<?xml version="1.0" encoding="UTF-8"?>
 <rdf:RDF xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://web.resource.org/cc/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/">
  <channel rdf:about="http://pinboard.in">
    <title>Pinboard (jm)</title>
    <link>https://pinboard.in/u:jm/public/</link>
    <description>recent bookmarks from jm</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://www.verizonmedia.com/technology/blog/apache-pulsar-overview"/>
	<rdf:li rdf:resource="https://iceberg.apache.org/"/>
	<rdf:li rdf:resource="https://engineering.pandora.com/apache-airflow-at-pandora-1d7a844d68ee"/>
	<rdf:li rdf:resource="https://mozilla.github.io/server-side-tls/ssl-config-generator/?server=nginx-1.10.3&amp;openssl=1.0.1e&amp;hsts=yes&amp;profile=modern"/>
	<rdf:li rdf:resource="https://issues.apache.org/jira/browse/LEGAL-303"/>
	<rdf:li rdf:resource="https://pixelastic.github.io/pokemonorbigdata/"/>
	<rdf:li rdf:resource="https://engineering.linkedin.com/blog/2015/10/open-sourcing-paldb--a-lightweight-companion-for-storing-side-da"/>
	<rdf:li rdf:resource="https://github.com/mapsme/omim"/>
	<rdf:li rdf:resource="http://chrisvest.github.io/stormpot/"/>
	<rdf:li rdf:resource="http://drbacchus.com/festina-lente/"/>
	<rdf:li rdf:resource="http://htrace.incubator.apache.org/"/>
	<rdf:li rdf:resource="http://databricks.com/blog/2014/12/19/announcing-spark-1-2.html"/>
	<rdf:li rdf:resource="https://github.com/FelixGV/tehuti"/>
	<rdf:li rdf:resource="http://spark.apache.org/docs/latest/streaming-programming-guide.html#overview"/>
	<rdf:li rdf:resource="https://www.youtube.com/watch?v=q1mndAYZlio"/>
	<rdf:li rdf:resource="http://spamassassin.apache.org/"/>
	<rdf:li rdf:resource="http://curator.apache.org/"/>
	<rdf:li rdf:resource="http://www.scribd.com/doc/131955288/Randomly-Failed-The-State-of-Randomness-in-Current-Java-Implementations"/>
	<rdf:li rdf:resource="http://blog.ivanristic.com/2013/08/defending-against-the-breach-attack.html"/>
	<rdf:li rdf:resource="http://blog.aggregateknowledge.com/2013/06/18/open-source-release-js-hll/"/>
	<rdf:li rdf:resource="https://blog.liveramp.com/2013/04/08/kafka-0-8-producer-performance-2/"/>
	<rdf:li rdf:resource="http://basho.com/riak-cs-is-now-open-source/"/>
	<rdf:li rdf:resource="http://square.github.com/cubism/"/>
	<rdf:li rdf:resource="http://incubator.apache.org/kafka/index.html"/>
	<rdf:li rdf:resource="http://www.mikealrogers.com/posts/apache-considered-harmful.html"/>
	<rdf:li rdf:resource="http://tech.blog.greplin.com/lucene-utilities-and-bloom-filters"/>
	<rdf:li rdf:resource="http://akka.io/"/>
	<rdf:li rdf:resource="http://avatraxiom.livejournal.com/102080.html"/>
	<rdf:li rdf:resource="http://www.elasticsearch.com/products/elasticsearch/"/>
	<rdf:li rdf:resource="http://www.prnewswire.com/news-releases/the-apache-software-foundation-announces-apache-spamassassin-version-330-82677727.html"/>
	<rdf:li rdf:resource="http://www.earthtimes.org/articles/show/subversion-submitted-to-become-a-project-at-the-apache-software-foundation,1028705.shtml"/>
	<rdf:li rdf:resource="https://blogs.apache.org/infra/entry/ddos_mystery_involving_linux_and#comments"/>
	<rdf:li rdf:resource="http://www.fudgie.org/"/>
	<rdf:li rdf:resource="http://blog.canonical.com/?p=192"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://www.verizonmedia.com/technology/blog/apache-pulsar-overview">
    <title>Apache Pulsar: Seamless Storage Evolution</title>
    <dc:date>2021-06-15T22:27:13+00:00</dc:date>
    <link>https://www.verizonmedia.com/technology/blog/apache-pulsar-overview</link>
    <dc:creator>jm</dc:creator><description><![CDATA[Impressive performance figures from the distributed messaging/streaming platform using NVMe and DCPMM persistent memory devices: 

