jdk 1.8+
mkdir redis-rdb-cli cd ./redis-rdb-cli wget https://github.com/leonchen83/redis-rdb-cli/releases/download/${version}/redis-rdb-cli.zip unzip redis-rdb-cli.zip sudo chmod -R 755 ./ cd ./bin ./rct -h
jdk 1.8+ maven-3.3.1+
git clone https://github.com/leonchen83/redis-rdb-cli.git cd redis-rdb-cli mvn clean install -Dmaven.test.skip=true cd target/redis-rdb-cli/bin ./rct -h
Add /path/to/redis-rdb-cli/bin to Path environment variable
usage: rct -f <format> -s <source> -o <file> [-d <num num...>] [-e <escape>] [-k <regex regex...>] [-t <type type...>] [-b <bytes>] [-l <n>] [-r] options: -b,--bytes <bytes> limit memory output(--format mem) to keys greater to or equal to this value (in bytes) -d,--db <num num...> database number. multiple databases can be provided. if not specified, all databases will be included. -e,--escape <escape> escape strings to encoding: raw (default), redis. -f,--format <format> format to export. valid formats are json, dump, diff, key, keyval, count, mem and resp -h,--help rct usage. -k,--key <regex regex...> keys to export. this can be a regex. if not specified, all keys will be returned. -l,--largest <n> limit memory output(--format mem) to only the top n keys (by size). -o,--out <file> output file. -r,--replace whether the generated aof with <replace> parameter(--format dump). if not specified, default value is false. -s,--source <source> <source> eg: /path/to/dump.rdb redis://host:port?authPassword=foobar redis:///path/to/dump.rdb. -t,--type <type type...> data type to export. possible values are string, hash, set, sortedset, list, module, stream. multiple types can be provided. if not specified, all data types will be returned. -v,--version rct version. examples: rct -f dump -s ./dump.rdb -o ./appendonly.aof -r rct -f resp -s redis://127.0.0.1:6379 -o ./target.aof -d 0 1 rct -f json -s ./dump.rdb -o ./target.json -k user.* product.* rct -f mem -s ./dump.rdb -o ./target.aof -e redis -t list -l 10 -b 1024
usage: rmt -s <source> [-m <uri> | -c <file>] [-d <num num...>] [-k <regex regex...>] [-t <type type...>] [-r] options: -c,--config <file> migrate data to cluster via redis cluster's <nodes.conf> file, if specified, no need to specify --migrate. -d,--db <num num...> database number. multiple databases can be provided. if not specified, all databases will be included. -h,--help rmt usage. -k,--key <regex regex...> keys to export. this can be a regex. if not specified, all keys will be returned. -m,--migrate <uri> migrate to uri. eg: redis://host:port?authPassword=foobar. -r,--replace replace exist key value. if not specified, default value is false. -s,--source <source> <source> eg: /path/to/dump.rdb redis://host:port?authPassword=foobar redis:///path/to/dump.rdb -t,--type <type type...> data type to export. possible values are string, hash, set, sortedset, list, module, stream. multiple types can be provided. if not specified, all data types will be returned. -v,--version rmt version. examples: rmt -s ./dump.rdb -c ./nodes.conf -t string -r rmt -s ./dump.rdb -m redis://127.0.0.1:6380 -t list -d 0 rmt -s redis://120.0.0.1:6379 -m redis://127.0.0.1:6380 -d 0
usage: rdt [-b <source> | -s <source> -c <file> | -m <file file...>] -o <file> [-d <num num...>] [-k <regex regex...>] [-t <type type...>] options: -b,--backup <source> backup <source> to local rdb file. eg: /path/to/dump.rdb redis://host:port?authPassword=foobar redis:///path/to/dump.rdb -c,--config <file> redis cluster's <nodes.conf> file(--split <source>). -d,--db <num num...> database number. multiple databases can be provided. if not specified, all databases will be included. -h,--help rdt usage. -k,--key <regex regex...> keys to export. this can be a regex. if not specified, all keys will be returned. -m,--merge <file file...> merge multi rdb files to one rdb file. -o,--out <file> if --backup <source> or --merge <file file...> specified. the <file> is the target file. if --split <source> specified. the <file> is the target path. -s,--split <source> split rdb to multi rdb files via cluster's <nodes.conf>. eg: /path/to/dump.rdb redis://host:port?authPassword=foobar redis:///path/to/dump -t,--type <type type...> data type to export. possible values are string, hash, set, sortedset, list, module, stream. multiple types can be provided. if not specified, all data types will be returned. -v,--version rdt version. examples: rdt -b ./dump.rdb -o ./dump.rdb1 -d 0 1 rdt -b redis://127.0.0.1:6379 -o ./dump.rdb -k user.* rdt -m ./dump1.rdb ./dump2.rdb -o ./dump.rdb -t hash rdt -s ./dump.rdb -c ./nodes.conf -o /path/to/folder -t hash -d 0 rdt -s redis://127.0.0.1:6379 -c ./nodes.conf -o /path/to/folder -d 0
rct, rdt and rmt all these commands support data filter by type,db and key RegEx(Java style).
