redis集群搭建
docker安装redis
dockerfile
FROM ruby:2.5-alpine
RUN sed -i 's/dl-cdn.alpinelinux.org/mirrors.aliyun.com/g' /etc/apk/repositories \
&& apk add gcc g++ libc-dev wget vim openssl-dev make linux-headers bash \
&& rm -rf /var/cache/apk/*
RUN wget https://rubygems.org/downloads/redis-4.0.2.gem && gem install -l ./redis-4.0.2.gem \
&& rm -f redis-4.0.2.gem
#通过选择更小的镜像,删除不必要文件清理不必要的安装缓存,从而瘦身镜像
#创建相关目录能够看到日志信息跟数据跟配置文件
RUN mkdir -p /usr/src/redis \
&& mkdir -p /usr/src/redis/data \
&& mkdir -p /usr/src/redis/conf \
&& mkdir -p /usr/src/sh \
&& mkdir -p /usr/src/redis/log
RUN wget -O /usr/src/redis/redis-4.0.11.tar.gz "http://download.redis.io/releases/redis-4.0.11.tar.gz" \
&& tar -xzf /usr/src/redis/redis-4.0.11.tar.gz -C /usr/src/redis \
&& cp /usr/src/redis/redis-4.0.11/src/redis-trib.rb /usr/src/redis/ \
&& rm -rf /usr/src/redis/redis-4.0.11.tar.tgz
RUN cd /usr/src/redis/redis-4.0.11 && make && make PREFIX=/usr/local/redis install \
&& ln -s /usr/local/redis/bin/* /usr/local/bin/ && rm -rf /usr/src/redis/redis-4.0.11
COPY ./redis/sh/cluster.sh /usr/src/sh
COPY ./redis/sh/redis-trib.rb /usr/src/sh/redis-trib.rb
RUN chmod +x /usr/src/sh/cluster.sh && chmod +x /usr/src/sh/redis-trib.rb
进入dockerfile所在目录执行build
docker build -t redis-cluster .
redis.conf
# Redis configuration file example.
#
# Note that in order to read the configuration file, Redis must be
# started with the file path as first argument:
#
# ./redis-server /path/to/redis.conf
# Note on units: when memory size is needed, it is possible to specify
# it in the usual form of 1k 5GB 4M and so forth:
#
# 1k => 1000 bytes
# 1kb => 1024 bytes
# 1m => 1000000 bytes
# 1mb => 1024*1024 bytes
# 1g => 1000000000 bytes
# 1gb => 1024*1024*1024 bytes
#
# units are case insensitive so 1GB 1Gb 1gB are all the same.
################################## INCLUDES ###################################
# Include one or more other config files here. This is useful if you
# have a standard template that goes to all Redis servers but also need
# to customize a few per-server settings. Include files can include
# other files, so use this wisely.
#
# Notice option "include" won't be rewritten by command "CONFIG REWRITE"
# from admin or Redis Sentinel. Since Redis always uses the last processed
# line as value of a configuration directive, you'd better put includes
# at the beginning of this file to avoid overwriting config change at runtime.
#
# If instead you are interested in using includes to override configuration
# options, it is better to use include as the last line.
#
# include /path/to/local.conf
# include /path/to/other.conf
################################## NETWORK #####################################
# By default, if no "bind" configuration directive is specified, Redis listens
# for connections from all the network interfaces available on the server.
# It is possible to listen to just one or multiple selected interfaces using
# the "bind" configuration directive, followed by one or more IP addresses.
#
# Examples:
#
# bind 192.168.1.100 10.0.0.1
# bind 127.0.0.1 ::1
#
# ~~~ WARNING ~~~ If the computer running Redis is directly exposed to the
# internet, binding to all the interfaces is dangerous and will expose the
# instance to everybody on the internet. So by default we uncomment the
# following bind directive, that will force Redis to listen only into
# the IPv4 lookback interface address (this means Redis will be able to
# accept connections only from clients running into the same computer it
# is running).
#
# IF YOU ARE SURE YOU WANT YOUR INSTANCE TO LISTEN TO ALL THE INTERFACES
# JUST COMMENT THE FOLLOWING LINE.
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
bind 0.0.0.0
# Protected mode is a layer of security protection, in order to avoid that
# Redis instances left open on the internet are accessed and exploited.
#
# When protected mode is on and if:
#
# 1) The server is not binding explicitly to a set of addresses using the
# "bind" directive.
# 2) No password is configured.
#
# The server only accepts connections from clients connecting from the
# IPv4 and IPv6 loopback addresses 127.0.0.1 and ::1, and from Unix domain
# sockets.
#
# By default protected mode is enabled. You should disable it only if
# you are sure you want clients from other hosts to connect to Redis
# even if no authentication is configured, nor a specific set of interfaces
# are explicitly listed using the "bind" directive.
protected-mode no
# Accept connections on the specified port, default is 6379 (IANA #815344).
# If port 0 is specified Redis will not listen on a TCP socket.
port 6379
# TCP listen() backlog.
#
# In high requests-per-second environments you need an high backlog in order
# to avoid slow clients connections issues. Note that the Linux kernel
# will silently truncate it to the value of /proc/sys/net/core/somaxconn so
# make sure to raise both the value of somaxconn and tcp_max_syn_backlog
# in order to get the desired effect.
tcp-backlog 511
# Unix socket.
#
# Specify the path for the Unix socket that will be used to listen for
# incoming connections. There is no default, so Redis will not listen
# on a unix socket when not specified.
#
# unixsocket /tmp/redis.sock
# unixsocketperm 700
# Close the connection after a client is idle for N seconds (0 to disable)
timeout 0
# TCP keepalive.
#
# If non-zero, use SO_KEEPALIVE to send TCP ACKs to clients in absence
# of communication. This is useful for two reasons:
#
# 1) Detect dead peers.
# 2) Take the connection alive from the point of view of network
# equipment in the middle.
#
# On Linux, the specified value (in seconds) is the period used to send ACKs.
# Note that to close the connection the double of the time is needed.
# On other kernels the period depends on the kernel configuration.
#
# A reasonable value for this option is 300 seconds, which is the new
# Redis default starting with Redis 3.2.1.
tcp-keepalive 300
################################# GENERAL #####################################
# By default Redis does not run as a daemon. Use 'yes' if you need it.
# Note that Redis will write a pid file in /var/run/redis.pid when daemonized.
daemonize no
# If you run Redis from upstart or systemd, Redis can interact with your
# supervision tree. Options:
# supervised no - no supervision interaction
# supervised upstart - signal upstart by putting Redis into SIGSTOP mode
# supervised systemd - signal systemd by writing READY=1 to $NOTIFY_SOCKET
# supervised auto - detect upstart or systemd method based on
# UPSTART_JOB or NOTIFY_SOCKET environment variables
# Note: these supervision methods only signal "process is ready."
# They do not enable continuous liveness pings back to your supervisor.
supervised no
# If a pid file is specified, Redis writes it where specified at startup
# and removes it at exit.
#
# When the server runs non daemonized, no pid file is created if none is
# specified in the configuration. When the server is daemonized, the pid file
# is used even if not specified, defaulting to "/var/run/redis.pid".
#
# Creating a pid file is best effort: if Redis is not able to create it
# nothing bad happens, the server will start and run normally.
pidfile "/var/run/redis_6379.pid"
# Specify the server verbosity level.
# This can be one of:
# debug (a lot of information, useful for development/testing)
# verbose (many rarely useful info, but not a mess like the debug level)
# notice (moderately verbose, what you want in production probably)
# warning (only very important / critical messages are logged)
loglevel notice
# Specify the log file name. Also the empty string can be used to force
# Redis to log on the standard output. Note that if you use standard
# output for logging but daemonize, logs will be sent to /dev/null
logfile "/usr/src/redis/log/redis.log"
# To enable logging to the system logger, just set 'syslog-enabled' to yes,
# and optionally update the other syslog parameters to suit your needs.
# syslog-enabled no
# Specify the syslog identity.
# syslog-ident redis
# Specify the syslog facility. Must be USER or between LOCAL0-LOCAL7.
# syslog-facility local0
# Set the number of databases. The default database is DB 0, you can select
# a different one on a per-connection basis using SELECT <dbid> where
# dbid is a number between 0 and 'databases'-1
databases 16
################################ SNAPSHOTTING ################################
#
# Save the DB on disk:
#
# save <seconds> <changes>
#
# Will save the DB if both the given number of seconds and the given
# number of write operations against the DB occurred.
#
# In the example below the behaviour will be to save:
# after 900 sec (15 min) if at least 1 key changed
# after 300 sec (5 min) if at least 10 keys changed
# after 60 sec if at least 10000 keys changed
#
# Note: you can disable saving completely by commenting out all "save" lines.
#
# It is also possible to remove all the previously configured save
# points by adding a save directive with a single empty string argument
# like in the following example:
#
# save ""
save 900 1
save 300 10
save 60 10000
# By default Redis will stop accepting writes if RDB snapshots are enabled
# (at least one save point) and the latest background save failed.
# This will make the user aware (in a hard way) that data is not persisting
# on disk properly, otherwise chances are that no one will notice and some
# disaster will happen.
#
# If the background saving process will start working again Redis will
# automatically allow writes again.
#
# However if you have setup your proper monitoring of the Redis server
# and persistence, you may want to disable this feature so that Redis will
# continue to work as usual even if there are problems with disk,
# permissions, and so forth.
stop-writes-on-bgsave-error yes
# Compress string objects using LZF when dump .rdb databases?
# For default that's set to 'yes' as it's almost always a win.
# If you want to save some CPU in the saving child set it to 'no' but
# the dataset will likely be bigger if you have compressible values or keys.
rdbcompression yes
# Since version 5 of RDB a CRC64 checksum is placed at the end of the file.
# This makes the format more resistant to corruption but there is a performance
# hit to pay (around 10%) when saving and loading RDB files, so you can disable it
# for maximum performances.
#
# RDB files created with checksum disabled have a checksum of zero that will
# tell the loading code to skip the check.
rdbchecksum yes
# The filename where to dump the DB
dbfilename "dump.rdb"
# The working directory.
#
# The DB will be written inside this directory, with the filename specified
# above using the 'dbfilename' configuration directive.
#
# The Append Only File will also be created inside this directory.
#
# Note that you must specify a directory here, not a file name.
dir "/usr/src/redis/data"