'Pulsar architecture can accommodate different types of hardware which allows users to balance performance and cost based on required throughput and latency. Pulsar has the capability to adapt to the next generation of storage devices to achieve better performance. We have also seen that persistent memory excels in the race to achieving higher write throughput by maintaining low latency. ']]></description>
<dc:subject>streaming distcomp distributed apache pulsar dcpmm nvme persistent-memory performance architecture storage</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:98dee1973e10/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:streaming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:distcomp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:pulsar"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:dcpmm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:nvme"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:persistent-memory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:performance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:architecture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:storage"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://iceberg.apache.org/">
    <title>Apache Iceberg (incubating)</title>
    <dc:date>2019-01-14T23:22:27+00:00</dc:date>
    <link>https://iceberg.apache.org/</link>
    <dc:creator>jm</dc:creator><description><![CDATA[Coming to presto soon apparently....

<blockquote>Iceberg tracks individual data files in a table instead of directories. This allows writers to create data files in-place and only adds files to the table in an explicit commit.

Table state is maintained in metadata files. All changes to table state create a new metadata file and replace the old metadata with an atomic operation. The table metadata file tracks the table schema, partitioning config, other properties, and snapshots of the table contents.

The atomic transitions from one table metadata file to the next provide snapshot isolation. Readers use the latest table state (snapshot) that was current when they load the table metadata and are not affected by changes until they refresh and pick up a new metadata location.</blockquote>

excellent -- this will let me obsolete so much of our own code :)
]]></description>
<dc:subject>presto storage s3 hive iceberg apache asf data architecture</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:07b6a7ecf2f8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:presto"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:storage"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:s3"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:hive"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:iceberg"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:asf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:architecture"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://engineering.pandora.com/apache-airflow-at-pandora-1d7a844d68ee">
    <title>Apache Airflow at Pandora – Algorithm and Blues</title>
    <dc:date>2018-03-16T23:52:35+00:00</dc:date>
    <link>https://engineering.pandora.com/apache-airflow-at-pandora-1d7a844d68ee</link>
    <dc:creator>jm</dc:creator><description><![CDATA[sounds like they are pretty into Airflow]]></description>
<dc:subject>airflow python apache pandora open-source scheduling dags</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:1360818f0557/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:airflow"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:pandora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:open-source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:scheduling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:dags"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://mozilla.github.io/server-side-tls/ssl-config-generator/?server=nginx-1.10.3&amp;openssl=1.0.1e&amp;hsts=yes&amp;profile=modern">
    <title>Generate Mozilla Security Recommended Web Server Configuration Files</title>
    <dc:date>2018-02-06T16:38:08+00:00</dc:date>
    <link>https://mozilla.github.io/server-side-tls/ssl-config-generator/?server=nginx-1.10.3&amp;openssl=1.0.1e&amp;hsts=yes&amp;profile=modern</link>
    <dc:creator>jm</dc:creator><description><![CDATA[this is quite cool -- generate web server configs to activate current best-practice TLS settings]]></description>
<dc:subject>web openssl nginx lighttpd apache haproxy hsts security ssl tls ops</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:70aa27c02be7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:openssl"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:nginx"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:lighttpd"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:haproxy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:hsts"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:security"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:ssl"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:tls"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:ops"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://issues.apache.org/jira/browse/LEGAL-303">
    <title>[LEGAL-303] ASF, RocksDB, and Facebook's BSD+patent grant licensing</title>
    <dc:date>2017-07-17T10:29:51+00:00</dc:date>
    <link>https://issues.apache.org/jira/browse/LEGAL-303</link>
    <dc:creator>jm</dc:creator><description><![CDATA[Facebook's licensing includes a "nuclear option" if a user acts in a way interpreted by Facebook as competing with them; the ASF has marked the license as "Category-X", and may not be included in Apache projects as a result.  Looks like RocksDB are going to relicense as dual GPLv2/ASL2 to clear this up, but React.js has not shown any plans to do so yet]]></description>
<dc:subject>react rocksdb licensing asl2 apache asf facebook open-source patents</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:a8d0f17f02f0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:react"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:rocksdb"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:licensing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:asl2"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:asf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:facebook"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:open-source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:patents"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://pixelastic.github.io/pokemonorbigdata/">
    <title>Is it Pokemon or Big Data ?</title>
    <dc:date>2015-11-25T17:15:21+00:00</dc:date>
    <link>https://pixelastic.github.io/pokemonorbigdata/</link>
    <dc:creator>jm</dc:creator><description><![CDATA[75%.  This is really quite tricky!]]></description>
<dc:subject>pokemon big-data apache hadoop funny quizzes</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:47b444c9bf43/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:pokemon"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:big-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:funny"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:quizzes"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://engineering.linkedin.com/blog/2015/10/open-sourcing-paldb--a-lightweight-companion-for-storing-side-da">
    <title>Open-sourcing PalDB, a lightweight companion for storing side data</title>
    <dc:date>2015-10-28T15:35:31+00:00</dc:date>
    <link>https://engineering.linkedin.com/blog/2015/10/open-sourcing-paldb--a-lightweight-companion-for-storing-side-da</link>
    <dc:creator>jm</dc:creator><description><![CDATA[a new LinkedIn open source data store, for write-once/read-mainly side data, java, Apache licensed.

