egress-proxies-operator/internal/provider/proxmox/task_test.go

package proxmox

import (
	"context"
	"errors"
	"strings"
	"testing"
	"time"

	"gitea.home.hrajfrisbee.cz/kacerr/egress-proxies-operator/internal/provider"
)

// addTask registers a fake task on node that ends with exit.
func addTask(f *fakeAPI, node, exit string) string {
	f.mu.Lock()
	defer f.mu.Unlock()
	return f.newTask(node, "qmstart", "150042", exit, nil)
}

func TestParseUPID_table(t *testing.T) {
	t.Parallel()
	tests := []struct {
		name     string
		upid     string
		wantNode string
	}{
		{name: "captured clone", upid: decodeData[string](t, "clone_response"), wantNode: "pv1-1"},
		{name: "captured task status", upid: decodeData[taskStatus](t, "task_status_stopped_ok").UPID, wantNode: "pv1-1"},
		{name: "captured upload", upid: decodeData[string](t, "upload_response_proxy_seeds"), wantNode: "pv1-1"},
		{name: "fake task on another node", upid: addTask(newFakeAPI(), "pv1-2", "OK"), wantNode: "pv1-2"},
		{name: "empty", upid: ""},
		{name: "prefix only", upid: "UPID:"},
		{name: "lower-case prefix", upid: "upid:pv1-1:0010F9DC:02801DA1:6AB37871:qmclone:9001:root@pam:"},
		{name: "no trailing colon", upid: "UPID:pv1-1:0010F9DC:02801DA1:6AB37871:qmclone:9001:root@pam"},
		{name: "slash in node", upid: "UPID:pv1/1:0010F9DC:02801DA1:6AB37871:qmclone:9001:root@pam:"},
		{name: "pid not hex", upid: "UPID:pv1-1:0010F9DZ:02801DA1:6AB37871:qmclone:9001:root@pam:"},
		{name: "missing user", upid: "UPID:pv1-1:0010F9DC:02801DA1:6AB37871:qmclone:9001::"},
	}
	for _, tc := range tests {
		t.Run(tc.name, func(t *testing.T) {
			t.Parallel()
			node, err := parseUPID(tc.upid)
			if tc.wantNode == "" {
				if !errors.Is(err, provider.ErrPermanent) {
					t.Errorf("parseUPID(%q) = %q, %v; want ErrPermanent", tc.upid, node, err)
				}
				return
			}
			if err != nil || node != tc.wantNode {
				t.Errorf("parseUPID(%q) = %q, %v; want %q", tc.upid, node, err, tc.wantNode)
			}
		})
	}
}

func TestWaitTask_table(t *testing.T) {
	t.Parallel()
	failedExit := loadTaskExit(t, "task_status_stopped_error")
	tests := []struct {
		name      string
		node      string
		exit      string
		upid      string // overrides the registered task's UPID
		polls     int
		budget    time.Duration
		cancelled bool
		statusErr error
		wantClass error // nil for success
		wantCalls int
		wantInErr string
		wantLog   string
	}{
		{name: "ok on the first poll", exit: "OK", wantCalls: 1},
		{name: "polls until stopped", exit: "OK", polls: 3, wantCalls: 4},
		{name: "polls the node the UPID names", node: "pv1-2", exit: "OK", wantCalls: 1},
		{name: "warnings count as success", exit: "WARNINGS: 2", wantCalls: 1, wantLog: `"msg"="proxmox task finished with warnings"`},
		{
			name: "failed exitstatus is transient and logged", exit: failedExit, wantClass: provider.ErrTransient, wantCalls: 1,
			wantInErr: failedExit, wantLog: `"msg"="proxmox task failed"`,
		},
		{name: "budget exceeded names the UPID", exit: "OK", polls: 1 << 30, budget: 20 * time.Millisecond, wantClass: provider.ErrTransient, wantCalls: -1, wantInErr: "UPID:pv1-1:"},
		{name: "ended ctx is transient", exit: "OK", polls: 1 << 30, cancelled: true, wantClass: provider.ErrTransient, wantCalls: 1, wantInErr: context.Canceled.Error()},
		{name: "malformed UPID makes no call", upid: "UPID:bogus", wantClass: provider.ErrPermanent, wantCalls: 0},
		{name: "status read failing is returned", exit: "OK", statusErr: loadAPIError(t, "err_forbidden"), wantClass: provider.ErrPermanent, wantCalls: 1, wantInErr: "Permission check failed"},
	}
	for _, tc := range tests {
		t.Run(tc.name, func(t *testing.T) {
			t.Parallel()
			fx := newFixture(t, 1)
			fx.fake.taskPolls = tc.polls
			if tc.statusErr != nil {
				fx.fake.failWith("TaskStatus", tc.statusErr)
			}
			node := tc.node
			if node == "" {
				node = fakeNode
			}
			upid := addTask(fx.fake, node, tc.exit)
			if tc.upid != "" {
				upid = tc.upid
			}
			budget := tc.budget
			if budget == 0 {
				budget = time.Minute
			}
			ctx := fx.ctx
			if tc.cancelled {
				var cancel context.CancelFunc
				ctx, cancel = context.WithCancel(ctx)
				cancel()
			}
			start := time.Now()
			err := fx.p.waitTask(ctx, fx.p.logger(ctx), upid, budget)
			if elapsed := time.Since(start); elapsed > 5*time.Second {
				t.Errorf("waitTask took %v", elapsed)
			}
			if tc.wantClass == nil {
				if err != nil {
					t.Fatalf("waitTask error = %v, want nil", err)
				}
			} else if classify("create", err) != tc.wantClass {
				t.Fatalf("waitTask error = %v, want class %v", err, tc.wantClass)
			}
			if tc.wantInErr != "" && !strings.Contains(err.Error(), tc.wantInErr) {
				t.Errorf("waitTask error = %q, want it to contain %q", err, tc.wantInErr)
			}
			if got := fx.fake.callCount("TaskStatus"); tc.wantCalls >= 0 && got != tc.wantCalls {
				t.Errorf("TaskStatus calls = %d, want %d", got, tc.wantCalls)
			}
			if tc.wantLog != "" {
				lines := fx.logs.matching(tc.wantLog)
				if len(lines) != 1 || !strings.Contains(lines[0], `"upid"="`+upid+`"`) || !strings.Contains(lines[0], `"exitstatus"="`+tc.exit+`"`) {
					t.Errorf("log lines %q = %v, want one with upid and exitstatus", tc.wantLog, lines)
				}
			}
		})
	}
}

