt;li&gt;nikste&lt;/li&gt;
-  &lt;li&gt;omaralvarez&lt;/li&gt;
-  &lt;li&gt;philippgrulich&lt;/li&gt;
-  &lt;li&gt;ramkrishna&lt;/li&gt;
-  &lt;li&gt;sahitya-pavurala&lt;/li&gt;
-  &lt;li&gt;samaitra&lt;/li&gt;
-  &lt;li&gt;smarthi&lt;/li&gt;
-  &lt;li&gt;spkavuly&lt;/li&gt;
-  &lt;li&gt;subhankar&lt;/li&gt;
-  &lt;li&gt;twalthr&lt;/li&gt;
-  &lt;li&gt;vasia&lt;/li&gt;
-  &lt;li&gt;xueyan.li&lt;/li&gt;
-  &lt;li&gt;zentol&lt;/li&gt;
-  &lt;li&gt;卫乐&lt;/li&gt;
-&lt;/ul&gt;
-</description>
-<pubDate>Mon, 08 Aug 2016 15:00:00 +0200</pubDate>
-<link>https://flink.apache.org/news/2016/08/08/release-1.1.0.html</link>
-<guid isPermaLink="true">/news/2016/08/08/release-1.1.0.html</guid>
-</item>
-
 </channel>
 </rss>
diff --git a/content/blog/index.html b/content/blog/index.html
index a10e198..a6c5829 100644
--- a/content/blog/index.html
+++ b/content/blog/index.html
@@ -196,6 +196,19 @@
     <!-- Blog posts -->
     
     <article>
+      <h2 class="blog-title"><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></h2>
+
+      <p>15 Oct 2020
+       Arvid Heise  &amp; Stephan Ewen </p>
+
+      <p>Apache Flink’s checkpoint-based fault tolerance mechanism is one of its defining features. Because of that design, Flink unifies batch and stream processing, can easily scale to both very small and extremely large scenarios and provides support for many operational features. In this post we recap the original checkpointing process in Flink, its core properties and issues under backpressure.</p>
+
+      <p><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">Continue reading &raquo;</a></p>
+    </article>
+
+    <hr>
+    
+    <article>
       <h2 class="blog-title"><a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></h2>
 
       <p>13 Oct 2020
@@ -324,19 +337,6 @@ as well as increased observability for operational purposes.</p>
 
     <hr>
     
-    <article>
-      <h2 class="blog-title"><a href="/2020/08/04/pyflink-pandas-udf-support-flink.html">PyFlink: The integration of Pandas into PyFlink</a></h2>
-
-      <p>04 Aug 2020
-       Jincheng Sun (<a href="https://twitter.com/sunjincheng121">@sunjincheng121</a>) &amp; Markos Sfikas (<a href="https://twitter.com/MarkSfik">@MarkSfik</a>)</p>
-
-      <p>The Apache Flink community put some great effort into integrating Pandas with PyFlink in the latest Flink version 1.11. Some of the added features include support for Pandas UDF and the conversion between Pandas DataFrame and Table. In this article, we will introduce how these functionalities work and how to use them with a step-by-step example.</p>
-
-      <p><a href="/2020/08/04/pyflink-pandas-udf-support-flink.html">Continue reading &raquo;</a></p>
-    </article>
-
-    <hr>
-    
 
     <!-- Pagination links -->
     
@@ -369,6 +369,16 @@ as well as increased observability for operational purposes.</p>
 
     <ul id="markdown-toc">
       
+      <li><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></li>
+
+      
+        
+      
+    
+      
+      
+
+      
       <li><a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></li>
 
       
diff --git a/content/blog/page10/index.html b/content/blog/page10/index.html
index f18e369..7f926e3 100644
--- a/content/blog/page10/index.html
+++ b/content/blog/page10/index.html
@@ -196,6 +196,20 @@
     <!-- Blog posts -->
     
     <article>
+      <h2 class="blog-title"><a href="/news/2017/04/04/dynamic-tables.html">Continuous Queries on Dynamic Tables</a></h2>
+
+      <p>04 Apr 2017 by Fabian Hueske, Shaoxuan Wang, and Xiaowei Jiang
+      </p>
+
+      <p><p>Flink's relational APIs, the Table API and SQL, are unified APIs for stream and batch processing, meaning that a query produces the same result when being evaluated on streaming or static data.</p>
+<p>In this blog post we discuss the future of these APIs and introduce the concept of Dynamic Tables. Dynamic tables will significantly expand the scope of the Table API and SQL on streams and enable many more advanced use cases. We discuss how streams and dynamic tables relate to each other and explain the semantics of continuously evaluating queries on dynamic tables.</p></p>
+
+      <p><a href="/news/2017/04/04/dynamic-tables.html">Continue reading &raquo;</a></p>
+    </article>
+
+    <hr>
+    
+    <article>
       <h2 class="blog-title"><a href="/news/2017/03/29/table-sql-api-update.html">From Streams to Tables and Back Again: An Update on Flink's Table & SQL API</a></h2>
 
