PD Control 使用说明

./pd-ctl store -u http://127.0.0.1:2379

./pd-ctl -i -u http://127.0.0.1:2379

export PD_ADDR=http://127.0.0.1:2379 &&
./pd-ctl

./pd-ctl -u https://127.0.0.1:2379 --cacert="path/to/ca" --cert="path/to/cert" --key="path/to/key"

>> cluster

{
  "id": 6493707687106161130,
  "max_peer_count": 3
}

>> config show

{
  "replication": {
    "enable-placement-rules": "false",
    "isolation-level": "",
    "location-labels": "",
    "max-replicas": 3,
    "strictly-match-label": "false"
  },
  "schedule": {
    "enable-cross-table-merge": "true",
    "enable-debug-metrics": "false",
    "enable-location-replacement": "true",
    "enable-make-up-replica": "true",
    "enable-one-way-merge": "false",
    "enable-remove-down-replica": "true",
    "enable-remove-extra-replica": "true",
    "enable-replace-offline-replica": "true",
    "high-space-ratio": 0.7,
    "hot-region-cache-hits-threshold": 3,
    "hot-region-schedule-limit": 4,
    "leader-schedule-limit": 4,
    "leader-schedule-policy": "count",
    "low-space-ratio": 0.8,
    "max-merge-region-keys": 200000,
    "max-merge-region-size": 20,
    "max-pending-peer-count": 16,
    "max-snapshot-count": 3,
    "max-store-down-time": "30m0s",
    "merge-schedule-limit": 8,
    "patrol-region-interval": "100ms",
    "region-schedule-limit": 2048,
    "region-score-formula-version": "v2",
    "replica-schedule-limit": 64,
    "scheduler-max-waiting-operator": 5,
    "split-merge-interval": "1h0m0s",
    "store-limit-mode": "manual",
    "tolerant-size-ratio": 0
  }
}

>> config show all

>> config show replication

{
  "max-replicas": 3,
  "isolation-level": "",
  "location-labels": "",
  "strictly-match-label": "false",
  "enable-placement-rules": "false"
}

>> config show cluster-version

"4.0.0"

>> health

[
  {
    "name": "pd",
    "member_id": 13195394291058371180,
    "client_urls": [
      "http://127.0.0.1:2379"
      ......
    ],
    "health": true
  }
  ......
]

>> hot read

>> hot write

>> hot store

>> label

>> label store zone cn

>> member

{
  "header": {......},
  "members": [......],
  "leader": {......},
  "etcd_leader": {......},
}

>> member delete name pd2

Success!

>> member delete id 1319539429105371180

Success!

>> member leader show

{
  "name": "pd",
  "member_id": 13155432540099656863,
  "peer_urls": [......],
  "client_urls": [......]
}

>> member leader resign

......

>> member leader transfer pd3

......

>> operator show                                        // 显示所有的 operators
>> operator show admin                                  // 显示所有的 admin operators
>> operator show leader                                 // 显示所有的 leader operators
>> operator show region                                 // 显示所有的 Region operators
>> operator add add-peer 1 2                            // 在 store 2 上新增 Region 1 的一个副本
>> operator add add-learner 1 2                         // 在 store 2 上新增 Region 1 的一个 learner 副本
>> operator add remove-peer 1 2                         // 移除 store 2 上的 Region 1 的一个副本
>> operator add transfer-leader 1 2                     // 把 Region 1 的 leader 调度到 store 2
>> operator add transfer-region 1 2 3 4                 // 把 Region 1 调度到 store 2,3,4
>> operator add transfer-peer 1 2 3                     // 把 Region 1 在 store 2 上的副本调度到 store 3
>> operator add merge-region 1 2                        // 将 Region 1 与 Region 2 合并
>> operator add split-region 1 --policy=approximate     // 将 Region 1 对半拆分成两个 Region，基于粗略估计值
>> operator add split-region 1 --policy=scan            // 将 Region 1 对半拆分成两个 Region，基于精确扫描值
>> operator remove 1                                    // 把 Region 1 的调度操作删掉
>> operator check 1                                     // 查看 Region 1 相关 operator 的状态

