Add volume server integration test suite and CI workflow (#8322)

* docs(volume_server): add integration test development plan * test(volume_server): add integration harness and profile matrix * test(volume_server/http): add admin and options integration coverage * test(volume_server/grpc): add state and status integration coverage * test(volume_server): auto-build weed binary and harden cluster startup * test(volume_server/http): add upload read range head delete coverage * test(volume_server/grpc): expand admin lifecycle and state coverage * docs(volume_server): update progress tracker for implemented tests * test(volume_server/http): cover if-none-match and invalid-range branches * test(volume_server/grpc): add batch delete integration coverage * docs(volume_server): log latest HTTP and gRPC test coverage * ci(volume_server): run volume server integration tests in github actions * test(volume_server/grpc): add needle status configure ping and leave coverage * docs(volume_server): record additional grpc coverage progress * test(volume_server/grpc): add vacuum integration coverage * docs(volume_server): record vacuum test coverage progress * test(volume_server/grpc): add read and write needle blob error-path coverage * docs(volume_server): record data rw grpc coverage progress * test(volume_server/http): add jwt auth integration coverage * test(volume_server/grpc): add sync copy and stream error-path coverage * docs(volume_server): record jwt and sync/copy test coverage * test(volume_server/grpc): add scrub and query integration coverage * test(volume_server/grpc): add volume tail sender and receiver coverage * docs(volume_server): record scrub query and tail test progress * test(volume_server/grpc): add readonly writable and collection lifecycle coverage * test(volume_server/http): add public-port cors and method parity coverage * test(volume_server/grpc): add blob meta and read-all success path coverage * test(volume_server/grpc): expand scrub and query variation coverage * test(volume_server/grpc): add tiering and remote fetch error-path coverage * test(volume_server/http): add unchanged write and delete edge-case coverage * test(volume_server/grpc): add ping unknown and unreachable target coverage * test(volume_server/grpc): add volume delete only-empty variation coverage * test(volume_server/http): add jwt fid-mismatch auth coverage * test(volume_server/grpc): add scrub ec auto-select empty coverage * test(volume_server/grpc): stabilize ping timestamp assertion * docs(volume_server): update integration coverage progress log * test(volume_server/grpc): add tier remote backend and config variation coverage * docs(volume_server): record tier remote variation progress * test(volume_server/grpc): add incremental copy and receive-file protocol coverage * test(volume_server/http): add read path shape and if-modified-since coverage * test(volume_server/grpc): add copy-file compaction and receive-file success coverage * test(volume_server/http): add passthrough headers and static asset coverage * test(volume_server/grpc): add ping filer unreachable coverage * docs(volume_server): record copy receive and http variant progress * test(volume_server/grpc): add erasure coding maintenance and missing-path coverage * docs(volume_server): record initial erasure coding rpc coverage * test(volume_server/http): add multi-range multipart response coverage * docs(volume_server): record multi-range http coverage progress * test(volume_server/grpc): add query empty-stripe no-match coverage * docs(volume_server): record query no-match stream behavior coverage * test(volume_server/http): add upload throttling timeout and replicate bypass coverage * docs(volume_server): record upload throttling coverage progress * test(volume_server/http): add download throttling timeout coverage * docs(volume_server): record download throttling coverage progress * test(volume_server/http): add jwt wrong-cookie fid mismatch coverage * docs(volume_server): record jwt wrong-cookie mismatch coverage * test(volume_server/http): add jwt expired-token rejection coverage * docs(volume_server): record jwt expired-token coverage * test(volume_server/http): add jwt query and cookie transport coverage * docs(volume_server): record jwt token transport coverage * test(volume_server/http): add jwt token-source precedence coverage * docs(volume_server): record jwt token-source precedence coverage * test(volume_server/http): add jwt header-over-cookie precedence coverage * docs(volume_server): record jwt header cookie precedence coverage * test(volume_server/http): add jwt