Author: brandonwilliams Date: Sat Sep 4 21:07:11 2010 New Revision: 992680
URL: http://svn.apache.org/viewvc?rev=992680&view=rev Log: Add missing comments/options to cassandra.yaml. Patch by brandonwilliams, reviewed by jbellis for CASSANDRA-1390 Modified: cassandra/trunk/conf/cassandra.yaml Modified: cassandra/trunk/conf/cassandra.yaml URL: http://svn.apache.org/viewvc/cassandra/trunk/conf/cassandra.yaml?rev=992680&r1=992679&r2=992680&view=diff ============================================================================== --- cassandra/trunk/conf/cassandra.yaml (original) +++ cassandra/trunk/conf/cassandra.yaml Sat Sep 4 21:07:11 2010 @@ -2,9 +2,22 @@ # See http://wiki.apache.org/cassandra/StorageConfiguration for # explanations of configuration directives. -# name of the cluster +# The name of the cluster. This is mainly used to prevent machines in +# one logical cluster from joining another. cluster_name: 'Test Cluster' +# If you are using an order-preserving partitioner and you know your key +# distribution, you can specify the token for this node to use. (Keys +# are sent to the node with the "closest" token, so distributing your +# tokens equally along the key distribution space will spread keys +# evenly across your cluster.) This setting is only checked the first +# time a node is started. + +# This can also be useful with RandomPartitioner to force equal spacing +# of tokens around the hash space, especially for clusters with a small +# number of nodes. +initial_token: + # Set to true to make new [non-seed] nodes automatically migrate data # to themselves from the pre-existing nodes in the cluster. Defaults # to false because you can only bootstrap N machines at a time from @@ -25,14 +38,35 @@ authority: org.apache.cassandra.auth.All # any IPartitioner may be used, including your own as long as it is on # the classpath. Out of the box, Cassandra provides # org.apache.cassandra.dht.RandomPartitioner +# org.apache.cassandra.dht.ByteOrderedPartitioner, # org.apache.cassandra.dht.OrderPreservingPartitioner, and # org.apache.cassandra.dht.CollatingOrderPreservingPartitioner. +# (CollatingOPP colates according to EN,US rules, not naive byte +# ordering. Use this as an example if you need locale-aware collation.) partitioner: org.apache.cassandra.dht.RandomPartitioner # directories where Cassandra should store data on disk. data_file_directories: - /var/lib/cassandra/data +# commit log +commitlog_directory: /var/lib/cassandra/commitlog + +# Size to allow commitlog to grow to before creating a new segment +commitlog_rotation_threshold_in_mb: 128 + +# commitlog_sync may be either "periodic" or "batch." +# When in batch mode, Cassandra won't ack writes until the commit log +# has been fsynced to disk. It will wait up to +# CommitLogSyncBatchWindowInMS milliseconds for other writes, before +# performing the sync. +commitlog_sync: periodic + +# the other option is "timed," where writes may be acked immediately +# and the CommitLog is simply synced every commitlog_sync_period_in_ms +# milliseconds. +commitlog_sync_period_in_ms: 10000 + # Addresses of hosts that are deemed contact points. # Cassandra nodes use this list of hosts to find each other and learn # the topology of the ring. You must change this if you are running @@ -90,6 +124,10 @@ thrift_framed_transport_size_in_mb: 15 # internal thrift overhead. thrift_max_message_length_in_mb: 16 +# Whether or not to take a snapshot before each compaction. Be +# careful using this option, since Cassandra won't clean up the +# snapshots for you. Mostly useful if you're paranoid when there +# is a data format change. snapshot_before_compaction: false # change this to increase the compaction thread's priority. In java, 1 is the @@ -111,28 +149,20 @@ memtable_throughput_in_mb: 64 # Number of objects in millions in the memtable before it is flushed memtable_operations_in_millions: 0.3 +# Add column indexes to a row after its contents reach this size. +# Increase if your column values are large, or if you have a very large +# number of columns. The competing causes are, Cassandra has to +# deserialize this much of the row to read a single column, so you want +# it to be small - at least if you do many partial-row reads - but all +# the index data is read for each access, so you don't want to generate +# that wastefully either. column_index_size_in_kb: 64 +# Size limit for rows being compacted in memory. Larger rows will spill +# over to disk and use a slower two-pass compaction process. A message +# will be logged specifying the row key. in_memory_compaction_limit_in_mb: 64 -# commit log -commitlog_directory: /var/lib/cassandra/commitlog - -# Size to allow commitlog to grow to before creating a new segment -commitlog_rotation_threshold_in_mb: 128 - -# commitlog_sync may be either "periodic" or "batch." -# When in batch mode, Cassandra won't ack writes until the commit log -# has been fsynced to disk. It will wait up to -# CommitLogSyncBatchWindowInMS milliseconds for other writes, before -# performing the sync. -commitlog_sync: periodic - -# the other option is "timed," where writes may be acked immediately -# and the CommitLog is simply synced every commitlog_sync_period_in_ms -# milliseconds. -commitlog_sync_period_in_ms: 10000 - # Time to wait for a reply from other nodes before failing the command rpc_timeout_in_ms: 10000