       <p>29 Mar 2017 by Timo Walther (<a href="https://twitter.com/">@twalthr</a>)
@@ -324,21 +338,6 @@
 
     <hr>
     
-    <article>
-      <h2 class="blog-title"><a href="/news/2016/08/08/release-1.1.0.html">Announcing Apache Flink 1.1.0</a></h2>
-
-      <p>08 Aug 2016
-      </p>
-
-      <p><div class="alert alert-success"><strong>Important</strong>: The Maven artifacts published with version 1.1.0 on Maven central have a Hadoop dependency issue. It is highly recommended to use <strong>1.1.1</strong> or <strong>1.1.1-hadoop1</strong> as the Flink version.</div>
-
-</p>
-
-      <p><a href="/news/2016/08/08/release-1.1.0.html">Continue reading &raquo;</a></p>
-    </article>
-
-    <hr>
-    
 
     <!-- Pagination links -->
     
@@ -371,6 +370,16 @@
 
     <ul id="markdown-toc">
       
+      <li><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></li>
+
+      
+        
+      
+    
+      
+      
+
+      
       <li><a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></li>
 
       
diff --git a/content/blog/page11/index.html b/content/blog/page11/index.html
index 1481598..b0db714 100644
--- a/content/blog/page11/index.html
+++ b/content/blog/page11/index.html
@@ -196,6 +196,21 @@
     <!-- Blog posts -->
     
     <article>
+      <h2 class="blog-title"><a href="/news/2016/08/08/release-1.1.0.html">Announcing Apache Flink 1.1.0</a></h2>
+
+      <p>08 Aug 2016
+      </p>
+
+      <p><div class="alert alert-success"><strong>Important</strong>: The Maven artifacts published with version 1.1.0 on Maven central have a Hadoop dependency issue. It is highly recommended to use <strong>1.1.1</strong> or <strong>1.1.1-hadoop1</strong> as the Flink version.</div>
+
+</p>
+
+      <p><a href="/news/2016/08/08/release-1.1.0.html">Continue reading &raquo;</a></p>
+    </article>
+
+    <hr>
+    
+    <article>
       <h2 class="blog-title"><a href="/news/2016/05/24/stream-sql.html">Stream Processing for Everyone with SQL and Apache Flink</a></h2>
 
       <p>24 May 2016 by Fabian Hueske (<a href="https://twitter.com/">@fhueske</a>)
@@ -325,19 +340,6 @@
 
     <hr>
     
-    <article>
-      <h2 class="blog-title"><a href="/news/2015/12/11/storm-compatibility.html">Storm Compatibility in Apache Flink: How to run existing Storm topologies on Flink</a></h2>
-
-      <p>11 Dec 2015 by Matthias J. Sax (<a href="https://twitter.com/">@MatthiasJSax</a>)
-      </p>
-
-      <p>In this blog post, we describe Flink's compatibility package for <a href="https://storm.apache.org">Apache Storm</a> that allows to embed Spouts (sources) and Bolts (operators) in a regular Flink streaming job. Furthermore, the compatibility package provides a Storm compatible API in order to execute whole Storm topologies with (almost) no code adaption.</p>
-
-      <p><a href="/news/2015/12/11/storm-compatibility.html">Continue reading &raquo;</a></p>
-    </article>
-
-    <hr>
-    
 
     <!-- Pagination links -->
     
@@ -370,6 +372,16 @@
 
     <ul id="markdown-toc">
       
+      <li><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></li>
+
+      
+        
+      
+    
+      
+      
+
+      
       <li><a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></li>
 
       
diff --git a/content/blog/page12/index.html b/content/blog/page12/index.html
index cd7fcd3..dfd3f30 100644
--- a/content/blog/page12/index.html
+++ b/content/blog/page12/index.html
@@ -196,6 +196,19 @@
     <!-- Blog posts -->
     
     <article>
+      <h2 class="blog-title"><a href="/news/2015/12/11/storm-compatibility.html">Storm Compatibility in Apache Flink: How to run existing Storm topologies on Flink</a></h2>
+
+      <p>11 Dec 2015 by Matthias J. Sax (<a href="https://twitter.com/">@MatthiasJSax</a>)
+      </p>
+
+      <p>In this blog post, we describe Flink's compatibility package for <a href="https://storm.apache.org">Apache Storm</a> that allows to embed Spouts (sources) and Bolts (operators) in a regular Flink streaming job. Furthermore, the compatibility package provides a Storm compatible API in order to execute whole Storm topologies with (almost) no code adaption.</p>
+
+      <p><a href="/news/2015/12/11/storm-compatibility.html">Continue reading &raquo;</a></p>
+    </article>
+
+    <hr>
+    
+    <article>
       <h2 class="blog-title"><a href="/news/2015/12/04/Introducing-windows.html">Introducing Stream Windows in Apache Flink</a></h2>
 
