mirror of
https://github.com/mulgadc/spinifex.git
synced 2026-10-20 11:21:49 +00:00
Josh Siviour
de64d6c63d
* feat(ecsgw): on-VM SigV4 client for the ECS agent→gateway channel
Adds internal/ecsgw, the twin of internal/eksgw: a TLS + SigV4 (service "ecs")
client the ecs-agent will use to reach the AWS gateway over HTTPS instead of
connecting to host NATS directly. Calls are AWS JSON 1.1 with an X-Amz-Target
action; the gateway relays onto ecs.* host-side, keeping NATS cluster-internal.
* feat(ecs): SubmitTaskStateChange gateway action → recordTaskState
Wires the AWS-API SubmitTaskStateChange action end to end (gateway action →
ecs.SubmitTaskStateChange NATS → daemon → Service.SubmitTaskStateChange) so a
gateway-routed agent reports task state without touching the NATS bus. The
handler maps the SDK input onto the same bus.TaskState shape and converges on
recordTaskState; the account is authoritative from the SigV4 caller, so an
instance cannot report state for another account's task.
* feat(ecs): durable assign KV inbox + PollAssignments gateway action
Scheduler writes task assigns into a per-instance KV inbox
(clusters/{cluster}/assignments/{instance}/{task}) instead of a
fire-and-forget core-NATS publish, and a new PollAssignments gateway
action lets a gateway-routed agent drain its inbox over TLS+SigV4.
At-least-once: an unacked assign is re-delivered on the next poll;
the agent acks accepted assigns (AckTaskIDs) and STOPPED transitions
reclaim stale inbox entries. The Poll response carries bus.Assign with
an RFC3339 time, so it is encoded with encoding/json (RawJSONActions)
rather than the jsonutil epoch-second marshaler.
* feat(ecs-agent): rewire control-plane off NATS onto the AWS gateway
The agent no longer connects to NATS. It registers, heartbeats, reports
task state, and receives assignments entirely through the AWS gateway
over TLS+SigV4, using seeded IAM credentials — keeping the NATS bus
host-internal and closing the trust-boundary gap (a tenant container
instance must not hold a shared bus token).
- controlPlane seam over ecsgw.Client replaces the NATS publisher:
Register (RegisterContainerInstance), SubmitTaskState
(SubmitTaskStateChange), PollAssignments.
- Heartbeat folds into a periodic idempotent re-register (refreshes
LastSeen); bus.Heartbeat is dropped from the agent.
- subscribeAssign (NATS subscribe) becomes a poll loop: drain the
inbox, dispatch each assign once, ack accepted taskIDs on the next
poll (at-least-once).
- config: ECS_ACCESS_KEY / ECS_SECRET_KEY / ECS_POLL_INTERVAL added,
ECS_NATS_URL removed; cloud-init initd seeds the IAM creds.
Tests move from the NATS publisher fake to a controlPlane fake.
* feat(ecs): cloud-init cred-seed + ecs-node bring-up script
ECS container instances are plain EC2 booted from the spinifex-ecs-node
AMI (AWS-faithful: no ECS-specific launch API). This renders the
cloud-init user-data that seeds /etc/spinifex-ecs/agent.env (gateway
URL/CA/region/cluster + IAM creds) and the gateway CA, then runs the
instance. The agent registers, heartbeats, polls assignments, and
reports task state entirely through the AWS gateway over TLS+SigV4 —
never NATS.
The guest dials the customer-facing gateway address (network advertise
IP), not the mgmt bridge, mirroring the EKS GatewayURL/AddonGatewayURL
split. Seeds the system key for now; scoped per-instance creds are a
follow-up (4g task-role endpoint).
* fix(ecs): reconcile dev merge — restore #418 ENI release + netns wiring
The 'Merge branch dev' resolution dropped code where Sprint 4d (#418,
awsvpc ENI-per-task) and the gateway control-plane rewrite (#419) touch
the same paths:
- recordTaskState STOPPED branch: reclaimTaskENI was clobbered by
reclaimAssignInbox; both are needed (release the task ENI AND drain the
KV inbox). Restores TestRecordTaskState_Awsvpc_ReleasesENIOnStopOnce.
