mirror of
https://github.com/mulgadc/spinifex.git
synced 2026-10-19 19:01:42 +00:00
Josh Siviour
92fa467c90
* refactor(e2e/multinode): flatten phase 11 + parallelize bucket #1 + drop phase numbers Split monolithic phase11_PlacementAndNATGateway (~430 lines, 8 inline sub-steps) into 6 top-level Tests, each owning its own VPC graph via t.Cleanup and layered setup helpers (spreadSetupVPC, spreadSetupBastion, spreadSetupPrivateTrio, spreadSetupNATGW). The cleanup-ordering test flips *bool latches as each explicit teardown step succeeds so the LIFO unwind is a no-op on the success path. Add t.Parallel() to read-only / independent Tests: ClusterHealth, InstanceDistribution, GuestSSH, VPCNetworking. Deviates from the mulga-siv-127 bead's bucket-#1 listing by keeping CrossNodeGateway sequential (asserts a snapshot equality across gateways that the parallel VPC test would break by churning instance count mid-assert) and CrossNodeOps sequential (stops/starts trio[0], would race GuestSSH). Both deviations documented in tests_test.go + plan doc. Drop the bash phase numbering (phaseN_X funcs + "Phase N" log strings) from the rest of the suite — 10 funcs renamed to runX. Phase numbers were a port-time crutch; the Test names now describe each scenario and phase numbers ageing into noise as bash is retired in Stage H. * refactor(e2e/multinode): collapse spread Tests + control execution order Two changes wedged together since they touch the same files: 1. Collapse the 6 top-level TestMultinodeSpread* Tests into a single TestMultinodeSpread with 6 t.Run sub-tests sharing one VPC + bastion + private trio + NAT GW setup chain. The 6-test split paid setup cost 6× — bastion launch + private trio launch + NAT GW provision per Test pushed phase-11 wall-clock near 60min vs ~15min monolithic. Shared- setup layout keeps JUnit granularity (one row per sub-test) while restoring the monolithic budget. Setup helpers register t.Cleanup against the outer test so teardown runs once at the end (LIFO: NAT GW → trio → bastion → VPC). 2. Move the TestMultinodeSpread wrapper into tests_test.go so file-source order controls execution position. Previously the func lived in placement_nat_test.go which sorts before preflight_test.go and tests_test.go alphabetically — Spread ran FIRST in the sequential bucket, defeating Preflight's fail-fast on a sick cluster. Wrapper now runs after NodeRecovery so the cluster has been fully degrade-tested before Spread's 4-VM + NAT GW + custom-VPC graph spins up.
62 lines
2.2 KiB
Go
62 lines
2.2 KiB
Go
//go:build e2e
|
|
|
|
package multinode
|
|
|
|
import (
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/aws/aws-sdk-go/aws"
|
|
"github.com/aws/aws-sdk-go/service/ec2"
|
|
"github.com/mulgadc/spinifex/tests/e2e/harness"
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
// runVolumeLifecycle is the Go port of volume lifecycle
|
|
// (run-multinode-e2e.sh:731-825). Creates a 10GiB volume, attaches to the
|
|
// first trio instance at /dev/sdf, detaches, deletes. Each step polls a
|
|
// matching state target (in-use/attached → available → 404).
|
|
//
|
|
// Volume is created + torn down inline (not via EnsureVolume) because the
|
|
// test exercises the full CRUD cycle including DeleteVolume — wiring it
|
|
// through Ensure* would have the fixture cleanup race the in-test delete
|
|
// and surface as InvalidVolume.NotFound.
|
|
func runVolumeLifecycle(t *testing.T, fix *Fixture) {
|
|
harness.Phase(t, "Multinode — Volume Lifecycle")
|
|
|
|
az := needAZ(t, fix)
|
|
trio := needInstanceTrio(t, fix)
|
|
require.NotEmpty(t, trio, "trio required")
|
|
target := trio[0]
|
|
|
|
harness.Step(t, "create 10GiB volume in %s", az)
|
|
create, err := fix.AWS.EC2.CreateVolume(&ec2.CreateVolumeInput{
|
|
AvailabilityZone: aws.String(az),
|
|
Size: aws.Int64(10),
|
|
})
|
|
require.NoError(t, err, "create-volume")
|
|
volID := aws.StringValue(create.VolumeId)
|
|
require.NotEmpty(t, volID, "create-volume returned empty VolumeId")
|
|
harness.Detail(t, "volume", volID)
|
|
|
|
harness.Step(t, "attach %s to %s as /dev/sdf", volID, target)
|
|
_, err = fix.AWS.EC2.AttachVolume(&ec2.AttachVolumeInput{
|
|
VolumeId: aws.String(volID),
|
|
InstanceId: aws.String(target),
|
|
Device: aws.String("/dev/sdf"),
|
|
})
|
|
require.NoError(t, err, "attach-volume")
|
|
harness.WaitForVolumeState(t, fix.AWS, volID, "in-use",
|
|
harness.WithTimeout(60*time.Second), harness.WithPoll(2*time.Second))
|
|
|
|
harness.Step(t, "detach %s", volID)
|
|
_, err = fix.AWS.EC2.DetachVolume(&ec2.DetachVolumeInput{VolumeId: aws.String(volID)})
|
|
require.NoError(t, err, "detach-volume")
|
|
harness.WaitForVolumeState(t, fix.AWS, volID, "available",
|
|
harness.WithTimeout(60*time.Second), harness.WithPoll(2*time.Second))
|
|
|
|
harness.Step(t, "delete %s", volID)
|
|
_, err = fix.AWS.EC2.DeleteVolume(&ec2.DeleteVolumeInput{VolumeId: aws.String(volID)})
|
|
require.NoError(t, err, "delete-volume")
|
|
}
|