mirror of
https://github.com/fnproject/fn.git
synced 2022-10-28 21:29:17 +03:00
5dc5740a54
* fn: runner status and docker load images Introducing a function run for pure runner Status calls. Previously, Status gRPC calls returned active inflight request counts with the purpose of a simple health checker. However this is not sufficient since it does not show if agent or docker is healthy. With this change, if pure runner is configured with a status image, that image is executed through docker. The call uses zero memory/cpu/tmpsize settings to ensure resource tracker does not block it. However, operators might not always have a docker repository accessible/available for status image. Or operators might not want the status to go over the network. To allow such cases, and in general possibly caching docker images, added a new environment variable FN_DOCKER_LOAD_FILE. If this is set, fn-agent during startup will load these images that were previously saved with 'docker save' into docker.
83 lines
2.2 KiB
Protocol Buffer
83 lines
2.2 KiB
Protocol Buffer
syntax = "proto3";
|
|
|
|
import "google/protobuf/empty.proto";
|
|
|
|
// Request to allocate a slot for a call
|
|
message TryCall {
|
|
string models_call_json = 1;
|
|
string slot_hash_id = 2;
|
|
map<string,string> extensions = 3;
|
|
}
|
|
|
|
// Data sent C2S and S2C - as soon as the runner sees the first of these it
|
|
// will start running. If empty content, there must be one of these with eof.
|
|
// The runner will send these for the body of the response, AFTER it has sent
|
|
// a CallEnding message.
|
|
message DataFrame {
|
|
bytes data = 1;
|
|
bool eof = 2;
|
|
}
|
|
|
|
message HttpHeader {
|
|
string key = 1;
|
|
string value = 2;
|
|
}
|
|
|
|
message HttpRespMeta {
|
|
int32 status_code = 1;
|
|
repeated HttpHeader headers = 2;
|
|
}
|
|
|
|
// Call has started to finish - data might not be here yet and it will be sent
|
|
// as DataFrames.
|
|
message CallResultStart {
|
|
oneof meta {
|
|
HttpRespMeta http = 100;
|
|
}
|
|
}
|
|
|
|
// Call has really finished, it might have completed or crashed
|
|
message CallFinished {
|
|
bool success = 1;
|
|
string details = 2;
|
|
int32 errorCode = 3;
|
|
string errorStr = 4;
|
|
string createdAt = 5;
|
|
string startedAt = 6;
|
|
string completedAt = 7;
|
|
}
|
|
|
|
message ClientMsg {
|
|
oneof body {
|
|
TryCall try = 1;
|
|
DataFrame data = 2;
|
|
}
|
|
}
|
|
|
|
message RunnerMsg {
|
|
oneof body {
|
|
CallResultStart result_start = 1;
|
|
DataFrame data = 2;
|
|
CallFinished finished = 3;
|
|
}
|
|
}
|
|
|
|
message RunnerStatus {
|
|
int32 active = 2; // Number of currently inflight responses
|
|
bool failed = 3; // if status was successful or not
|
|
string id = 4; // call id if status image was used
|
|
string details = 5; // details for logging/debug
|
|
int32 errorCode = 6; // error code if not successful
|
|
string errorStr = 7; // error description if not successful
|
|
string createdAt = 8; // call latency details: initialization time
|
|
string startedAt = 9; // call latency details: start time in container
|
|
string completedAt = 10; // call latency details: end time
|
|
}
|
|
|
|
service RunnerProtocol {
|
|
rpc Engage (stream ClientMsg) returns (stream RunnerMsg);
|
|
|
|
// Rather than rely on Prometheus for this, expose status that's specific to the runner lifecycle through this.
|
|
rpc Status(google.protobuf.Empty) returns (RunnerStatus);
|
|
}
|