>> ping

time: 43.12698ms

>> region

{
  "count": 1,
  "regions": [......]
}

>> region 2

{
  "id": 2,
  "start_key": "7480000000000000FF1D00000000000000F8",
  "end_key": "7480000000000000FF1F00000000000000F8",
  "epoch": {
    "conf_ver": 1,
    "version": 15
  },
  "peers": [
    {
      "id": 40,
      "store_id": 3
    }
  ],
  "leader": {
    "id": 40,
    "store_id": 3
  },
  "written_bytes": 0,
  "read_bytes": 0,
  "written_keys": 0,
  "read_keys": 0,
  "approximate_size": 1,
  "approximate_keys": 0
}

>> region key 7480000000000000FF1300000000000000F8
{
  "region": {
    "id": 2,
    ......
  }
}

>> region key --format=raw abc

{
  "region": {
    "id": 2,
    ......
  }
}

>> region key --format=encode 't\200\000\000\000\000\000\000\377\035_r\200\000\000\000\000\377\017U\320\000\000\000\000\000\372'

{
  "region": {
    "id": 2,
    ......
  }
}

>> region scan

{
  "count": 20,
  "regions": [......],
}

>> region sibling 2

{
  "count": 2,
  "regions": [......],
}

>> region startkey --format=raw abc

{
  "count": 16,
  "regions": [......],
}

>> region store 2

{
  "count": 10,
  "regions": [......],
}

>> region topread

{
  "count": 16,
  "regions": [......],
}

>> region topwrite

{
  "count": 16,
  "regions": [......],
}

>> region topconfver

{
  "count": 16,
  "regions": [......],
}

>> region topversion

{
  "count": 16,
  "regions": [......],
}

>> region topsize

{
  "count": 16,
  "regions": [......],
}

>> region check miss-peer

{
  "count": 2,
  "regions": [......],
}

>> scheduler show                                 // 显示所有的 schedulers
>> scheduler add grant-leader-scheduler 1         // 把 store 1 上的所有 Region 的 leader 调度到 store 1
>> scheduler add evict-leader-scheduler 1         // 把 store 1 上的所有 Region 的 leader 从 store 1 调度出去
>> scheduler config evict-leader-scheduler        // v4.0.0 起，展示该调度器具体在哪些 store 上
>> scheduler add shuffle-leader-scheduler         // 随机交换不同 store 上的 leader
>> scheduler add shuffle-region-scheduler         // 随机调度不同 store 上的 Region
>> scheduler remove grant-leader-scheduler-1      // 把对应的调度器删掉，`-1` 对应 store ID
>> scheduler pause balance-region-scheduler 10    // 暂停运行 balance-region 调度器 10 秒
>> scheduler pause all 10                         // 暂停运行所有的调度器 10 秒
>> scheduler resume balance-region-scheduler      // 继续运行 balance-region 调度器 
>> scheduler resume all                           // 继续运行所有的调度器 
>> scheduler config balance-hot-region-scheduler  // 显示 balance-hot-region 调度器的配置

>> scheduler config balance-hot-region-scheduler  // 显示 balance-hot-region 调度器的所有配置
{
  "min-hot-byte-rate": 100,
  "min-hot-key-rate": 10,
  "max-zombie-rounds": 3,
  "max-peer-number": 1000,
  "byte-rate-rank-step-ratio": 0.05,
  "key-rate-rank-step-ratio": 0.05,
  "count-rank-step-ratio": 0.01,
  "great-dec-ratio": 0.95,
  "minor-dec-ratio": 0.99,
  "src-tolerance-ratio": 1.02,
  "dst-tolerance-ratio": 1.02
}

>> store

{
  "count": 3,
  "stores": [...]
}

>> store 1

  ......

>> store delete 1

  ......