################################# REPLICATION #################################
# Master-Slave replication. Use slaveof to make a Redis instance a copy of
# another Redis server. A few things to understand ASAP about Redis replication.
#
# 1) Redis replication is asynchronous, but you can configure a master to
# stop accepting writes if it appears to be not connected with at least
# a given number of slaves.
# 2) Redis slaves are able to perform a partial resynchronization with the
# master if the replication link is lost for a relatively small amount of
# time. You may want to configure the replication backlog size (see the next
# sections of this file) with a sensible value depending on your needs.
# 3) Replication is automatic and does not need user intervention. After a
# network partition slaves automatically try to reconnect to masters
# and resynchronize with them.
#
# slaveof <masterip> <masterport>
# If the master is password protected (using the "requirepass" configuration
# directive below) it is possible to tell the slave to authenticate before
# starting the replication synchronization process, otherwise the master will
# refuse the slave request.
#
masterauth sixstar
# When a slave loses its connection with the master, or when the replication
# is still in progress, the slave can act in two different ways:
#
# 1) if slave-serve-stale-data is set to 'yes' (the default) the slave will
# still reply to client requests, possibly with out of date data, or the
# data set may just be empty if this is the first synchronization.
#
# 2) if slave-serve-stale-data is set to 'no' the slave will reply with
# an error "SYNC with master in progress" to all the kind of commands
# but to INFO and SLAVEOF.
#
slave-serve-stale-data yes
# You can configure a slave instance to accept writes or not. Writing against
# a slave instance may be useful to store some ephemeral data (because data
# written on a slave will be easily deleted after resync with the master) but
# may also cause problems if clients are writing to it because of a
# misconfiguration.
#
# Since Redis 2.6 by default slaves are read-only.
#
# Note: read only slaves are not designed to be exposed to untrusted clients
# on the internet. It's just a protection layer against misuse of the instance.
# Still a read only slave exports by default all the administrative commands
# such as CONFIG, DEBUG, and so forth. To a limited extent you can improve
# security of read only slaves using 'rename-command' to shadow all the
# administrative / dangerous commands.
slave-read-only yes
# Replication SYNC strategy: disk or socket.
#
# -------------------------------------------------------
# WARNING: DISKLESS REPLICATION IS EXPERIMENTAL CURRENTLY
# -------------------------------------------------------
#
# New slaves and reconnecting slaves that are not able to continue the replication
# process just receiving differences, need to do what is called a "full
# synchronization". An RDB file is transmitted from the master to the slaves.
# The transmission can happen in two different ways:
#
# 1) Disk-backed: The Redis master creates a new process that writes the RDB
# file on disk. Later the file is transferred by the parent
# process to the slaves incrementally.
# 2) Diskless: The Redis master creates a new process that directly writes the
# RDB file to slave sockets, without touching the disk at all.
#
# With disk-backed replication, while the RDB file is generated, more slaves
# can be queued and served with the RDB file as soon as the current child producing
# the RDB file finishes its work. With diskless replication instead once
# the transfer starts, new slaves arriving will be queued and a new transfer
# will start when the current one terminates.
#
# When diskless replication is used, the master waits a configurable amount of
# time (in seconds) before starting the transfer in the hope that multiple slaves
# will arrive and the transfer can be parallelized.
#
# With slow disks and fast (large bandwidth) networks, diskless replication
# works better.
repl-diskless-sync no
# When diskless replication is enabled, it is possible to configure the delay
# the server waits in order to spawn the child that transfers the RDB via socket
# to the slaves.
#
# This is important since once the transfer starts, it is not possible to serve
# new slaves arriving, that will be queued for the next RDB transfer, so the server
# waits a delay in order to let more slaves arrive.
#
# The delay is specified in seconds, and by default is 5 seconds. To disable
# it entirely just set it to 0 seconds and the transfer will start ASAP.
repl-diskless-sync-delay 5
# Slaves send PINGs to server in a predefined interval. It's possible to change
# this interval with the repl_ping_slave_period option. The default value is 10
# seconds.
#
# repl-ping-slave-period 10
# The following option sets the replication timeout for:
#
# 1) Bulk transfer I/O during SYNC, from the point of view of slave.
# 2) Master timeout from the point of view of slaves (data, pings).
# 3) Slave timeout from the point of view of masters (REPLCONF ACK pings).
#
# It is important to make sure that this value is greater than the value
# specified for repl-ping-slave-period otherwise a timeout will be detected
# every time there is low traffic between the master and the slave.
#
# repl-timeout 60
# Disable TCP_NODELAY on the slave socket after SYNC?
#
# If you select "yes" Redis will use a smaller number of TCP packets and
# less bandwidth to send data to slaves. But this can add a delay for
# the data to appear on the slave side, up to 40 milliseconds with
# Linux kernels using a default configuration.
#
# If you select "no" the delay for data to appear on the slave side will
# be reduced but more bandwidth will be used for replication.
#
# By default we optimize for low latency, but in very high traffic conditions
# or when the master and slaves are many hops away, turning this to "yes" may
# be a good idea.
repl-disable-tcp-nodelay no
# Set the replication backlog size. The backlog is a buffer that accumulates
# slave data when slaves are disconnected for some time, so that when a slave
# wants to reconnect again, often a full resync is not needed, but a partial
# resync is enough, just passing the portion of data the slave missed while
# disconnected.
#
# The bigger the replication backlog, the longer the time the slave can be
# disconnected and later be able to perform a partial resynchronization.
#
# The backlog is only allocated once there is at least a slave connected.
# repl-backlog-size 1mb
# After a master has no longer connected slaves for some time, the backlog
# will be freed. The following option configures the amount of seconds that
# need to elapse, starting from the time the last slave disconnected, for
# the backlog buffer to be freed.
#
# A value of 0 means to never release the backlog.
#
# repl-backlog-ttl 3600
# The slave priority is an integer number published by Redis in the INFO output.
# It is used by Redis Sentinel in order to select a slave to promote into a
# master if the master is no longer working correctly.
#
# A slave with a low priority number is considered better for promotion, so
# for instance if there are three slaves with priority 10, 100, 25 Sentinel will
# pick the one with priority 10, that is the lowest.
#
# However a special priority of 0 marks the slave as not able to perform the
# role of master, so a slave with priority of 0 will never be selected by
# Redis Sentinel for promotion.
#
# By default the priority is 100.
slave-priority 100
# It is possible for a master to stop accepting writes if there are less than
# N slaves connected, having a lag less or equal than M seconds.
#
# The N slaves need to be in "online" state.
#
# The lag in seconds, that must be <= the specified value, is calculated from
# the last ping received from the slave, that is usually sent every second.
#
# This option does not GUARANTEE that N replicas will accept the write, but
# will limit the window of exposure for lost writes in case not enough slaves
# are available, to the specified number of seconds.
#
# For example to require at least 3 slaves with a lag <= 10 seconds use:
#
# min-slaves-to-write 3
# min-slaves-max-lag 10
#
# Setting one or the other to 0 disables the feature.
#
# By default min-slaves-to-write is set to 0 (feature disabled) and
# min-slaves-max-lag is set to 10.
# A Redis master is able to list the address and port of the attached
# slaves in different ways. For example the "INFO replication" section
# offers this information, which is used, among other tools, by
# Redis Sentinel in order to discover slave instances.
# Another place where this info is available is in the output of the
# "ROLE" command of a masteer.
#
# The listed IP and address normally reported by a slave is obtained
# in the following way:
#
# IP: The address is auto detected by checking the peer address
# of the socket used by the slave to connect with the master.
#
# Port: The port is communicated by the slave during the replication
# handshake, and is normally the port that the slave is using to
# list for connections.
#
# However when port forwarding or Network Address Translation (NAT) is
# used, the slave may be actually reachable via different IP and port
# pairs. The following two options can be used by a slave in order to
# report to its master a specific set of IP and port, so that both INFO
# and ROLE will report those values.
#
# There is no need to use both the options if you need to override just
# the port or the IP address.
#
# slave-announce-ip 5.5.5.5
# slave-announce-port 1234
################################## SECURITY ###################################
# Require clients to issue AUTH <PASSWORD> before processing any other
# commands. This might be useful in environments in which you do not trust
# others with access to the host running redis-server.
#
# This should stay commented out for backward compatibility and because most
# people do not need auth (e.g. they run their own servers).
#
# Warning: since Redis is pretty fast an outside user can try up to
# 150k passwords per second against a good box. This means that you should
# use a very strong password otherwise it will be very easy to break.
#
requirepass sixstar
# Command renaming.
#
# It is possible to change the name of dangerous commands in a shared
# environment. For instance the CONFIG command may be renamed into something
# hard to guess so that it will still be available for internal-use tools
# but not available for general clients.
#
# Example:
#
# rename-command CONFIG b840fc02d524045429941cc15f59e41cb7be6c52
#
# It is also possible to completely kill a command by renaming it into
# an empty string:
#
# rename-command CONFIG ""
#
# Please note that changing the name of commands that are logged into the
# AOF file or transmitted to slaves may cause problems.
################################### LIMITS ####################################
# Set the max number of connected clients at the same time. By default
# this limit is set to 10000 clients, however if the Redis server is not
# able to configure the process file limit to allow for the specified limit
# the max number of allowed clients is set to the current file limit
# minus 32 (as Redis reserves a few file descriptors for internal uses).
#
# Once the limit is reached Redis will close all the new connections sending
# an error 'max number of clients reached'.
#
# maxclients 10000
# Don't use more memory than the specified amount of bytes.
# When the memory limit is reached Redis will try to remove keys
# according to the eviction policy selected (see maxmemory-policy).
#
# If Redis can't remove keys according to the policy, or if the policy is
# set to 'noeviction', Redis will start to reply with errors to commands
# that would use more memory, like SET, LPUSH, and so on, and will continue
# to reply to read-only commands like GET.
#
# This option is usually useful when using Redis as an LRU cache, or to set
# a hard memory limit for an instance (using the 'noeviction' policy).
#
# WARNING: If you have slaves attached to an instance with maxmemory on,
# the size of the output buffers needed to feed the slaves are subtracted
# from the used memory count, so that network problems / resyncs will
# not trigger a loop where keys are evicted, and in turn the output
# buffer of slaves is full with DELs of keys evicted triggering the deletion
# of more keys, and so forth until the database is completely emptied.
#
# In short... if you have slaves attached it is suggested that you set a lower
# limit for maxmemory so that there is some free RAM on the system for slave
# output buffers (but this is not needed if the policy is 'noeviction').
#maxmemory 100000
# MAXMEMORY POLICY: how Redis will select what to remove when maxmemory
# is reached. You can select among five behaviors:
#
# volatile-lru -> remove the key with an expire set using an LRU algorithm
# allkeys-lru -> remove any key according to the LRU algorithm
# volatile-random -> remove a random key with an expire set
# allkeys-random -> remove a random key, any key
# volatile-ttl -> remove the key with the nearest expire time (minor TTL)
# noeviction -> don't expire at all, just return an error on write operations
#
# Note: with any of the above policies, Redis will return an error on write
# operations, when there are no suitable keys for eviction.
#
# At the date of writing these commands are: set setnx setex append
# incr decr rpush lpush rpushx lpushx linsert lset rpoplpush sadd
# sinter sinterstore sunion sunionstore sdiff sdiffstore zadd zincrby
# zunionstore zinterstore hset hsetnx hmset hincrby incrby decrby
# getset mset msetnx exec sort
#
# The default is:
#
maxmemory-policy noeviction
# LRU and minimal TTL algorithms are not precise algorithms but approximated
# algorithms (in order to save memory), so you can tune it for speed or
# accuracy. For default Redis will check five keys and pick the one that was
# used less recently, you can change the sample size using the following
# configuration directive.
#
# The default of 5 produces good enough results. 10 Approximates very closely
# true LRU but costs a bit more CPU. 3 is very fast but not very accurate.
#
# maxmemory-samples 5
############################## APPEND ONLY MODE ###############################
# By default Redis asynchronously dumps the dataset on disk. This mode is
# good enough in many applications, but an issue with the Redis process or
# a power outage may result into a few minutes of writes lost (depending on
# the configured save points).
#
# The Append Only File is an alternative persistence mode that provides
# much better durability. For instance using the default data fsync policy
# (see later in the config file) Redis can lose just one second of writes in a
# dramatic event like a server power outage, or a single write if something
# wrong with the Redis process itself happens, but the operating system is
# still running correctly.
#
# AOF and RDB persistence can be enabled at the same time without problems.
# If the AOF is enabled on startup Redis will load the AOF, that is the file
# with the better durability guarantees.
#
# Please check http://redis.io/topics/persistence for more information.
appendonly yes
# The name of the append only file (default: "appendonly.aof")
appendfilename "appen.aof"