       <p>04 Dec 2015 by Fabian Hueske (<a href="https://twitter.com/">@fhueske</a>)
@@ -333,20 +346,6 @@ vertex-centric or gather-sum-apply to Flink dataflows.</p>
 
     <hr>
     
-    <article>
-      <h2 class="blog-title"><a href="/news/2015/05/11/Juggling-with-Bits-and-Bytes.html">Juggling with Bits and Bytes</a></h2>
-
-      <p>11 May 2015 by Fabian Hüske (<a href="https://twitter.com/">@fhueske</a>)
-      </p>
-
-      <p><p>Nowadays, a lot of open-source systems for analyzing large data sets are implemented in Java or other JVM-based programming languages. The most well-known example is Apache Hadoop, but also newer frameworks such as Apache Spark, Apache Drill, and also Apache Flink run on JVMs. A common challenge that JVM-based data analysis engines face is to store large amounts of data in memory - both for caching and for efficient processing such as sorting and joining of data. Managing the [...]
-<p>In this blog post we discuss how Apache Flink manages memory, talk about its custom data de/serialization stack, and show how it operates on binary data.</p></p>
-
-      <p><a href="/news/2015/05/11/Juggling-with-Bits-and-Bytes.html">Continue reading &raquo;</a></p>
-    </article>
-
-    <hr>
-    
 
     <!-- Pagination links -->
     
@@ -379,6 +378,16 @@ vertex-centric or gather-sum-apply to Flink dataflows.</p>
 
     <ul id="markdown-toc">
       
+      <li><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></li>
+
+      
+        
+      
+    
+      
+      
+
+      
       <li><a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></li>
 
       
diff --git a/content/blog/page13/index.html b/content/blog/page13/index.html
index 17f6208..3f6a732 100644
--- a/content/blog/page13/index.html
+++ b/content/blog/page13/index.html
@@ -196,6 +196,20 @@
     <!-- Blog posts -->
     
     <article>
+      <h2 class="blog-title"><a href="/news/2015/05/11/Juggling-with-Bits-and-Bytes.html">Juggling with Bits and Bytes</a></h2>
+
+      <p>11 May 2015 by Fabian Hüske (<a href="https://twitter.com/">@fhueske</a>)
+      </p>
+
+      <p><p>Nowadays, a lot of open-source systems for analyzing large data sets are implemented in Java or other JVM-based programming languages. The most well-known example is Apache Hadoop, but also newer frameworks such as Apache Spark, Apache Drill, and also Apache Flink run on JVMs. A common challenge that JVM-based data analysis engines face is to store large amounts of data in memory - both for caching and for efficient processing such as sorting and joining of data. Managing the [...]
+<p>In this blog post we discuss how Apache Flink manages memory, talk about its custom data de/serialization stack, and show how it operates on binary data.</p></p>
+
+      <p><a href="/news/2015/05/11/Juggling-with-Bits-and-Bytes.html">Continue reading &raquo;</a></p>
+    </article>
+
+    <hr>
+    
+    <article>
       <h2 class="blog-title"><a href="/news/2015/04/13/release-0.9.0-milestone1.html">Announcing Flink 0.9.0-milestone1 preview release</a></h2>
 
       <p>13 Apr 2015
@@ -340,21 +354,6 @@ and offers a new API including definition of flexible windows.</p>
 
     <hr>
     
-    <article>
-      <h2 class="blog-title"><a href="/news/2014/11/04/release-0.7.0.html">Apache Flink 0.7.0 available</a></h2>
-
-      <p>04 Nov 2014
-      </p>
-
-      <p><p>We are pleased to announce the availability of Flink 0.7.0. This release includes new user-facing features as well as performance and bug fixes, brings the Scala and Java APIs in sync, and introduces Flink Streaming. A total of 34 people have contributed to this release, a big thanks to all of them!</p>
-
-</p>
-
-      <p><a href="/news/2014/11/04/release-0.7.0.html">Continue reading &raquo;</a></p>
-    </article>
-
-    <hr>
-    
 
     <!-- Pagination links -->
     
@@ -387,6 +386,16 @@ and offers a new API including definition of flexible windows.</p>
 