func TestWaitTask_quietAtV0(t *testing.T) {
	t.Parallel()
	fx := newFixture(t, 0)
	err := fx.p.waitTask(fx.ctx, fx.p.logger(fx.ctx), addTask(fx.fake, fakeNode, "boom"), time.Minute)
	if err == nil {
		t.Fatal("waitTask on a failed task returned nil")
	}
	if lines := fx.logs.all(); len(lines) != 0 {
		t.Errorf("V(0) lines = %v, want none", lines)
	}
}

func TestWaitUnlocked_table(t *testing.T) {
	t.Parallel()
	tests := []struct {
		name string
		lock string
		// onCall runs on the n-th VMConfig call (1-based) under f.mu.
		onCall    func(f *fakeAPI, n int)
		budget    time.Duration
		cancelled bool
		wantErr   func(error) bool
		wantCalls int
	}{
		{name: "unlocked answers at once", wantCalls: 1},
		{
			name: "waits until the lock clears", lock: "clone", wantCalls: 3,
			onCall: func(f *fakeAPI, n int) {
				if n == 3 {
					f.vms[testVMID].lock = ""
				}
			},
		},
		{
			name: "lock that never clears is transient", lock: "clone", budget: 20 * time.Millisecond, wantCalls: -1,
			wantErr: func(err error) bool {
				return errors.Is(err, provider.ErrTransient) && strings.Contains(err.Error(), "the lock on VM 150042")
			},
		},
		{
			name: "VM removed by a failed clone gives does not exist", lock: "clone", wantCalls: 2,
			onCall: func(f *fakeAPI, n int) {
				if n == 2 {
					delete(f.vms, testVMID)
				}
			},
			wantErr: isNotExist,
		},
		{
			name: "ended ctx is transient", lock: "clone", cancelled: true, wantCalls: 1,
			wantErr: func(err error) bool {
				return errors.Is(err, provider.ErrTransient) && errors.Is(err, context.Canceled)
			},
		},
	}
	for _, tc := range tests {
		t.Run(tc.name, func(t *testing.T) {
			t.Parallel()
			fx := newFixture(t, 1)
			fx.addOurVM(testVMID, testName, "stopped").lock = tc.lock
			var n int
			fx.fake.hookOn("VMConfig", func() error {
				fx.fake.mu.Lock()
				defer fx.fake.mu.Unlock()
				n++
				if tc.onCall != nil {
					tc.onCall(fx.fake, n)
				}
				return nil
			})
			budget := tc.budget
			if budget == 0 {
				budget = time.Minute
			}
			ctx := fx.ctx
			if tc.cancelled {
				var cancel context.CancelFunc
				ctx, cancel = context.WithCancel(ctx)
				cancel()
			}
			cfg, err := fx.p.waitUnlocked(ctx, fakeNode, testVMID, budget)
			if tc.wantErr == nil {
				if err != nil || cfg["name"] != testName || cfg["lock"] != "" {
					t.Errorf("waitUnlocked = %v, %v; want the unlocked config", cfg, err)
				}
			} else if !tc.wantErr(err) || cfg != nil {
				t.Errorf("waitUnlocked = %v, %v; want no config and the expected error", cfg, err)
			}
			if got := fx.fake.callCount("VMConfig"); tc.wantCalls >= 0 && got != tc.wantCalls {
				t.Errorf("VMConfig calls = %d, want %d", got, tc.wantCalls)
			}
		})
	}
}