redis-shake数据同步与迁移工具

 文章系转载，便于整理和分类，原文地址：https://developer.aliyun.com/article/691794

# This file is the configuration of redis-shake.

# If you have any problem, please visit: https://github.com/alibaba/RedisShake/wiki/FAQ
# 有疑问请先查阅：https://github.com/alibaba/RedisShake/wiki/FAQ

# current configuration version, do not modify.
# 当前配置文件的版本号，请不要修改该值。
conf.version = 1

# id
id = redis-shake

# The log file name, if left blank, it will be printed to stdout,
# otherwise it will be printed to the specified file.
# 日志文件名，留空则会打印到 stdout，否则打印到指定文件。
# for example:
#   log.file =
#   log.file = /var/log/redis-shake.log
log.file =

# log level: "none", "error", "warn", "info", "debug".
# default is "info".
# 日志等级，可选：none error warn info debug
# 默认为：info
log.level = info

# 进程文件存储目录，留空则会输出到当前目录,
# 注意这个是目录，真正生成的 pid 是 {pid_path}/{id}.pid
# 例如：
#   pid_path = ./
#   pid_path = /var/run/
pid_path = 

# pprof port.
system_profile = 9310

# restful port, set -1 means disable, in `restore` mode RedisShake will exit once finish restoring RDB only if this value
# is -1, otherwise, it'll wait forever.
# restful port, 查看 metric 端口, -1 表示不启用. 如果是`restore`模式，只有设置为-1才会在完成RDB恢复后退出，否则会一直block。
#   http://127.0.0.1:9320/conf   查看 redis-shake 使用的配置
#   http://127.0.0.1:9320/metric 查看 redis-shake 的同步情况
http_profile = 9320

# parallel routines number used in RDB file syncing. default is 64.
# 启动多少个并发线程同步一个RDB文件。
parallel = 32

# source redis configuration.
# used in `dump`, `sync` and `rump`.
# source redis type, e.g. "standalone" (default), "sentinel" or "cluster".
#   1. "standalone": standalone db mode.
#   2. "sentinel": the redis address is read from sentinel.
#   3. "cluster": the source redis has several db.
#   4. "proxy": the proxy address, currently, only used in "rump" mode.
# used in `dump`, `sync` and `rump`.
# 源端 Redis 的类型，可选：standalone sentinel cluster proxy
# 注意：proxy 只用于 rump 模式。
source.type = standalone

# ip:port
# the source address can be the following:
#   1. single db address. for "standalone" type.
#   2. ${sentinel_master_name}:${master or slave}@sentinel single/cluster address, e.g., mymaster:master@127.0.0.1:26379;127.0.0.1:26380, or @127.0.0.1:26379;127.0.0.1:26380. for "sentinel" type.
#   3. cluster that has several db nodes split by semicolon(;). for "cluster" type. e.g., 10.1.1.1:20331;10.1.1.2:20441.
#   4. proxy address(used in "rump" mode only). for "proxy" type.
# 源redis地址。对于sentinel或者开源cluster模式，输入格式为"master名字:拉取角色为master或者slave@sentinel的地址"，别的cluster
# 架构，比如codis, twemproxy, aliyun proxy等需要配置所有master或者slave的db地址。
# 源端 redis 的地址
#   1. standalone 模式配置 ip:port, 例如: 10.1.1.1:20331
#   2. cluster 模式需要配置所有 nodes 的 ip:port, 例如: source.address = 10.1.1.1:20331;10.1.1.2:20441
source.address = 127.0.0.1:20441

# source password, left blank means no password.
# 源端密码，留空表示无密码。
source.password_raw =

# auth type, don't modify it
source.auth_type = auth
# tls enable, true or false. Currently, only support standalone.
# open source redis does NOT support tls so far, but some cloud versions do.
source.tls_enable = false
# Whether to verify the validity of the redis certificate, true means verification, false means no verification
source.tls_skip_verify = false
# input RDB file.
# used in `decode` and `restore`.
# if the input is list split by semicolon(;), redis-shake will restore the list one by one.
# 如果是decode或者restore，这个参数表示读取的rdb文件。支持输入列表，例如：rdb.0;rdb.1;rdb.2
# redis-shake将会挨个进行恢复。
source.rdb.input =
# the concurrence of RDB syncing, default is len(source.address) or len(source.rdb.input).
# used in `dump`, `sync` and `restore`. 0 means default.
# This is useless when source.type isn't cluster or only input is only one RDB.
# 拉取的并发度，如果是`dump`或者`sync`，默认是source.address中db的个数，`restore`模式默认len(source.rdb.input)。
# 假如db节点/输入的rdb有5个，但rdb.parallel=3，那么一次只会
# 并发拉取3个db的全量数据，直到某个db的rdb拉取完毕并进入增量，才会拉取第4个db节点的rdb，
# 以此类推，最后会有len(source.address)或者len(rdb.input)个增量线程同时存在。
source.rdb.parallel = 0
# for special cloud vendor: ucloud
# used in `decode` and `restore`.
# ucloud集群版的rdb文件添加了slot前缀，进行特判剥离: ucloud_cluster。
source.rdb.special_cloud = 

