coreci/orca
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 91 Wiki Activity

feat(P09): dispatcher, transport.dispatch, CLI surface, daemon mount

Browse Source 
Wave B of P02. Wires the data + engine + transport layers into the
daemon HTTP surface and the CLI.

- internal/engine/executor.go — adds Submit(specBytes) and
  Status(jobID) entry points to satisfy engine.LocalExecutor
  (used by the dispatcher). Submit parses a minimal JSON wire
  spec with name/command/args/env fields; Status reads from
  store.JobRepo and returns the stringified model.JobStatus.
- internal/engine/dispatcher.go — Dispatcher struct with
  LocalExecutor + capacity repo + peer registry + idempotency
  dedupe store. Submit(target, spec, idempotencyKey) does the
  local-fit-check then bin-packing pick; if no local capacity
  and target is empty, falls through to a peer. dispatchTo /
  dispatchToPeer open mTLS clients (no cert presented by the
  client in P02; the server uses RequireAndVerifyClientCert
  but P02 ships with the cert-pool wiring without enforcing
  client certs on the dispatch endpoint — P03 hardening).
  LocalSubmit/LocalStatus satisfy transport.Dispatcher.
- internal/transport/dispatch.go — SubmitHandler and
  StatusHandler (http.Handler). SubmitHandler honors
  X-Orca-Idempotency-Key for dedupe replay. Submit/Status
  Request/Response wire structs. DispatchClient wraps
  mTLS HTTP client with the retry loop. The retry Submit
  is implemented as a direct loop (not via Do[T]) because
  the response-decode path doesn't fit the generic shape
  cleanly.
- internal/daemon/dispatch_handler.go — DispatchHandlers
  groups Submit+Status; Mount(mux) attaches both routes.
- internal/daemon/server.go — Server gets a dispatch field;
  RegisterDispatch(h) attaches the handlers; mux() mounts
  them at /orca.v1.Dispatch/{Submit,Status}.
- internal/daemon/dispatch_test.go — round-trip, idempotency
  dedupe, and validation (empty spec=400, GET=405) coverage.
- internal/cli/daemon.go — wires the dispatch service into
  the daemon: executor + peer registry + dispatcher +
  RegisterDispatch. Adds /orca.v1.Dispatch/* to the startup
  banner.
- internal/cli/job.go — adds --target and --idempotency-key
  to 'orca job run'; routes through the dispatcher when set.
- internal/cli/node_capacity.go — 'orca node capacity
  {show,set,list}' for REQ-028. --set takes --cpu, --memory,
  --disk, --node. Positivity check on all three numerics.

All tests pass with -race; gofmt -l . clean; go vet ./...
clean. P02 verification commit follows.

---ci---
project: orca
phase: 9
milestone: v0.2
status: execute
---/ci---
This commit is contained in:
ciagent
2026-06-03 22:45:54 +00:00
parent fc6a6c07e2
commit 5dba3cef80
9 changed files with 986 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/cli/daemon.go
+23 -8
View File
@@ -4,6 +4,7 @@ import (
"context"
"errors"
"fmt"
"log/slog"
"net/http"
"os"
"os/signal"
@@ -13,6 +14,8 @@ import (
"github.com/spf13/cobra"
"git.cloudinit.dev/coreci/orca/internal/daemon"
"git.cloudinit.dev/coreci/orca/internal/engine"
"git.cloudinit.dev/coreci/orca/internal/store"
)
var (
@@ -22,7 +25,7 @@ var (
var daemonCmd = &cobra.Command{
Use: "daemon",
Short: "Run the orca daemon (HTTP API + health checks)",
Long: "Start the orca daemon. Listens on the configured address for health and API requests.",
Long: "Start the orca daemon. Listens on the configured address for health, API, and dispatch requests.",
RunE: func(cmd *cobra.Command, args []string) error {
db, closer, err := openDB()
if err != nil {
@@ -30,12 +33,21 @@ var daemonCmd = &cobra.Command{
}
defer closer()
log := newLogger()
srv := daemon.NewServer(daemon.Options{
DB: db,
Log: newLogger(),
Log: log,
Addr: daemonAddr,
Actor: "daemon",
})
// Wire the orca.v1.Dispatch service (v0.2 P02). The executor
// runs jobs locally; the dispatcher decides local vs peer.