     <ul id="markdown-toc">
       
+      <li><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></li>
+
+      
+        
+      
+    
+      
+      
+
+      
       <li><a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></li>
 
       
diff --git a/content/blog/page14/index.html b/content/blog/page14/index.html
index efa4cbb..323f0b8 100644
--- a/content/blog/page14/index.html
+++ b/content/blog/page14/index.html
@@ -196,6 +196,21 @@
     <!-- Blog posts -->
     
     <article>
+      <h2 class="blog-title"><a href="/news/2014/11/04/release-0.7.0.html">Apache Flink 0.7.0 available</a></h2>
+
+      <p>04 Nov 2014
+      </p>
+
+      <p><p>We are pleased to announce the availability of Flink 0.7.0. This release includes new user-facing features as well as performance and bug fixes, brings the Scala and Java APIs in sync, and introduces Flink Streaming. A total of 34 people have contributed to this release, a big thanks to all of them!</p>
+
+</p>
+
+      <p><a href="/news/2014/11/04/release-0.7.0.html">Continue reading &raquo;</a></p>
+    </article>
+
+    <hr>
+    
+    <article>
       <h2 class="blog-title"><a href="/news/2014/10/03/upcoming_events.html">Upcoming Events</a></h2>
 
       <p>03 Oct 2014
@@ -275,6 +290,16 @@ academic and open source project that Flink originates from.</p>
 
     <ul id="markdown-toc">
       
+      <li><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></li>
+
+      
+        
+      
+    
+      
+      
+
+      
       <li><a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></li>
 
       
diff --git a/content/blog/page2/index.html b/content/blog/page2/index.html
index b99a0fb..0142cd6 100644
--- a/content/blog/page2/index.html
+++ b/content/blog/page2/index.html
@@ -196,6 +196,19 @@
     <!-- Blog posts -->
     
     <article>
+      <h2 class="blog-title"><a href="/2020/08/04/pyflink-pandas-udf-support-flink.html">PyFlink: The integration of Pandas into PyFlink</a></h2>
+
+      <p>04 Aug 2020
+       Jincheng Sun (<a href="https://twitter.com/sunjincheng121">@sunjincheng121</a>) &amp; Markos Sfikas (<a href="https://twitter.com/MarkSfik">@MarkSfik</a>)</p>
+
+      <p>The Apache Flink community put some great effort into integrating Pandas with PyFlink in the latest Flink version 1.11. Some of the added features include support for Pandas UDF and the conversion between Pandas DataFrame and Table. In this article, we will introduce how these functionalities work and how to use them with a step-by-step example.</p>
+
+      <p><a href="/2020/08/04/pyflink-pandas-udf-support-flink.html">Continue reading &raquo;</a></p>
+    </article>
+
+    <hr>
+    
+    <article>
       <h2 class="blog-title"><a href="/news/2020/07/30/demo-fraud-detection-3.html">Advanced Flink Application Patterns Vol.3: Custom Window Processing</a></h2>
 
       <p>30 Jul 2020
@@ -330,19 +343,6 @@ and provide a tutorial for running Streaming ETL with Flink on Zeppelin.</p>
 
     <hr>
     
-    <article>
-      <h2 class="blog-title"><a href="/news/2020/06/11/community-update.html">Flink Community Update - June'20</a></h2>
-
-      <p>11 Jun 2020
-       Marta Paes (<a href="https://twitter.com/morsapaes">@morsapaes</a>)</p>
-
-      <p>And suddenly it’s June. The previous month has been calm on the surface, but quite hectic underneath — the final testing phase for Flink 1.11 is moving at full speed, Stateful Functions 2.1 is out in the wild and Flink has made it into Google Season of Docs 2020.</p>
-
-      <p><a href="/news/2020/06/11/community-update.html">Continue reading &raquo;</a></p>
-    </article>
-
-    <hr>
-    
 
     <!-- Pagination links -->
     
@@ -375,6 +375,16 @@ and provide a tutorial for running Streaming ETL with Flink on Zeppelin.</p>
 
     <ul id="markdown-toc">
       
+      <li><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></li>
+
+      
+        
+      
+    
+      
+      
+
+      
       <li><a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></li>
 
       
diff --git a/content/blog/page3/index.html b/content/blog/page3/index.html
index 4afca1c..8bad354 100644
--- a/content/blog/page3/index.html
+++ b/content/blog/page3/index.html
@@ -196,6 +196,19 @@
     <!-- Blog posts -->
     
     <article>
+      <h2 class="blog-title"><a href="/news/2020/06/11/community-update.html">Flink Community Update - June'20</a></h2>
+
+      <p>11 Jun 2020
+       Marta Paes (<a href="https://twitter.com/morsapaes">@morsapaes</a>)</p>
+
+      <p>And suddenly it’s June. The previous month has been calm on the surface, but quite hectic underneath — the final testing phase for Flink 1.11 is moving at full speed, Stateful Functions 2.1 is out in the wild and Flink has made it into Google Season of Docs 2020.</p>
+
+      <p><a href="/news/2020/06/11/community-update.html">Continue reading &raquo;</a></p>
+    </article>
+
+    <hr>
+    
+    <article>
       <h2 class="blog-title"><a href="/news/2020/06/09/release-statefun-2.1.0.html">Stateful Functions 2.1.0 Release Announcement</a></h2>
 