# target redis configuration. used in `restore`, `sync` and `rump`.
# the type of target redis can be "standalone", "proxy" or "cluster".
#   1. "standalone": standalone db mode.
#   2. "sentinel": the redis address is read from sentinel.
#   3. "cluster": open source cluster (not supported currently).
#   4. "proxy": proxy layer ahead redis. Data will be inserted in a round-robin way if more than 1 proxy given.
# 目的redis的类型，支持standalone，sentinel，cluster和proxy四种模式。
target.type = standalone
# ip:port
# the target address can be the following:
#   1. single db address. for "standalone" type.
#   2. ${sentinel_master_name}:${master or slave}@sentinel single/cluster address, e.g., mymaster:master@127.0.0.1:26379;127.0.0.1:26380, or @127.0.0.1:26379;127.0.0.1:26380. for "sentinel" type.
#   3. cluster that has several db nodes split by semicolon(;). for "cluster" type.
#   4. proxy address. for "proxy" type.
target.address = 127.0.0.1:6379

# target password, left blank means no password.
# 目的端密码，留空表示无密码。
target.password_raw =

# auth type, don't modify it
target.auth_type = auth
# all the data will be written into this db. < 0 means disable.
target.db = -1

# Format: 0-5;1-3 ,Indicates that the data of the source db0 is written to the target db5, and 
# the data of the source db1 is all written to the target db3. 
# Note: When target.db is specified, target.dbmap will not take effect.
# 例如 0-5;1-3 表示源端 db0 的数据会被写入目的端 db5, 源端 db1 的数据会被写入目的端 db3
# 当 target.db 开启的时候 target.dbmap 不会生效.
target.dbmap =

# tls enable, true or false. Currently, only support standalone.
# open source redis does NOT support tls so far, but some cloud versions do.
target.tls_enable = false
# Whether to verify the validity of the redis certificate, true means verification, false means no verification
target.tls_skip_verify = false
# output RDB file prefix.
# used in `decode` and `dump`.
# 如果是decode或者dump，这个参数表示输出的rdb前缀，比如输入有3个db，那么dump分别是:
# ${output_rdb}.0, ${output_rdb}.1, ${output_rdb}.2
target.rdb.output = local_dump
# some redis proxy like twemproxy doesn't support to fetch version, so please set it here.
# e.g., target.version = 4.0
target.version =

# use for expire key, set the time gap when source and target timestamp are not the same.
# 用于处理过期的键值，当迁移两端不一致的时候，目的端需要加上这个值
fake_time =

# how to solve when destination restore has the same key.
# rewrite: overwrite. 
# none: panic directly.
# ignore: skip this key. not used in rump mode.
# used in `restore`, `sync` and `rump`.
# 当源目的有重复 key 时是否进行覆写, 可选值:
#   1. rewrite: 源端覆盖目的端
#   2. none: 一旦发生进程直接退出
#   3. ignore: 保留目的端key，忽略源端的同步 key. 该值在 rump 模式下不会生效.
key_exists = none