RocksDB discussion: https://www.facebook.com/groups/rocksdb.dev/permalink/834956096602906/]]></description>
<dc:subject>linkedin open-source storage side-data data config paldb java apache databases</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:5f9ff3f038de/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:linkedin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:open-source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:storage"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:side-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:config"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:paldb"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:databases"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/mapsme/omim">
    <title>excellent offline mapping app MAPS.ME goes open source</title>
    <dc:date>2015-09-30T15:08:47+00:00</dc:date>
    <link>https://github.com/mapsme/omim</link>
    <dc:creator>jm</dc:creator><description><![CDATA["MAPS.ME is an open source cross-platform offline maps application, built on top of crowd-sourced OpenStreetMap data. It was publicly released for iOS and Android."]]></description>
<dc:subject>maps.me mapping maps open-source apache ios android mobile</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:a1c891d21ad8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:maps.me"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:mapping"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:maps"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:open-source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:ios"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:android"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:mobile"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://chrisvest.github.io/stormpot/">
    <title>Stormpot</title>
    <dc:date>2015-09-08T10:43:41+00:00</dc:date>
    <link>http://chrisvest.github.io/stormpot/</link>
    <dc:creator>jm</dc:creator><description><![CDATA[<blockquote>an object pooling library for Java. Use it to recycle objects that are expensive to create. The library will take care of creating and destroying your objects in the background. Stormpot is very mature, is used in production, and has done over a trillion claim-release cycles in testing. It is faster and scales better than any competing pool.</blockquote>

Apache-licensed, and extremely fast: https://medium.com/@chrisvest/released-stormpot-2-4-eeab4aec86d0]]></description>
<dc:subject>java stormpot object-pooling object-pools pools allocation gc open-source apache performance</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:ef38e7baa4ad/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:stormpot"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:object-pooling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:object-pools"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:pools"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:allocation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:gc"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:open-source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:performance"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://drbacchus.com/festina-lente/">
    <title>Festina Lente</title>
    <dc:date>2015-07-29T21:57:09+00:00</dc:date>
    <link>http://drbacchus.com/festina-lente/</link>
    <dc:creator>jm</dc:creator><description><![CDATA[A lovely eulogy for Nóirín Plunkett, from Rich Bowen.  RIP Nóirín :(]]></description>
<dc:subject>noirin-plunkett memorials eulogies rip asf apache</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:9cb6106513a9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:noirin-plunkett"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:memorials"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:eulogies"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:rip"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:asf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://htrace.incubator.apache.org/">
    <title>Apache HTrace</title>
    <dc:date>2015-05-12T16:06:27+00:00</dc:date>
    <link>http://htrace.incubator.apache.org/</link>
    <dc:creator>jm</dc:creator><description><![CDATA[a Zipkin-compatible distributed-system tracing framework in Java, in the Apache Incubator]]></description>
<dc:subject>zipkin tracing trace apache incubator java debugging</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:7241ab3bdb05/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:zipkin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:tracing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:trace"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:incubator"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:debugging"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://databricks.com/blog/2014/12/19/announcing-spark-1-2.html">
    <title>Spark 1.2 released</title>
    <dc:date>2014-12-22T14:14:17+00:00</dc:date>
    <link>http://databricks.com/blog/2014/12/19/announcing-spark-1-2.html</link>
    <dc:creator>jm</dc:creator><description><![CDATA[This is the version with the superfast petabyte-sort record:<blockquote>Spark 1.2 includes several cross-cutting optimizations focused on performance for large scale workloads. Two new features Databricks developed for our world record petabyte sort with Spark are turned on by default in Spark 1.2. The first is a re-architected network transfer subsystem that exploits Netty 4’s zero-copy IO and off heap buffer management. The second is Spark’s sort based shuffle implementation, which we’ve now made the default after significant testing in Spark 1.1. Together, we’ve seen these features give as much as 5X performance improvement for workloads with very large shuffles.</blockquote>