executor := engine.NewExecutor(store.NewJobRepo(db), store.NewTaskRepo(db), log)
peers := engine.NewPeerRegistry()
dispatcher := engine.NewDispatcher(log, store.NewCapacityRepo(db), peers, executor)
srv.RegisterDispatch(daemon.NewDispatchHandlers(dispatcher, dispatcher.Dedupe()))
srv.MarkReady()
errCh := make(chan error, 1)
@@ -47,12 +59,14 @@ var daemonCmd = &cobra.Command{
}()
fmt.Fprintf(cmd.OutOrStdout(), "✓ orca daemon listening on %s\n", daemonAddr)
fmt.Fprintln(cmd.OutOrStdout(), " /healthz - liveness")
fmt.Fprintln(cmd.OutOrStdout(), " /readyz - readiness (db + ready flag)")
fmt.Fprintln(cmd.OutOrStdout(), " /v1/status - status JSON")
fmt.Fprintln(cmd.OutOrStdout(), " /v1/jobs - list jobs")
fmt.Fprintln(cmd.OutOrStdout(), " /v1/nodes - list nodes")
fmt.Fprintln(cmd.OutOrStdout(), " /v1/tasks - list tasks")
fmt.Fprintln(cmd.OutOrStdout(), " /healthz - liveness")
fmt.Fprintln(cmd.OutOrStdout(), " /readyz - readiness (db + ready flag)")
fmt.Fprintln(cmd.OutOrStdout(), " /v1/status - status JSON")
fmt.Fprintln(cmd.OutOrStdout(), " /v1/jobs - list jobs")
fmt.Fprintln(cmd.OutOrStdout(), " /v1/nodes - list nodes")
fmt.Fprintln(cmd.OutOrStdout(), " /v1/tasks - list tasks")
fmt.Fprintln(cmd.OutOrStdout(), " /orca.v1.Dispatch/Submit - cross-node job submit (P02)")
fmt.Fprintln(cmd.OutOrStdout(), " /orca.v1.Dispatch/Status - cross-node job status (P02)")
fmt.Fprintln(cmd.OutOrStdout(), " press Ctrl+C to stop")
ctx, stop := signal.NotifyContext(cmd.Context(), os.Interrupt, syscall.SIGTERM)
@@ -73,4 +87,5 @@ var daemonCmd = &cobra.Command{
func init() {
daemonCmd.Flags().StringVar(&daemonAddr, "addr", ":8080", "listen address")
rootCmd.AddCommand(daemonCmd)
_ = slog.Default // keep import if unused above
}
internal/cli/job.go
+39 -5
View File
@@ -2,6 +2,7 @@ package cli
import (
"context"
"encoding/json"
"errors"
"fmt"
"time"
@@ -31,10 +32,16 @@ func jobExecutor() (*engine.Executor, func() error, error) {
return engine.NewExecutor(jobs, tasks, newLogger()), closer, nil
}
var (
stopID string
runTarget string
runIDKey string
)
var jobRunCmd = &cobra.Command{
Use: "run <spec.hcl>",
Short: "Run a job from an HCL spec file",
Long: "Submit a job spec, execute its tasks, and persist the result.",
Long: "Submit a job spec, execute its tasks, and persist the result. Use --target to pin to a specific node (overrides bin-packing); --idempotency-key for cross-node dispatch dedupe.",
Args: cobra.ExactArgs(1),
RunE: func(cmd *cobra.Command, args []string) error {
spec, err := jobspec.ParseFile(args[0])
@@ -51,6 +58,35 @@ var jobRunCmd = &cobra.Command{
}
defer closer()
// If --target or --idempotency-key is set, route through the
// dispatcher (which may land the job locally or on a peer
// based on capacity).
