ClickHouse Keeper

<keeper_server>
    <tcp_port>2181</tcp_port>
    <server_id>1</server_id>
    <log_storage_path>/var/lib/clickhouse/coordination/log</log_storage_path>
    <snapshot_storage_path>/var/lib/clickhouse/coordination/snapshots</snapshot_storage_path>

    <coordination_settings>
        <operation_timeout_ms>10000</operation_timeout_ms>
        <session_timeout_ms>30000</session_timeout_ms>
        <raft_logs_level>trace</raft_logs_level>
    </coordination_settings>

    <raft_configuration>
        <server>
            <id>1</id>
            <hostname>zoo1</hostname>
            <port>9234</port>
        </server>
        <server>
            <id>2</id>
            <hostname>zoo2</hostname>
            <port>9234</port>
        </server>
        <server>
            <id>3</id>
            <hostname>zoo3</hostname>
            <port>9234</port>
        </server>
    </raft_configuration>
</keeper_server>

clickhouse-keeper --config /etc/your_path_to_config/config.xml

clickhouse keeper --config /etc/your_path_to_config/config.xml

echo mntr | nc localhost 9181

imok

zk_version      v21.11.1.1-prestable-7a4a0b0edef0ad6e0aa662cd3b90c3f4acf796e7
zk_avg_latency  0
zk_max_latency  0
zk_min_latency  0
zk_packets_received     68
zk_packets_sent 68
zk_num_alive_connections        1
zk_outstanding_requests 0
zk_server_state leader
zk_slow_member_backpressure      0
zk_znode_count  4
zk_watch_count  1
zk_ephemerals_count     0
zk_approximate_data_size        723
zk_open_file_descriptor_count   310
zk_max_file_descriptor_count    10240
zk_leader_uptime        1234
zk_sum_leader_unavailable_time 1234
zk_cnt_leader_unavailable_time 1
zk_sum_election_time 1234
zk_cnt_election_time 1
zk_followers    0
zk_synced_followers     0

ClickHouse Keeper version: v21.11.1.1-prestable-7a4a0b0edef0ad6e0aa662cd3b90c3f4acf796e7
Latency min/avg/max: 0/0/0
Received: 2
Sent : 2
Connections: 1
Outstanding: 0
Zxid: 34
Mode: leader
Node count: 4

ClickHouse Keeper version: v21.11.1.1-prestable-7a4a0b0edef0ad6e0aa662cd3b90c3f4acf796e7
Clients:
 192.168.1.1:52852(recved=0,sent=0)
 192.168.1.1:52042(recved=24,sent=48)
Latency min/avg/max: 0/0/0
Received: 4
Sent : 4
Connections: 1
Outstanding: 0
Zxid: 36
Mode: leader
Node count: 4

Server stats reset.

server_id=1
tcp_port=2181
four_letter_word_white_list=*
log_storage_path=./coordination/logs
snapshot_storage_path=./coordination/snapshots
max_requests_batch_size=100
session_timeout_ms=30000
operation_timeout_ms=10000
dead_session_check_period_ms=500
heart_beat_interval_ms=500
election_timeout_lower_bound_ms=1000
election_timeout_upper_bound_ms=2000
reserved_log_items=1000000000000000
snapshot_distance=10000
auto_forwarding=true
shutdown_timeout=5000
startup_timeout=240000
raft_logs_level=information
snapshots_to_keep=3
rotate_log_storage_interval=100000
stale_log_gap=10000
fresh_log_gap=200
max_requests_batch_size=100
quorum_reads=false
force_sync=false
compress_logs=true
compress_snapshots_with_zstd_format=true
snapshot_zstd_compression_level=3
configuration_change_tries_count=20

 192.168.1.1:52163(recved=0,sent=0,sid=0xffffffffffffffff,lop=NA,est=1636454787393,to=30000,lzxid=0xffffffffffffffff,lresp=0,llat=0,minlat=0,avglat=0,maxlat=0)
 192.168.1.1:52042(recved=9,sent=18,sid=0x0000000000000001,lop=List,est=1636454739887,to=30000,lcxid=0x0000000000000005,lzxid=0x0000000000000005,lresp=1636454739892,llat=0,minlat=0,avglat=0,maxlat=0)

Connection stats reset.

