open-nomad/plugins/device/proto/device.proto

// Copyright (c) HashiCorp, Inc.
// SPDX-License-Identifier: MPL-2.0

syntax = "proto3";
package hashicorp.nomad.plugins.device;
option go_package = "proto";

import "google/protobuf/timestamp.proto";
import "google/protobuf/duration.proto";
import "plugins/shared/structs/proto/attribute.proto";
import "plugins/shared/structs/proto/stats.proto";

// DevicePlugin is the API exposed by device plugins
service DevicePlugin {
  // Fingerprint allows the device plugin to return a set of   
  // detected devices and provide a mechanism to update the state of
  // the device.
  rpc Fingerprint(FingerprintRequest) returns (stream FingerprintResponse) {}

  // Reserve is called by the client before starting an allocation
  // that requires access to the plugin’s devices. The plugin can use
  // this to run any setup steps and provides the mounting details to 
  // the Nomad client
  rpc Reserve(ReserveRequest) returns (ReserveResponse) {}

  // Stats returns a stream of device statistics.
  rpc Stats(StatsRequest) returns (stream StatsResponse) {}
}

// FingerprintRequest is used to request for devices to be fingerprinted.
message FingerprintRequest {}

// FingerprintResponse returns a set of detected devices.
message FingerprintResponse {
    // device_group is a group of devices that share a vendor, device_type, and
    // device_name. This is returned as a set so that a single plugin could
    // potentially detect several device types and models.
    repeated DeviceGroup device_group = 1;
}

// DeviceGroup is a group of devices that share a vendor, device type and name.
message DeviceGroup {
  // vendor is the name of the vendor of the device
  string vendor = 1;

  // device_type is the type of the device (gpu, fpga, etc).
  string device_type = 2;
  
  // device_name is the name of the device.
  string device_name = 3;

  // devices is the set of devices detected by the plugin.
  repeated DetectedDevice devices = 4;

  // attributes allows adding attributes to be used for constraints or
  // affinities.
  map<string, hashicorp.nomad.plugins.shared.structs.Attribute> attributes = 5;
}

// DetectedDevice is a single detected device.
message DetectedDevice {
  // ID is the ID of the device. This ID is used during allocation and must be
  // stable across restarts of the device driver.
  // buf:lint:ignore FIELD_LOWER_SNAKE_CASE
  string ID = 1;

  // Health of the device.
  bool healthy = 2;
  
  // health_description allows the device plugin to optionally 
  // annotate the health field with a human readable reason.
  string health_description = 3;

  // hw_locality is optionally set to expose hardware locality information for
  // more optimal placement decisions.
  DeviceLocality hw_locality = 4;
}

// DeviceLocality is used to expose HW locality information about a device.
message DeviceLocality {
  // pci_bus_id is the PCI bus ID for the device. If reported, it
  // allows Nomad to make NUMA aware optimizations.
  string pci_bus_id = 1; 
}


// ReserveRequest is used to ask the device driver for information on 
// how to allocate the requested devices.
message ReserveRequest {
  // device_ids are the requested devices.
  repeated string device_ids = 1;
}

// ReserveResponse informs Nomad how to expose the requested devices
// to the the task.
message ReserveResponse {
  // container_res contains information on how to mount the device
  // into a task isolated using container technologies (where the 
  // host is shared)
  ContainerReservation container_res = 1;
}

// ContainerReservation returns how to mount the device into a 
// container that shares the host OS.
message ContainerReservation {
  // List of environment variable to be set
  map<string, string> envs = 1;

  // Mounts for the task.
  repeated Mount mounts = 2;

  // Devices for the task.
  repeated DeviceSpec devices = 3;
}

// Mount specifies a host volume to mount into a task.
// where device library or tools are installed on host and task
message Mount {
  // Path of the mount within the task.
  string task_path = 1;

  // Path of the mount on the host.
  string host_path = 2;

  // If set, the mount is read-only.
  bool read_only = 3;
}

// DeviceSpec specifies a host device to mount into a task.
message DeviceSpec {
  // Path of the device within the task.
  string task_path = 1;

  // Path of the device on the host.
  string host_path = 2;

  // Cgroups permissions of the device, candidates are one or more of
  // * r - allows task to read from the specified device.
  // * w - allows task to write to the specified device.
  // * m - allows task to create device files that do not yet exist
  string permissions = 3;
}


// StatsRequest is used to parameterize the retrieval of statistics.
message StatsRequest {
    // collection_interval is the duration in which to collect statistics.
    google.protobuf.Duration collection_interval = 1;
}

// StatsResponse returns the statistics for each device group.
message StatsResponse {
  // groups contains statistics for each device group.
  repeated DeviceGroupStats groups = 1;
}

// DeviceGroupStats contains statistics for each device of a particular
// device group, identified by the vendor, type and name of the device.
message DeviceGroupStats {
  string vendor = 1;
  string type = 2;
  string name = 3;

  // instance_stats is a mapping of each device ID to its statistics.
  map<string, DeviceStats> instance_stats = 4;
}

// DeviceStats is the statistics for an individual device
message DeviceStats {
  // summary exposes a single summary metric that should be the most  
  // informative to users.
  hashicorp.nomad.plugins.shared.structs.StatValue summary = 1;

  // stats contains the verbose statistics for the device.
  hashicorp.nomad.plugins.shared.structs.StatObject stats = 2;

  // timestamp is the time the statistics were collected.
  google.protobuf.Timestamp timestamp = 3;
}