       <p>09 Jun 2020
@@ -321,19 +334,6 @@ This release marks a big milestone: Stateful Functions 2.0 is not only an API up
 
     <hr>
     
-    <article>
-      <h2 class="blog-title"><a href="/news/2020/04/01/community-update.html">Flink Community Update - April'20</a></h2>
-
-      <p>01 Apr 2020
-       Marta Paes (<a href="https://twitter.com/morsapaes">@morsapaes</a>)</p>
-
-      <p>While things slow down around us, the Apache Flink community is privileged to remain as active as ever. This blogpost combs through the past few months to give you an update on the state of things in Flink — from core releases to Stateful Functions; from some good old community stats to a new development blog.</p>
-
-      <p><a href="/news/2020/04/01/community-update.html">Continue reading &raquo;</a></p>
-    </article>
-
-    <hr>
-    
 
     <!-- Pagination links -->
     
@@ -366,6 +366,16 @@ This release marks a big milestone: Stateful Functions 2.0 is not only an API up
 
     <ul id="markdown-toc">
       
+      <li><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></li>
+
+      
+        
+      
+    
+      
+      
+
+      
       <li><a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></li>
 
       
diff --git a/content/blog/page4/index.html b/content/blog/page4/index.html
index fed0e77..52f1a36 100644
--- a/content/blog/page4/index.html
+++ b/content/blog/page4/index.html
@@ -196,6 +196,19 @@
     <!-- Blog posts -->
     
     <article>
+      <h2 class="blog-title"><a href="/news/2020/04/01/community-update.html">Flink Community Update - April'20</a></h2>
+
+      <p>01 Apr 2020
+       Marta Paes (<a href="https://twitter.com/morsapaes">@morsapaes</a>)</p>
+
+      <p>While things slow down around us, the Apache Flink community is privileged to remain as active as ever. This blogpost combs through the past few months to give you an update on the state of things in Flink — from core releases to Stateful Functions; from some good old community stats to a new development blog.</p>
+
+      <p><a href="/news/2020/04/01/community-update.html">Continue reading &raquo;</a></p>
+    </article>
+
+    <hr>
+    
+    <article>
       <h2 class="blog-title"><a href="/features/2020/03/27/flink-for-data-warehouse.html">Flink as Unified Engine for Modern Data Warehousing: Production-Ready Hive Integration</a></h2>
 
       <p>27 Mar 2020
@@ -318,21 +331,6 @@
 
     <hr>
     
-    <article>
-      <h2 class="blog-title"><a href="/news/2019/12/11/release-1.8.3.html">Apache Flink 1.8.3 Released</a></h2>
-
-      <p>11 Dec 2019
-       Hequn Cheng </p>
-
-      <p><p>The Apache Flink community released the third bugfix version of the Apache Flink 1.8 series.</p>
-
-</p>
-
-      <p><a href="/news/2019/12/11/release-1.8.3.html">Continue reading &raquo;</a></p>
-    </article>
-
-    <hr>
-    
 
     <!-- Pagination links -->
     
@@ -365,6 +363,16 @@
 
     <ul id="markdown-toc">
       
+      <li><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></li>
+
+      
+        
+      
+    
+      
+      
+
+      
       <li><a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></li>
 
       
diff --git a/content/blog/page5/index.html b/content/blog/page5/index.html
index 7b2a3cc..94e06da 100644
--- a/content/blog/page5/index.html
+++ b/content/blog/page5/index.html
@@ -196,6 +196,21 @@
     <!-- Blog posts -->
     
     <article>
+      <h2 class="blog-title"><a href="/news/2019/12/11/release-1.8.3.html">Apache Flink 1.8.3 Released</a></h2>
+
+      <p>11 Dec 2019
+       Hequn Cheng </p>
+
+      <p><p>The Apache Flink community released the third bugfix version of the Apache Flink 1.8 series.</p>
+
+</p>
+
+      <p><a href="/news/2019/12/11/release-1.8.3.html">Continue reading &raquo;</a></p>
+    </article>
+
+    <hr>
+    
+    <article>
       <h2 class="blog-title"><a href="/news/2019/12/09/flink-kubernetes-kudo.html">Running Apache Flink on Kubernetes with KUDO</a></h2>
 