]]></description>
<dc:subject>spark sorting hadoop map-reduce batch databricks apache netty</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:6d93115441ec/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:spark"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:sorting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:hadoop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:map-reduce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:batch"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:databricks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:netty"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/FelixGV/tehuti">
    <title>FelixGV/tehuti</title>
    <dc:date>2014-10-09T10:53:00+00:00</dc:date>
    <link>https://github.com/FelixGV/tehuti</link>
    <dc:creator>jm</dc:creator><description><![CDATA[Felix says: 

'Like I said, I'd like to move it to a more general / non-personal repo in the future, but haven't had the time yet. Anyway, you can still browse the code there for now. It is not a big code base so not that hard to wrap one's mind around it.

It is Apache licensed and both Kafka and Voldemort are using it so I would say it is pretty self-contained (although Kafka has not moved to Tehuti proper, it is essentially the same code they're using, minus a few small fixes missing that we added).

Tehuti is a bit lower level than CodaHale (i.e.: you need to choose exactly which stats you want to measure and the boundaries of your histograms), but this is the type of stuff you would build a wrapper for and then re-use within your code base. For example: the Voldemort RequestCounter class.']]></description>
<dc:subject>asl2 apache open-source tehuti metrics percentiles quantiles statistics measurement latency kafka voldemort linkedin</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:a2f55ebce7bb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:asl2"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:open-source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:tehuti"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:percentiles"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:quantiles"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:measurement"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:latency"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:kafka"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:voldemort"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:linkedin"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://spark.apache.org/docs/latest/streaming-programming-guide.html#overview">
    <title>Spark Streaming</title>
    <dc:date>2014-05-16T21:35:38+00:00</dc:date>
    <link>http://spark.apache.org/docs/latest/streaming-programming-guide.html#overview</link>
    <dc:creator>jm</dc:creator><description><![CDATA[<blockquote>an extension of the core Spark API that allows enables high-throughput, fault-tolerant stream processing of live data streams. Data can be ingested from many sources like Kafka, Flume, Twitter, ZeroMQ or plain old TCP sockets and be processed using complex algorithms expressed with high-level functions like map, reduce, join and window. Finally, processed data can be pushed out to filesystems, databases, and live dashboards. In fact, you can apply Spark’s in-built machine learning algorithms, and graph processing algorithms on data streams.</blockquote>

]]></description>
<dc:subject>spark streams stream-processing cep scalability apache machine-learning graphs</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:62c1e3c0e756/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:spark"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:streams"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:stream-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:cep"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:graphs"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/watch?v=q1mndAYZlio">
    <title>Building a large scale CDN with Apache Traffic Server</title>
    <dc:date>2014-05-07T10:53:57+00:00</dc:date>
    <link>https://www.youtube.com/watch?v=q1mndAYZlio</link>
    <dc:creator>jm</dc:creator><description><![CDATA[via Ilya Grigorik: 'Great under-the-hood look at how Comcast built and operates their internal CDN for delivering video (on-demand + live). Some highlights: switched to own (open-source) stack; ~250 servers pushing ~1.5Pb of data/day with ~5Pb of storage capacity.']]></description>
<dc:subject>cdn comcast video presentations apache traffic-server vod</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:9d0c215518cc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:cdn"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:comcast"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:presentations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:traffic-server"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:vod"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://spamassassin.apache.org/">
    <title>SpamAssassin 3.4.0 released</title>
    <dc:date>2014-02-12T10:53:51+00:00</dc:date>
    <link>http://spamassassin.apache.org/</link>
    <dc:creator>jm</dc:creator><description><![CDATA[Good to see the guys cracking on without me ;)