Environment:
clickhouse.keeper.version=v21.11.1.1-prestable-7a4a0b0edef0ad6e0aa662cd3b90c3f4acf796e7
host.name=ZBMAC-C02D4054M.local
os.name=Darwin
os.arch=x86_64
os.version=19.6.0
cpu.count=12
user.name=root
user.home=/Users/JackyWoo/
user.dir=/Users/JackyWoo/project/jd/clickhouse/cmake-build-debug/programs/
user.tmp=/var/folders/b4/smbq5mfj7578f2jzwn602tt40000gn/T/

snapshot_dir_size: 0
log_dir_size: 3875

rw

1 connections watching 1 paths
Total watches:1

0x0000000000000001
    /clickhouse/task_queue/ddl

/clickhouse/task_queue/ddl
    0x0000000000000001

Sessions dump (2):
0x0000000000000001
0x0000000000000002
Sessions with Ephemerals (1):
0x0000000000000001
 /clickhouse/task_queue/ddl

100

first_log_idx   1
first_log_term  1
last_log_idx    101
last_log_term   1
last_committed_log_idx  100
leader_committed_log_idx    101
target_committed_log_idx    101
last_snapshot_idx   50

Sent leadership request to leader.

filtered_list   1
multi_read  1
check_not_exists    0

$ echo bpon | nc localhost 9181   # sent to the leader
Slow member backpressure is ON. Writes now commit at the speed of the slowest reachable voting replica; replicas with `can_become_leader` off are not waited for. A new leader switches it off, so send this again after a leader change.

$ echo bpon | nc localhost 9181   # sent to a follower
Sent slow member backpressure ON request to leader. Check `zk_slow_member_backpressure` in `mntr` on the leader, which `zk_server_state` identifies, to see whether it took effect.

$ echo bpof | nc localhost 9181
Sent slow member backpressure OFF request to leader.

Sent yield leadership request to leader.

FileOpen        62      Number of files opened.
Seek    4       Number of times the 'lseek' function was called.
ReadBufferFromFileDescriptorRead        126     Number of reads (read/pread) from a file descriptor. Does not include sockets.
ReadBufferFromFileDescriptorReadFailed  0       Number of times the read (read/pread) from a file descriptor have failed.
ReadBufferFromFileDescriptorReadBytes   178846  Number of bytes read from file descriptors. If the file is compressed, this will show the compressed data size.
WriteBufferFromFileDescriptorWrite      7       Number of writes (write/pwrite) to a file descriptor. Does not include sockets.
WriteBufferFromFileDescriptorWriteFailed        0       Number of times the write (write/pwrite) to a file descriptor have failed.
WriteBufferFromFileDescriptorWriteBytes 153     Number of bytes written to file descriptors. If the file is compressed, this will show compressed data size.
FileSync        2       Number of times the F_FULLFSYNC/fsync/fdatasync function was called for files.
DirectorySync   0       Number of times the F_FULLFSYNC/fsync/fdatasync function was called for directories.
FileSyncElapsedMicroseconds     12756   Total time spent waiting for F_FULLFSYNC/fsync/fdatasync syscall for files.
DirectorySyncElapsedMicroseconds        0       Total time spent waiting for F_FULLFSYNC/fsync/fdatasync syscall for directories.
ReadCompressedBytes     0       Number of bytes (the number of bytes before decompression) read from compressed sources (files, network).
CompressedReadBufferBlocks      0       Number of compressed blocks (the blocks of data that are compressed independent of each other) read from compressed sources (files, network).
CompressedReadBufferBytes       0       Number of uncompressed bytes (the number of bytes after decompression) read from compressed sources (files, network).
AIOWrite        0       Number of writes with Linux or FreeBSD AIO interface
AIOWriteBytes   0       Number of bytes written with Linux or FreeBSD AIO interface
...

<clickhouse>
    <keeper_server>
        <http_control>
            <port>9182</port>
            <readiness>
                <endpoint>/ready</endpoint>
            </readiness>
        </http_control>
    </keeper_server>
</clickhouse>

<clickhouse>
    <keeper_server>
        <feature_flags>
            <multi_read>0</multi_read>
            <check_not_exists>1</check_not_exists>
        </feature_flags>
    </keeper_server>
</clickhouse>

SYSTEM STOP MERGES;

clickhouse-keeper-converter \
  --zookeeper-logs-dir /var/lib/zookeeper/version-2 \
  --zookeeper-snapshots-dir /var/lib/zookeeper/version-2 \
  --output-dir /path/to/clickhouse/keeper/snapshots