       <p>09 Dec 2019
@@ -321,19 +336,6 @@
 
     <hr>
     
-    <article>
-      <h2 class="blog-title"><a href="/2019/06/26/broadcast-state.html">A Practical Guide to Broadcast State in Apache Flink</a></h2>
-
-      <p>26 Jun 2019
-       Fabian Hueske (<a href="https://twitter.com/fhueske">@fhueske</a>)</p>
-
-      <p>Apache Flink has multiple types of operator state, one of which is called Broadcast State. In this post, we explain what Broadcast State is, and show an example of how it can be applied to an application that evaluates dynamic patterns on an event stream.</p>
-
-      <p><a href="/2019/06/26/broadcast-state.html">Continue reading &raquo;</a></p>
-    </article>
-
-    <hr>
-    
 
     <!-- Pagination links -->
     
@@ -366,6 +368,16 @@
 
     <ul id="markdown-toc">
       
+      <li><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></li>
+
+      
+        
+      
+    
+      
+      
+
+      
       <li><a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></li>
 
       
diff --git a/content/blog/page6/index.html b/content/blog/page6/index.html
index aeea76f..edf7fcc 100644
--- a/content/blog/page6/index.html
+++ b/content/blog/page6/index.html
@@ -196,6 +196,19 @@
     <!-- Blog posts -->
     
     <article>
+      <h2 class="blog-title"><a href="/2019/06/26/broadcast-state.html">A Practical Guide to Broadcast State in Apache Flink</a></h2>
+
+      <p>26 Jun 2019
+       Fabian Hueske (<a href="https://twitter.com/fhueske">@fhueske</a>)</p>
+
+      <p>Apache Flink has multiple types of operator state, one of which is called Broadcast State. In this post, we explain what Broadcast State is, and show an example of how it can be applied to an application that evaluates dynamic patterns on an event stream.</p>
+
+      <p><a href="/2019/06/26/broadcast-state.html">Continue reading &raquo;</a></p>
+    </article>
+
+    <hr>
+    
+    <article>
       <h2 class="blog-title"><a href="/2019/06/05/flink-network-stack.html">A Deep-Dive into Flink's Network Stack</a></h2>
 
       <p>05 Jun 2019
@@ -320,21 +333,6 @@ for more details.</p>
 
     <hr>
     
-    <article>
-      <h2 class="blog-title"><a href="/news/2019/02/25/release-1.6.4.html">Apache Flink 1.6.4 Released</a></h2>
-
-      <p>25 Feb 2019
-      </p>
-
-      <p><p>The Apache Flink community released the fourth bugfix version of the Apache Flink 1.6 series.</p>
-
-</p>
-
-      <p><a href="/news/2019/02/25/release-1.6.4.html">Continue reading &raquo;</a></p>
-    </article>
-
-    <hr>
-    
 
     <!-- Pagination links -->
     
@@ -367,6 +365,16 @@ for more details.</p>
 
     <ul id="markdown-toc">
       
+      <li><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></li>
+
+      
+        
+      
+    
+      
+      
+
+      
       <li><a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></li>
 
       
diff --git a/content/blog/page7/index.html b/content/blog/page7/index.html
index a4a2c03..4a09aac 100644
--- a/content/blog/page7/index.html
+++ b/content/blog/page7/index.html
@@ -196,6 +196,21 @@
     <!-- Blog posts -->
     
     <article>
+      <h2 class="blog-title"><a href="/news/2019/02/25/release-1.6.4.html">Apache Flink 1.6.4 Released</a></h2>
+
+      <p>25 Feb 2019
+      </p>
+
+      <p><p>The Apache Flink community released the fourth bugfix version of the Apache Flink 1.6 series.</p>
+
+</p>
+
+      <p><a href="/news/2019/02/25/release-1.6.4.html">Continue reading &raquo;</a></p>
+    </article>
+
+    <hr>
+    
+    <article>
       <h2 class="blog-title"><a href="/news/2019/02/15/release-1.7.2.html">Apache Flink 1.7.2 Released</a></h2>
 
       <p>15 Feb 2019
@@ -330,21 +345,6 @@ Please check the <a href="https://issues.apache.org/jira/secure/ReleaseNote.jspa
 
     <hr>
     
-    <article>
-      <h2 class="blog-title"><a href="/news/2018/09/20/release-1.5.4.html">Apache Flink 1.5.4 Released</a></h2>
-
-      <p>20 Sep 2018
-      </p>
-
-      <p><p>The Apache Flink community released the fourth bugfix version of the Apache Flink 1.5 series.</p>
-
-</p>
-
-      <p><a href="/news/2018/09/20/release-1.5.4.html">Continue reading &raquo;</a></p>
-    </article>
-
-    <hr>
-    
 
     <!-- Pagination links -->
     
@@ -377,6 +377,16 @@ Please check the <a href="https://issues.apache.org/jira/secure/ReleaseNote.jspa
 
