upgrade to use cassandra 1.x and latest hector

config/src/main/resources/cassandra.yaml

@@ -21,21 +21,13 @@ cluster_name: 'Test Cluster'
 # a random token, which will lead to hot spots.
 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
-# an existing cluster of N, so if you are bringing up a cluster of
-# 10 machines with 3 seeds you would have to do it in stages.  Leaving
-# this off for the initial start simplifies that.
-auto_bootstrap: false
-
 # See http://wiki.apache.org/cassandra/HintedHandoff
 hinted_handoff_enabled: true
 # this defines the maximum amount of time a dead host will have hints
 # generated.  After it has been dead this long, hints will be dropped.
 max_hint_window_in_ms: 3600000 # one hour
-# Sleep this long after delivering each row or row fragment
-hinted_handoff_throttle_delay_in_ms: 50
+# Sleep this long after delivering each hint
+hinted_handoff_throttle_delay_in_ms: 1
 
 # authentication backend, implementing IAuthenticator; used to identify users
 authenticator: org.apache.cassandra.auth.AllowAllAuthenticator
@@ -74,26 +66,92 @@ data_file_directories:
 # commit log
 commitlog_directory: ./tmp/commitlog
 
+# Maximum size of the key cache in memory.
+#
+# Each key cache hit saves 1 seek and each row cache hit saves 2 seeks at the
+# minimum, sometimes more. The key cache is fairly tiny for the amount of
+# time it saves, so it's worthwhile to use it at large numbers.
+# The row cache saves even more time, but must store the whole values of
+# its rows, so it is extremely space-intensive. It's best to only use the
+# row cache if you have hot rows or static rows.
+#
+# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup.
+#
+# Default value is 2 (call hold > 200000 keys). Set to 0 to disable key cache.
+#key_cache_size_in_mb: 2
+
+# Duration in seconds after which Cassandra should
+# safe the keys cache. Caches are saved to saved_caches_directory as
+# specified in this configuration file.
+#
+# Saved caches greatly improve cold-start speeds, and is relatively cheap in
+# terms of I/O for the key cache. Row cache saving is much more expensive and
+# has limited use.
+#
+# Default is 14400 or 4 hours.
+#key_cache_save_period: 14400
+
+# Number of keys from the key cache to save
+# Disabled by default, meaning all keys are going to be saved
+# key_cache_keys_to_save: 100
+
+# Maximum size of the row cache in memory.
+# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup.
+#
+# Default value is 0, to disable row caching.
+#row_cache_size_in_mb: 0
+
+# Duration in seconds after which Cassandra should
+# safe the row cache. Caches are saved to saved_caches_directory as specified
+# in this configuration file.
+#
+# Saved caches greatly improve cold-start speeds, and is relatively cheap in
+# terms of I/O for the key cache. Row cache saving is much more expensive and
+# has limited use.
+#
+# Default is 0 to disable saving the row cache.
+#row_cache_save_period: 0
+
+# Number of keys from the row cache to save
+# Disabled by default, meaning all keys are going to be saved
+# row_cache_keys_to_save: 100
+
+# The provider for the row cache to use.
+#
+# Supported values are: ConcurrentLinkedHashCacheProvider, SerializingCacheProvider
+#
+# SerializingCacheProvider serialises the contents of the row and stores
+# it in native memory, i.e., off the JVM Heap. Serialized rows take
+# significantly less memory than "live" rows in the JVM, so you can cache
+# more rows in a given memory footprint.  And storing the cache off-heap
+# means you can use smaller heap sizes, reducing the impact of GC pauses.
+#
+# It is also valid to specify the fully-qualified class name to a class
+# that implements org.apache.cassandra.cache.IRowCacheProvider.
+#
+# Defaults to SerializingCacheProvider
+#row_cache_provider: SerializingCacheProvider
+
 # saved caches
 saved_caches_directory: ./tmp/saved_caches
 
-# 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
+# commitlog_sync_batch_window_in_ms milliseconds for other writes, before
 # performing the sync.
-commitlog_sync: periodic
-
+#
+# commitlog_sync: batch
+# commitlog_sync_batch_window_in_ms: 50
+#
 # the other option is "periodic" where writes may be acked immediately
 # and the CommitLog is simply synced every commitlog_sync_period_in_ms
 # milliseconds.
+commitlog_sync: periodic
 commitlog_sync_period_in_ms: 10000
 
-# any class that implements the SeedProvider interface and has a constructor that takes a Map<String, String> of
-# parameters will do.
+# any class that implements the SeedProvider interface and has a
+# constructor that takes a Map<String, String> of parameters will do.
 seed_provider:
     # Addresses of hosts that are deemed contact points. 
     # Cassandra nodes use this list of hosts to find each other and learn
@@ -102,6 +160,7 @@ seed_provider:
     - class_name: org.apache.cassandra.locator.SimpleSeedProvider
       parameters:
           # seeds is actually a comma-delimited list of addresses.
+          # Ex: "<ip1>,<ip2>,<ip3>"
           - seeds: "127.0.0.1"
 
