Author: matei
Date: Fri Jul 18 20:55:11 2014
New Revision: 1611801
URL: http://svn.apache.org/r1611801
Log:
tweak
Modified:
spark/faq.md
spark/site/faq.html
Modified: spark/faq.md
URL:
http://svn.apache.org/viewvc/spark/faq.md?rev=1611801&r1=1611800&r2=1611801&view=diff
==============================================================================
--- spark/faq.md (original)
+++ spark/faq.md Fri Jul 18 20:55:11 2014
@@ -23,7 +23,7 @@ streaming, interactive queries, and mach
<p class="answer">Spark supports Scala, Java and Python.</p>
<p class="question">How large a cluster can Spark scale to?</p>
-<p class="answer">We are aware of multiple deployments on over 1000 nodes.</p>
+<p class="answer">We have seen multiple deployments on over 1000 nodes.</p>
<p class="question">What happens when a cached dataset does not fit in
memory?</p>
<p class="answer">Spark can either spill it to disk or recompute the
partitions that don't fit in RAM each time they are requested. By default, it
uses recomputation, but you can set a dataset's <a
href="{{site.url}}docs/latest/scala-programming-guide.html#rdd-persistence">storage
level</a> to <code>MEMORY_AND_DISK</code> to avoid this. </p>
Modified: spark/site/faq.html
URL:
http://svn.apache.org/viewvc/spark/site/faq.html?rev=1611801&r1=1611800&r2=1611801&view=diff
==============================================================================
--- spark/site/faq.html (original)
+++ spark/site/faq.html Fri Jul 18 20:55:11 2014
@@ -174,7 +174,7 @@ streaming, interactive queries, and mach
<p class="answer">Spark supports Scala, Java and Python.</p>
<p class="question">How large a cluster can Spark scale to?</p>
-<p class="answer">We are aware of multiple deployments on over 1000 nodes.</p>
+<p class="answer">We have seen multiple deployments on over 1000 nodes.</p>
<p class="question">What happens when a cached dataset does not fit in
memory?</p>
<p class="answer">Spark can either spill it to disk or recompute the
partitions that don't fit in RAM each time they are requested. By default, it
uses recomputation, but you can set a dataset's <a
href="/docs/latest/scala-programming-guide.html#rdd-persistence">storage
level</a> to <code>MEMORY_AND_DISK</code> to avoid this. </p>