# The fsync() call tells the Operating System to actually write data on disk
# instead of waiting for more data in the output buffer. Some OS will really flush
# data on disk, some other OS will just try to do it ASAP.
#
# Redis supports three different modes:
#
# no: don't fsync, just let the OS flush the data when it wants. Faster.
# always: fsync after every write to the append only log. Slow, Safest.
# everysec: fsync only one time every second. Compromise.
#
# The default is "everysec", as that's usually the right compromise between
# speed and data safety. It's up to you to understand if you can relax this to
# "no" that will let the operating system flush the output buffer when
# it wants, for better performances (but if you can live with the idea of
# some data loss consider the default persistence mode that's snapshotting),
# or on the contrary, use "always" that's very slow but a bit safer than
# everysec.
#
# More details please check the following article:
# http://antirez.com/post/redis-persistence-demystified.html
#
# If unsure, use "everysec".
# appendfsync always
appendfsync everysec
# appendfsync no
# When the AOF fsync policy is set to always or everysec, and a background
# saving process (a background save or AOF log background rewriting) is
# performing a lot of I/O against the disk, in some Linux configurations
# Redis may block too long on the fsync() call. Note that there is no fix for
# this currently, as even performing fsync in a different thread will block
# our synchronous write(2) call.
#
# In order to mitigate this problem it's possible to use the following option
# that will prevent fsync() from being called in the main process while a
# BGSAVE or BGREWRITEAOF is in progress.
#
# This means that while another child is saving, the durability of Redis is
# the same as "appendfsync none". In practical terms, this means that it is
# possible to lose up to 30 seconds of log in the worst scenario (with the
# default Linux settings).
#
# If you have latency problems turn this to "yes". Otherwise leave it as
# "no" that is the safest pick from the point of view of durability.
no-appendfsync-on-rewrite no
# Automatic rewrite of the append only file.
# Redis is able to automatically rewrite the log file implicitly calling
# BGREWRITEAOF when the AOF log size grows by the specified percentage.
#
# This is how it works: Redis remembers the size of the AOF file after the
# latest rewrite (if no rewrite has happened since the restart, the size of
# the AOF at startup is used).
#
# This base size is compared to the current size. If the current size is
# bigger than the specified percentage, the rewrite is triggered. Also
# you need to specify a minimal size for the AOF file to be rewritten, this
# is useful to avoid rewriting the AOF file even if the percentage increase
# is reached but it is still pretty small.
#
# Specify a percentage of zero in order to disable the automatic AOF
# rewrite feature.
auto-aof-rewrite-percentage 100
auto-aof-rewrite-min-size 64mb
# An AOF file may be found to be truncated at the end during the Redis
# startup process, when the AOF data gets loaded back into memory.
# This may happen when the system where Redis is running
# crashes, especially when an ext4 filesystem is mounted without the
# data=ordered option (however this can't happen when Redis itself
# crashes or aborts but the operating system still works correctly).
#
# Redis can either exit with an error when this happens, or load as much
# data as possible (the default now) and start if the AOF file is found
# to be truncated at the end. The following option controls this behavior.
#
# If aof-load-truncated is set to yes, a truncated AOF file is loaded and
# the Redis server starts emitting a log to inform the user of the event.
# Otherwise if the option is set to no, the server aborts with an error
# and refuses to start. When the option is set to no, the user requires
# to fix the AOF file using the "redis-check-aof" utility before to restart
# the server.
#
# Note that if the AOF file will be found to be corrupted in the middle
# the server will still exit with an error. This option only applies when
# Redis will try to read more data from the AOF file but not enough bytes
# will be found.
aof-load-truncated yes
################################ LUA SCRIPTING ###############################
# Max execution time of a Lua script in milliseconds.
#
# If the maximum execution time is reached Redis will log that a script is
# still in execution after the maximum allowed time and will start to
# reply to queries with an error.
#
# When a long running script exceeds the maximum execution time only the
# SCRIPT KILL and SHUTDOWN NOSAVE commands are available. The first can be
# used to stop a script that did not yet called write commands. The second
# is the only way to shut down the server in the case a write command was
# already issued by the script but the user doesn't want to wait for the natural
# termination of the script.
#
# Set it to 0 or a negative value for unlimited execution without warnings.
lua-time-limit 5000
################################ REDIS CLUSTER ###############################
#
# ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# WARNING EXPERIMENTAL: Redis Cluster is considered to be stable code, however
# in order to mark it as "mature" we need to wait for a non trivial percentage
# of users to deploy it in production.
# ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
#
# Normal Redis instances can't be part of a Redis Cluster; only nodes that are
# started as cluster nodes can. In order to start a Redis instance as a
# cluster node enable the cluster support uncommenting the following:
#
cluster-enabled yes
# Every cluster node has a cluster configuration file. This file is not
# intended to be edited by hand. It is created and updated by Redis nodes.
# Every Redis Cluster node requires a different cluster configuration file.
# Make sure that instances running in the same system do not have
# overlapping cluster configuration file names.
#
cluster-config-file nodes-6379.conf
#指定ip端口
#cluster-announce-ip
#cluster-announce-port
# Cluster node timeout is the amount of milliseconds a node must be unreachable
# for it to be considered in failure state.
# Most other internal time limits are multiple of the node timeout.
#
cluster-node-timeout 15000
# A slave of a failing master will avoid to start a failover if its data
# looks too old.
#
# There is no simple way for a slave to actually have a exact measure of
# its "data age", so the following two checks are performed:
#
# 1) If there are multiple slaves able to failover, they exchange messages
# in order to try to give an advantage to the slave with the best
# replication offset (more data from the master processed).
# Slaves will try to get their rank by offset, and apply to the start
# of the failover a delay proportional to their rank.
#
# 2) Every single slave computes the time of the last interaction with
# its master. This can be the last ping or command received (if the master
# is still in the "connected" state), or the time that elapsed since the
# disconnection with the master (if the replication link is currently down).
# If the last interaction is too old, the slave will not try to failover
# at all.
#
# The point "2" can be tuned by user. Specifically a slave will not perform
# the failover if, since the last interaction with the master, the time
# elapsed is greater than:
#
# (node-timeout * slave-validity-factor) + repl-ping-slave-period
#
# So for example if node-timeout is 30 seconds, and the slave-validity-factor
# is 10, and assuming a default repl-ping-slave-period of 10 seconds, the
# slave will not try to failover if it was not able to talk with the master
# for longer than 310 seconds.
#
# A large slave-validity-factor may allow slaves with too old data to failover
# a master, while a too small value may prevent the cluster from being able to
# elect a slave at all.
#
# For maximum availability, it is possible to set the slave-validity-factor
# to a value of 0, which means, that slaves will always try to failover the
# master regardless of the last time they interacted with the master.
# (However they'll always try to apply a delay proportional to their
# offset rank).
#
# Zero is the only value able to guarantee that when all the partitions heal
# the cluster will always be able to continue.
#
# cluster-slave-validity-factor 10
# Cluster slaves are able to migrate to orphaned masters, that are masters
# that are left without working slaves. This improves the cluster ability
# to resist to failures as otherwise an orphaned master can't be failed over
# in case of failure if it has no working slaves.
#
# Slaves migrate to orphaned masters only if there are still at least a
# given number of other working slaves for their old master. This number
# is the "migration barrier". A migration barrier of 1 means that a slave
# will migrate only if there is at least 1 other working slave for its master
# and so forth. It usually reflects the number of slaves you want for every
# master in your cluster.
#
# Default is 1 (slaves migrate only if their masters remain with at least
# one slave). To disable migration just set it to a very large value.
# A value of 0 can be set but is useful only for debugging and dangerous
# in production.
#
# cluster-migration-barrier 1
# By default Redis Cluster nodes stop accepting queries if they detect there
# is at least an hash slot uncovered (no available node is serving it).
# This way if the cluster is partially down (for example a range of hash slots
# are no longer covered) all the cluster becomes, eventually, unavailable.
# It automatically returns available as soon as all the slots are covered again.
#
# However sometimes you want the subset of the cluster which is working,
# to continue to accept queries for the part of the key space that is still
# covered. In order to do so, just set the cluster-require-full-coverage
# option to no.
#
# cluster-require-full-coverage yes
# In order to setup your cluster make sure to read the documentation
# available at http://redis.io web site.
################################## SLOW LOG ###################################
# The Redis Slow Log is a system to log queries that exceeded a specified
# execution time. The execution time does not include the I/O operations
# like talking with the client, sending the reply and so forth,
# but just the time needed to actually execute the command (this is the only
# stage of command execution where the thread is blocked and can not serve
# other requests in the meantime).
#
# You can configure the slow log with two parameters: one tells Redis
# what is the execution time, in microseconds, to exceed in order for the
# command to get logged, and the other parameter is the length of the
# slow log. When a new command is logged the oldest one is removed from the
# queue of logged commands.
# The following time is expressed in microseconds, so 1000000 is equivalent
# to one second. Note that a negative number disables the slow log, while
# a value of zero forces the logging of every command.
slowlog-log-slower-than 10000
# There is no limit to this length. Just be aware that it will consume memory.
# You can reclaim memory used by the slow log with SLOWLOG RESET.
slowlog-max-len 128
################################ LATENCY MONITOR ##############################
# The Redis latency monitoring subsystem samples different operations
# at runtime in order to collect data related to possible sources of
# latency of a Redis instance.
#
# Via the LATENCY command this information is available to the user that can
# print graphs and obtain reports.
#
# The system only logs operations that were performed in a time equal or
# greater than the amount of milliseconds specified via the
# latency-monitor-threshold configuration directive. When its value is set
# to zero, the latency monitor is turned off.
#
# By default latency monitoring is disabled since it is mostly not needed
# if you don't have latency issues, and collecting data has a performance
# impact, that while very small, can be measured under big load. Latency
# monitoring can easily be enabled at runtime using the command
# "CONFIG SET latency-monitor-threshold <milliseconds>" if needed.
latency-monitor-threshold 0
############################# EVENT NOTIFICATION ##############################
# Redis can notify Pub/Sub clients about events happening in the key space.
# This feature is documented at http://redis.io/topics/notifications
#
# For instance if keyspace events notification is enabled, and a client
# performs a DEL operation on key "foo" stored in the Database 0, two
# messages will be published via Pub/Sub:
#
# PUBLISH __keyspace@0__:foo del
# PUBLISH __keyevent@0__:del foo
#
# It is possible to select the events that Redis will notify among a set
# of classes. Every class is identified by a single character:
#
# K Keyspace events, published with __keyspace@<db>__ prefix.
# E Keyevent events, published with __keyevent@<db>__ prefix.
# g Generic commands (non-type specific) like DEL, EXPIRE, RENAME, ...
# $ String commands
# l List commands
# s Set commands
# h Hash commands
# z Sorted set commands
# x Expired events (events generated every time a key expires)
# e Evicted events (events generated when a key is evicted for maxmemory)
# A Alias for g$lshzxe, so that the "AKE" string means all the events.
#
# The "notify-keyspace-events" takes as argument a string that is composed
# of zero or multiple characters. The empty string means that notifications
# are disabled.
#
# Example: to enable list and generic events, from the point of view of the
# event name, use:
#
# notify-keyspace-events Elg
#
# Example 2: to get the stream of the expired keys subscribing to channel
# name __keyevent@0__:expired use:
#
# notify-keyspace-events Ex
#
# By default all notifications are disabled because most users don't need
# this feature and the feature has some overhead. Note that if you don't
# specify at least one of K or E, no events will be delivered.
notify-keyspace-events ""