 # emergency pressure valve: each time heap usage after a full (CMS)
@@ -142,12 +201,16 @@ concurrent_reads: 32
 concurrent_writes: 32
 
 # Total memory to use for memtables.  Cassandra will flush the largest
-# memtable when this much memory is used.  Prefer using this to
-# the older, per-ColumnFamily memtable flush thresholds.
+# memtable when this much memory is used.
 # If omitted, Cassandra will set it to 1/3 of the heap.
-# If set to 0, only the old flush thresholds are used.
 # memtable_total_space_in_mb: 2048
 
+# Total space to use for commitlogs. 
+# If space gets above this value (it will round up to the next nearest
+# segment multiple), Cassandra will flush every dirty CF in the oldest
+# segment and remove it.
+# commitlog_total_space_in_mb: 4096
+
 # This sets the amount of memtable flush writer threads.  These will
 # be blocked by disk io, and each one will hold a memtable in memory
 # while blocked. If you have a large heap and many data directories,
@@ -167,6 +230,10 @@ sliced_buffer_size_in_kb: 64
 # TCP port, for commands and data
 storage_port: 7000
 
+# SSL port, for encrypted communication.  Unused unless enabled in
+# encryption_options
+ssl_storage_port: 7001
+
 # Address to bind to and tell other Cassandra nodes to connect to. You
 # _must_ change this if you want multiple nodes to be able to
 # communicate!
@@ -179,29 +246,53 @@ storage_port: 7000
 # Setting this to 0.0.0.0 is always wrong.
 listen_address: localhost
 
+# Address to broadcast to other Cassandra nodes
+# Leaving this blank will set it to the same value as listen_address
+# broadcast_address: 1.2.3.4
+
 # The address to bind the Thrift RPC service to -- clients connect
 # here. Unlike ListenAddress above, you *can* specify 0.0.0.0 here if
 # you want Thrift to listen on all interfaces.
 # 
 # Leaving this blank has the same effect it does for ListenAddress,
 # (i.e. it will be based on the configured hostname of the node).
-rpc_address: 0.0.0.0
+rpc_address: localhost
 # port for Thrift to listen for clients on
 rpc_port: 9160
 
 # enable or disable keepalive on rpc connections
 rpc_keepalive: true
 
-# Cassandra uses thread-per-client for client RPC.  This can
-# be expensive in memory used for thread stack for a large
-# enough number of clients.  (Hence, connection pooling is
-# very, very strongly recommended.)
-# 
+# Cassandra provides three options for the RPC Server:
+#
+# sync  -> One connection per thread in the rpc pool (see below).
+#          For a very large number of clients, memory will be your limiting
+#          factor; on a 64 bit JVM, 128KB is the minimum stack size per thread.
+#          Connection pooling is very, very strongly recommended.
+#
+# async -> Nonblocking server implementation with one thread to serve 
+#          rpc connections.  This is not recommended for high throughput use
+#          cases. Async has been tested to be about 50% slower than sync
+#          or hsha and is deprecated: it will be removed in the next major release.
+#
+# hsha  -> Stands for "half synchronous, half asynchronous." The rpc thread pool 
+#          (see below) is used to manage requests, but the threads are multiplexed
+#          across the different clients.
+#
+# The default is sync because on Windows hsha is about 30% slower.  On Linux,
+# sync/hsha performance is about the same, with hsha of course using less memory.
+rpc_server_type: sync
+
 # Uncomment rpc_min|max|thread to set request pool size.
-# You would primarily set max as a safeguard against misbehaved
-# clients; if you do hit the max, Cassandra will block until
-# one disconnects before accepting more.  The defaults are
-# min of 16 and max unlimited.
+# You would primarily set max for the sync server to safeguard against
+# misbehaved clients; if you do hit the max, Cassandra will block until one
+# disconnects before accepting more.  The defaults for sync are min of 16 and max
+# unlimited.
+# 
+# For the Hsha server, the min and max both default to quadruple the number of
+# CPU cores.
+#
+# This configuration is ignored by the async server.
 #
 # rpc_min_threads: 16
 # rpc_max_threads: 2048
@@ -231,10 +322,6 @@ incremental_backups: false
 # is a data format change.
 snapshot_before_compaction: false
 
-# change this to increase the compaction thread's priority.  In java, 1 is the
-# lowest priority and that is our default.
-# compaction_thread_priority: 1
-
 # 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
@@ -249,28 +336,48 @@ column_index_size_in_kb: 64
 # will be logged specifying the row key.
 in_memory_compaction_limit_in_mb: 64
 
-# Number of compaction threads. This default to the number of processors,
-# enabling multiple compactions to execute at once. Using more than one
-# thread is highly recommended to preserve read performance in a mixed
-# read/write workload as this avoids sstables from accumulating during long
-# running compactions. The default is usually fine and if you experience
-# problems with compaction running too slowly or too fast, you should look at
+# Number of simultaneous compactions to allow, NOT including
+# validation "compactions" for anti-entropy repair.  Simultaneous
+# compactions can help preserve read performance in a mixed read/write
+# workload, by mitigating the tendency of small sstables to accumulate
+# during a single long running compactions. The default is usually
+# fine and if you experience problems with compaction running too
+# slowly or too fast, you should look at
 # compaction_throughput_mb_per_sec first.
-# Uncomment to make compaction mono-threaded.
+#
+# This setting has no effect on LeveledCompactionStrategy.
+#
+# concurrent_compactors defaults to the number of cores.
+# Uncomment to make compaction mono-threaded, the pre-0.8 default.
 #concurrent_compactors: 1
 
