src/kudu/consensus/metadata.proto

// Licensed to the Apache Software Foundation (ASF) under one
// or more contributor license agreements.  See the NOTICE file
// distributed with this work for additional information
// regarding copyright ownership.  The ASF licenses this file
// to you under the Apache License, Version 2.0 (the
// "License"); you may not use this file except in compliance
// with the License.  You may obtain a copy of the License at
//
//   http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing,
// software distributed under the License is distributed on an
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
// KIND, either express or implied.  See the License for the
// specific language governing permissions and limitations
// under the License.
syntax = "proto2";
package kudu.consensus;

option java_package = "org.apache.kudu.consensus";

import "kudu/common/common.proto";

// ===========================================================================
//  Consensus Metadata
// ===========================================================================

// Per-replica attributes.
message RaftPeerAttrsPB {
  // Whether to promote a replica when it has caught up with the leader,
  // changing its membership type from NON_VOTER to VOTER. This field is
  // applicable only for NON_VOTER replicas.
  optional bool promote = 1 [ default = false ];

  // If set to 'true', the replica needs to be replaced regardless of
  // its health report.
  optional bool replace = 2 [ default = false ];
}

// Report on a replica's (peer's) health.
message HealthReportPB {
  // HealthStatus respresents a fully-connected state machine, where
  // transitions between any of the states are allowed.
  enum HealthStatus {
    // No information on the health status.
    UNKNOWN = 999;

    // Replica has failed and needs replacement. The failure might be a
    // transient one, so replica may return to a healthy state soon.
    FAILED = 0;

    // Replica is functioning properly.
    HEALTHY = 1;

    // Replica has failed in an irreversible and unrecoverable way and needs
    // replacement. The failure is permanent and the replica definitely cannot
    // return to a healthy state.
    FAILED_UNRECOVERABLE = 2;
  }

  // Overall health status of a replica. Reflects at least the responsiveness
  // (i.e. time of last contact) and the lag of the replica's WAL
  // behind the leader's.
  optional HealthStatus overall_health = 1;
}

// A peer in a configuration.
message RaftPeerPB {
  // The possible roles for peers.
  enum Role {
    UNKNOWN_ROLE = 999;

    // Indicates this node is a follower in the configuration, i.e. that it participates
    // in majorities and accepts Consensus::Update() calls.
    FOLLOWER = 0;

    // Indicates this node is the current leader of the configuration, i.e. that it
    // participates in majorities and accepts Consensus::Append() calls.
    LEADER = 1;

    // Indicates that this node participates in the configuration in a passive role,
    // i.e. that it accepts Consensus::Update() calls but does not participate
    // in elections or majorities.
    LEARNER = 2;

    // Indicates that this node is not a participant of the configuration, i.e. does
    // not accept Consensus::Update() or Consensus::Update() and cannot
    // participate in elections or majorities. This is usually the role of a node
    // that leaves the configuration.
    NON_PARTICIPANT = 3;
  };

  enum MemberType {
    UNKNOWN_MEMBER_TYPE = 999;
    NON_VOTER = 0;
    VOTER = 1;
  };

  // Permanent uuid is optional: RaftPeerPB/RaftConfigPB instances may
  // be created before the permanent uuid is known (e.g., when
  // manually specifying a configuration for Master/CatalogManager);
  // permanent uuid can be retrieved at a later time through RPC.
  optional bytes permanent_uuid = 1;
  optional MemberType member_type = 2;
  optional HostPortPB last_known_addr = 3;

  // Replica attributes.
  optional RaftPeerAttrsPB attrs = 4;

  // Replica's health report, as seen by the leader. This is a run-time
  // only field, it should not be persisted or read from the persistent storage.
  optional HealthReportPB health_report = 5;
}

// A set of peers, serving a single tablet.
message RaftConfigPB {
  // The index of the operation which serialized this RaftConfigPB through
  // consensus. It is set when the operation is consensus-committed (replicated
  // to a majority of voters) and before the consensus metadata is updated.
  // It is left undefined if the operation isn't committed.
  optional int64 opid_index = 1;

  // Obsolete. This parameter has been retired.
  optional bool OBSOLETE_local = 2;

  // Flag to allow unsafe config change operations.
  optional bool unsafe_config_change = 4 [ default = false ];

  // The set of peers in the configuration.
  repeated RaftPeerPB peers = 3;
}

// Represents a snapshot of a configuration at a given moment in time.
message ConsensusStatePB {
  // A configuration is always guaranteed to have a known term.
  required int64 current_term = 1;

  // There may not always be a leader of a configuration at any given time.
  //
  // The node that the local peer considers to be leader changes based on rules
  // defined in the Raft specification. Roughly, this corresponds either to
  // being elected leader (in the case that the local peer is the leader), or
  // when an update is accepted from another node, which basically just amounts
  // to a term check on the UpdateConsensus() RPC request.
  //
  // Whenever the local peer sees a new term, the leader flag is cleared until
  // a new leader is acknowledged based on the above criteria. Simply casting a
  // vote for a peer is not sufficient to assume that the peer has won the
  // election, so we do not update this field based on our vote.
  //
  // The leader may be a part of the committed or the pending configuration (or both).
  optional string leader_uuid = 2;

  // The committed peers. Initial peership is set on tablet start, so this
  // field should always be present.
  required RaftConfigPB committed_config = 3;

  // The peers in the pending configuration, if there is one.
  optional RaftConfigPB pending_config = 4;
}

// This PB is used to serialize all of the persistent state needed for
// Consensus that is not in the WAL, such as leader election and
// communication on startup.
message ConsensusMetadataPB {
  // Last-committed peership.
  required RaftConfigPB committed_config = 1;

  // Latest term this server has seen.
  // When a configuration is first created, initialized to 0.
  //
  // Whenever a new election is started, the candidate increments this by one
  // and requests votes from peers.
  //
  // If any RPC request or response is received from another node containing a term higher
  // than this one, the server should step down to FOLLOWER and set its current_term to
  // match the caller's term.
  //
  // If a follower receives an UpdateConsensus RPC with a term lower than this
  // term, then that implies that the RPC is coming from a former LEADER who has
  // not realized yet that its term is over. In that case, we will reject the
  // UpdateConsensus() call with ConsensusErrorPB::INVALID_TERM.
  //
  // If a follower receives a RequestConsensusVote() RPC with an earlier term,
  // the vote is denied.
  required int64 current_term = 2;

  // Permanent UUID of the candidate voted for in 'current_term', or not present
  // if no vote was made in the current term.
  optional string voted_for = 3;
}