For example:
rct -f dump -s /path/to/dump.rdb -o /path/to/dump.aof -d 0 rct -f dump -s /path/to/dump.rdb -o /path/to/dump.aof -t string hash rmt -s /path/to/dump.rdb -m redis://192.168.1.105:6379 -r -d 0 1 -t list
rct -f dump -s /path/to/dump.rdb -o /path/to/dump.aof -r cat /path/to/dump.aof | /redis/src/redis-cli -p 6379 --pipe
rct -f dump -s /path/to/dump.rdb -o /path/to/dump.aof
rct -f json -s /path/to/dump.rdb -o /path/to/dump.json
rct -f count -s /path/to/dump.rdb -o /path/to/dump.csv
rct -f mem -s /path/to/dump.rdb -o /path/to/dump.mem -l 50
rct -f diff -s /path/to/dump1.rdb -o /path/to/dump1.diff rct -f diff -s /path/to/dump2.rdb -o /path/to/dump2.diff diff /path/to/dump1.diff /path/to/dump2.diff
rct -f resp -s /path/to/dump.rdb -o /path/to/appendonly.aof
rmt -s /path/to/dump.rdb -m redis://192.168.1.105:6379 -r
rmt -s /path/to/dump.rdb -c ./nodes-30001.conf -r
or simply use following cmd without nodes-30001.conf
rmt -s /path/to/dump.rdb -m redis://127.0.0.1:30001 -r
rdt -b redis://192.168.1.105:6379 -o /path/to/dump.rdb
rdt -b /path/to/dump.rdb -o /path/to/filtered-dump.rdb -d 0 -t string
rdt -s ./dump.rdb -c ./nodes.conf -o /path/to/folder -d 0
rdt -m ./dump1.rdb ./dump2.rdb -o ./dump.rdb -t hash
More configurable parameter can be modified in /path/to/redis-rdb-cli/conf/redis-rdb-cli.conf
Since v0.1.9, the rct -f mem support showing result in grafana dashboard like the following:
img
If you want to turn it on. you MUST install docker and docker-compose first, the installation please refer to docker
Then run the following command:
cd /path/to/redis-rdb-cli/dashboard docker-compose up -d
cd /path/to/redis-rdb-cli/conf/redis-rdb-cli.conf
Then change parameter metric_gateway from none to prometheus.
Open http://localhost:3000 to check the rct -f mem's result.
All done!
The rmt command use the following 4 parameters(redis-rdb-cli.conf) to migrate data to remote.
migrate_batch_size=4096 migrate_threads=4 migrate_flush=yes migrate_retries=1
The most important parameter is migrate_threads=4. this means we use the following threading model to migrate data.
single redis ----> single redis +--------------+ +----------+ thread 1 +--------------+ | | +----| Endpoint |-------------------| | | | | +----------+ | | | | | | | | | | +----------+ thread 2 | | | | |----| Endpoint |-------------------| | | | | +----------+ | | | Source Redis |----| | Target Redis | | | | +----------+ thread 3 | | | | |----| Endpoint |-------------------| | | | | +----------+ | | | | | | | | | | +----------+ thread 4 | | | | +----| Endpoint |-------------------| | +--------------+ +----------+ +--------------+
single redis ----> redis cluster +--------------+ +----------+ thread 1 +--------------+ | | +----| Endpoints|-------------------| | | | | +----------+ | | | | | | | | | | +----------+ thread 2 | | | | |----| Endpoints|-------------------| | | | | +----------+ | | | Source Redis |----| | Redis cluster| | | | +----------+ thread 3 | | | | |----| Endpoints|-------------------| | | | | +----------+ | | | | | | | | | | +----------+ thread 4 | | | | +----| Endpoints|-------------------| | +--------------+ +----------+ +--------------+
The difference between cluster migration and single migration is Endpoint and Endpoints. In cluster migration the Endpoints contains multi Endpoint to point to every master instance in cluster. For example:
3 masters 3 replicas redis cluster. if migrate_threads=4 then we have 3 * 4 = 12 connections that connected with master instance.
The following 3 parameters affect migration performance
migrate_batch_size=4096 migrate_retries=1 migrate_flush=yes
By default we use redis pipeline to migrate data to remote. the migrate_batch_size is the pipeline batch size. if migrate_batch_size=1 then the pipeline devolved into 1 single command to sent and wait the response from remote.
The migrate_retries=1 means if socket error occurred. we recreate a new socket and retry to send that failed command to target redis with migrate_retries times.
The migrate_flush=yes means we write every 1 command to socket. then we invoke SocketOutputStream.flush() immediately. if migrate_flush=no we invoke SocketOutputStream.flush() when write to socket every 64KB. notice that this parameter also affect migrate_retries. the migrate_retries only take effect when migrate_flush=yes
+---------------+ +-------------------+ restore +---------------+ | | | redis dump format |---------------->| | | | |-------------------| restore | | | | convert | redis dump format |---------------->| | | Dump rdb |------------>|-------------------| restore | Targe Redis | | | | redis dump format |---------------->| | | | |-------------------| restore | | | | | redis dump format |---------------->| | +---------------+ +-------------------+ +---------------+
We use cluster's nodes.conf to migrate data to cluster. because of we did't handle the MOVED ASK redirection. so the only limitation is that the cluster MUST in stable state during the migration. this means the cluster MUST have no migrating, importing slot and no switch slave to master.