############################### ADVANCED CONFIG ###############################
# Hashes are encoded using a memory efficient data structure when they have a
# small number of entries, and the biggest entry does not exceed a given
# threshold. These thresholds can be configured using the following directives.
hash-max-ziplist-entries 512
hash-max-ziplist-value 64
# Lists are also encoded in a special way to save a lot of space.
# The number of entries allowed per internal list node can be specified
# as a fixed maximum size or a maximum number of elements.
# For a fixed maximum size, use -5 through -1, meaning:
# -5: max size: 64 Kb <-- not recommended for normal workloads
# -4: max size: 32 Kb <-- not recommended
# -3: max size: 16 Kb <-- probably not recommended
# -2: max size: 8 Kb <-- good
# -1: max size: 4 Kb <-- good
# Positive numbers mean store up to _exactly_ that number of elements
# per list node.
# The highest performing option is usually -2 (8 Kb size) or -1 (4 Kb size),
# but if your use case is unique, adjust the settings as necessary.
list-max-ziplist-size -2
# Lists may also be compressed.
# Compress depth is the number of quicklist ziplist nodes from *each* side of
# the list to *exclude* from compression. The head and tail of the list
# are always uncompressed for fast push/pop operations. Settings are:
# 0: disable all list compression
# 1: depth 1 means "don't start compressing until after 1 node into the list,
# going from either the head or tail"
# So: [head]->node->node->...->node->[tail]
# [head], [tail] will always be uncompressed; inner nodes will compress.
# 2: [head]->[next]->node->node->...->node->[prev]->[tail]
# 2 here means: don't compress head or head->next or tail->prev or tail,
# but compress all nodes between them.
# 3: [head]->[next]->[next]->node->node->...->node->[prev]->[prev]->[tail]
# etc.
list-compress-depth 0
# Sets have a special encoding in just one case: when a set is composed
# of just strings that happen to be integers in radix 10 in the range
# of 64 bit signed integers.
# The following configuration setting sets the limit in the size of the
# set in order to use this special memory saving encoding.
set-max-intset-entries 512
# Similarly to hashes and lists, sorted sets are also specially encoded in
# order to save a lot of space. This encoding is only used when the length and
# elements of a sorted set are below the following limits:
zset-max-ziplist-entries 128
zset-max-ziplist-value 64
# HyperLogLog sparse representation bytes limit. The limit includes the
# 16 bytes header. When an HyperLogLog using the sparse representation crosses
# this limit, it is converted into the dense representation.
#
# A value greater than 16000 is totally useless, since at that point the
# dense representation is more memory efficient.
#
# The suggested value is ~ 3000 in order to have the benefits of
# the space efficient encoding without slowing down too much PFADD,
# which is O(N) with the sparse encoding. The value can be raised to
# ~ 10000 when CPU is not a concern, but space is, and the data set is
# composed of many HyperLogLogs with cardinality in the 0 - 15000 range.
hll-sparse-max-bytes 3000
# Active rehashing uses 1 millisecond every 100 milliseconds of CPU time in
# order to help rehashing the main Redis hash table (the one mapping top-level
# keys to values). The hash table implementation Redis uses (see dict.c)
# performs a lazy rehashing: the more operation you run into a hash table
# that is rehashing, the more rehashing "steps" are performed, so if the
# server is idle the rehashing is never complete and some more memory is used
# by the hash table.
#
# The default is to use this millisecond 10 times every second in order to
# actively rehash the main dictionaries, freeing memory when possible.
#
# If unsure:
# use "activerehashing no" if you have hard latency requirements and it is
# not a good thing in your environment that Redis can reply from time to time
# to queries with 2 milliseconds delay.
#
# use "activerehashing yes" if you don't have such hard requirements but
# want to free memory asap when possible.
activerehashing yes
# The client output buffer limits can be used to force disconnection of clients
# that are not reading data from the server fast enough for some reason (a
# common reason is that a Pub/Sub client can't consume messages as fast as the
# publisher can produce them).
#
# The limit can be set differently for the three different classes of clients:
#
# normal -> normal clients including MONITOR clients
# slave -> slave clients
# pubsub -> clients subscribed to at least one pubsub channel or pattern
#
# The syntax of every client-output-buffer-limit directive is the following:
#
# client-output-buffer-limit <class> <hard limit> <soft limit> <soft seconds>
#
# A client is immediately disconnected once the hard limit is reached, or if
# the soft limit is reached and remains reached for the specified number of
# seconds (continuously).
# So for instance if the hard limit is 32 megabytes and the soft limit is
# 16 megabytes / 10 seconds, the client will get disconnected immediately
# if the size of the output buffers reach 32 megabytes, but will also get
# disconnected if the client reaches 16 megabytes and continuously overcomes
# the limit for 10 seconds.
#
# By default normal clients are not limited because they don't receive data
# without asking (in a push way), but just after a request, so only
# asynchronous clients may create a scenario where data is requested faster
# than it can read.
#
# Instead there is a default limit for pubsub and slave clients, since
# subscribers and slaves receive data in a push fashion.
#
# Both the hard or the soft limit can be disabled by setting them to zero.
client-output-buffer-limit normal 0 0 0
client-output-buffer-limit slave 256mb 64mb 60
client-output-buffer-limit pubsub 32mb 8mb 60
# Redis calls an internal function to perform many background tasks, like
# closing connections of clients in timeout, purging expired keys that are
# never requested, and so forth.
#
# Not all tasks are performed with the same frequency, but Redis checks for
# tasks to perform according to the specified "hz" value.
#
# By default "hz" is set to 10. Raising the value will use more CPU when
# Redis is idle, but at the same time will make Redis more responsive when
# there are many keys expiring at the same time, and timeouts may be
# handled with more precision.
#
# The range is between 1 and 500, however a value over 100 is usually not
# a good idea. Most users should use the default of 10 and raise this up to
# 100 only in environments where very low latency is required.
hz 10
# When a child rewrites the AOF file, if the following option is enabled
# the file will be fsync-ed every 32 MB of data generated. This is useful
# in order to commit the file to the disk more incrementally and avoid
# big latency spikes.
aof-rewrite-incremental-fsync yes
# Generated by CONFIG REWRITE
sh文件
cluster.sh
echo " cluster-announce-ip $REALIP
cluster-announce-port $PORT
cluster-announce-bus-port $PORT2
" >> /usr/src/redis/conf/redis.conf
redis-server /usr/src/redis/conf/redis.conf
redis-trib.rb (快速创建redis集群,官方提供维护的包,下面已经设置了集群密码,如果不需要搜索password删除即可)
#!/usr/bin/env ruby
# TODO (temporary here, we'll move this into the Github issues once
# redis-trib initial implementation is completed).
#
# - Make sure that if the rehashing fails in the middle redis-trib will try
# to recover.
# - When redis-trib performs a cluster check, if it detects a slot move in
# progress it should prompt the user to continue the move from where it
# stopped.
# - Gracefully handle Ctrl+C in move_slot to prompt the user if really stop
# while rehashing, and performing the best cleanup possible if the user
# forces the quit.
# - When doing "fix" set a global Fix to true, and prompt the user to
# fix the problem if automatically fixable every time there is something
# to fix. For instance:
# 1) If there is a node that pretend to receive a slot, or to migrate a
# slot, but has no entries in that slot, fix it.
# 2) If there is a node having keys in slots that are not owned by it
# fix this condition moving the entries in the same node.
# 3) Perform more possibly slow tests about the state of the cluster.
# 4) When aborted slot migration is detected, fix it.
require 'rubygems'
require 'redis'
ClusterHashSlots = 16384
MigrateDefaultTimeout = 60000
MigrateDefaultPipeline = 10
RebalanceDefaultThreshold = 2
$verbose = false
def xputs(s)
case s[0..2]
when ">>>"
color="29;1"
when "[ER"
color="31;1"
when "[WA"
color="31;1"
when "[OK"
color="32"
when "[FA","***"
color="33"
else
color=nil
end
color = nil if ENV['TERM'] != "xterm"
print "\033[#{color}m" if color
print s
print "\033[0m" if color
print "\n"
end
class ClusterNode
def initialize(addr)
s = addr.split("@")[0].split(":")
if s.length < 2
puts "Invalid IP or Port (given as #{addr}) - use IP:Port format"
exit 1
end
port = s.pop # removes port from split array
ip = s.join(":") # if s.length > 1 here, it's IPv6, so restore address
@r = nil
@info = {}
@info[:host] = ip
@info[:port] = port
@info[:slots] = {}
@info[:migrating] = {}
@info[:importing] = {}
@info[:replicate] = false
@dirty = false # True if we need to flush slots info into node.
@friends = []
end
def friends
@friends
end
def slots
@info[:slots]
end
def has_flag?(flag)
@info[:flags].index(flag)
end
def to_s
"#{@info[:host]}:#{@info[:port]}"
end
def connect(o={})
return if @r
print "Connecting to node #{self}: " if $verbose
STDOUT.flush
begin
@r = Redis.new(:host => @info[:host], :port => @info[:port], :timeout => 60, :password => "sixstar")
@r.ping
rescue
xputs "[ERR] Sorry, can't connect to node #{self}"
exit 1 if o[:abort]
@r = nil
end
xputs "OK" if $verbose
end
def assert_cluster
info = @r.info
if !info["cluster_enabled"] || info["cluster_enabled"].to_i == 0
xputs "[ERR] Node #{self} is not configured as a cluster node."
exit 1
end
end
def assert_empty
if !(@r.cluster("info").split("\r\n").index("cluster_known_nodes:1")) ||
(@r.info['db0'])
xputs "[ERR] Node #{self} is not empty. Either the node already knows other nodes (check with CLUSTER NODES) or contains some key in database 0."
exit 1
end
end
def load_info(o={})
self.connect
nodes = @r.cluster("nodes").split("\n")
nodes.each{|n|
# name addr flags role ping_sent ping_recv link_status slots
split = n.split
name,addr,flags,master_id,ping_sent,ping_recv,config_epoch,link_status = split[0..6]
slots = split[8..-1]
info = {
:name => name,
:addr => addr,
:flags => flags.split(","),
:replicate => master_id,
:ping_sent => ping_sent.to_i,
:ping_recv => ping_recv.to_i,
:link_status => link_status
}
info[:replicate] = false if master_id == "-"
if info[:flags].index("myself")
@info = @info.merge(info)
@info[:slots] = {}
slots.each{|s|
if s[0..0] == '['
if s.index("->-") # Migrating
slot,dst = s[1..-1].split("->-")
@info[:migrating][slot.to_i] = dst
elsif s.index("-<-") # Importing
slot,src = s[1..-1].split("-<-")
@info[:importing][slot.to_i] = src
end
elsif s.index("-")
start,stop = s.split("-")
self.add_slots((start.to_i)..(stop.to_i))
else
self.add_slots((s.to_i)..(s.to_i))
end
} if slots
@dirty = false
@r.cluster("info").split("\n").each{|e|
k,v=e.split(":")
k = k.to_sym
v.chop!
if k != :cluster_state
@info[k] = v.to_i
else
@info[k] = v
end
}
elsif o[:getfriends]
@friends << info
end
}
end
def add_slots(slots)
slots.each{|s|
@info[:slots][s] = :new
}
@dirty = true
end
def set_as_replica(node_id)
@info[:replicate] = node_id
@dirty = true
end
def flush_node_config
return if !@dirty
if @info[:replicate]
begin
@r.cluster("replicate",@info[:replicate])
rescue
# If the cluster did not already joined it is possible that
# the slave does not know the master node yet. So on errors
# we return ASAP leaving the dirty flag set, to flush the
# config later.
return
end
else
new = []
@info[:slots].each{|s,val|
if val == :new
new << s
@info[:slots][s] = true
end
}
@r.cluster("addslots",*new)
end
@dirty = false
end
def info_string
# We want to display the hash slots assigned to this node
# as ranges, like in: "1-5,8-9,20-25,30"
#
# Note: this could be easily written without side effects,
# we use 'slots' just to split the computation into steps.
# First step: we want an increasing array of integers
# for instance: [1,2,3,4,5,8,9,20,21,22,23,24,25,30]
slots = @info[:slots].keys.sort
# As we want to aggregate adjacent slots we convert all the
# slot integers into ranges (with just one element)
# So we have something like [1..1,2..2, ... and so forth.
slots.map!{|x| x..x}
# Finally we group ranges with adjacent elements.
slots = slots.reduce([]) {|a,b|
if !a.empty? && b.first == (a[-1].last)+1
a[0..-2] + [(a[-1].first)..(b.last)]
else
a + [b]
end
}
# Now our task is easy, we just convert ranges with just one
# element into a number, and a real range into a start-end format.
# Finally we join the array using the comma as separator.
slots = slots.map{|x|
x.count == 1 ? x.first.to_s : "#{x.first}-#{x.last}"
}.join(",")
role = self.has_flag?("master") ? "M" : "S"
if self.info[:replicate] and @dirty
is = "S: #{self.info[:name]} #{self.to_s}"
else
is = "#{role}: #{self.info[:name]} #{self.to_s}\n"+
" slots:#{slots} (#{self.slots.length} slots) "+
"#{(self.info[:flags]-["myself"]).join(",")}"
end
if self.info[:replicate]
is += "\n replicates #{info[:replicate]}"
elsif self.has_flag?("master") && self.info[:replicas]
is += "\n #{info[:replicas].length} additional replica(s)"
end
is
end
# Return a single string representing nodes and associated slots.
# TODO: remove slaves from config when slaves will be handled
# by Redis Cluster.
def get_config_signature
config = []
@r.cluster("nodes").each_line{|l|
s = l.split
slots = s[8..-1].select {|x| x[0..0] != "["}
next if slots.length == 0
config << s[0]+":"+(slots.sort.join(","))
}
config.sort.join("|")
end
def info
@info
end
def is_dirty?
@dirty
end
def r
@r
end
end
class RedisTrib
def initialize
@nodes = []
@fix = false
@errors = []
@timeout = MigrateDefaultTimeout
end
def check_arity(req_args, num_args)
if ((req_args > 0 and num_args != req_args) ||
(req_args < 0 and num_args < req_args.abs))
xputs "[ERR] Wrong number of arguments for specified sub command"
exit 1
end
end
def add_node(node)
@nodes << node
end
def reset_nodes
@nodes = []
end
def cluster_error(msg)
@errors << msg
xputs msg
end
# Return the node with the specified ID or Nil.
def get_node_by_name(name)
@nodes.each{|n|
return n if n.info[:name] == name.downcase
}
return nil
end
# Like get_node_by_name but the specified name can be just the first
# part of the node ID as long as the prefix in unique across the
# cluster.
def get_node_by_abbreviated_name(name)
l = name.length
candidates = []
@nodes.each{|n|
if n.info[:name][0...l] == name.downcase
candidates << n
end
}
return nil if candidates.length != 1
candidates[0]
end
# This function returns the master that has the least number of replicas
# in the cluster. If there are multiple masters with the same smaller
# number of replicas, one at random is returned.
def get_master_with_least_replicas
masters = @nodes.select{|n| n.has_flag? "master"}
sorted = masters.sort{|a,b|
a.info[:replicas].length <=> b.info[:replicas].length
}
sorted[0]
end
def check_cluster(opt={})
xputs ">>> Performing Cluster Check (using node #{@nodes[0]})"
show_nodes if !opt[:quiet]
check_config_consistency
check_open_slots
check_slots_coverage
end
def show_cluster_info
masters = 0
keys = 0
@nodes.each{|n|
if n.has_flag?("master")
puts "#{n} (#{n.info[:name][0...8]}...) -> #{n.r.dbsize} keys | #{n.slots.length} slots | "+
"#{n.info[:replicas].length} slaves."
masters += 1
keys += n.r.dbsize
end
}
xputs "[OK] #{keys} keys in #{masters} masters."
keys_per_slot = sprintf("%.2f",keys/16384.0)
puts "#{keys_per_slot} keys per slot on average."
end
# Merge slots of every known node. If the resulting slots are equal
# to ClusterHashSlots, then all slots are served.
def covered_slots
slots = {}
@nodes.each{|n|
slots = slots.merge(n.slots)
}
slots
end
def check_slots_coverage
xputs ">>> Check slots coverage..."
slots = covered_slots
if slots.length == ClusterHashSlots
xputs "[OK] All #{ClusterHashSlots} slots covered."
else
cluster_error \
"[ERR] Not all #{ClusterHashSlots} slots are covered by nodes."
fix_slots_coverage if @fix
end
end
def check_open_slots
xputs ">>> Check for open slots..."
open_slots = []
@nodes.each{|n|
if n.info[:migrating].size > 0
cluster_error \
"[WARNING] Node #{n} has slots in migrating state (#{n.info[:migrating].keys.join(",")})."
