etcd/etcdserver/etcdserverpb/rpc.proto

syntax = "proto3";
package etcdserverpb;

import "github.com/gogo/protobuf/gogoproto/gogo.proto";
import "github.com/coreos/etcd/storage/storagepb/kv.proto";

// Interface exported by the server.
service etcd {
  // Range gets the keys in the range from the store.
  rpc Range(RangeRequest) returns (RangeResponse) {}

  // Put puts the given key into the store.
  // A put request increases the index of the store,
  // and generates one event in the event history.
  rpc Put(PutRequest) returns (PutResponse) {}

  // Delete deletes the given range from the store.
  // A delete request increase the index of the store,
  // and generates one event in the event history.
  rpc DeleteRange(DeleteRangeRequest) returns (DeleteRangeResponse) {}

  // Tnx processes all the requests in one transaction.
  // A tnx request increases the index of the store,
  // and generates events with the same index in the event history.
  rpc Tnx(TnxRequest) returns (TnxResponse) {}

  // Compact compacts the event history in etcd. User should compact the
  // event history periodically, or it will grow infinitely.
  rpc Compact(CompactionRequest) returns (CompactionResponse) {}
}

message ResponseHeader {
  // an error type message?
  string error = 1;
  uint64 cluster_id = 2;
  uint64 member_id = 3;
  // index of the store when the request was applied.
  int64 index = 4;
  // term of raft when the request was applied.
  uint64 raft_term = 5;
}

message RangeRequest {
  // if the range_end is not given, the request returns the key.
  bytes key = 1;
  // if the range_end is given, it gets the keys in range [key, range_end).
  bytes range_end = 2;
  // limit the number of keys returned.
  int64 limit = 3;
  // the response will be consistent with previous request with same token if the token is 
  // given and is vaild.
  bytes consistent_token = 4;
}

message RangeResponse {
  ResponseHeader header = 1;
  repeated storagepb.KeyValue kvs = 2;
  bytes consistent_token = 3;
}

message PutRequest {
  bytes key = 1;
  bytes value = 2;
}

message PutResponse {
  ResponseHeader header = 1;
}

message DeleteRangeRequest {
  // if the range_end is not given, the request deletes the key.
  bytes key = 1;
  // if the range_end is given, it deletes the keys in range [key, range_end).
  bytes range_end = 2;
}

message DeleteRangeResponse {
  ResponseHeader header = 1;
}

message RequestUnion {
  oneof request {
    RangeRequest request_range = 1;
    PutRequest request_put = 2;
    DeleteRangeRequest request_delete_range = 3;
  }
}

message ResponseUnion {
  oneof response {
    RangeResponse reponse_range = 1;
    PutResponse response_put = 2;
    DeleteRangeResponse response_delete_range = 3;
  }
}

message Compare {
  enum CompareType {
    EQUAL = 0;
    GREATER = 1;
    LESS = 2;
  }
  CompareType type = 1;
  // key path
  bytes key = 2;
  oneof target {
    // version of the given key
    int64 version = 3;
    // create index of the given key
    int64 create_index = 4;
    // last modified index of the given key
    int64 mod_index = 5;
    // value of the given key
    bytes value = 6;
  }
}

// First all the compare requests are processed.
// If all the compare succeed, all the success
// requests will be processed.
// Or all the failure requests will be processed and
// all the errors in the comparison will be returned.

// From google paxosdb paper:
// Our implementation hinges around a powerful primitive which we call MultiOp. All other database
// operations except for iteration are implemented as a single call to MultiOp. A MultiOp is applied atomically
// and consists of three components:
// 1. A list of tests called guard. Each test in guard checks a single entry in the database. It may check
// for the absence or presence of a value, or compare with a given value. Two different tests in the guard
// may apply to the same or different entries in the database. All tests in the guard are applied and
// MultiOp returns the results. If all tests are true, MultiOp executes t op (see item 2 below), otherwise
// it executes f op (see item 3 below).
// 2. A list of database operations called t op. Each operation in the list is either an insert, delete, or
// lookup operation, and applies to a single database entry. Two different operations in the list may apply
// to the same or different entries in the database. These operations are executed
// if guard evaluates to
// true.
// 3. A list of database operations called f op. Like t op, but executed if guard evaluates to false.
message TnxRequest {
  repeated Compare compare = 1;
  repeated RequestUnion success = 2;
  repeated RequestUnion failure = 3;
}

message TnxResponse {
  ResponseHeader header = 1;
  bool succeeded = 2;
  repeated ResponseUnion responses = 3;
}

message CompactionRequest {
  int64 index = 1;
}

message CompactionResponse {
  ResponseHeader header = 1;
}