Author: jbellis
Date: Fri Jan 14 19:13:44 2011
New Revision: 1059124
URL: http://svn.apache.org/viewvc?rev=1059124&view=rev
Log:
update concurrent_reads default setting + comments
patch by Stu Hood; reviewed by jbellis for CASSANDRA-1972
Modified:
cassandra/branches/cassandra-0.7/conf/cassandra.yaml
Modified: cassandra/branches/cassandra-0.7/conf/cassandra.yaml
URL:
http://svn.apache.org/viewvc/cassandra/branches/cassandra-0.7/conf/cassandra.yaml?rev=1059124&r1=1059123&r2=1059124&view=diff
==============================================================================
--- cassandra/branches/cassandra-0.7/conf/cassandra.yaml (original)
+++ cassandra/branches/cassandra-0.7/conf/cassandra.yaml Fri Jan 14 19:13:44
2011
@@ -104,12 +104,16 @@ seeds:
# non-mmapped i/o.)
disk_access_mode: auto
-# Unlike most systems, in Cassandra writes are faster than reads, so
-# you can afford more of those in parallel. A good rule of thumb is 2
-# concurrent reads per processor core. Increase ConcurrentWrites to
-# the number of clients writing at once if you enable CommitLogSync +
-# CommitLogSyncDelay. -->
-concurrent_reads: 8
+# For workloads with more data than can fit in memory, Cassandra's
+# bottleneck will be reads that need to fetch data from
+# disk. "concurrent_reads" should be set to (16 * number_of_drives) in
+# order to allow the operations to enqueue low enough in the stack
+# that the OS and drives can reorder them.
+#
+# On the other hand, since writes are almost never IO bound, the ideal
+# number of "concurrent_writes" is dependent on the number of cores in
+# your system; (8 * number_of_cores) is a good rule of thumb.
+concurrent_reads: 32
concurrent_writes: 32
# This sets the amount of memtable flush writer threads. These will