open_slots += n.info[:migrating].keys
end
if n.info[:importing].size > 0
cluster_error \
"[WARNING] Node #{n} has slots in importing state (#{n.info[:importing].keys.join(",")})."
open_slots += n.info[:importing].keys
end
}
open_slots.uniq!
if open_slots.length > 0
xputs "[WARNING] The following slots are open: #{open_slots.join(",")}"
end
if @fix
open_slots.each{|slot| fix_open_slot slot}
end
end
def nodes_with_keys_in_slot(slot)
nodes = []
@nodes.each{|n|
next if n.has_flag?("slave")
nodes << n if n.r.cluster("getkeysinslot",slot,1).length > 0
}
nodes
end
def fix_slots_coverage
not_covered = (0...ClusterHashSlots).to_a - covered_slots.keys
xputs ">>> Fixing slots coverage..."
xputs "List of not covered slots: " + not_covered.join(",")
# For every slot, take action depending on the actual condition:
# 1) No node has keys for this slot.
# 2) A single node has keys for this slot.
# 3) Multiple nodes have keys for this slot.
slots = {}
not_covered.each{|slot|
nodes = nodes_with_keys_in_slot(slot)
slots[slot] = nodes
xputs "Slot #{slot} has keys in #{nodes.length} nodes: #{nodes.join(", ")}"
}
none = slots.select {|k,v| v.length == 0}
single = slots.select {|k,v| v.length == 1}
multi = slots.select {|k,v| v.length > 1}
# Handle case "1": keys in no node.
if none.length > 0
xputs "The folowing uncovered slots have no keys across the cluster:"
xputs none.keys.join(",")
yes_or_die "Fix these slots by covering with a random node?"
none.each{|slot,nodes|
node = @nodes.sample
xputs ">>> Covering slot #{slot} with #{node}"
node.r.cluster("addslots",slot)
}
end
# Handle case "2": keys only in one node.
if single.length > 0
xputs "The folowing uncovered slots have keys in just one node:"
puts single.keys.join(",")
yes_or_die "Fix these slots by covering with those nodes?"
single.each{|slot,nodes|
xputs ">>> Covering slot #{slot} with #{nodes[0]}"
nodes[0].r.cluster("addslots",slot)
}
end
# Handle case "3": keys in multiple nodes.
if multi.length > 0
xputs "The folowing uncovered slots have keys in multiple nodes:"
xputs multi.keys.join(",")
yes_or_die "Fix these slots by moving keys into a single node?"
multi.each{|slot,nodes|
target = get_node_with_most_keys_in_slot(nodes,slot)
xputs ">>> Covering slot #{slot} moving keys to #{target}"
target.r.cluster('addslots',slot)
target.r.cluster('setslot',slot,'stable')
nodes.each{|src|
next if src == target
# Set the source node in 'importing' state (even if we will
# actually migrate keys away) in order to avoid receiving
# redirections for MIGRATE.
src.r.cluster('setslot',slot,'importing',target.info[:name])
move_slot(src,target,slot,:dots=>true,:fix=>true,:cold=>true)
src.r.cluster('setslot',slot,'stable')
}
}
end
end
# Return the owner of the specified slot
def get_slot_owners(slot)
owners = []
@nodes.each{|n|
next if n.has_flag?("slave")
n.slots.each{|s,_|
owners << n if s == slot
}
}
owners
end
# Return the node, among 'nodes' with the greatest number of keys
# in the specified slot.
def get_node_with_most_keys_in_slot(nodes,slot)
best = nil
best_numkeys = 0
@nodes.each{|n|
next if n.has_flag?("slave")
numkeys = n.r.cluster("countkeysinslot",slot)
if numkeys > best_numkeys || best == nil
best = n
best_numkeys = numkeys
end
}
return best
end
# Slot 'slot' was found to be in importing or migrating state in one or
# more nodes. This function fixes this condition by migrating keys where
# it seems more sensible.
def fix_open_slot(slot)
puts ">>> Fixing open slot #{slot}"
# Try to obtain the current slot owner, according to the current
# nodes configuration.
owners = get_slot_owners(slot)
owner = owners[0] if owners.length == 1
migrating = []
importing = []
@nodes.each{|n|
next if n.has_flag? "slave"
if n.info[:migrating][slot]
migrating << n
elsif n.info[:importing][slot]
importing << n
elsif n.r.cluster("countkeysinslot",slot) > 0 && n != owner
xputs "*** Found keys about slot #{slot} in node #{n}!"
importing << n
end
}
puts "Set as migrating in: #{migrating.join(",")}"
puts "Set as importing in: #{importing.join(",")}"
# If there is no slot owner, set as owner the slot with the biggest
# number of keys, among the set of migrating / importing nodes.
if !owner
xputs ">>> Nobody claims ownership, selecting an owner..."
owner = get_node_with_most_keys_in_slot(@nodes,slot)
# If we still don't have an owner, we can't fix it.
if !owner
xputs "[ERR] Can't select a slot owner. Impossible to fix."
exit 1
end
# Use ADDSLOTS to assign the slot.
puts "*** Configuring #{owner} as the slot owner"
owner.r.cluster("setslot",slot,"stable")
owner.r.cluster("addslots",slot)
# Make sure this information will propagate. Not strictly needed
# since there is no past owner, so all the other nodes will accept
# whatever epoch this node will claim the slot with.
owner.r.cluster("bumpepoch")
# Remove the owner from the list of migrating/importing
# nodes.
migrating.delete(owner)
importing.delete(owner)
end
# If there are multiple owners of the slot, we need to fix it
# so that a single node is the owner and all the other nodes
# are in importing state. Later the fix can be handled by one
# of the base cases above.
#
# Note that this case also covers multiple nodes having the slot
# in migrating state, since migrating is a valid state only for
# slot owners.
if owners.length > 1
owner = get_node_with_most_keys_in_slot(owners,slot)
owners.each{|n|
next if n == owner
n.r.cluster('delslots',slot)
n.r.cluster('setslot',slot,'importing',owner.info[:name])
importing.delete(n) # Avoid duplciates
importing << n
}
owner.r.cluster('bumpepoch')
end
# Case 1: The slot is in migrating state in one slot, and in
# importing state in 1 slot. That's trivial to address.
if migrating.length == 1 && importing.length == 1
move_slot(migrating[0],importing[0],slot,:dots=>true,:fix=>true)
# Case 2: There are multiple nodes that claim the slot as importing,
# they probably got keys about the slot after a restart so opened
# the slot. In this case we just move all the keys to the owner
# according to the configuration.
elsif migrating.length == 0 && importing.length > 0
xputs ">>> Moving all the #{slot} slot keys to its owner #{owner}"
importing.each {|node|
next if node == owner
move_slot(node,owner,slot,:dots=>true,:fix=>true,:cold=>true)
xputs ">>> Setting #{slot} as STABLE in #{node}"
node.r.cluster("setslot",slot,"stable")
}
# Case 3: There are no slots claiming to be in importing state, but
# there is a migrating node that actually don't have any key. We
# can just close the slot, probably a reshard interrupted in the middle.
elsif importing.length == 0 && migrating.length == 1 &&
migrating[0].r.cluster("getkeysinslot",slot,10).length == 0
migrating[0].r.cluster("setslot",slot,"stable")
else
xputs "[ERR] Sorry, Redis-trib can't fix this slot yet (work in progress). Slot is set as migrating in #{migrating.join(",")}, as importing in #{importing.join(",")}, owner is #{owner}"
end
end
# Check if all the nodes agree about the cluster configuration
def check_config_consistency
if !is_config_consistent?
cluster_error "[ERR] Nodes don't agree about configuration!"
else
xputs "[OK] All nodes agree about slots configuration."
end
end
def is_config_consistent?
signatures=[]
@nodes.each{|n|
signatures << n.get_config_signature
}
return signatures.uniq.length == 1
end
def wait_cluster_join
print "Waiting for the cluster to join"
while !is_config_consistent?
print "."
STDOUT.flush
sleep 1
end
print "\n"
end
def alloc_slots
nodes_count = @nodes.length
masters_count = @nodes.length / (@replicas+1)
masters = []
# The first step is to split instances by IP. This is useful as
# we'll try to allocate master nodes in different physical machines
# (as much as possible) and to allocate slaves of a given master in
# different physical machines as well.
#
# This code assumes just that if the IP is different, than it is more
# likely that the instance is running in a different physical host
# or at least a different virtual machine.
ips = {}
@nodes.each{|n|
ips[n.info[:host]] = [] if !ips[n.info[:host]]
ips[n.info[:host]] << n
}
# Select master instances
puts "Using #{masters_count} masters:"
interleaved = []
stop = false
while not stop do
# Take one node from each IP until we run out of nodes
# across every IP.
ips.each do |ip,nodes|
if nodes.empty?
# if this IP has no remaining nodes, check for termination
if interleaved.length == nodes_count
# stop when 'interleaved' has accumulated all nodes
stop = true
next
end
else
# else, move one node from this IP to 'interleaved'
interleaved.push nodes.shift
end
end
end
masters = interleaved.slice!(0, masters_count)
nodes_count -= masters.length
masters.each{|m| puts m}
# Rotating the list sometimes helps to get better initial
# anti-affinity before the optimizer runs.
interleaved.push interleaved.shift
# Alloc slots on masters. After interleaving to get just the first N
# should be optimal. With slaves is more complex, see later...
slots_per_node = ClusterHashSlots.to_f / masters_count
first = 0
cursor = 0.0
masters.each_with_index{|n,masternum|
last = (cursor+slots_per_node-1).round
if last > ClusterHashSlots || masternum == masters.length-1
last = ClusterHashSlots-1
end
last = first if last < first # Min step is 1.
n.add_slots first..last
first = last+1
cursor += slots_per_node
}
# Select N replicas for every master.
# We try to split the replicas among all the IPs with spare nodes
# trying to avoid the host where the master is running, if possible.
#
# Note we loop two times. The first loop assigns the requested
# number of replicas to each master. The second loop assigns any
# remaining instances as extra replicas to masters. Some masters
# may end up with more than their requested number of replicas, but
# all nodes will be used.
assignment_verbose = false
[:requested,:unused].each do |assign|
masters.each do |m|
assigned_replicas = 0
while assigned_replicas < @replicas
break if nodes_count == 0
if assignment_verbose
if assign == :requested
puts "Requesting total of #{@replicas} replicas " \
"(#{assigned_replicas} replicas assigned " \
"so far with #{nodes_count} total remaining)."
elsif assign == :unused
puts "Assigning extra instance to replication " \
"role too (#{nodes_count} remaining)."
end
end
# Return the first node not matching our current master
node = interleaved.find{|n| n.info[:host] != m.info[:host]}
# If we found a node, use it as a best-first match.
# Otherwise, we didn't find a node on a different IP, so we
# go ahead and use a same-IP replica.
if node
slave = node
interleaved.delete node
else
slave = interleaved.shift
end
slave.set_as_replica(m.info[:name])
nodes_count -= 1
assigned_replicas += 1
puts "Adding replica #{slave} to #{m}"
# If we are in the "assign extra nodes" loop,
# we want to assign one extra replica to each
# master before repeating masters.
# This break lets us assign extra replicas to masters
# in a round-robin way.
break if assign == :unused
end
end
end
optimize_anti_affinity
end
def optimize_anti_affinity
score,aux = get_anti_affinity_score
return if score == 0
xputs ">>> Trying to optimize slaves allocation for anti-affinity"
maxiter = 500*@nodes.length # Effort is proportional to cluster size...
while maxiter > 0
score,offenders = get_anti_affinity_score
break if score == 0 # Optimal anti affinity reached
# We'll try to randomly swap a slave's assigned master causing
# an affinity problem with another random slave, to see if we
# can improve the affinity.
first = offenders.shuffle.first
nodes = @nodes.select{|n| n != first && n.info[:replicate]}
break if nodes.length == 0
second = nodes.shuffle.first
first_master = first.info[:replicate]
second_master = second.info[:replicate]
first.set_as_replica(second_master)
second.set_as_replica(first_master)
new_score,aux = get_anti_affinity_score
# If the change actually makes thing worse, revert. Otherwise
# leave as it is becuase the best solution may need a few
# combined swaps.
if new_score > score
first.set_as_replica(first_master)
second.set_as_replica(second_master)
end
maxiter -= 1
end
score,aux = get_anti_affinity_score
if score == 0
xputs "[OK] Perfect anti-affinity obtained!"