'2014-02-11: SpamAssassin 3.4.0 has been released adding native support for IPv6, improved DNS Blocklist technology and support for massively-scalable Bayesian filtering using the Redis backend.']]></description>
<dc:subject>antispam open-source spamassassin apache</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:04b9d97e777d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:antispam"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:open-source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:spamassassin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://curator.apache.org/">
    <title>Apache Curator</title>
    <dc:date>2014-01-30T22:09:06+00:00</dc:date>
    <link>http://curator.apache.org/</link>
    <dc:creator>jm</dc:creator><description><![CDATA[Netflix open-source library to make using ZooKeeper from Java less of a PITA.  I really wish I'd used this now, having reimplemented some key parts of it after failures in prod ;)]]></description>
<dc:subject>zookeeper netflix apache curator java libraries open-source</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:2a32e89d7f29/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:zookeeper"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:netflix"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:curator"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:libraries"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:open-source"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.scribd.com/doc/131955288/Randomly-Failed-The-State-of-Randomness-in-Current-Java-Implementations">
    <title>Randomly Failed! The State of Randomness in Current Java Implementations</title>
    <dc:date>2013-08-12T09:06:00+00:00</dc:date>
    <link>http://www.scribd.com/doc/131955288/Randomly-Failed-The-State-of-Randomness-in-Current-Java-Implementations</link>
    <dc:creator>jm</dc:creator><description><![CDATA[This would appear to be the paper which sparked off the drama around BitCoin thefts from wallets generated on Android devices:

<blockquote>
The SecureRandom PRNG is the primary source of randomness for Java and is used e.g., by cryptographic operations. This underlines its importance regarding security. Some of fallback solutions of the investigated implementations [are] revealed to be weak and predictable or capable of being inﬂuenced. Very alarming are the defects found in Apache Harmony, since it is partly used by Android.</blockquote>

More on the BitCoin drama: https://bitcointalk.org/index.php?topic=271486.40 , http://bitcoin.org/en/alert/2013-08-11-android]]></description>
<dc:subject>android java prng random security bugs apache-harmony apache crypto bitcoin papers</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:016d49a82951/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:android"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:prng"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:random"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:security"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:bugs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache-harmony"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:crypto"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:bitcoin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:papers"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://blog.ivanristic.com/2013/08/defending-against-the-breach-attack.html">
    <title>Ivan Ristić: Defending against the BREACH attack</title>
    <dc:date>2013-08-07T20:33:04+00:00</dc:date>
    <link>http://blog.ivanristic.com/2013/08/defending-against-the-breach-attack.html</link>
    <dc:creator>jm</dc:creator><description><![CDATA[One interesting response to this HTTPS compression-based MITM attack:

<blockquote>The award for least-intrusive and entirely painless mitigation proposal goes to Paul Querna who, on the httpd-dev mailing list, proposed to use the HTTP chunked encoding to randomize response length. Chunked encoding is a HTTP feature that is typically used when the size of the response body is not known in advance; only the size of the next chunk is known. Because chunks carry some additional information, they affect the size of the response, but not the content. By forcing more chunks than necessary, for example, you can increase the length of the response. To the attacker, who can see only the size of the response body, but not anything else, the chunks are invisible. (Assuming they're not sent in individual TCP packets or TLS records, of course.)  This mitigation technique is very easy to implement at the web server level, which makes it the least expensive option. There is only a question about its effectiveness. No one has done the maths yet, but most seem to agree that response length randomization slows down the attacker, but does not prevent the attack entirely. But, if the attack can be slowed down significantly, perhaps it will be as good as prevented.</blockquote>

]]></description>
<dc:subject>mitm attacks hacking security compression http https protocols tls ssl tcp chunked-encoding apache</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:13c0a7ba2031/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:mitm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:attacks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:hacking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:security"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:compression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:http"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:https"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:protocols"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:tls"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:ssl"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:tcp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:chunked-encoding"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://blog.aggregateknowledge.com/2013/06/18/open-source-release-js-hll/">
    <title>js-hll</title>
    <dc:date>2013-06-25T21:37:50+00:00</dc:date>
    <link>http://blog.aggregateknowledge.com/2013/06/18/open-source-release-js-hll/</link>
    <dc:creator>jm</dc:creator><description><![CDATA[Good UI for exploration of HyperLogLog set intersections and unions.