>> store label 1 zone cn

>> store weight 1 5 10

>> store remove-tombstone              // 删除所有 tombstone 状态的 store
>> store limit                         // 显示所有 store 添加和删除 peer 的速度上限
>> store limit add-peer                // 显示所有 store 添加 peer 的速度上限
>> store limit remove-peer             // 显示所有 store 删除 peer 的速度上限
>> store limit all 5                   // 设置所有 store 添加和删除 peer 的速度上限为每分钟 5 个
>> store limit 1 5                     // 设置 store 1 添加和删除 peer 的速度上限为每分钟 5 个
>> store limit all 5 add-peer          // 设置所有 store 添加 peer 的速度上限为每分钟 5 个
>> store limit 1 5 add-peer            // 设置 store 1 添加 peer 的速度上限为每分钟 5 个
>> store limit 1 5 remove-peer         // 设置 store 1 删除 peer 的速度上限为每分钟 5 个
>> store limit all 5 remove-peer       // 设置所有 store 删除 peer 的速度上限为每分钟 5 个
>> store limit-scene                   // 显示所有的限速场景（实验性功能）
{
  "Idle": 100,
  "Low": 50,
  "Normal": 32,
  "High": 12
}
>> store limit-scene idle 100          // 设置 load 为 idle 场景下，添加/删除 peer 的速度上限为每分钟 100 个

>> log warn

>> tso 395181938313123110

system:  2017-10-09 05:50:59 +0800 CST
logic:  120102

» store --jq=".stores[].store | { id, address, state_name}"

{"id":1,"address":"127.0.0.1:20161","state_name":"Up"}
{"id":30,"address":"127.0.0.1:20162","state_name":"Up"}
...

» store --jq=".stores[] | {id: .store.id, available: .status.available}"

{"id":1,"available":"10 GiB"}
{"id":30,"available":"10 GiB"}
...

» store --jq='.stores[].store | select(.state_name!="Up") | { id, address, state_name}'

{"id":1,"address":"127.0.0.1:20161""state_name":"Offline"}
{"id":5,"address":"127.0.0.1:20162""state_name":"Offline"}
...

» store --jq='.stores[].store | select(.labels | length>0 and contains([{"key":"engine","value":"tiflash"}])) | { id, address, state_name}'

{"id":1,"address":"127.0.0.1:20161""state_name":"Up"}
{"id":5,"address":"127.0.0.1:20162""state_name":"Up"}
...

» region --jq=".regions[] | {id: .id, peer_stores: [.peers[].store_id]}"

{"id":2,"peer_stores":[1,30,31]}
{"id":4,"peer_stores":[1,31,34]}
...

» region --jq=".regions[] | {id: .id, peer_stores: [.peers[].store_id] | select(length != 3)}"

{"id":12,"peer_stores":[30,32]}
{"id":2,"peer_stores":[1,30,31,32]}

» region --jq=".regions[] | {id: .id, peer_stores: [.peers[].store_id] | select(any(.==30))}"

{"id":6,"peer_stores":[1,30,31]}
{"id":22,"peer_stores":[1,30,32]}
...

» region --jq=".regions[] | {id: .id, peer_stores: [.peers[].store_id] | select(any(.==(30,31)))}"

{"id":16,"peer_stores":[1,30,34]}
{"id":28,"peer_stores":[1,30,32]}
{"id":12,"peer_stores":[30,32]}
...

» region --jq=".regions[] | {id: .id, peer_stores: [.peers[].store_id] | select(length as $total | map(if .==(1,30,31) then . else empty end) | length>=$total-length) }"

{"id":2,"peer_stores":[1,30,31,32]}
{"id":12,"peer_stores":[30,32]}
{"id":14,"peer_stores":[1,30,32]}
...

» region --jq=".regions[] | {id: .id, peer_stores: [.peers[].store_id] | select(length>1 and any(.==1) and all(.!=(30,31)))}"

{"id":24,"peer_stores":[1,32,33]}

» region --jq=".regions[] | {id: .id, remove_peer: [.peers[].store_id] | select(length>1) | map(if .==(30,31) then . else empty end) | select(length==1)}"

{"id":12,"remove_peer":[30]}
{"id":4,"remove_peer":[31]}
{"id":22,"remove_peer":[30]}
...