query-over-cookie precedence coverage * docs(volume_server): record jwt query cookie precedence coverage * test(volume_server/grpc): add setstate version mismatch and nil-state coverage * docs(volume_server): record setstate validation coverage * test(volume_server/grpc): add readonly persist-true lifecycle coverage * docs(volume_server): record readonly persist variation coverage * test(volume_server/http): add options origin cors header coverage * docs(volume_server): record options origin cors coverage * test(volume_server/http): add trace unsupported-method parity coverage * docs(volume_server): record trace method parity coverage * test(volume_server/grpc): add batch delete cookie-check variation coverage * docs(volume_server): record batch delete cookie-check coverage * test(volume_server/grpc): add admin lifecycle missing and maintenance variants * docs(volume_server): record admin lifecycle edge-case coverage * test(volume_server/grpc): add mixed batch delete status matrix coverage * docs(volume_server): record mixed batch delete matrix coverage * test(volume_server/http): add jwt-profile ui access gating coverage * docs(volume_server): record jwt ui-gating http coverage * test(volume_server/http): add propfind unsupported-method parity coverage * docs(volume_server): record propfind method parity coverage * test(volume_server/grpc): add volume configure success and rollback-path coverage * docs(volume_server): record volume configure branch coverage * test(volume_server/grpc): add volume needle status missing-path coverage * docs(volume_server): record volume needle status error-path coverage * test(volume_server/http): add readDeleted query behavior coverage * docs(volume_server): record readDeleted http behavior coverage * test(volume_server/http): add delete ts override parity coverage * docs(volume_server): record delete ts parity coverage * test(volume_server/grpc): add invalid blob/meta offset coverage * docs(volume_server): record invalid blob/meta offset coverage * test(volume_server/grpc): add read-all mixed volume abort coverage * docs(volume_server): record read-all mixed-volume abort coverage * test(volume_server/http): assert head response body parity * docs(volume_server): record head body parity assertion * test(volume_server/grpc): assert status state and memory payload completeness * docs(volume_server): record volume server status payload coverage * test(volume_server/grpc): add batch delete chunk-manifest rejection coverage * docs(volume_server): record batch delete chunk-manifest coverage * test(volume_server/grpc): add query cookie-mismatch eof parity coverage * docs(volume_server): record query cookie-mismatch parity coverage * test(volume_server/grpc): add ping master success target coverage * docs(volume_server): record ping master success coverage * test(volume_server/http): add head if-none-match conditional parity * docs(volume_server): record head if-none-match parity coverage * test(volume_server/http): add head if-modified-since parity coverage * docs(volume_server): record head if-modified-since parity coverage * test(volume_server/http): add connect unsupported-method parity coverage * docs(volume_server): record connect method parity coverage * test(volume_server/http): assert options allow-headers cors parity * docs(volume_server): record options allow-headers coverage * test(volume_server/framework): add dual volume cluster integration harness * test(volume_server/http): add missing-local read mode proxy redirect local coverage * docs(volume_server): record read mode missing-local matrix coverage * test(volume_server/http): add download over-limit replica proxy fallback coverage * docs(volume_server): record download replica fallback coverage * test(volume_server/http): add missing-local readDeleted proxy redirect parity coverage * docs(volume_server): record missing-local readDeleted mode coverage * test(volume_server/framework): add single-volume cluster with filer harness * test(volume_server/grpc): add ping filer success target coverage * docs(volume_server): record ping filer success coverage * test(volume_server/http): add proxied-loop guard download timeout coverage * docs(volume_server): record proxied-loop download coverage * test(volume_server/http): add disabled upload and download limit coverage * docs(volume_server): record disabled throttling path coverage * test(volume_server/grpc): add idempotent volume server leave coverage * docs(volume_server): record leave idempotence coverage * test(volume_server/http): add redirect collection query preservation coverage * docs(volume_server): record