<clickhouse>
    <storage_configuration>
        <disks>
            <log_local>
                <type>local</type>
                <path>/var/lib/clickhouse/coordination/logs/</path>
            </log_local>
            <log_s3_plain>
                <type>s3_plain</type>
                <endpoint>https://some_s3_endpoint/logs/</endpoint>
                <access_key_id>ACCESS_KEY</access_key_id>
                <secret_access_key>SECRET_KEY</secret_access_key>
            </log_s3_plain>
            <snapshot_local>
                <type>local</type>
                <path>/var/lib/clickhouse/coordination/snapshots/</path>
            </snapshot_local>
            <snapshot_s3_plain>
                <type>s3_plain</type>
                <endpoint>https://some_s3_endpoint/snapshots/</endpoint>
                <access_key_id>ACCESS_KEY</access_key_id>
                <secret_access_key>SECRET_KEY</secret_access_key>
            </snapshot_s3_plain>
            <state_s3_plain>
                <type>s3_plain</type>
                <endpoint>https://some_s3_endpoint/state/</endpoint>
                <access_key_id>ACCESS_KEY</access_key_id>
                <secret_access_key>SECRET_KEY</secret_access_key>
            </state_s3_plain>
        </disks>
    </storage_configuration>
</clickhouse>

<clickhouse>
    <keeper_server>
        <log_storage_disk>log_s3_plain</log_storage_disk>
        <latest_log_storage_disk>log_local</latest_log_storage_disk>

        <snapshot_storage_disk>snapshot_s3_plain</snapshot_storage_disk>
        <latest_snapshot_storage_disk>snapshot_local</latest_snapshot_storage_disk>
    </keeper_server>
</clickhouse>

<clickhouse>
    <keeper_server>
        <old_log_storage_disk>log_local</old_log_storage_disk>
        <old_log_storage_disk>log_s3_plain</old_log_storage_disk>
        <log_storage_disk>log_local2</log_storage_disk>

        <old_snapshot_storage_disk>snapshot_s3_plain</old_snapshot_storage_disk>
        <old_snapshot_storage_disk>snapshot_local</old_snapshot_storage_disk>
        <snapshot_storage_disk>snapshot_local2</snapshot_storage_disk>
    </keeper_server>
</clickhouse>

curl 127.0.0.1:9363/metrics

    <remote_servers>
        <cluster_1S_2R>
            <shard>
                <replica>
                    <host>chnode1.marsnet.local</host>
                    <port>9440</port>
                    <user>default</user>
                    <password>ClickHouse123!</password>
                    <secure>1</secure>
                </replica>
                <replica>
                    <host>chnode2.marsnet.local</host>
                    <port>9440</port>
                    <user>default</user>
                    <password>ClickHouse123!</password>
                    <secure>1</secure>
                </replica>
            </shard>
        </cluster_1S_2R>
    </remote_servers>

    <macros>
        <shard>1</shard>
        <replica>replica_1</replica>
    </macros>

CREATE DATABASE db_uuid
      ON CLUSTER 'cluster_1S_2R'
      ENGINE Atomic;

CREATE DATABASE db_uuid ON CLUSTER cluster_1S_2R
ENGINE = Atomic

Query id: 07fb7e65-beb4-4c30-b3ef-bd303e5c42b5

┌─host──────────────────┬─port─┬─status─┬─error─┬─num_hosts_remaining─┬─num_hosts_active─┐
│ chnode2.marsnet.local │ 9440 │      0 │       │                   1 │                0 │
│ chnode1.marsnet.local │ 9440 │      0 │       │                   0 │                0 │
└───────────────────────┴──────┴────────┴───────┴─────────────────────┴──────────────────┘

CREATE TABLE db_uuid.uuid_table1 ON CLUSTER 'cluster_1S_2R'
   (
     id UInt64,
     column1 String
   )
   ENGINE = ReplicatedMergeTree('/clickhouse/tables/{shard}/db_uuid/{uuid}', '{replica}' )
   ORDER BY (id);

CREATE TABLE db_uuid.uuid_table1 ON CLUSTER cluster_1S_2R
(
    `id` UInt64,
    `column1` String
)
ENGINE = ReplicatedMergeTree('/clickhouse/tables/{shard}/db_uuid/{uuid}', '{replica}')
ORDER BY id

Query id: 8f542664-4548-4a02-bd2a-6f2c973d0dc4

┌─host──────────────────┬─port─┬─status─┬─error─┬─num_hosts_remaining─┬─num_hosts_active─┐
│ chnode1.marsnet.local │ 9440 │      0 │       │                   1 │                0 │
│ chnode2.marsnet.local │ 9440 │      0 │       │                   0 │                0 │
└───────────────────────┴──────┴────────┴───────┴─────────────────────┴──────────────────┘

CREATE TABLE db_uuid.dist_uuid_table1 ON CLUSTER 'cluster_1S_2R'
   (
     id UInt64,
     column1 String
   )
   ENGINE = Distributed('cluster_1S_2R', 'db_uuid', 'uuid_table1' );

CREATE TABLE db_uuid.dist_uuid_table1 ON CLUSTER cluster_1S_2R
(
    `id` UInt64,
    `column1` String
)
ENGINE = Distributed('cluster_1S_2R', 'db_uuid', 'uuid_table1')