elsif score >= 10000
puts "[WARNING] Some slaves are in the same host as their master"
else
puts "[WARNING] Some slaves of the same master are in the same host"
end
end
# Return the anti-affinity score, which is a measure of the amount of
# violations of anti-affinity in the current cluster layout, that is, how
# badly the masters and slaves are distributed in the different IP
# addresses so that slaves of the same master are not in the master
# host and are also in different hosts.
#
# The score is calculated as follows:
#
# SAME_AS_MASTER = 10000 * each slave in the same IP of its master.
# SAME_AS_SLAVE = 1 * each slave having the same IP as another slave
# of the same master.
# FINAL_SCORE = SAME_AS_MASTER + SAME_AS_SLAVE
#
# So a greater score means a worse anti-affinity level, while zero
# means perfect anti-affinity.
#
# The anti affinity optimizator will try to get a score as low as
# possible. Since we do not want to sacrifice the fact that slaves should
# not be in the same host as the master, we assign 10000 times the score
# to this violation, so that we'll optimize for the second factor only
# if it does not impact the first one.
#
# The function returns two things: the above score, and the list of
# offending slaves, so that the optimizer can try changing the
# configuration of the slaves violating the anti-affinity goals.
def get_anti_affinity_score
score = 0
offending = [] # List of offending slaves to return to the caller
# First, split nodes by host
host_to_node = {}
@nodes.each{|n|
host = n.info[:host]
host_to_node[host] = [] if host_to_node[host] == nil
host_to_node[host] << n
}
# Then, for each set of nodes in the same host, split by
# related nodes (masters and slaves which are involved in
# replication of each other)
host_to_node.each{|host,nodes|
related = {}
nodes.each{|n|
if !n.info[:replicate]
name = n.info[:name]
related[name] = [] if related[name] == nil
related[name] << :m
else
name = n.info[:replicate]
related[name] = [] if related[name] == nil
related[name] << :s
end
}
# Now it's trivial to check, for each related group having the
# same host, what is their local score.
related.each{|id,types|
next if types.length < 2
types.sort! # Make sure :m if the first if any
if types[0] == :m
score += 10000 * (types.length-1)
else
score += 1 * types.length
end
# Populate the list of offending nodes
@nodes.each{|n|
if n.info[:replicate] == id &&
n.info[:host] == host
offending << n
end
}
}
}
return score,offending
end
def flush_nodes_config
@nodes.each{|n|
n.flush_node_config
}
end
def show_nodes
@nodes.each{|n|
xputs n.info_string
}
end
# Redis Cluster config epoch collision resolution code is able to eventually
# set a different epoch to each node after a new cluster is created, but
# it is slow compared to assign a progressive config epoch to each node
# before joining the cluster. However we do just a best-effort try here
# since if we fail is not a problem.
def assign_config_epoch
config_epoch = 1
@nodes.each{|n|
begin
n.r.cluster("set-config-epoch",config_epoch)
rescue
end
config_epoch += 1
}
end
def join_cluster
# We use a brute force approach to make sure the node will meet
# each other, that is, sending CLUSTER MEET messages to all the nodes
# about the very same node.
# Thanks to gossip this information should propagate across all the
# cluster in a matter of seconds.
first = false
@nodes.each{|n|
if !first then first = n.info; next; end # Skip the first node
n.r.cluster("meet",first[:host],first[:port])
}
end
def yes_or_die(msg)
print "#{msg} (type 'yes' to accept): "
STDOUT.flush
if !(STDIN.gets.chomp.downcase == "yes")
xputs "*** Aborting..."
exit 1
end
end
def load_cluster_info_from_node(nodeaddr)
node = ClusterNode.new(nodeaddr)
node.connect(:abort => true)
node.assert_cluster
node.load_info(:getfriends => true)
add_node(node)
node.friends.each{|f|
next if f[:flags].index("noaddr") ||
f[:flags].index("disconnected") ||
f[:flags].index("fail")
fnode = ClusterNode.new(f[:addr])
fnode.connect()
next if !fnode.r
begin
fnode.load_info()
add_node(fnode)
rescue => e
xputs "[ERR] Unable to load info for node #{fnode}"
end
}
populate_nodes_replicas_info
end
# This function is called by load_cluster_info_from_node in order to
# add additional information to every node as a list of replicas.
def populate_nodes_replicas_info
# Start adding the new field to every node.
@nodes.each{|n|
n.info[:replicas] = []
}
# Populate the replicas field using the replicate field of slave
# nodes.
@nodes.each{|n|
if n.info[:replicate]
master = get_node_by_name(n.info[:replicate])
if !master
xputs "*** WARNING: #{n} claims to be slave of unknown node ID #{n.info[:replicate]}."
else
master.info[:replicas] << n
end
end
}
end
# Given a list of source nodes return a "resharding plan"
# with what slots to move in order to move "numslots" slots to another
# instance.
def compute_reshard_table(sources,numslots)
moved = []
# Sort from bigger to smaller instance, for two reasons:
# 1) If we take less slots than instances it is better to start
# getting from the biggest instances.
# 2) We take one slot more from the first instance in the case of not
# perfect divisibility. Like we have 3 nodes and need to get 10
# slots, we take 4 from the first, and 3 from the rest. So the
# biggest is always the first.
sources = sources.sort{|a,b| b.slots.length <=> a.slots.length}
source_tot_slots = sources.inject(0) {|sum,source|
sum+source.slots.length
}
sources.each_with_index{|s,i|
# Every node will provide a number of slots proportional to the
# slots it has assigned.
n = (numslots.to_f/source_tot_slots*s.slots.length)
if i == 0
n = n.ceil
else
n = n.floor
end
s.slots.keys.sort[(0...n)].each{|slot|
if moved.length < numslots
moved << {:source => s, :slot => slot}
end
}
}
return moved
end
def show_reshard_table(table)
table.each{|e|
puts " Moving slot #{e[:slot]} from #{e[:source].info[:name]}"
}
end
# Move slots between source and target nodes using MIGRATE.
#
# Options:
# :verbose -- Print a dot for every moved key.
# :fix -- We are moving in the context of a fix. Use REPLACE.
# :cold -- Move keys without opening slots / reconfiguring the nodes.
# :update -- Update nodes.info[:slots] for source/target nodes.
# :quiet -- Don't print info messages.
def move_slot(source,target,slot,o={})
o = {:pipeline => MigrateDefaultPipeline}.merge(o)
# We start marking the slot as importing in the destination node,
# and the slot as migrating in the target host. Note that the order of
# the operations is important, as otherwise a client may be redirected
# to the target node that does not yet know it is importing this slot.
if !o[:quiet]
print "Moving slot #{slot} from #{source} to #{target}: "
STDOUT.flush
end
if !o[:cold]
target.r.cluster("setslot",slot,"importing",source.info[:name])
source.r.cluster("setslot",slot,"migrating",target.info[:name])
end
# Migrate all the keys from source to target using the MIGRATE command
while true
keys = source.r.cluster("getkeysinslot",slot,o[:pipeline])
break if keys.length == 0
begin
source.r.client.call(["migrate",target.info[:host],target.info[:port],"",0,@timeout,:keys,*keys])
rescue => e
if o[:fix] && e.to_s =~ /BUSYKEY/
xputs "*** Target key exists. Replacing it for FIX."
source.r.client.call(["migrate",target.info[:host],target.info[:port],"",0,@timeout,:replace,:keys,*keys])
else
puts ""
xputs "[ERR] Calling MIGRATE: #{e}"
exit 1
end
end
print "."*keys.length if o[:dots]
STDOUT.flush
end
puts if !o[:quiet]
# Set the new node as the owner of the slot in all the known nodes.
if !o[:cold]
@nodes.each{|n|
next if n.has_flag?("slave")
n.r.cluster("setslot",slot,"node",target.info[:name])
}
end
# Update the node logical config
if o[:update] then
source.info[:slots].delete(slot)
target.info[:slots][slot] = true
end
end
# redis-trib subcommands implementations.
def check_cluster_cmd(argv,opt)
load_cluster_info_from_node(argv[0])
check_cluster
end
def info_cluster_cmd(argv,opt)
load_cluster_info_from_node(argv[0])
show_cluster_info
end
def rebalance_cluster_cmd(argv,opt)
opt = {
'pipeline' => MigrateDefaultPipeline,
'threshold' => RebalanceDefaultThreshold
}.merge(opt)
# Load nodes info before parsing options, otherwise we can't
# handle --weight.
load_cluster_info_from_node(argv[0])
# Options parsing
threshold = opt['threshold'].to_i
autoweights = opt['auto-weights']
weights = {}
opt['weight'].each{|w|
fields = w.split("=")
node = get_node_by_abbreviated_name(fields[0])
if !node || !node.has_flag?("master")
puts "*** No such master node #{fields[0]}"
exit 1
end
weights[node.info[:name]] = fields[1].to_f
} if opt['weight']
useempty = opt['use-empty-masters']
# Assign a weight to each node, and compute the total cluster weight.
total_weight = 0
nodes_involved = 0
@nodes.each{|n|
if n.has_flag?("master")
next if !useempty && n.slots.length == 0
n.info[:w] = weights[n.info[:name]] ? weights[n.info[:name]] : 1
total_weight += n.info[:w]
nodes_involved += 1
end
}
# Check cluster, only proceed if it looks sane.
check_cluster(:quiet => true)
if @errors.length != 0
puts "*** Please fix your cluster problems before rebalancing"
exit 1
end
# Calculate the slots balance for each node. It's the number of
# slots the node should lose (if positive) or gain (if negative)
# in order to be balanced.
threshold = opt['threshold'].to_f
threshold_reached = false
@nodes.each{|n|
if n.has_flag?("master")
next if !n.info[:w]
expected = ((ClusterHashSlots.to_f / total_weight) *
n.info[:w]).to_i
n.info[:balance] = n.slots.length - expected
# Compute the percentage of difference between the
# expected number of slots and the real one, to see
# if it's over the threshold specified by the user.
over_threshold = false
if threshold > 0
if n.slots.length > 0
err_perc = (100-(100.0*expected/n.slots.length)).abs
over_threshold = true if err_perc > threshold
elsif expected > 0
over_threshold = true
end
end
threshold_reached = true if over_threshold
end
}
if !threshold_reached
xputs "*** No rebalancing needed! All nodes are within the #{threshold}% threshold."
return
end
# Only consider nodes we want to change
sn = @nodes.select{|n|
n.has_flag?("master") && n.info[:w]
}
# Because of rounding, it is possible that the balance of all nodes
# summed does not give 0. Make sure that nodes that have to provide
# slots are always matched by nodes receiving slots.
total_balance = sn.map{|x| x.info[:balance]}.reduce{|a,b| a+b}
while total_balance > 0
sn.each{|n|
if n.info[:balance] < 0 && total_balance > 0
n.info[:balance] -= 1
total_balance -= 1
end
}
end
# Sort nodes by their slots balance.
sn = sn.sort{|a,b|
a.info[:balance] <=> b.info[:balance]
}
xputs ">>> Rebalancing across #{nodes_involved} nodes. Total weight = #{total_weight}"
if $verbose
sn.each{|n|
puts "#{n} balance is #{n.info[:balance]} slots"
}
end
# Now we have at the start of the 'sn' array nodes that should get
# slots, at the end nodes that must give slots.
# We take two indexes, one at the start, and one at the end,
# incrementing or decrementing the indexes accordingly til we
# find nodes that need to get/provide slots.
dst_idx = 0
src_idx = sn.length - 1
while dst_idx < src_idx
dst = sn[dst_idx]
src = sn[src_idx]
numslots = [dst.info[:balance],src.info[:balance]].map{|n|
n.abs
}.min
if numslots > 0
puts "Moving #{numslots} slots from #{src} to #{dst}"
# Actaully move the slots.
reshard_table = compute_reshard_table([src],numslots)
if reshard_table.length != numslots
xputs "*** Assertio failed: Reshard table != number of slots"
exit 1
end
if opt['simulate']
print "#"*reshard_table.length
else
reshard_table.each{|e|
move_slot(e[:source],dst,e[:slot],
:quiet=>true,
:dots=>false,
:update=>true,
:pipeline=>opt['pipeline'])
print "#"
STDOUT.flush
}
end
puts
end
# Update nodes balance.
dst.info[:balance] += numslots
src.info[:balance] -= numslots
dst_idx += 1 if dst.info[:balance] == 0
src_idx -= 1 if src.info[:balance] == 0
end
end
def fix_cluster_cmd(argv,opt)
@fix = true
@timeout = opt['timeout'].to_i if opt['timeout']
load_cluster_info_from_node(argv[0])
check_cluster
end
def reshard_cluster_cmd(argv,opt)
opt = {'pipeline' => MigrateDefaultPipeline}.merge(opt)
load_cluster_info_from_node(argv[0])
check_cluster
if @errors.length != 0
puts "*** Please fix your cluster problems before resharding"
exit 1
end
@timeout = opt['timeout'].to_i if opt['timeout'].to_i
# Get number of slots
if opt['slots']
numslots = opt['slots'].to_i
else
numslots = 0
while numslots <= 0 or numslots > ClusterHashSlots
print "How many slots do you want to move (from 1 to #{ClusterHashSlots})? "
numslots = STDIN.gets.to_i
end
end
# Get the target instance
if opt['to']
target = get_node_by_name(opt['to'])
if !target || target.has_flag?("slave")
xputs "*** The specified node is not known or not a master, please retry."