redirect collection query coverage * test(volume_server/http): assert admin server headers on status and health * docs(volume_server): record admin server header coverage * test(volume_server/http): assert healthz request-id echo parity * docs(volume_server): record healthz request-id parity coverage * test(volume_server/http): add over-limit invalid-vid download branch coverage * docs(volume_server): record over-limit invalid-vid branch coverage * test(volume_server/http): add public-port static asset coverage * docs(volume_server): record public static endpoint coverage * test(volume_server/http): add public head method parity coverage * docs(volume_server): record public head parity coverage * test(volume_server/http): add throttling wait-then-proceed path coverage * docs(volume_server): record throttling wait-then-proceed coverage * test(volume_server/http): add read cookie-mismatch not-found coverage * docs(volume_server): record read cookie-mismatch coverage * test(volume_server/http): add throttling timeout-recovery coverage * docs(volume_server): record throttling timeout-recovery coverage * test(volume_server/grpc): add ec generate mount info unmount lifecycle coverage * docs(volume_server): record ec positive lifecycle coverage * test(volume_server/grpc): add ec shard read and blob delete lifecycle coverage * docs(volume_server): record ec shard read/blob delete lifecycle coverage * test(volume_server/grpc): add ec rebuild and to-volume error branch coverage * docs(volume_server): record ec rebuild and to-volume branch coverage * test(volume_server/grpc): add ec shards-to-volume success roundtrip coverage * docs(volume_server): record ec shards-to-volume success coverage * test(volume_server/grpc): add ec receive and copy-file missing-source coverage * docs(volume_server): record ec receive and copy-file coverage * test(volume_server/grpc): add ec last-shard delete cleanup coverage * docs(volume_server): record ec last-shard delete cleanup coverage * test(volume_server/grpc): add volume copy success path coverage * docs(volume_server): record volume copy success coverage * test(volume_server/grpc): add volume copy overwrite-destination coverage * docs(volume_server): record volume copy overwrite coverage * test(volume_server/http): add write error-path variant coverage * docs(volume_server): record http write error-path coverage * test(volume_server/http): add conditional header precedence coverage * docs(volume_server): record conditional header precedence coverage * test(volume_server/http): add oversized combined range guard coverage * docs(volume_server): record oversized range guard coverage * test(volume_server/http): add image resize and crop read coverage * docs(volume_server): record image transform coverage * test(volume_server/http): add chunk-manifest expansion and bypass coverage * docs(volume_server): record chunk-manifest read coverage * test(volume_server/http): add compressed read encoding matrix coverage * docs(volume_server): record compressed read matrix coverage * test(volume_server/grpc): add tail receiver source replication coverage * docs(volume_server): record tail receiver replication coverage * test(volume_server/grpc): add tail sender large-needle chunking coverage * docs(volume_server): record tail sender chunking coverage * test(volume_server/grpc): add ec-backed volume needle status coverage * docs(volume_server): record ec-backed needle status coverage * test(volume_server/grpc): add ec shard copy from peer success coverage * docs(volume_server): record ec shard copy success coverage * test(volume_server/http): add chunk-manifest delete child cleanup coverage * docs(volume_server): record chunk-manifest delete cleanup coverage * test(volume_server/http): add chunk-manifest delete failure-path coverage * docs(volume_server): record chunk-manifest delete failure coverage * test(volume_server/grpc): add ec shard copy source-unavailable coverage * docs(volume_server): record ec shard copy source-unavailable coverage * parallel
2026-02-13 00:40:56 -08:00
parent c433fee36a
commit beeb375a88
41 changed files with 9459 additions and 0 deletions
--- a/test/volume_server/framework/cluster_dual.go
+++ b/test/volume_server/framework/cluster_dual.go
@@ -0,0 +1,293 @@
+package framework
+
+import (
+	"fmt"
+	"net"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strconv"
+	"sync"
+	"testing"
+
+	"github.com/seaweedfs/seaweedfs/test/volume_server/matrix"
+)
+
+type DualVolumeCluster struct {
+	testingTB testing.TB
+	profile   matrix.Profile
+
+	weedBinary string
+	baseDir    string