<blockquote>One of the first things that we wanted to do with HyperLogLog when we first started playing with it was to support and expose it natively in the browser. The thought of allowing users to directly interact with these structures -- perform arbitrary unions and intersections on effectively unbounded sets all on the client -- was exhilarating to us. [...] we are pleased to announce the open-source release of AK’s HyperLogLog implementation for JavaScript, js-hll. We are releasing this code under the Apache License, Version 2.0.

We knew that we couldn’t just release a bunch of JavaScript code without allowing you to see it in action — that would be a crime. We passed a few ideas around and the one that kept bubbling to the top was a way to kill two birds with one stone. We wanted something that would showcase what you can do with HLL in the browser and give us a tool for explaining HLLs. It is typical for us to explain how HLL intersections work using a Venn diagram. You draw some overlapping circles with a border that represents the error and you talk about how if that border is close to or larger than the intersection then you can’t say much about the size of that intersection. This works just ok on a whiteboard but what you really want is to just build a visualization that allows you to select from some sets and see the overlap. Maybe even play with the precision a little bit to see how that changes the result. Well, we did just that!</blockquote>

]]></description>
<dc:subject>javascript ui hll hyperloglog algorithms sketching js sets intersection union apache open-source</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:aedd388dbaa3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:javascript"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:ui"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:hll"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:hyperloglog"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:sketching"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:js"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:intersection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:union"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:open-source"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://blog.liveramp.com/2013/04/08/kafka-0-8-producer-performance-2/">
    <title>Kafka 0.8 Producer Performance</title>
    <dc:date>2013-04-10T22:24:27+00:00</dc:date>
    <link>https://blog.liveramp.com/2013/04/08/kafka-0-8-producer-performance-2/</link>
    <dc:creator>jm</dc:creator><description><![CDATA[Great benchmarking from Piotr Kozikowski at the LiveRamp team, into performance of the upcoming Kafka 0.8 release]]></description>
<dc:subject>performance kafka apache benchmarks ops queueing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:2f67886faaa2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:performance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:kafka"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:benchmarks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:ops"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:queueing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://basho.com/riak-cs-is-now-open-source/">
    <title>Riak CS is now ASL2 open source</title>
    <dc:date>2013-03-20T13:35:04+00:00</dc:date>
    <link>http://basho.com/riak-cs-is-now-open-source/</link>
    <dc:creator>jm</dc:creator><description><![CDATA['Organizations and users can now access the source code on Github and download the latest packages from the downloads page. Also, today, we announced that Riak CS Enterprise is now available as commercial licensed software, featuring multi-datacenter replication technology and 24×7 Basho customer support.']]></description>
<dc:subject>riak riak-cs nosql storage basho open-source github apache asl2</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:6120c0a8fb9a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:riak"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:riak-cs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:nosql"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:storage"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:basho"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:open-source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:github"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:asl2"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://square.github.com/cubism/">
    <title>Cubism.js</title>
    <dc:date>2012-04-24T20:04:30+00:00</dc:date>
    <link>http://square.github.com/cubism/</link>
    <dc:creator>jm</dc:creator><description><![CDATA['a D3 plugin for visualizing time series. Use Cubism to construct better realtime dashboards.' Apache-licensed; nice realtime update style; overlays multiple data sources well.  I think I now have a good use-case for this]]></description>
<dc:subject>javascript library visualization dataviz tsd data apache open-source</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:c44f693703d5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:javascript"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:library"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:dataviz"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:tsd"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:open-source"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://incubator.apache.org/kafka/index.html">
    <title>Apache Kafka</title>
    <dc:date>2012-02-12T00:59:16+00:00</dc:date>
    <link>http://incubator.apache.org/kafka/index.html</link>