exit 1
end
else
target = nil
while not target
print "What is the receiving node ID? "
target = get_node_by_name(STDIN.gets.chop)
if !target || target.has_flag?("slave")
xputs "*** The specified node is not known or not a master, please retry."
target = nil
end
end
end
# Get the source instances
sources = []
if opt['from']
opt['from'].split(',').each{|node_id|
if node_id == "all"
sources = "all"
break
end
src = get_node_by_name(node_id)
if !src || src.has_flag?("slave")
xputs "*** The specified node is not known or is not a master, please retry."
exit 1
end
sources << src
}
else
xputs "Please enter all the source node IDs."
xputs " Type 'all' to use all the nodes as source nodes for the hash slots."
xputs " Type 'done' once you entered all the source nodes IDs."
while true
print "Source node ##{sources.length+1}:"
line = STDIN.gets.chop
src = get_node_by_name(line)
if line == "done"
break
elsif line == "all"
sources = "all"
break
elsif !src || src.has_flag?("slave")
xputs "*** The specified node is not known or is not a master, please retry."
elsif src.info[:name] == target.info[:name]
xputs "*** It is not possible to use the target node as source node."
else
sources << src
end
end
end
if sources.length == 0
puts "*** No source nodes given, operation aborted"
exit 1
end
# Handle soures == all.
if sources == "all"
sources = []
@nodes.each{|n|
next if n.info[:name] == target.info[:name]
next if n.has_flag?("slave")
sources << n
}
end
# Check if the destination node is the same of any source nodes.
if sources.index(target)
xputs "*** Target node is also listed among the source nodes!"
exit 1
end
puts "\nReady to move #{numslots} slots."
puts " Source nodes:"
sources.each{|s| puts " "+s.info_string}
puts " Destination node:"
puts " #{target.info_string}"
reshard_table = compute_reshard_table(sources,numslots)
puts " Resharding plan:"
show_reshard_table(reshard_table)
if !opt['yes']
print "Do you want to proceed with the proposed reshard plan (yes/no)? "
yesno = STDIN.gets.chop
exit(1) if (yesno != "yes")
end
reshard_table.each{|e|
move_slot(e[:source],target,e[:slot],
:dots=>true,
:pipeline=>opt['pipeline'])
}
end
# This is an helper function for create_cluster_cmd that verifies if
# the number of nodes and the specified replicas have a valid configuration
# where there are at least three master nodes and enough replicas per node.
def check_create_parameters
masters = @nodes.length/(@replicas+1)
if masters < 3
puts "*** ERROR: Invalid configuration for cluster creation."
puts "*** Redis Cluster requires at least 3 master nodes."
puts "*** This is not possible with #{@nodes.length} nodes and #{@replicas} replicas per node."
puts "*** At least #{3*(@replicas+1)} nodes are required."
exit 1
end
end
def create_cluster_cmd(argv,opt)
opt = {'replicas' => 0}.merge(opt)
@replicas = opt['replicas'].to_i
xputs ">>> Creating cluster"
argv[0..-1].each{|n|
node = ClusterNode.new(n)
node.connect(:abort => true)
node.assert_cluster
node.load_info
node.assert_empty
add_node(node)
}
check_create_parameters
xputs ">>> Performing hash slots allocation on #{@nodes.length} nodes..."
alloc_slots
show_nodes
yes_or_die "Can I set the above configuration?"
flush_nodes_config
xputs ">>> Nodes configuration updated"
xputs ">>> Assign a different config epoch to each node"
assign_config_epoch
xputs ">>> Sending CLUSTER MEET messages to join the cluster"
join_cluster
# Give one second for the join to start, in order to avoid that
# wait_cluster_join will find all the nodes agree about the config as
# they are still empty with unassigned slots.
sleep 1
wait_cluster_join
flush_nodes_config # Useful for the replicas
# Reset the node information, so that when the
# final summary is listed in check_cluster about the newly created cluster
# all the nodes would get properly listed as slaves or masters
reset_nodes
load_cluster_info_from_node(argv[0])
check_cluster
end
def addnode_cluster_cmd(argv,opt)
xputs ">>> Adding node #{argv[0]} to cluster #{argv[1]}"
# Check the existing cluster
load_cluster_info_from_node(argv[1])
check_cluster
# If --master-id was specified, try to resolve it now so that we
# abort before starting with the node configuration.
if opt['slave']
if opt['master-id']
master = get_node_by_name(opt['master-id'])
if !master
xputs "[ERR] No such master ID #{opt['master-id']}"
end
else
master = get_master_with_least_replicas
xputs "Automatically selected master #{master}"
end
end
# Add the new node
new = ClusterNode.new(argv[0])
new.connect(:abort => true)
new.assert_cluster
new.load_info
new.assert_empty
first = @nodes.first.info
add_node(new)
# Send CLUSTER MEET command to the new node
xputs ">>> Send CLUSTER MEET to node #{new} to make it join the cluster."
new.r.cluster("meet",first[:host],first[:port])
# Additional configuration is needed if the node is added as
# a slave.
if opt['slave']
wait_cluster_join
xputs ">>> Configure node as replica of #{master}."
new.r.cluster("replicate",master.info[:name])
end
xputs "[OK] New node added correctly."
end
def delnode_cluster_cmd(argv,opt)
id = argv[1].downcase
xputs ">>> Removing node #{id} from cluster #{argv[0]}"
# Load cluster information
load_cluster_info_from_node(argv[0])
# Check if the node exists and is not empty
node = get_node_by_name(id)
if !node
xputs "[ERR] No such node ID #{id}"
exit 1
end
if node.slots.length != 0
xputs "[ERR] Node #{node} is not empty! Reshard data away and try again."
exit 1
end
# Send CLUSTER FORGET to all the nodes but the node to remove
xputs ">>> Sending CLUSTER FORGET messages to the cluster..."
@nodes.each{|n|
next if n == node
if n.info[:replicate] && n.info[:replicate].downcase == id
# Reconfigure the slave to replicate with some other node
master = get_master_with_least_replicas
xputs ">>> #{n} as replica of #{master}"
n.r.cluster("replicate",master.info[:name])
end
n.r.cluster("forget",argv[1])
}
# Finally shutdown the node
xputs ">>> SHUTDOWN the node."
node.r.shutdown
end
def set_timeout_cluster_cmd(argv,opt)
timeout = argv[1].to_i
if timeout < 100
puts "Setting a node timeout of less than 100 milliseconds is a bad idea."
exit 1
end
# Load cluster information
load_cluster_info_from_node(argv[0])
ok_count = 0
err_count = 0
# Send CLUSTER FORGET to all the nodes but the node to remove
xputs ">>> Reconfiguring node timeout in every cluster node..."
@nodes.each{|n|
begin
n.r.config("set","cluster-node-timeout",timeout)
n.r.config("rewrite")
ok_count += 1
xputs "*** New timeout set for #{n}"
rescue => e
puts "ERR setting node-timeot for #{n}: #{e}"
err_count += 1
end
}
xputs ">>> New node timeout set. #{ok_count} OK, #{err_count} ERR."
end
def call_cluster_cmd(argv,opt)
cmd = argv[1..-1]
cmd[0] = cmd[0].upcase
# Load cluster information
load_cluster_info_from_node(argv[0])
xputs ">>> Calling #{cmd.join(" ")}"
@nodes.each{|n|
begin
res = n.r.send(*cmd)
puts "#{n}: #{res}"
rescue => e
puts "#{n}: #{e}"
end
}
end
def import_cluster_cmd(argv,opt)
source_addr = opt['from']
xputs ">>> Importing data from #{source_addr} to cluster #{argv[1]}"
use_copy = opt['copy']
use_replace = opt['replace']
# Check the existing cluster.
load_cluster_info_from_node(argv[0])
check_cluster
# Connect to the source node.
xputs ">>> Connecting to the source Redis instance"
src_host,src_port = source_addr.split(":")
source = Redis.new(:host =>src_host, :port =>src_port)
if source.info['cluster_enabled'].to_i == 1
xputs "[ERR] The source node should not be a cluster node."
end
xputs "*** Importing #{source.dbsize} keys from DB 0"
# Build a slot -> node map
slots = {}
@nodes.each{|n|
n.slots.each{|s,_|
slots[s] = n
}
}
# Use SCAN to iterate over the keys, migrating to the
# right node as needed.
cursor = nil
while cursor != 0
cursor,keys = source.scan(cursor, :count => 1000)
cursor = cursor.to_i
keys.each{|k|
# Migrate keys using the MIGRATE command.
slot = key_to_slot(k)
target = slots[slot]
print "Migrating #{k} to #{target}: "
STDOUT.flush
begin
cmd = ["migrate",target.info[:host],target.info[:port],k,0,@timeout]
cmd << :copy if use_copy
cmd << :replace if use_replace
source.client.call(cmd)
rescue => e
puts e
else
puts "OK"
end
}
end
end
def help_cluster_cmd(argv,opt)
show_help
exit 0
end
# Parse the options for the specific command "cmd".
# Returns an hash populate with option => value pairs, and the index of
# the first non-option argument in ARGV.
def parse_options(cmd)
idx = 1 ; # Current index into ARGV
options={}
while idx < ARGV.length && ARGV[idx][0..1] == '--'
if ARGV[idx][0..1] == "--"
option = ARGV[idx][2..-1]
idx += 1
# --verbose is a global option
if option == "verbose"
$verbose = true
next
end
if ALLOWED_OPTIONS[cmd] == nil || ALLOWED_OPTIONS[cmd][option] == nil
puts "Unknown option '#{option}' for command '#{cmd}'"
exit 1
end
if ALLOWED_OPTIONS[cmd][option] != false
value = ARGV[idx]
idx += 1
else
value = true
end
# If the option is set to [], it's a multiple arguments
# option. We just queue every new value into an array.
if ALLOWED_OPTIONS[cmd][option] == []
options[option] = [] if !options[option]
options[option] << value
else
options[option] = value
end
else
# Remaining arguments are not options.
break
end
end
# Enforce mandatory options
if ALLOWED_OPTIONS[cmd]
ALLOWED_OPTIONS[cmd].each {|option,val|
if !options[option] && val == :required
puts "Option '--#{option}' is required "+ \
"for subcommand '#{cmd}'"
exit 1
end
}
end
return options,idx
end
end
#################################################################################
# Libraries
#
# We try to don't depend on external libs since this is a critical part
# of Redis Cluster.
#################################################################################