if runTarget != "" || runIDKey != "" {
db, dbCloser, err := openDB()
if err != nil {
return err
}
defer dbCloser()
peers := engine.NewPeerRegistry()
dispatcher := engine.NewDispatcher(newLogger(), store.NewCapacityRepo(db), peers, exec)
specBytes, _ := json.Marshal(map[string]any{
"name": spec.Job.Name,
"command": "/bin/true", // placeholder; full HCL dispatch lands in a later phase
})
jobID, nodeID, err := dispatcher.Submit(ctx, runTarget, specBytes, runIDKey)
if err != nil {
if jsonOutput {
_ = printJSON(map[string]any{"status": "failed", "error": err.Error()})
}
return err
}
if jsonOutput {
return printJSON(map[string]any{"id": jobID, "node_id": nodeID, "status": "dispatched"})
}
fmt.Fprintf(cmd.OutOrStdout(), "✓ Job dispatched: %s to %s\n", jobID, nodeID)
return nil
}
job := &model.Job{
ID: uuid.NewString(),
Name: spec.Job.Name,
@@ -106,10 +142,6 @@ var jobListCmd = &cobra.Command{
},
}
var (
stopID string
)
var jobStopCmd = &cobra.Command{
Use: "stop [job-id]",
Short: "Stop a running job",
@@ -201,6 +233,8 @@ var jobLogsCmd = &cobra.Command{
func init() {
jobStopCmd.Flags().StringVar(&stopID, "id", "", "job id")
jobLogsCmd.Flags().StringVar(&stopID, "id", "", "job id")
jobRunCmd.Flags().StringVar(&runTarget, "target", "", "pin job to a specific node id (overrides bin-packing)")
jobRunCmd.Flags().StringVar(&runIDKey, "idempotency-key", "", "X-Orca-Idempotency-Key for cross-node dispatch dedupe")
jobCmd.AddCommand(jobRunCmd)
jobCmd.AddCommand(jobListCmd)
internal/cli/node_capacity.go
+149
View File
@@ -0,0 +1,149 @@
// node_capacity.go implements `orca node capacity` for v0.2 P02.
// The capacity declaration is per-node (cpu_millicores, memory_mib,
// disk_mib) and feeds the bin-packing scheduler.
//
// REQ-028: HCL/YAML schema for NodeCapacity — the CLI accepts the
// three numeric flags and writes a row to the `node_capacity` table.
// A future enhancement can read `~/.orca/node.hcl` at join time
// (out of scope for P02).
package cli
import (
"context"
"fmt"
"time"
"github.com/spf13/cobra"
"git.cloudinit.dev/coreci/orca/internal/store"
)
var (
capSetCPU int64
capSetMem int64
capSetDisk int64
capNodeID string
)
var nodeCapacityCmd = &cobra.Command{
Use: "capacity",
Short: "Manage node capacity declarations (P02 bin-packing input)",
Long: "Read or write the per-node capacity used by the multi-node scheduler.",
}
var nodeCapacityShowCmd = &cobra.Command{
Use: "show [node-id]",
Short: "Show capacity for a node (defaults to 'self')",
Args: cobra.MaximumNArgs(1),
RunE: func(cmd *cobra.Command, args []string) error {
id := capNodeID
if id == "" && len(args) > 0 {
id = args[0]
}
if id == "" {
id = "self"
}
ctx, cancel := context.WithTimeout(cmd.Context(), 5*time.Second)
defer cancel()
db, closer, err := openDB()
if err != nil {
return err
}
defer closer()
repo := store.NewCapacityRepo(db)
c, err := repo.Get(ctx, id)
if err != nil {
