mirror of
https://github.com/NVIDIA/OpenShell.git
synced 2026-10-16 05:20:22 +08:00
* feat(gpu)!: add resource requirements BREAKING CHANGE: SandboxSpec.gpu and DriverSandboxSpec.gpu were replaced with resource_requirements.gpu, changing protobuf field 9 from a bool to a message for both public and driver APIs. Signed-off-by: Evan Lezar <elezar@nvidia.com> * refactor(gpu): pass requirements through sandbox create Pass the coupled GPU requirement object through the CLI sandbox_create boundary instead of splitting presence and count into separate arguments. Signed-off-by: Evan Lezar <elezar@nvidia.com> * refactor(gpu): pass requirements to timeout message Pass ResourceRequirements into the provisioning timeout message helper so GPU hints are derived from the same nested request object used to create the sandbox. Signed-off-by: Evan Lezar <elezar@nvidia.com> * refactor(gpu): pass driver requirements through helpers Thread Option<GpuResourceRequirements> through driver validation and rendering helpers instead of splitting GPU presence and count into separate arguments. Signed-off-by: Evan Lezar <elezar@nvidia.com> * fix(gpu): validate exact device requests Require exact driver GPU device lists to be tied to a GPU request, allow a single exact device to use the default countless request, and require explicit matching counts for multi-device lists. Signed-off-by: Evan Lezar <elezar@nvidia.com> --------- Signed-off-by: Evan Lezar <elezar@nvidia.com>
293 lines
10 KiB
Protocol Buffer
293 lines
10 KiB
Protocol Buffer
// SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
// SPDX-License-Identifier: Apache-2.0
|
|
|
|
syntax = "proto3";
|
|
|
|
package openshell.compute.v1;
|
|
|
|
import "google/protobuf/struct.proto";
|
|
|
|
// Internal compute-driver contract used by the gateway.
|
|
//
|
|
// Conventions:
|
|
// - This file owns driver-native request, response, and observation types.
|
|
// - Compute drivers must not import or return the public `openshell.v1.Sandbox`
|
|
// resource model.
|
|
// - The gateway translates between these internal driver-native messages and
|
|
// the public OpenShell API resource model.
|
|
service ComputeDriver {
|
|
// Report driver capabilities and defaults.
|
|
rpc GetCapabilities(GetCapabilitiesRequest) returns (GetCapabilitiesResponse);
|
|
|
|
// Validate a sandbox before create-time provisioning.
|
|
rpc ValidateSandboxCreate(ValidateSandboxCreateRequest)
|
|
returns (ValidateSandboxCreateResponse);
|
|
|
|
// Fetch the platform-observed sandbox state for one sandbox.
|
|
rpc GetSandbox(GetSandboxRequest) returns (GetSandboxResponse);
|
|
|
|
// List platform-observed sandbox state for all sandboxes.
|
|
rpc ListSandboxes(ListSandboxesRequest) returns (ListSandboxesResponse);
|
|
|
|
// Provision platform resources for a sandbox.
|
|
rpc CreateSandbox(CreateSandboxRequest) returns (CreateSandboxResponse);
|
|
|
|
// Stop platform resources for a sandbox without deleting its record.
|
|
rpc StopSandbox(StopSandboxRequest) returns (StopSandboxResponse);
|
|
|
|
// Tear down platform resources for a sandbox.
|
|
rpc DeleteSandbox(DeleteSandboxRequest) returns (DeleteSandboxResponse);
|
|
|
|
// Stream sandbox observations from the platform.
|
|
rpc WatchSandboxes(WatchSandboxesRequest) returns (stream WatchSandboxesEvent);
|
|
}
|
|
|
|
message GetCapabilitiesRequest {}
|
|
|
|
message GetCapabilitiesResponse {
|
|
reserved 4, 5;
|
|
reserved "supports_gpu", "gpu_count";
|
|
|
|
// Human-readable driver name.
|
|
string driver_name = 1;
|
|
// Driver implementation version string.
|
|
string driver_version = 2;
|
|
// Default sandbox image recommended by the driver.
|
|
string default_image = 3;
|
|
}
|
|
|
|
// Driver-owned sandbox model used for create requests and platform observations.
|
|
//
|
|
// This intentionally omits gateway-owned lifecycle fields such as the public
|
|
// `openshell.v1.SandboxPhase` and persisted metadata. The gateway derives and
|
|
// stores those fields after translating driver observations.
|
|
message DriverSandbox {
|
|
// Stable sandbox ID assigned by the gateway.
|
|
string id = 1;
|
|
// Compute-runtime sandbox name.
|
|
string name = 2;
|
|
// Compute-platform namespace or equivalent tenancy boundary.
|
|
string namespace = 3;
|
|
// Provisioning input supplied by the gateway. Drivers may omit this in
|
|
// observed snapshots returned by Get/List/Watch.