     <ul id="markdown-toc">
       
+      <li><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></li>
+
+      
+        
+      
+    
+      
+      
+
+      
       <li><a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></li>
 
       
diff --git a/content/blog/page8/index.html b/content/blog/page8/index.html
index 54677d5..8a29d42 100644
--- a/content/blog/page8/index.html
+++ b/content/blog/page8/index.html
@@ -196,6 +196,21 @@
     <!-- Blog posts -->
     
     <article>
+      <h2 class="blog-title"><a href="/news/2018/09/20/release-1.5.4.html">Apache Flink 1.5.4 Released</a></h2>
+
+      <p>20 Sep 2018
+      </p>
+
+      <p><p>The Apache Flink community released the fourth bugfix version of the Apache Flink 1.5 series.</p>
+
+</p>
+
+      <p><a href="/news/2018/09/20/release-1.5.4.html">Continue reading &raquo;</a></p>
+    </article>
+
+    <hr>
+    
+    <article>
       <h2 class="blog-title"><a href="/news/2018/08/21/release-1.5.3.html">Apache Flink 1.5.3 Released</a></h2>
 
       <p>21 Aug 2018
@@ -328,19 +343,6 @@
 
     <hr>
     
-    <article>
-      <h2 class="blog-title"><a href="/features/2018/01/30/incremental-checkpointing.html">Managing Large State in Apache Flink: An Intro to Incremental Checkpointing</a></h2>
-
-      <p>30 Jan 2018
-       Stefan Ricther (<a href="https://twitter.com/StefanRRicther">@StefanRRicther</a>) &amp; Chris Ward (<a href="https://twitter.com/chrischinch">@chrischinch</a>)</p>
-
-      <p>Flink 1.3.0 introduced incremental checkpointing, making it possible for applications with large state to generate checkpoints more efficiently.</p>
-
-      <p><a href="/features/2018/01/30/incremental-checkpointing.html">Continue reading &raquo;</a></p>
-    </article>
-
-    <hr>
-    
 
     <!-- Pagination links -->
     
@@ -373,6 +375,16 @@
 
     <ul id="markdown-toc">
       
+      <li><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></li>
+
+      
+        
+      
+    
+      
+      
+
+      
       <li><a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></li>
 
       
diff --git a/content/blog/page9/index.html b/content/blog/page9/index.html
index 9534b82..610fe2e 100644
--- a/content/blog/page9/index.html
+++ b/content/blog/page9/index.html
@@ -196,6 +196,19 @@
     <!-- Blog posts -->
     
     <article>
+      <h2 class="blog-title"><a href="/features/2018/01/30/incremental-checkpointing.html">Managing Large State in Apache Flink: An Intro to Incremental Checkpointing</a></h2>
+
+      <p>30 Jan 2018
+       Stefan Ricther (<a href="https://twitter.com/StefanRRicther">@StefanRRicther</a>) &amp; Chris Ward (<a href="https://twitter.com/chrischinch">@chrischinch</a>)</p>
+
+      <p>Flink 1.3.0 introduced incremental checkpointing, making it possible for applications with large state to generate checkpoints more efficiently.</p>
+
+      <p><a href="/features/2018/01/30/incremental-checkpointing.html">Continue reading &raquo;</a></p>
+    </article>
+
+    <hr>
+    
+    <article>
       <h2 class="blog-title"><a href="/news/2017/12/21/2017-year-in-review.html">Apache Flink in 2017: Year in Review</a></h2>
 
       <p>21 Dec 2017
@@ -331,20 +344,6 @@ what’s coming in Flink 1.4.0 as well as a preview of what the Flink community
 
     <hr>
     
-    <article>
-      <h2 class="blog-title"><a href="/news/2017/04/04/dynamic-tables.html">Continuous Queries on Dynamic Tables</a></h2>
-
-      <p>04 Apr 2017 by Fabian Hueske, Shaoxuan Wang, and Xiaowei Jiang
-      </p>
-
-      <p><p>Flink's relational APIs, the Table API and SQL, are unified APIs for stream and batch processing, meaning that a query produces the same result when being evaluated on streaming or static data.</p>
-<p>In this blog post we discuss the future of these APIs and introduce the concept of Dynamic Tables. Dynamic tables will significantly expand the scope of the Table API and SQL on streams and enable many more advanced use cases. We discuss how streams and dynamic tables relate to each other and explain the semantics of continuously evaluating queries on dynamic tables.</p></p>
-
-      <p><a href="/news/2017/04/04/dynamic-tables.html">Continue reading &raquo;</a></p>
-    </article>
-
-    <hr>
-    
 
     <!-- Pagination links -->
     
@@ -377,6 +376,16 @@ what’s coming in Flink 1.4.0 as well as a preview of what the Flink community
 