Query id: 3bc7f339-ab74-4c7d-a752-1ffe54219c0e

┌─host──────────────────┬─port─┬─status─┬─error─┬─num_hosts_remaining─┬─num_hosts_active─┐
│ chnode2.marsnet.local │ 9440 │      0 │       │                   1 │                0 │
│ chnode1.marsnet.local │ 9440 │      0 │       │                   0 │                0 │
└───────────────────────┴──────┴────────┴───────┴─────────────────────┴──────────────────┘

INSERT INTO db_uuid.uuid_table1
   ( id, column1)
   VALUES
   ( 1, 'abc');

INSERT INTO db_uuid.uuid_table1 (id, column1) FORMAT Values

Query id: 0f178db7-50a6-48e2-9a1b-52ed14e6e0f9

Ok.

1 row in set. Elapsed: 0.033 sec.

INSERT INTO db_uuid.uuid_table1
   ( id, column1)
   VALUES
   ( 2, 'def');

INSERT INTO db_uuid.uuid_table1 (id, column1) FORMAT Values

Query id: edc6f999-3e7d-40a0-8a29-3137e97e3607

Ok.

1 row in set. Elapsed: 0.529 sec.

SELECT * FROM db_uuid.dist_uuid_table1;

SELECT *
FROM db_uuid.dist_uuid_table1

Query id: 6cbab449-9e7f-40fe-b8c2-62d46ba9f5c8

┌─id─┬─column1─┐
│  1 │ abc     │
└────┴─────────┘
┌─id─┬─column1─┐
│  2 │ def     │
└────┴─────────┘

2 rows in set. Elapsed: 0.007 sec.

<default_replica_path>/clickhouse/tables/{shard}/db_uuid/{uuid}</default_replica_path>
<default_replica_name>{replica}</default_replica_name>

CREATE TABLE db_uuid.uuid_table1 ON CLUSTER 'cluster_1S_2R'
   (
     id UInt64,
     column1 String
   )
   ENGINE = ReplicatedMergeTree
   ORDER BY (id);

CREATE TABLE db_uuid.uuid_table1 ON CLUSTER cluster_1S_2R
(
    `id` UInt64,
    `column1` String
)
ENGINE = ReplicatedMergeTree
ORDER BY id

Query id: ab68cda9-ae41-4d6d-8d3b-20d8255774ee

┌─host──────────────────┬─port─┬─status─┬─error─┬─num_hosts_remaining─┬─num_hosts_active─┐
│ chnode2.marsnet.local │ 9440 │      0 │       │                   1 │                0 │
│ chnode1.marsnet.local │ 9440 │      0 │       │                   0 │                0 │
└───────────────────────┴──────┴────────┴───────┴─────────────────────┴──────────────────┘

2 rows in set. Elapsed: 1.175 sec.

SHOW CREATE TABLE db_uuid.uuid_table1;

SHOW CREATE TABLE db_uuid.uuid_table1

CREATE TABLE db_uuid.uuid_table1
(
    `id` UInt64,
    `column1` String
)
ENGINE = ReplicatedMergeTree('/clickhouse/tables/{shard}/db_uuid/{uuid}', '{replica}')
ORDER BY id

1 row in set. Elapsed: 0.003 sec.

SELECT * FROM system.tables
WHERE database = 'db_uuid' AND name = 'uuid_table1';

SELECT * FROM system.zookeeper
WHERE path = '/clickhouse/tables/1/db_uuid/9e8a3cc2-0dec-4438-81a7-c3e63ce2a1cf/replicas';

SELECT name, engine FROM system.databases WHERE name = 'db_uuid';

SELECT
    name,
    engine
FROM system.databases
WHERE name = 'db_uuid'

Query id: b047d459-a1d2-4016-bcf9-3e97e30e49c2

┌─name────┬─engine─┐
│ db_uuid │ Atomic │
└─────────┴────────┘

1 row in set. Elapsed: 0.004 sec.

server.id = server_host:server_port[;server_type][;server_priority]
server.id2 = ...
...

:) get /keeper/config
server.1=zoo1:9234;participant;1
server.2=zoo2:9234;participant;1
server.3=zoo3:9234;participant;1

# Add two new servers
reconfig add "server.5=localhost:123,server.6=localhost:234;learner"
# Remove two other servers
reconfig remove "3,4"
# Change existing server priority to 8
reconfig add "server.5=localhost:5123;participant;8"

# Add two new servers, remove two other servers
reconfig(joining="server.5=localhost:123,server.6=localhost:234;learner", leaving="3,4")

# Change existing server priority to 8
reconfig(joining="server.5=localhost:5123;participant;8", leaving=None)