|
|
DriverSandboxSpec spec = 4;
|
|
// Raw platform-observed status.
|
|
DriverSandboxStatus status = 5;
|
|
}
|
|
|
|
// Driver-owned provisioning inputs required to create a sandbox.
|
|
message DriverSandboxSpec {
|
|
// Log level exposed to processes running inside the sandbox.
|
|
string log_level = 1;
|
|
// Environment variables injected into the sandbox runtime.
|
|
map<string, string> environment = 5;
|
|
// Runtime template consumed by the driver during provisioning.
|
|
DriverSandboxTemplate template = 6;
|
|
// Portable resource requirements used by the gateway for driver selection
|
|
// and by drivers for provisioning.
|
|
ResourceRequirements resource_requirements = 9;
|
|
reserved 10;
|
|
reserved "gpu_device";
|
|
// Gateway-minted JWT identifying this sandbox to the gateway. Set by
|
|
// the gateway on create; the driver materialises it via its native
|
|
// secret mechanism (Docker/Podman/VM bind-mount a per-sandbox file;
|
|
// the Kubernetes driver ignores this field and relies on its projected
|
|
// ServiceAccount token bootstrap instead). Never echoed to the public
|
|
// Sandbox proto.
|
|
string sandbox_token = 11;
|
|
}
|
|
|
|
message ResourceRequirements {
|
|
// GPU requirements for the sandbox. Presence indicates a GPU request.
|
|
GpuResourceRequirements gpu = 1;
|
|
}
|
|
|
|
// Driver GPU resource requirements.
|
|
message GpuResourceRequirements {
|
|
// Optional number of GPUs requested. When omitted, the request is for one
|
|
// GPU using the selected driver's default assignment behavior.
|
|
optional uint32 count = 1;
|
|
}
|
|
|
|
// Driver-owned runtime template consumed by the compute platform.
|
|
//
|
|
// This message describes the sandbox workload in backend-neutral terms.
|
|
// Platform-specific knobs (Kubernetes runtimeClassName, annotations,
|
|
// volumeClaimTemplates, etc.) belong in `platform_config`.
|
|
message DriverSandboxTemplate {
|
|
// Fully-qualified OCI image reference used to boot the sandbox.
|
|
string image = 1;
|
|
// Socket path inside the sandbox where the agent service listens.
|
|
string agent_socket_path = 3;
|
|
// Metadata labels applied to compute-platform resources.
|
|
// Drivers map these to the platform's native tagging mechanism
|
|
// (Kubernetes labels, cloud instance tags, etc.).
|
|
map<string, string> labels = 4;
|
|
// Additional environment variables injected into the sandbox runtime.
|
|
map<string, string> environment = 6;
|
|
// Typed compute-resource requirements for the sandbox workload.
|
|
DriverResourceRequirements resources = 10;
|
|
// Opaque, platform-specific configuration passed through to the driver.
|
|
// The gateway does not inspect this; each driver defines its own schema.
|
|
// For the Kubernetes driver this carries fields such as runtimeClassName,
|
|
// annotations, and volumeClaimTemplates.
|
|
google.protobuf.Struct platform_config = 11;
|
|
// Caller-provided config for the selected driver only.
|
|
// This is the inner block selected from public SandboxTemplate.driver_config.
|
|
// The selected driver owns nested schema validation.
|
|
google.protobuf.Struct driver_config = 12;
|
|
}
|
|
|
|
// Typed compute-resource requirements.
|
|
//
|
|
// Values use Kubernetes-style quantity strings (e.g. "500m", "2", "4Gi")
|
|
// because they are a well-known, widely-adopted notation. Drivers for
|
|
// non-Kubernetes platforms must parse these strings into their native units.
|
|
message DriverResourceRequirements {
|
|
// Minimum CPU cores requested (e.g. "500m", "2").
|
|
string cpu_request = 1;
|
|
// Maximum CPU cores allowed (e.g. "500m", "4").
|
|
string cpu_limit = 2;
|
|
// Minimum memory requested (e.g. "256Mi", "4Gi").
|
|
string memory_request = 3;
|
|
// Maximum memory allowed (e.g. "512Mi", "8Gi").
|
|
string memory_limit = 4;
|
|
}
|
|
|
|
// Raw status observed directly from the compute platform.
|
|
//
|
|
// The gateway derives the public `openshell.v1.SandboxPhase` from these
|
|
// conditions plus `deleting`.
|
|
message DriverSandboxStatus {
|
|
// Compute-platform sandbox object name.
|
|
string sandbox_name = 1;
|
|
// Platform-assigned instance identifier for the compute unit running the
|
|
// sandbox agent (e.g. Kubernetes pod name, VM instance ID, hostname).
|
|
// The gateway uses this to correlate incoming connections back to a sandbox.