    <dc:creator>jm</dc:creator><description><![CDATA['Kafka provides a publish-subscribe solution that can handle all activity stream data and processing on a consumer-scale web site. This kind of activity (page views, searches, and other user actions) are a key ingredient in many of the social feature on the modern web. This data is typically handled by "logging" and ad hoc log aggregation solutions due to the throughput requirements. This kind of ad hoc solution is a viable solution to providing logging data to an offline analysis system like Hadoop, but is very limiting for building real-time processing. Kafka aims to unify offline and online processing by providing a mechanism for parallel load into Hadoop as well as the ability to partition real-time consumption over a cluster of machines.'  neat
]]></description>
<dc:subject>kafka linkedin apache distributed messaging pubsub queue incubator scaling</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:92e2d30f6bea/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:kafka"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:linkedin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:messaging"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:pubsub"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:queue"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:incubator"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:scaling"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.mikealrogers.com/posts/apache-considered-harmful.html">
    <title>Apache considered harmful</title>
    <dc:date>2011-11-23T21:59:04+00:00</dc:date>
    <link>http://www.mikealrogers.com/posts/apache-considered-harmful.html</link>
    <dc:creator>jm</dc:creator><description><![CDATA[ouch]]></description>
<dc:subject>git asf apache via:hn github programming</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:jm/b:fd68b4e57a32/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:git"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:asf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:via:hn"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:github"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:programming"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://tech.blog.greplin.com/lucene-utilities-and-bloom-filters">
    <title>Lucene Utilities and Bloom Filters - Greplin:tech</title>
    <dc:date>2011-04-13T23:20:49+00:00</dc:date>
    <link>http://tech.blog.greplin.com/lucene-utilities-and-bloom-filters</link>
    <dc:creator>jm</dc:creator><description><![CDATA['Storing 50,000 2.5KB items in a traditional hash set requires over 125MB, but if you're willing to accept a 1-in-10,000 false positive rate on lookups, [this] bloom filter requires under 500KB' - interesting variation on the basic concept.  Java, Apache-licensed]]></description>
<dc:subject>search bloom-filters greplin open-source apache false-positives</dc:subject>
<dc:identifier>https://pinboard.in/u:jm/b:b2a894a638d9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:bloom-filters"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:greplin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:open-source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:false-positives"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://akka.io/">
    <title>Akka</title>
    <dc:date>2011-03-27T22:20:47+00:00</dc:date>
    <link>http://akka.io/</link>
    <dc:creator>jm</dc:creator><description><![CDATA['platform for event-driven, scalable, and fault-tolerant architectures on the JVM' .. Actor-based, 'let-it-crash', Apache-licensed, Java and Scala APIs, remote Actors, transactional memory -- looks quite nice]]></description>
<dc:subject>scala java concurrency scalability apache akka actors erlang fault-tolerance events</dc:subject>
<dc:identifier>https://pinboard.in/u:jm/b:d8d97dabbd34/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:scala"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:java"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:concurrency"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:scalability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:akka"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:actors"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:erlang"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:fault-tolerance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:events"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://avatraxiom.livejournal.com/102080.html">
    <title>avatraxiom: Improving Web Security: Six Ways the Apache.org JIRA Attack Could Have Been Prevented by Better Code</title>
    <dc:date>2010-04-13T17:05:28+00:00</dc:date>
    <link>http://avatraxiom.livejournal.com/102080.html</link>
    <dc:creator>jm</dc:creator><description><![CDATA[by a Bugzilla developer. ;)]]></description>
<dc:subject>asf apache bugzilla jira xss security hacks</dc:subject>
<dc:identifier>https://pinboard.in/u:jm/b:72c5f6462cc3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:asf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:bugzilla"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:jira"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:xss"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:security"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:hacks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.elasticsearch.com/products/elasticsearch/">
    <title>ElasticSearch</title>
    <dc:date>2010-02-12T21:24:08+00:00</dc:date>
    <link>http://www.elasticsearch.com/products/elasticsearch/</link>
    <dc:creator>jm</dc:creator><description><![CDATA[nifty; Apache-licensed distributed, RESTful, JSON-over-HTTP, schemaless search server with multi-tenancy]]></description>
<dc:subject>search distributed rest json apache elasticsearch http</dc:subject>