+	configDir  string
+	logsDir    string
+	keepLogs   bool
+
+	masterPort     int
+	masterGrpcPort int
+
+	volumePort0     int
+	volumeGrpcPort0 int
+	volumePubPort0  int
+	volumePort1     int
+	volumeGrpcPort1 int
+	volumePubPort1  int
+
+	masterCmd *exec.Cmd
+	volumeCmd0 *exec.Cmd
+	volumeCmd1 *exec.Cmd
+
+	cleanupOnce sync.Once
+}
+
+func StartDualVolumeCluster(t testing.TB, profile matrix.Profile) *DualVolumeCluster {
+	t.Helper()
+
+	weedBinary, err := FindOrBuildWeedBinary()
+	if err != nil {
+		t.Fatalf("resolve weed binary: %v", err)
+	}
+
+	baseDir, keepLogs, err := newWorkDir()
+	if err != nil {
+		t.Fatalf("create temp test directory: %v", err)
+	}
+
+	configDir := filepath.Join(baseDir, "config")
+	logsDir := filepath.Join(baseDir, "logs")
+	masterDataDir := filepath.Join(baseDir, "master")
+	volumeDataDir0 := filepath.Join(baseDir, "volume0")
+	volumeDataDir1 := filepath.Join(baseDir, "volume1")
+	for _, dir := range []string{configDir, logsDir, masterDataDir, volumeDataDir0, volumeDataDir1} {
+		if mkErr := os.MkdirAll(dir, 0o755); mkErr != nil {
+			t.Fatalf("create %s: %v", dir, mkErr)
+		}
+	}
+
+	if err = writeSecurityConfig(configDir, profile); err != nil {
+		t.Fatalf("write security config: %v", err)
+	}
+
+	masterPort, masterGrpcPort, err := allocateMasterPortPair()
+	if err != nil {
+		t.Fatalf("allocate master port pair: %v", err)
+	}
+
+	ports, err := allocatePorts(6)
+	if err != nil {
+		t.Fatalf("allocate volume ports: %v", err)
+	}
+
+	c := &DualVolumeCluster{
+		testingTB:      t,
+		profile:        profile,
+		weedBinary:     weedBinary,
+		baseDir:        baseDir,
+		configDir:      configDir,
+		logsDir:        logsDir,
+		keepLogs:       keepLogs,
+		masterPort:     masterPort,
+		masterGrpcPort: masterGrpcPort,
+		volumePort0:    ports[0],
+		volumeGrpcPort0: ports[1],
+		volumePubPort0: ports[0],
+		volumePort1:    ports[2],
+		volumeGrpcPort1: ports[3],
+		volumePubPort1: ports[2],
+	}
+	if profile.SplitPublicPort {
+		c.volumePubPort0 = ports[4]
+		c.volumePubPort1 = ports[5]
+	}
+
+	if err = c.startMaster(masterDataDir); err != nil {
+		c.Stop()
+		t.Fatalf("start master: %v", err)
+	}
+	if err = c.waitForHTTP(c.MasterURL() + "/dir/status"); err != nil {
+		masterLog := c.tailLog("master.log")
+		c.Stop()
+		t.Fatalf("wait for master readiness: %v\nmaster log tail:\n%s", err, masterLog)
+	}
+
+	if err = c.startVolume(0, volumeDataDir0); err != nil {
+		masterLog := c.tailLog("master.log")
+		c.Stop()
+		t.Fatalf("start first volume server: %v\nmaster log tail:\n%s", err, masterLog)
+	}
+	if err = c.waitForHTTP(c.VolumeAdminURL(0) + "/status"); err != nil {
+		volumeLog := c.tailLog("volume0.log")
+		c.Stop()
+		t.Fatalf("wait for first volume readiness: %v\nvolume log tail:\n%s", err, volumeLog)
+	}
+	if err = c.waitForTCP(c.VolumeGRPCAddress(0)); err != nil {
+		volumeLog := c.tailLog("volume0.log")
+		c.Stop()
+		t.Fatalf("wait for first volume grpc readiness: %v\nvolume log tail:\n%s", err, volumeLog)
+	}
+
+	if err = c.startVolume(1, volumeDataDir1); err != nil {
+		volumeLog := c.tailLog("volume0.log")
+		c.Stop()
+		t.Fatalf("start second volume server: %v\nfirst volume log tail:\n%s", err, volumeLog)
+	}
+	if err = c.waitForHTTP(c.VolumeAdminURL(1) + "/status"); err != nil {
+		volumeLog := c.tailLog("volume1.log")
+		c.Stop()
+		t.Fatalf("wait for second volume readiness: %v\nvolume log tail:\n%s", err, volumeLog)
+	}
+	if err = c.waitForTCP(c.VolumeGRPCAddress(1)); err != nil {
+		volumeLog := c.tailLog("volume1.log")
+		c.Stop()
+		t.Fatalf("wait for second volume grpc readiness: %v\nvolume log tail:\n%s", err, volumeLog)
+	}
+
+	t.Cleanup(func() {
+		c.Stop()
+	})
+
+	return c
+}
+
+func (c *DualVolumeCluster) Stop() {
+	if c == nil {
+		return
+	}
+	c.cleanupOnce.Do(func() {
+		stopProcess(c.volumeCmd1)
+		stopProcess(c.volumeCmd0)
+		stopProcess(c.masterCmd)
+		if !c.keepLogs && !c.testingTB.Failed() {
+			_ = os.RemoveAll(c.baseDir)
+		} else if c.baseDir != "" {
+			c.testingTB.Logf("volume server integration logs kept at %s", c.baseDir)
+		}
+	})
+}
+
+func (c *DualVolumeCluster) startMaster(dataDir string) error {
+	logFile, err := os.Create(filepath.Join(c.logsDir, "master.log"))
+	if err != nil {
+		return err
+	}
+
+	args := []string{
+		"-config_dir=" + c.configDir,
+		"master",
+		"-ip=127.0.0.1",
+		"-port=" + strconv.Itoa(c.masterPort),
+		"-port.grpc=" + strconv.Itoa(c.masterGrpcPort),
+		"-mdir=" + dataDir,
+		"-peers=none",
+		"-volumeSizeLimitMB=" + strconv.Itoa(testVolumeSizeLimitMB),
+		"-defaultReplication=000",
+	}
+
+	c.masterCmd = exec.Command(c.weedBinary, args...)
+	c.masterCmd.Dir = c.baseDir
+	c.masterCmd.Stdout = logFile
+	c.masterCmd.Stderr = logFile
+	return c.masterCmd.Start()
+}
+
+func (c *DualVolumeCluster) startVolume(index int, dataDir string) error {
+	logName := fmt.Sprintf("volume%d.log", index)
+	logFile, err := os.Create(filepath.Join(c.logsDir, logName))
+	if err != nil {
+		return err
+	}
+
+	volumePort := c.volumePort0
+	volumeGrpcPort := c.volumeGrpcPort0
+	volumePubPort := c.volumePubPort0
+	if index == 1 {
+		volumePort = c.volumePort1
+		volumeGrpcPort = c.volumeGrpcPort1
+		volumePubPort = c.volumePubPort1
+	}
+
+	args := []string{
+		"-config_dir=" + c.configDir,
+		"volume",
+		"-ip=127.0.0.1",
+		"-port=" + strconv.Itoa(volumePort),
+		"-port.grpc=" + strconv.Itoa(volumeGrpcPort),
+		"-port.public=" + strconv.Itoa(volumePubPort),
+		"-dir=" + dataDir,
+		"-max=16",
+		"-master=127.0.0.1:" + strconv.Itoa(c.masterPort),
+		"-readMode=" + c.profile.ReadMode,
+		"-concurrentUploadLimitMB=" + strconv.Itoa(c.profile.ConcurrentUploadLimitMB),
+		"-concurrentDownloadLimitMB=" + strconv.Itoa(c.profile.ConcurrentDownloadLimitMB),
+	}
+	if c.profile.InflightUploadTimeout > 0 {
+		args = append(args, "-inflightUploadDataTimeout="+c.profile.InflightUploadTimeout.String())
+	}
+	if c.profile.InflightDownloadTimeout > 0 {
+		args = append(args, "-inflightDownloadDataTimeout="+c.profile.InflightDownloadTimeout.String())
+	}
+
+	cmd := exec.Command(c.weedBinary, args...)
+	cmd.Dir = c.baseDir
+	cmd.Stdout = logFile
+	cmd.Stderr = logFile
+
+	if err = cmd.Start(); err != nil {
+		return err
+	}
+	if index == 1 {
+		c.volumeCmd1 = cmd
+	} else {
+		c.volumeCmd0 = cmd
+	}
+	return nil
+}
+
+func (c *DualVolumeCluster) waitForHTTP(url string) error {
+	return (&Cluster{}).waitForHTTP(url)
+}
+
+func (c *DualVolumeCluster) waitForTCP(addr string) error {
+	return (&Cluster{}).waitForTCP(addr)
+}
+
+func (c *DualVolumeCluster) tailLog(logName string) string {
+	return (&Cluster{logsDir: c.logsDir}).tailLog(logName)
+}
+
+func (c *DualVolumeCluster) MasterAddress() string {
+	return net.JoinHostPort("127.0.0.1", strconv.Itoa(c.masterPort))
+}
+
+func (c *DualVolumeCluster) MasterURL() string {
+	return "http://" + c.MasterAddress()
+}
+
+func (c *DualVolumeCluster) VolumeAdminAddress(index int) string {
+	if index == 1 {
+		return net.JoinHostPort("127.0.0.1", strconv.Itoa(c.volumePort1))
+	}
+	return net.JoinHostPort("127.0.0.1", strconv.Itoa(c.volumePort0))
+}
+
+func (c *DualVolumeCluster) VolumePublicAddress(index int) string {
+	if index == 1 {
+		return net.JoinHostPort("127.0.0.1", strconv.Itoa(c.volumePubPort1))
+	}
+	return net.JoinHostPort("127.0.0.1", strconv.Itoa(c.volumePubPort0))
+}
+
+func (c *DualVolumeCluster) VolumeGRPCAddress(index int) string {
+	if index == 1 {
+		return net.JoinHostPort("127.0.0.1", strconv.Itoa(c.volumeGrpcPort1))
+	}
+	return net.JoinHostPort("127.0.0.1", strconv.Itoa(c.volumeGrpcPort0))
+}
+
+func (c *DualVolumeCluster) VolumeAdminURL(index int) string {
+	return "http://" + c.VolumeAdminAddress(index)
+}
+
+func (c *DualVolumeCluster) VolumePublicURL(index int) string {
+	return "http://" + c.VolumePublicAddress(index)
+}