- ecs-agent Agent: the netns field, its init, and the setupTaskNetns/
teardownTaskNetns wrappers were lost when the controlPlane Agent struct
won the merge, leaving taskrun.go calling undefined methods.
- eni_test assign assertion read the assign over NATS; #419 delivers it via
the durable KV inbox, so it now polls via PollAssignments.
- taskrun_test netns cases used the removed historyPub fake; switched to
fakeCP to match the controlPlane seam.
77 lines
2.2 KiB
Go
77 lines
2.2 KiB
Go
package ecsgw
|
|
|
|
import (
|
|
"io"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"strings"
|
|
"testing"
|
|
"time"
|
|
)
|
|
|
|
func newTestClient(t *testing.T, srv *httptest.Server) *Client {
|
|
t.Helper()
|
|
c, err := New(srv.URL, "", "AKIDTEST", "secret", "ap-southeast-2", time.Second)
|
|
if err != nil {
|
|
t.Fatalf("New: %v", err)
|
|
}
|
|
c.httpClient = srv.Client()
|
|
return c
|
|
}
|
|
|
|
// Call signs for service "ecs", sets the X-Amz-Target action, and returns the
|
|
// 2xx body.
|
|
func TestClient_CallSignsAndTargets(t *testing.T) {
|
|
var gotTarget, gotAuth, gotBody string
|
|
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
gotTarget = r.Header.Get("X-Amz-Target")
|
|
gotAuth = r.Header.Get("Authorization")
|
|
b, _ := io.ReadAll(r.Body)
|
|
gotBody = string(b)
|
|
_, _ = w.Write([]byte(`{"ok":true}`))
|
|
}))
|
|
defer srv.Close()
|
|
|
|
c := newTestClient(t, srv)
|
|
out, err := c.Call("RegisterContainerInstance", []byte(`{"instanceId":"i-1"}`))
|
|
if err != nil {
|
|
t.Fatalf("Call: %v", err)
|
|
}
|
|
if string(out) != `{"ok":true}` {
|
|
t.Errorf("body = %q", out)
|
|
}
|
|
if gotTarget != targetPrefix+"RegisterContainerInstance" {
|
|
t.Errorf("target = %q", gotTarget)
|
|
}
|
|
if gotBody != `{"instanceId":"i-1"}` {
|
|
t.Errorf("relayed body = %q", gotBody)
|
|
}
|
|
if !strings.Contains(gotAuth, "AWS4-HMAC-SHA256") || !strings.Contains(gotAuth, "/ecs/aws4_request") {
|
|
t.Errorf("auth header not SigV4 for ecs: %q", gotAuth)
|
|
}
|
|
}
|
|
|
|
// A non-2xx gateway response surfaces as an error carrying status + body.
|
|
func TestClient_CallErrorStatus(t *testing.T) {
|
|
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
|
|
w.WriteHeader(http.StatusForbidden)
|
|
_, _ = w.Write([]byte(`{"__type":"AccessDenied"}`))
|
|
}))
|
|
defer srv.Close()
|
|
|
|
c := newTestClient(t, srv)
|
|
if _, err := c.Call("Heartbeat", []byte(`{}`)); err == nil ||
|
|
!strings.Contains(err.Error(), "403") || !strings.Contains(err.Error(), "AccessDenied") {
|
|
t.Fatalf("want 403 AccessDenied error, got %v", err)
|
|
}
|
|
}
|
|
|
|
func TestNew_Validation(t *testing.T) {
|
|
if _, err := New("", "", "a", "b", "r", 0); err == nil {
|
|
t.Error("want error for empty baseURL")
|
|
}
|
|
if _, err := New("https://gw:9999", "", "", "b", "r", 0); err == nil {
|
|
t.Error("want error for empty access key")
|
|
}
|
|
}
|