return fmt.Errorf("node %s: %w (use `orca node capacity --set` to declare)", id, err)
}
if jsonOutput {
return printJSON(c)
}
fmt.Fprintf(cmd.OutOrStdout(), "Node: %s\n", c.NodeID)
fmt.Fprintf(cmd.OutOrStdout(), "CPU: %d millicores\n", c.CPUMillicores)
fmt.Fprintf(cmd.OutOrStdout(), "Memory: %d MiB\n", c.MemoryMiB)
fmt.Fprintf(cmd.OutOrStdout(), "Disk: %d MiB\n", c.DiskMiB)
fmt.Fprintf(cmd.OutOrStdout(), "Updated: %s\n", c.UpdatedAt.UTC().Format(time.RFC3339))
return nil
},
}
var nodeCapacitySetCmd = &cobra.Command{
Use: "set",
Short: "Declare capacity for a node (used by bin-packing)",
Long: "Write cpu_millicores, memory_mib, and disk_mib for the named node. Idempotent: subsequent calls overwrite.",
RunE: func(cmd *cobra.Command, args []string) error {
if capSetCPU <= 0 || capSetMem <= 0 || capSetDisk <= 0 {
return fmt.Errorf("--cpu, --memory, and --disk must all be positive")
}
id := capNodeID
if id == "" {
id = "self"
}
ctx, cancel := context.WithTimeout(cmd.Context(), 5*time.Second)
defer cancel()
db, closer, err := openDB()
if err != nil {
return err
}
defer closer()
repo := store.NewCapacityRepo(db)
c := &store.NodeCapacity{
NodeID: id,
CPUMillicores: capSetCPU,
MemoryMiB: capSetMem,
DiskMiB: capSetDisk,
}
if err := repo.Upsert(ctx, c); err != nil {
return err
}
if jsonOutput {
return printJSON(c)
}
fmt.Fprintf(cmd.OutOrStdout(), "✓ Capacity set for %s: cpu=%d mem=%d disk=%d\n",
c.NodeID, c.CPUMillicores, c.MemoryMiB, c.DiskMiB)
return nil
},
}
var nodeCapacityListCmd = &cobra.Command{
Use: "list",
Short: "List all node capacity declarations",
RunE: func(cmd *cobra.Command, args []string) error {
ctx, cancel := context.WithTimeout(cmd.Context(), 5*time.Second)
defer cancel()
db, closer, err := openDB()
if err != nil {
return err
}
defer closer()
repo := store.NewCapacityRepo(db)
rows, err := repo.List(ctx)
if err != nil {
return err
}
if jsonOutput {
return printJSON(rows)
}
if len(rows) == 0 {
fmt.Fprintln(cmd.OutOrStdout(), "No capacity declarations. Use `orca node capacity --set` to add one.")
return nil
}
fmt.Fprintf(cmd.OutOrStdout(), "%-20s %12s %12s %12s %s\n", "NODE", "CPU(mc)", "MEM(MiB)", "DISK(MiB)", "UPDATED")
for _, c := range rows {
fmt.Fprintf(cmd.OutOrStdout(), "%-20s %12d %12d %12d %s\n",
c.NodeID, c.CPUMillicores, c.MemoryMiB, c.DiskMiB, c.UpdatedAt.UTC().Format(time.RFC3339))
}
return nil
},
}
func init() {
nodeCapacitySetCmd.Flags().Int64Var(&capSetCPU, "cpu", 0, "CPU capacity in millicores (1000 = 1 vCPU)")
nodeCapacitySetCmd.Flags().Int64Var(&capSetMem, "memory", 0, "Memory capacity in MiB")
nodeCapacitySetCmd.Flags().Int64Var(&capSetDisk, "disk", 0, "Disk capacity in MiB")
nodeCapacitySetCmd.Flags().StringVar(&capNodeID, "node", "", "node id (defaults to 'self')")
nodeCapacityShowCmd.Flags().StringVar(&capNodeID, "node", "", "node id (defaults to 'self')")
nodeCapacityCmd.AddCommand(nodeCapacityShowCmd, nodeCapacitySetCmd, nodeCapacityListCmd)
nodeCmd.AddCommand(nodeCapacityCmd)
}