|
|
string instance_id = 2;
|
|
// File descriptor or address for reaching the agent service inside the
|
|
// sandbox, when available.
|
|
string agent_fd = 3;
|
|
// File descriptor or address for reaching the sandbox supervisor service,
|
|
// when available.
|
|
string sandbox_fd = 4;
|
|
// Raw readiness and lifecycle conditions reported by the platform.
|
|
repeated DriverCondition conditions = 5;
|
|
// True when the compute platform has begun deleting this sandbox.
|
|
bool deleting = 6;
|
|
}
|
|
|
|
// Raw compute-platform condition.
|
|
message DriverCondition {
|
|
// Condition class reported by the compute platform.
|
|
string type = 1;
|
|
// Condition status value such as `True`, `False`, or `Unknown`.
|
|
string status = 2;
|
|
// Short machine-readable reason associated with the condition.
|
|
string reason = 3;
|
|
// Human-readable condition message.
|
|
string message = 4;
|
|
// Timestamp reported by the platform for the last transition.
|
|
string last_transition_time = 5;
|
|
}
|
|
|
|
// Raw compute-platform event correlated to a sandbox.
|
|
message DriverPlatformEvent {
|
|
// Event timestamp in milliseconds since epoch.
|
|
int64 timestamp_ms = 1;
|
|
// Event source (for example `kubernetes`).
|
|
string source = 2;
|
|
// Event type or severity (for example `Normal` or `Warning`).
|
|
string type = 3;
|
|
// Short machine-readable reason code.
|
|
string reason = 4;
|
|
// Human-readable event message.
|
|
string message = 5;
|
|
// Optional platform-specific metadata attached to the event.
|
|
map<string, string> metadata = 6;
|
|
}
|
|
|
|
message ValidateSandboxCreateRequest {
|
|
// Proposed sandbox configuration to validate before provisioning.
|
|
DriverSandbox sandbox = 1;
|
|
}
|
|
|
|
message ValidateSandboxCreateResponse {}
|
|
|
|
message GetSandboxRequest {
|
|
// Stable sandbox ID stored by the gateway.
|
|
string sandbox_id = 1;
|
|
// Compute-runtime name used by the driver.
|
|
string sandbox_name = 2;
|
|
}
|
|
|
|
message GetSandboxResponse {
|
|
// Platform-observed sandbox snapshot returned by the driver.
|
|
DriverSandbox sandbox = 1;
|
|
}
|
|
|
|
message ListSandboxesRequest {}
|
|
|
|
message ListSandboxesResponse {
|
|
// Platform-observed sandbox snapshots returned by the driver.
|
|
repeated DriverSandbox sandboxes = 1;
|
|
}
|
|
|
|
message CreateSandboxRequest {
|
|
// Sandbox configuration to provision on the compute platform.
|
|
DriverSandbox sandbox = 1;
|
|
}
|
|
|
|
message CreateSandboxResponse {}
|
|
|
|
message StopSandboxRequest {
|
|
// Stable sandbox ID stored by the gateway.
|
|
string sandbox_id = 1;
|
|
// Compute-runtime name used by the driver.
|
|
string sandbox_name = 2;
|
|
}
|
|
|
|
message StopSandboxResponse {}
|
|
|
|
message DeleteSandboxRequest {
|
|
// Stable sandbox ID stored by the gateway.
|
|
string sandbox_id = 1;
|
|
// Compute-runtime name used by the driver.
|
|
string sandbox_name = 2;
|
|
}
|
|
|
|
message DeleteSandboxResponse {
|
|
// True when a platform resource was deleted by this request.
|
|
bool deleted = 1;
|
|
}
|
|
|
|
message WatchSandboxesRequest {}
|
|
|
|
message WatchSandboxesSandboxEvent {
|
|
// Updated driver-native snapshot for one sandbox.
|
|
DriverSandbox sandbox = 1;
|
|
}
|
|
|
|
message WatchSandboxesDeletedEvent {
|
|
// Sandbox ID removed from the compute platform.
|
|
string sandbox_id = 1;
|
|
}
|
|
|
|
message WatchSandboxesPlatformEvent {
|
|
// Sandbox ID correlated to the platform event.
|
|
string sandbox_id = 1;
|
|
// Raw platform event emitted for the sandbox.
|
|
DriverPlatformEvent event = 2;
|
|
}
|
|
|
|
message WatchSandboxesEvent {
|
|
oneof payload {
|
|
// Updated or newly observed sandbox snapshot.
|
|
WatchSandboxesSandboxEvent sandbox = 1;
|
|
// Sandbox deletion observation.
|
|
WatchSandboxesDeletedEvent deleted = 2;
|
|
// Raw platform event correlated to a sandbox.
|
|
WatchSandboxesPlatformEvent platform_event = 3;
|
|
}
|
|
}
|