# This is the CRC16 algorithm used by Redis Cluster to hash keys.
# Implementation according to CCITT standards.
#
# This is actually the XMODEM CRC 16 algorithm, using the
# following parameters:
#
# Name : "XMODEM", also known as "ZMODEM", "CRC-16/ACORN"
# Width : 16 bit
# Poly : 1021 (That is actually x^16 + x^12 + x^5 + 1)
# Initialization : 0000
# Reflect Input byte : False
# Reflect Output CRC : False
# Xor constant to output CRC : 0000
# Output for "123456789" : 31C3
module RedisClusterCRC16
def RedisClusterCRC16.crc16(bytes)
crc = 0
bytes.each_byte{|b|
crc = ((crc<<8) & 0xffff) ^ XMODEMCRC16Lookup[((crc>>8)^b) & 0xff]
}
crc
end
private
XMODEMCRC16Lookup = [
0x0000,0x1021,0x2042,0x3063,0x4084,0x50a5,0x60c6,0x70e7,
0x8108,0x9129,0xa14a,0xb16b,0xc18c,0xd1ad,0xe1ce,0xf1ef,
0x1231,0x0210,0x3273,0x2252,0x52b5,0x4294,0x72f7,0x62d6,
0x9339,0x8318,0xb37b,0xa35a,0xd3bd,0xc39c,0xf3ff,0xe3de,
0x2462,0x3443,0x0420,0x1401,0x64e6,0x74c7,0x44a4,0x5485,
0xa56a,0xb54b,0x8528,0x9509,0xe5ee,0xf5cf,0xc5ac,0xd58d,
0x3653,0x2672,0x1611,0x0630,0x76d7,0x66f6,0x5695,0x46b4,
0xb75b,0xa77a,0x9719,0x8738,0xf7df,0xe7fe,0xd79d,0xc7bc,
0x48c4,0x58e5,0x6886,0x78a7,0x0840,0x1861,0x2802,0x3823,
0xc9cc,0xd9ed,0xe98e,0xf9af,0x8948,0x9969,0xa90a,0xb92b,
0x5af5,0x4ad4,0x7ab7,0x6a96,0x1a71,0x0a50,0x3a33,0x2a12,
0xdbfd,0xcbdc,0xfbbf,0xeb9e,0x9b79,0x8b58,0xbb3b,0xab1a,
0x6ca6,0x7c87,0x4ce4,0x5cc5,0x2c22,0x3c03,0x0c60,0x1c41,
0xedae,0xfd8f,0xcdec,0xddcd,0xad2a,0xbd0b,0x8d68,0x9d49,
0x7e97,0x6eb6,0x5ed5,0x4ef4,0x3e13,0x2e32,0x1e51,0x0e70,
0xff9f,0xefbe,0xdfdd,0xcffc,0xbf1b,0xaf3a,0x9f59,0x8f78,
0x9188,0x81a9,0xb1ca,0xa1eb,0xd10c,0xc12d,0xf14e,0xe16f,
0x1080,0x00a1,0x30c2,0x20e3,0x5004,0x4025,0x7046,0x6067,
0x83b9,0x9398,0xa3fb,0xb3da,0xc33d,0xd31c,0xe37f,0xf35e,
0x02b1,0x1290,0x22f3,0x32d2,0x4235,0x5214,0x6277,0x7256,
0xb5ea,0xa5cb,0x95a8,0x8589,0xf56e,0xe54f,0xd52c,0xc50d,
0x34e2,0x24c3,0x14a0,0x0481,0x7466,0x6447,0x5424,0x4405,
0xa7db,0xb7fa,0x8799,0x97b8,0xe75f,0xf77e,0xc71d,0xd73c,
0x26d3,0x36f2,0x0691,0x16b0,0x6657,0x7676,0x4615,0x5634,
0xd94c,0xc96d,0xf90e,0xe92f,0x99c8,0x89e9,0xb98a,0xa9ab,
0x5844,0x4865,0x7806,0x6827,0x18c0,0x08e1,0x3882,0x28a3,
0xcb7d,0xdb5c,0xeb3f,0xfb1e,0x8bf9,0x9bd8,0xabbb,0xbb9a,
0x4a75,0x5a54,0x6a37,0x7a16,0x0af1,0x1ad0,0x2ab3,0x3a92,
0xfd2e,0xed0f,0xdd6c,0xcd4d,0xbdaa,0xad8b,0x9de8,0x8dc9,
0x7c26,0x6c07,0x5c64,0x4c45,0x3ca2,0x2c83,0x1ce0,0x0cc1,
0xef1f,0xff3e,0xcf5d,0xdf7c,0xaf9b,0xbfba,0x8fd9,0x9ff8,
0x6e17,0x7e36,0x4e55,0x5e74,0x2e93,0x3eb2,0x0ed1,0x1ef0
]
end
# Turn a key name into the corrisponding Redis Cluster slot.
def key_to_slot(key)
# Only hash what is inside {...} if there is such a pattern in the key.
# Note that the specification requires the content that is between
# the first { and the first } after the first {. If we found {} without
# nothing in the middle, the whole key is hashed as usually.
s = key.index "{"
if s
e = key.index "}",s+1
if e && e != s+1
key = key[s+1..e-1]
end
end
RedisClusterCRC16.crc16(key) % 16384
end
#################################################################################
# Definition of commands
#################################################################################
COMMANDS={
"create" => ["create_cluster_cmd", -2, "host1:port1 ... hostN:portN"],
"check" => ["check_cluster_cmd", 2, "host:port"],
"info" => ["info_cluster_cmd", 2, "host:port"],
"fix" => ["fix_cluster_cmd", 2, "host:port"],
"reshard" => ["reshard_cluster_cmd", 2, "host:port"],
"rebalance" => ["rebalance_cluster_cmd", -2, "host:port"],
"add-node" => ["addnode_cluster_cmd", 3, "new_host:new_port existing_host:existing_port"],
"del-node" => ["delnode_cluster_cmd", 3, "host:port node_id"],
"set-timeout" => ["set_timeout_cluster_cmd", 3, "host:port milliseconds"],
"call" => ["call_cluster_cmd", -3, "host:port command arg arg .. arg"],
"import" => ["import_cluster_cmd", 2, "host:port"],
"help" => ["help_cluster_cmd", 1, "(show this help)"]
}
ALLOWED_OPTIONS={
"create" => {"replicas" => true},
"add-node" => {"slave" => false, "master-id" => true},
"import" => {"from" => :required, "copy" => false, "replace" => false},
"reshard" => {"from" => true, "to" => true, "slots" => true, "yes" => false, "timeout" => true, "pipeline" => true},
"rebalance" => {"weight" => [], "auto-weights" => false, "use-empty-masters" => false, "timeout" => true, "simulate" => false, "pipeline" => true, "threshold" => true},
"fix" => {"timeout" => MigrateDefaultTimeout},
}
def show_help
puts "Usage: redis-trib <command> <options> <arguments ...>\n\n"
COMMANDS.each{|k,v|
puts " #{k.ljust(15)} #{v[2]}"
if ALLOWED_OPTIONS[k]
ALLOWED_OPTIONS[k].each{|optname,has_arg|
puts " --#{optname}" + (has_arg ? " <arg>" : "")
}
end
}
puts "\nFor check, fix, reshard, del-node, set-timeout you can specify the host and port of any working node in the cluster.\n"
end
# Sanity check
if ARGV.length == 0
show_help
exit 1
end
rt = RedisTrib.new
cmd_spec = COMMANDS[ARGV[0].downcase]
if !cmd_spec
puts "Unknown redis-trib subcommand '#{ARGV[0]}'"
exit 1
end
# Parse options
cmd_options,first_non_option = rt.parse_options(ARGV[0].downcase)
rt.check_arity(cmd_spec[1],ARGV.length-(first_non_option-1))
# Dispatch
rt.send(cmd_spec[0],ARGV[first_non_option..-1],cmd_options)
设置网段
docker network create --subnet=192.168.1.0/16 redis-network
docker network ls 查看网段
docker network insect 网段id ,查看详情
docker-composer编排
#能够编排管理3个容器,php,redis,nginx
version: "3.6"
services: #服务
master-1:
image: redis-cluster #镜像名称
container_name: cluster-1 #生成的容器名称
environment:
- REALIP=118.24.109.254 #宿主机ip
- PORT=6390
- PORT2=16390
networks:
redis-network: #之前创建的网络名称
ipv4_address: 192.168.1.20 #设置ip地址
working_dir: /usr/src/redis #工作目录
stdin_open: true
tty: true
ports:
- "6390:6379"
- "16390:16379"
volumes:
- /usr/test/10/redis/master-1:/usr/src/redis #目录映射
entrypoint:
- /bin/bash
- /usr/src/sh/cluster.sh
master-2:
image: redis-cluster
container_name: cluster-2
environment:
- REALIP=118.24.109.254
- PORT=6391
- PORT2=16391
networks:
redis-network: #网络名称
ipv4_address: 192.168.1.21 #设置ip地址
working_dir: /usr/src/redis #工作目录
stdin_open: true
tty: true
ports:
- "6391:6379"
- "16391:16379"
volumes:
- /usr/test/10/redis/master-2:/usr/src/redis
entrypoint:
- /bin/bash
- /usr/src/sh/cluster.sh
master-3:
image: redis-cluster
container_name: cluster-3
environment:
- REALIP=118.24.109.254
- PORT=6392
- PORT2=16392
networks:
redis-network: #网络名称
ipv4_address: 192.168.1.22 #设置ip地址
working_dir: /usr/src/redis #工作目录
stdin_open: true
tty: true
ports:
- "6392:6379"
- "16392:16379"
volumes:
- /usr/test/10/redis/master-3:/usr/src/redis
entrypoint:
- /bin/bash
- /usr/src/sh/cluster.sh
slave-1:
image: redis-cluster
container_name: cluster-4
environment:
- REALIP=118.24.109.254
- PORT=6393
- PORT2=16393
networks:
redis-network: #网络名称
ipv4_address: 192.168.1.23 #设置ip地址
working_dir: /usr/src/redis #工作目录
stdin_open: true
tty: true
ports:
- "6393:6379"
- "16393:16379"
volumes:
- /usr/test/10/redis/slave-1:/usr/src/redis
entrypoint:
- /bin/sh
- /usr/src/sh/cluster.sh
slave-2:
image: redis-cluster
container_name: cluster-5
environment:
- REALIP=118.24.109.254
- PORT=6394
- PORT2=16394
networks:
redis-network: #网络名称
ipv4_address: 192.168.1.24 #设置ip地址
working_dir: /usr/src/redis #工作目录
stdin_open: true
tty: true
ports:
- "6394:6379"
- "16394:16379"
volumes:
- /usr/test/10/redis/slave-2:/usr/src/redis
entrypoint:
- /bin/bash
- /usr/src/sh/cluster.sh
slave-3:
image: redis-cluster
container_name: cluster-6
environment:
- REALIP=118.24.109.254
- PORT=6395
- PORT2=16395
networks:
redis-network: #网络名称
ipv4_address: 192.168.1.25 #设置ip地址
working_dir: /usr/src/redis #工作目录
stdin_open: true
tty: true
ports:
- "6395:6379"
- "16395:16379"
volumes:
- /usr/test/10/redis/slave-3:/usr/src/redis
entrypoint:
- /bin/bash
- /usr/src/sh/cluster.sh
#引用外部预先定义好的网段
networks:
redis-network:
external:
name: redis-network
docker ps查看容器运行情况
集群构建
进入随机一个容器
docker exec -it cluster-1 bash
cd /usr/src/sh
进去容器进去到有redis-trib.rb(基于ruby写的文件)文件的目录下运行,创建集群,会自动分配槽节点,前面是master,后面是slave
./redis-trib.rb create --replicas 1 192.168.162.133:6390 192.168.162.133:6391 192.168.162.133:6392 192.168.162.133:6393 192.168.162.133:6394 192.168.162.133:6395
注意事项:
如果设置了集群master 密码,需要修改redis-trib.rb 99行 timeout => 60后面 + :password=>“123456”
reshard 迁移槽节点 rebalance 重新分配槽节点
注意扩容缩容前需要迁移槽,然后再增加节点或者下线节点
如果要重新建立集群需要删除原来集群生成的配置文件,如nodes-6379.conf,集群配置由集群自动生成,不可以自己修改,否则可能会出现预想不到的问题,
集群配置文件名称由redis.conf( cluster-config-file nodes-6379.conf(集群配置文件名称))定义
客户端封装批量删除操作
客户端连接集群最好使用redis扩展,predis扩展对集群的封装没那么好
安装predis
<?php
require "vendor/autoload.php";
//1.将数据槽跟节点的关系映射 (为了能够知道某个key,对应的节点)
try{
$server=[
'118.24.109.254:6398',
'118.24.109.254:6392',
'118.24.109.254:6390',
'118.24.109.254:6391'
];
$options=[
'cluster'=>'redis',
'parameters'=>
[
'password'=>'sixstar'
]
];
$client=new Predis\Client($server,$options);
$connectionId=$server[array_rand($server)];
//得到槽节点信息,保存在某个缓存文件当中
$slotInfo=$client->getClientFor($connectionId)->executeRaw(['cluster','slots']);
/* 槽范围 节点ip
* [1,1000]=>118.24.109.254:6380
*
* */
$slotNodes=[]; //数据槽跟节点的映射关系
foreach ($slotInfo as $slots=>$nodes){
$slotNodes[$nodes[0].','.$nodes[1]]=$nodes[2][0].':'.$nodes[2][1];
}
//执行批量删除操作
$delKeys=['name1','name2','name3','name4','name5','name6'];
//2.得到key跟节点的对应关系
$crc=new \Predis\Cluster\Hash\CRC16();
/*
* 使用管道发送命令,可以节约一点网络资源
* ['118.24.109.254:6390']=>'name1,name2'
* ['118.24.109.254:6391']=>'name4,name5'
* ['118.24.109.254:6393']=>'name3'
*
* */
//作业封装mget函数,用来批量操作
$slotKeys=[];
foreach ($delKeys as $keyName){
$code=$crc->hash($keyName) % 16384; //计算出某个key对应的槽节点
//循环匹配,如果key在某个节点的范围之内就拼接数据(有可能多个key在同一节点)
array_walk($slotNodes,function($node,$slotRange)use($code,&$slotKeys,$keyName){
$range=explode(",",$slotRange);
//判断某个key计算出来的槽,是否在这个范围之内,如果是就添加
if($code>=$range[0] && $code<=$range[1] ){
$slotKeys[$node][]=$keyName;
}
});
}
//执行命令并且返回结果
foreach ($slotKeys as $node=>$keys){
$res=$client->getClientFor($node)->pipeline(function ($pipe)use($keys){
foreach ($keys as $v) {
$pipe->del($v);
}
});
//对应下key跟结果
var_dump($res);
}
}catch (\Exception $e){
var_dump($e->getMessage());
//更新缓存信息因为槽跟节点的对应关系已经发生改变了,并且发送命令到正确的节点上
if(strpos($e->getMessage(),"moved") !==false){
}
}