     <ul id="markdown-toc">
       
+      <li><a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></li>
+
+      
+        
+      
+    
+      
+      
+
+      
       <li><a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></li>
 
       
diff --git a/content/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-1.png b/content/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-1.png
new file mode 100644
index 0000000..9432b27
Binary files /dev/null and b/content/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-1.png differ
diff --git a/content/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-2.png b/content/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-2.png
new file mode 100644
index 0000000..0f4d46d
Binary files /dev/null and b/content/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-2.png differ
diff --git a/content/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-3.png b/content/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-3.png
new file mode 100644
index 0000000..650601d
Binary files /dev/null and b/content/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-3.png differ
diff --git a/content/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-4.png b/content/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-4.png
new file mode 100644
index 0000000..43d88c0
Binary files /dev/null and b/content/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-4.png differ
diff --git a/content/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-5.png b/content/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-5.png
new file mode 100644
index 0000000..2ed23b2
Binary files /dev/null and b/content/img/blog/2020-10-15-from-aligned-to-unaligned-checkpoints-part-1/from-aligned-to-unaligned-checkpoints-part-1-5.png differ
diff --git a/content/index.html b/content/index.html
index eab92db..1b94731 100644
--- a/content/index.html
+++ b/content/index.html
@@ -568,6 +568,9 @@
 
   <dl>
       
+        <dt> <a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></dt>
+        <dd>Apache Flink’s checkpoint-based fault tolerance mechanism is one of its defining features. Because of that design, Flink unifies batch and stream processing, can easily scale to both very small and extremely large scenarios and provides support for many operational features. In this post we recap the original checkpointing process in Flink, its core properties and issues under backpressure.</dd>
+      
         <dt> <a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></dt>
         <dd>This blog post dives deep into the internals of the StateFun runtime, taking a look at how it enables consistent and fault-tolerant stateful serverless applications.</dd>
       
@@ -587,9 +590,6 @@ as well as increased observability for operational purposes.</p>
       
         <dt> <a href="/news/2020/09/04/community-update.html">Flink Community Update - August'20</a></dt>
         <dd>Ah, so much for a quiet August month. This time around, we bring you some new Flink Improvement Proposals (FLIPs), a preview of the upcoming Flink Stateful Functions 2.2 release and a look into how far Flink has come in comparison to 2019.</dd>
-      
-        <dt> <a href="/2020/09/01/flink-1.11-memory-management-improvements.html">Memory Management improvements for Flink’s JobManager in Apache Flink 1.11</a></dt>
-        <dd>In a previous blog post, we focused on the memory model of the TaskManagers and its improvements with the Apache Flink 1.10 release. This blog post addresses the same topic but for Flink's JobManager instead.</dd>
     
   </dl>
 
diff --git a/content/zh/index.html b/content/zh/index.html
index 57c6b6a..e12a1af 100644
--- a/content/zh/index.html
+++ b/content/zh/index.html
@@ -565,6 +565,9 @@
 
   <dl>
       
+        <dt> <a href="/2020/10/15/from-aligned-to-unaligned-checkpoints-part-1.html">From Aligned to Unaligned Checkpoints - Part 1: Checkpoints, Alignment, and Backpressure</a></dt>
+        <dd>Apache Flink’s checkpoint-based fault tolerance mechanism is one of its defining features. Because of that design, Flink unifies batch and stream processing, can easily scale to both very small and extremely large scenarios and provides support for many operational features. In this post we recap the original checkpointing process in Flink, its core properties and issues under backpressure.</dd>
+      
         <dt> <a href="/news/2020/10/13/stateful-serverless-internals.html">Stateful Functions Internals: Behind the scenes of Stateful Serverless</a></dt>
         <dd>This blog post dives deep into the internals of the StateFun runtime, taking a look at how it enables consistent and fault-tolerant stateful serverless applications.</dd>
       
@@ -584,9 +587,6 @@ as well as increased observability for operational purposes.</p>
       
         <dt> <a href="/news/2020/09/04/community-update.html">Flink Community Update - August'20</a></dt>
         <dd>Ah, so much for a quiet August month. This time around, we bring you some new Flink Improvement Proposals (FLIPs), a preview of the upcoming Flink Stateful Functions 2.2 release and a look into how far Flink has come in comparison to 2019.</dd>
-      
-        <dt> <a href="/2020/09/01/flink-1.11-memory-management-improvements.html">Memory Management improvements for Flink’s JobManager in Apache Flink 1.11</a></dt>
-        <dd>In a previous blog post, we focused on the memory model of the TaskManagers and its improvements with the Apache Flink 1.10 release. This blog post addresses the same topic but for Flink's JobManager instead.</dd>
     
   </dl>