<dc:identifier>https://pinboard.in/u:jm/b:0b0daaf0ae91/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:search"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:rest"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:json"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:elasticsearch"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:http"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.prnewswire.com/news-releases/the-apache-software-foundation-announces-apache-spamassassin-version-330-82677727.html">
    <title>The Apache Software Foundation Announces Apache SpamAssassin Version 3.3.0</title>
    <dc:date>2010-01-26T16:34:43+00:00</dc:date>
    <link>http://www.prnewswire.com/news-releases/the-apache-software-foundation-announces-apache-spamassassin-version-330-82677727.html</link>
    <dc:creator>jm</dc:creator><description><![CDATA[w00t!]]></description>
<dc:subject>asf apache spamassassin releases 3.3.0 anti-spam</dc:subject>
<dc:identifier>https://pinboard.in/u:jm/b:1d69fed5b2e1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:asf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:spamassassin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:releases"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:3.3.0"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:anti-spam"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.earthtimes.org/articles/show/subversion-submitted-to-become-a-project-at-the-apache-software-foundation,1028705.shtml">
    <title>Subversion Submitted to Become a Project at The Apache Software Foundation</title>
    <dc:date>2009-11-04T17:56:42+00:00</dc:date>
    <link>http://www.earthtimes.org/articles/show/subversion-submitted-to-become-a-project-at-the-apache-software-foundation,1028705.shtml</link>
    <dc:creator>jm</dc:creator><description><![CDATA[woot!]]></description>
<dc:subject>svn subversion asf apache open-source incubator</dc:subject>
<dc:identifier>https://pinboard.in/u:jm/b:de5ce9add3cd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:svn"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:subversion"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:asf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:open-source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:incubator"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://blogs.apache.org/infra/entry/ddos_mystery_involving_linux_and#comments">
    <title>DDOS mystery involving Linux and mod_ssl</title>
    <dc:date>2009-10-19T15:09:38+00:00</dc:date>
    <link>https://blogs.apache.org/infra/entry/ddos_mystery_involving_linux_and#comments</link>
    <dc:creator>jm</dc:creator><description><![CDATA[connections to brutus.apache.org, "GET / HTTP/1.1", massive HTTPS DDOS.  no idea what's going on]]></description>
<dc:subject>apache asf ddos https httpd mod_ssl</dc:subject>
<dc:identifier>https://pinboard.in/u:jm/b:a02a0daec994/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:asf"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:ddos"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:https"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:httpd"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:mod_ssl"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.fudgie.org/">
    <title>glTail.rb - realtime logfile visualization</title>
    <dc:date>2009-07-21T09:28:15+00:00</dc:date>
    <link>http://www.fudgie.org/</link>
    <dc:creator>jm</dc:creator><description><![CDATA['View real-time data and statistics from any logfile on any server with SSH, in an intuitive and entertaining way', supporting postfix/spamd/clamd logs among loads of others.  very cool if a little silly]]></description>
<dc:subject>dataviz visualization tail gltail opengl linux apache spamd spamassassin logs statistics sysadmin analytics animation analysis server ruby monitoring logging logfiles</dc:subject>
<dc:identifier>https://pinboard.in/u:jm/b:be37d5036892/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:dataviz"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:tail"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:gltail"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:opengl"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:linux"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:spamd"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:spamassassin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:logs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:sysadmin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:analytics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:animation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:server"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:ruby"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:monitoring"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:logging"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:logfiles"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://blog.canonical.com/?p=192">
    <title>Launchpad is now open source</title>
    <dc:date>2009-07-21T08:59:49+00:00</dc:date>
    <link>http://blog.canonical.com/?p=192</link>
    <dc:creator>jm</dc:creator><description><![CDATA[Canonical _finally_ open source (under the AGPL) their bug tracker/project hosting platform.  yay!  here's hoping it's reasonably easy to deploy.  maybe it would be viable for the ASF... hmm]]></description>
<dc:subject>canonical launchpad open-source apache hosting projects ubuntu agpl</dc:subject>
<dc:identifier>https://pinboard.in/u:jm/b:9990e9fe0e8b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:canonical"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:launchpad"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:open-source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:apache"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:hosting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:projects"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:ubuntu"/>
	<rdf:li rdf:resource="https://pinboard.in/u:jm/t:agpl"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>