mirror of
https://github.com/mulgadc/spinifex.git
synced 2026-10-20 03:11:46 +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.
89 lines
2.8 KiB
Go
89 lines
2.8 KiB
Go
package main
|
|
|
|
import (
|
|
"os"
|
|
"path/filepath"
|
|
"testing"
|
|
"time"
|
|
)
|
|
|
|
func TestLoadConfig_Defaults(t *testing.T) {
|
|
// Ensure env vars don't leak in from the host.
|
|
for _, k := range []string{"ECS_GATEWAY_URL", "ECS_GATEWAY_CA", "ECS_REGION",
|
|
"ECS_CLUSTER", "ECS_ACCESS_KEY", "ECS_SECRET_KEY", "ECS_IMDS_BASE",
|
|
"ECS_CONTAINERD_SOCKET", "ECS_HEARTBEAT_INTERVAL", "ECS_POLL_INTERVAL"} {
|
|
t.Setenv(k, "")
|
|
}
|
|
cfg := loadConfig(filepath.Join(t.TempDir(), "absent.env"))
|
|
if cfg.GatewayCA != defaultGatewayCA {
|
|
t.Errorf("GatewayCA = %q, want default", cfg.GatewayCA)
|
|
}
|
|
if cfg.IMDSBase != defaultIMDSBase {
|
|
t.Errorf("IMDSBase = %q, want default", cfg.IMDSBase)
|
|
}
|
|
if cfg.ContainerdSocket != defaultContainerdSocket {
|
|
t.Errorf("ContainerdSocket = %q, want default", cfg.ContainerdSocket)
|
|
}
|
|
if cfg.ClusterName != "default" {
|
|
t.Errorf("ClusterName = %q, want default", cfg.ClusterName)
|
|
}
|
|
if cfg.Heartbeat != defaultHeartbeat {
|
|
t.Errorf("Heartbeat = %v, want %v", cfg.Heartbeat, defaultHeartbeat)
|
|
}
|
|
if cfg.PollInterval != defaultPollInterval {
|
|
t.Errorf("PollInterval = %v, want %v", cfg.PollInterval, defaultPollInterval)
|
|
}
|
|
}
|
|
|
|
func TestLoadConfig_FileThenEnvOverride(t *testing.T) {
|
|
dir := t.TempDir()
|
|
envFile := filepath.Join(dir, "agent.env")
|
|
body := "# comment\nECS_GATEWAY_URL=https://gw.file\nECS_REGION=us-west-2\nECS_CLUSTER=prod\n"
|
|
if err := os.WriteFile(envFile, []byte(body), 0o600); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
t.Setenv("ECS_GATEWAY_URL", "https://gw.env")
|
|
t.Setenv("ECS_ACCESS_KEY", "AKIAENV")
|
|
|
|
cfg := loadConfig(envFile)
|
|
if cfg.GatewayURL != "https://gw.env" {
|
|
t.Errorf("GatewayURL = %q, want env override", cfg.GatewayURL)
|
|
}
|
|
if cfg.Region != "us-west-2" {
|
|
t.Errorf("Region = %q, want from file", cfg.Region)
|
|
}
|
|
if cfg.ClusterName != "prod" {
|
|
t.Errorf("ClusterName = %q, want from file", cfg.ClusterName)
|
|
}
|
|
if cfg.AccessKey != "AKIAENV" {
|
|
t.Errorf("AccessKey = %q, want env", cfg.AccessKey)
|
|
}
|
|
}
|
|
|
|
func TestLoadConfig_HeartbeatOverride(t *testing.T) {
|
|
t.Setenv("ECS_HEARTBEAT_INTERVAL", "5s")
|
|
if cfg := loadConfig(filepath.Join(t.TempDir(), "absent.env")); cfg.Heartbeat != 5*time.Second {
|
|
t.Errorf("Heartbeat = %v, want 5s", cfg.Heartbeat)
|
|
}
|
|
// Garbage value falls back to the default, not zero.
|
|
t.Setenv("ECS_HEARTBEAT_INTERVAL", "not-a-duration")
|
|
if cfg := loadConfig(filepath.Join(t.TempDir(), "absent.env")); cfg.Heartbeat != defaultHeartbeat {
|
|
t.Errorf("Heartbeat = %v, want default on bad value", cfg.Heartbeat)
|
|
}
|
|
}
|
|
|
|
func TestParseEnvFile_SkipsBlankAndComments(t *testing.T) {
|
|
dir := t.TempDir()
|
|
p := filepath.Join(dir, "f.env")
|
|
if err := os.WriteFile(p, []byte("\n# c\nA=1\nnokeyval\nB = 2 \n"), 0o600); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
m := parseEnvFile(p)
|
|
if m["A"] != "1" || m["B"] != "2" {
|
|
t.Errorf("parse mismatch: %#v", m)
|
|
}
|
|
if _, ok := m["nokeyval"]; ok {
|
|
t.Errorf("line without = should be skipped")
|
|
}
|
|
}
|