+# Multi-threaded compaction. When enabled, each compaction will use
+# up to one thread per core, plus one thread per sstable being merged.
+# This is usually only useful for SSD-based hardware: otherwise, 
+# your concern is usually to get compaction to do LESS i/o (see:
+# compaction_throughput_mb_per_sec), not more.
+multithreaded_compaction: false
+
 # Throttles compaction to the given total throughput across the entire
 # system. The faster you insert data, the faster you need to compact in
 # order to keep the sstable count down, but in general, setting this to
 # 16 to 32 times the rate you are inserting data is more than sufficient.
-# Setting this to 0 disables throttling.
+# Setting this to 0 disables throttling. Note that this account for all types
+# of compaction, including validation compaction.
 compaction_throughput_mb_per_sec: 16
 
 # Track cached row keys during compaction, and re-cache their new
 # positions in the compacted sstable.  Disable if you use really large
 # key caches.
 compaction_preheat_key_cache: true
 
+# Throttles all outbound streaming file transfers on this node to the
+# given total throughput in Mbps. This is necessary because Cassandra does
+# mostly sequential IO when streaming data during bootstrap or repair, which
+# can lead to saturating the network connection and degrading rpc performance.
+# When unset, the default is 400 Mbps or 50 MB/s.
+# stream_throughput_outbound_megabits_per_sec: 400
+
 # Time to wait for a reply from other nodes before failing the command 
 rpc_timeout_in_ms: 10000
 
@@ -294,11 +401,6 @@ rpc_timeout_in_ms: 10000
 #    explicitly configured in cassandra-topology.properties.
 endpoint_snitch: org.apache.cassandra.locator.SimpleSnitch
 
-# dynamic_snitch -- This boolean controls whether the above snitch is
-# wrapped with a dynamic snitch, which will monitor read latencies
-# and avoid reading from hosts that have slowed (due to compaction,
-# for instance)
-dynamic_snitch: true
 # controls how often to perform the more expensive part of host score
 # calculation
 dynamic_snitch_update_interval_in_ms: 100 
@@ -312,7 +414,7 @@ dynamic_snitch_reset_interval_in_ms: 600000
 # expressed as a double which represents a percentage.  Thus, a value of
 # 0.2 means Cassandra would continue to prefer the static snitch values
 # until the pinned host was 20% worse than the fastest.
-dynamic_snitch_badness_threshold: 0.0
+dynamic_snitch_badness_threshold: 0.1
 
 # request_scheduler -- Set this to a class that implements
 # RequestScheduler, which will schedule incoming client requests
@@ -354,24 +456,40 @@ request_scheduler: org.apache.cassandra.scheduler.NoScheduler
 # the request scheduling. Currently the only valid option is keyspace.
 # request_scheduler_id: keyspace
 
-# The Index Interval determines how large the sampling of row keys
-#  is for a given SSTable. The larger the sampling, the more effective
-#  the index is at the cost of space.
+# index_interval controls the sampling of entries from the primrary
+# row index in terms of space versus time.  The larger the interval,
+# the smaller and less effective the sampling will be.  In technicial
+# terms, the interval coresponds to the number of index entries that
+# are skipped between taking each sample.  All the sampled entries
+# must fit in memory.  Generally, a value between 128 and 512 here
+# coupled with a large key cache size on CFs results in the best trade
+# offs.  This value is not often changed, however if you have many
+# very small rows (many to an OS page), then increasing this will
+# often lower memory usage without a impact on performance.
 index_interval: 128
 
 # Enable or disable inter-node encryption
 # Default settings are TLS v1, RSA 1024-bit keys (it is imperative that
 # users generate their own keys) TLS_RSA_WITH_AES_128_CBC_SHA as the cipher
 # suite for authentication, key exchange and encryption of the actual data transfers.
 # NOTE: No custom encryption options are enabled at the moment
-# The available internode options are : all, none
+# The available internode options are : all, none, dc, rack
+#
+# If set to dc cassandra will encrypt the traffic between the DCs
+# If set to rack cassandra will encrypt the traffic between the racks
 #
 # The passwords used in these options must match the passwords used when generating
 # the keystore and truststore.  For instructions on generating these files, see:
 # http://download.oracle.com/javase/6/docs/technotes/guides/security/jsse/JSSERefGuide.html#CreateKeystore
+#
 encryption_options:
     internode_encryption: none
     keystore: conf/.keystore
     keystore_password: cassandra
     truststore: conf/.truststore
     truststore_password: cassandra
+    # More advanced defaults below:
+    # protocol: TLS
+    # algorithm: SunX509
+    # store_type: JKS
+    # cipher_suites: [TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA]