accumulo-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
Subject [2/2] accumulo git commit: Jekyll build from gh-pages:f30cc51
Date Thu, 23 Jun 2016 15:12:42 GMT
Jekyll build from gh-pages:f30cc51

Add a paragraph on the smaller keys for index blocks improvement


Branch: refs/heads/asf-site
Commit: 604500f884382a51c34da5bf831c7594b7d84307
Parents: 45d81df
Author: Josh Elser <>
Authored: Thu Jun 23 11:11:05 2016 -0400
Committer: Josh Elser <>
Committed: Thu Jun 23 11:11:40 2016 -0400

 feed.xml                 | 4 ++--
 release_notes/1.7.2.html | 6 +++++-
 2 files changed, 7 insertions(+), 3 deletions(-)
diff --git a/feed.xml b/feed.xml
index 61f86f0..9491b3d 100644
--- a/feed.xml
+++ b/feed.xml
@@ -6,8 +6,8 @@
     <atom:link href="" rel="self" type="application/rss+xml"/>
-    <pubDate>Thu, 23 Jun 2016 11:00:50 -0400</pubDate>
-    <lastBuildDate>Thu, 23 Jun 2016 11:00:50 -0400</lastBuildDate>
+    <pubDate>Thu, 23 Jun 2016 11:11:36 -0400</pubDate>
+    <lastBuildDate>Thu, 23 Jun 2016 11:11:36 -0400</lastBuildDate>
     <generator>Jekyll v3.0.5</generator>
diff --git a/release_notes/1.7.2.html b/release_notes/1.7.2.html
index c4d8fdc..168579a 100644
--- a/release_notes/1.7.2.html
+++ b/release_notes/1.7.2.html
@@ -205,10 +205,14 @@ upgrade to 1.7 should consider 1.7.2 as a starting point.</p>
 <p>An improvement was introduced to allow a max age before WAL files would be automatically
rolled. Without a max age, they could stay open for writing indefinitely, blocking the Hadoop
DataNode decomissioning process. For more information, see <a href="">ACCUMULO-4004</a>.</p>
-<h3 id="remove-copy-of-cached-rfile-index-blocks">Remove copy of cached RFile index
+<h3 id="remove-unnecessary-copy-of-cached-rfile-index-blocks">Remove unnecessary copy
of cached RFile index blocks</h3>
 <p>Accumulo maintains an cache for file blocks in-memory as a performance optimization.
This can be done safely because Accumulo RFiles are immutable, thus their blocks are also
immutable. There are two types of these blocks: index and data blocks. Index blocks refer
to the b-tree style index inside of each Accumulo RFile, while data blocks contain the sorted
Key-Value pairs. In previous versions, when Accumulo extracted an Index block from the in-memory
cache, it would copy the data. <a href="">ACCUMULO-4164</a>
removes this unnecessary copy as the contents are immutable and can be passed by reference.
Ensuring that the Index blocks are not copied when accessed from the cache is a big performance
gain at the file-access level.</p>
+<h3 id="analyze-key-length-to-avoid-choosing-large-keys-for-rfile-index-blocks">Analyze
Key-length to avoid choosing large Keys for RFile Index blocks</h3>
+<p>Accumulo’s RFile index blocks are made up of a Key which exists in the file and
points to that specific location in the corresponding RFile data block. Thus, the size of
the RFile index blocks is largely dominated by the size of the Keys which are used by the
index. <a href="">ACCUMULO-4314</a>
is an improvement which uses statistics on the length of the Keys in the Rfile to avoid choosing
Keys for the index whose length is greater than three standard deviations for the RFile. By
choosing smaller Keys for the index, Accumulo can access the RFile index faster and keep more
Index blocks cached in memory. Initial tests showed that with this change, the RFile index
size was nearly cut in half.</p>
 <h3 id="minor-performance-improvements">Minor performance improvements.</h3>
 <p>Tablet servers would previously always hsync at the start of a minor compaction,
causing delays in the write pipeline. These additional syncs were determined to provide no
additional durability guarantees and have been removed. See <a href="">ACCUMULO-4112</a>
for additional detail.</p>

View raw message