# filter db, key, slot, lua.
# filter db.
# used in `restore`, `sync` and `rump`.
# e.g., "0;5;10" means match db0, db5 and db10.
# at most one of `filter.db.whitelist` and `filter.db.blacklist` parameters can be given.
# if the filter.db.whitelist is not empty, the given db list will be passed while others filtered.
# if the filter.db.blacklist is not empty, the given db list will be filtered while others passed.
# all dbs will be passed if no condition given.
# 指定的db被通过，比如0;5;10将会使db0, db5, db10通过, 其他的被过滤
filter.db.whitelist =
# 指定的db被过滤，比如0;5;10将会使db0, db5, db10过滤，其他的被通过
filter.db.blacklist =
# filter key with prefix string. multiple keys are separated by ';'.
# e.g., "abc;bzz" match let "abc", "abc1", "abcxxx", "bzz" and "bzzwww".
# used in `restore`, `sync` and `rump`.
# at most one of `filter.key.whitelist` and `filter.key.blacklist` parameters can be given.
# if the filter.key.whitelist is not empty, the given keys will be passed while others filtered.
# if the filter.key.blacklist is not empty, the given keys will be filtered while others passed.
# all the namespace will be passed if no condition given.
# 支持按前缀过滤key，只让指定前缀的key通过，分号分隔。比如指定abc，将会通过abc, abc1, abcxxx
filter.key.whitelist =
# 支持按前缀过滤key，不让指定前缀的key通过，分号分隔。比如指定abc，将会阻塞abc, abc1, abcxxx
filter.key.blacklist =
# filter given slot, multiple slots are separated by ';'.
# e.g., 1;2;3
# used in `sync`.
# 指定过滤slot，只让指定的slot通过
filter.slot =
# filter give commands. multiple commands are separated by ';'.
# e.g., "flushall;flushdb".
# used in `sync`.
# at most one of `filter.command.whitelist` and `filter.command.blacklist` parameters can be given.
# if the filter.command.whitelist is not empty, the given commands will be passed while others filtered.
# if the filter.command.blacklist is not empty, the given commands will be filtered.
# besides, the other config caused filters also effect as usual, e.g. filter.lua = true would filter lua commands.
# all the commands, except the other config caused filtered commands, will be passed if no condition given.
# 只让指定命令通过，分号分隔
filter.command.whitelist =
# 不让指定命令通过，分号分隔
# 除了这些指定的命令外，其他配置选项指定的过滤命令也会照常生效，如开启 filter.lua 将会过滤 lua 相关命令
filter.command.blacklist =
# filter lua script. true means not pass. However, in redis 5.0, the lua 
# converts to transaction(multi+{commands}+exec) which will be passed.
# 控制不让lua脚本通过，true表示不通过
filter.lua = false

# big key threshold, the default is 500 * 1024 * 1024 bytes. If the value is bigger than
# this given value, all the field will be spilt and write into the target in order. If
# the target Redis type is Codis, this should be set to 1, please checkout FAQ to find 
# the reason.
# 正常key如果不大，那么都是直接调用restore写入到目的端，如果key对应的value字节超过了给定
# 的值，那么会分批依次一个一个写入。如果目的端是Codis，这个需要置为1，具体原因请查看FAQ。
# 如果目的端大版本小于源端，也建议设置为1。
big_key_threshold = 524288000

# enable metric
# used in `sync`.
# 是否启用metric
metric = true
# print in log
# 是否将metric打印到log中
metric.print_log = false

# sender information.
# sender flush buffer size of byte.
# used in `sync`.
# 发送缓存的字节长度，超过这个阈值将会强行刷缓存发送
sender.size = 104857600
# sender flush buffer size of oplog number.
# used in `sync`. flush sender buffer when bigger than this threshold.
# 发送缓存的报文个数，超过这个阈值将会强行刷缓存发送，对于目的端是cluster的情况，这个值
# 的调大将会占用部分内存。
sender.count = 4095
# delay channel size. once one oplog is sent to target redis, the oplog id and timestamp will also
# stored in this delay queue. this timestamp will be used to calculate the time delay when receiving
# ack from target redis.
# used in `sync`.
# 用于metric统计时延的队列
sender.delay_channel_size = 65535

# enable keep_alive option in TCP when connecting redis.
# the unit is second.
# 0 means disable.
# TCP keep-alive保活参数，单位秒，0表示不启用。
keep_alive = 0

# used in `rump`.
# number of keys captured each time. default is 100.
# 每次scan的个数，不配置则默认100.
scan.key_number = 50
# used in `rump`.
# we support some special redis types that don't use default `scan` command like alibaba cloud and tencent cloud.
# 有些版本具有特殊的格式，与普通的scan命令有所不同，我们进行了特殊的适配。目前支持腾讯云的集群版"tencent_cluster"
# 和阿里云的集群版"aliyun_cluster"，注释主从版不需要配置，只针对集群版。
scan.special_cloud =
# used in `rump`.
# we support to fetching data from given file which marks the key list.
# 有些云版本，既不支持sync/psync，也不支持scan，我们支持从文件中进行读取所有key列表并进行抓取：一行一个key。
scan.key_file =

# limit the rate of transmission. Only used in `rump` currently.
# e.g., qps = 1000 means pass 1000 keys per second. default is 500,000(0 means default)
qps = 200000

# enable resume from break point, please visit xxx to see more details.
# 断点续传开关
resume_from_break_point = false

# ----------------splitter----------------
# below variables are useless for current open source version so don't set.

# replace hash tag.
# used in `sync`.
replace_hash_tag = false