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/grpc/batch_delete_test.go
+++ b/test/volume_server/grpc/batch_delete_test.go
@@ -0,0 +1,264 @@
+package volume_server_grpc_test
+
+import (
+	"bytes"
+	"context"
+	"net/http"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/seaweedfs/seaweedfs/test/volume_server/framework"
+	"github.com/seaweedfs/seaweedfs/test/volume_server/matrix"
+	"github.com/seaweedfs/seaweedfs/weed/pb/volume_server_pb"
+)
+
+func TestBatchDeleteInvalidFidAndMaintenanceMode(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	cluster := framework.StartSingleVolumeCluster(t, matrix.P1())
+	conn, client := framework.DialVolumeServer(t, cluster.VolumeGRPCAddress())
+	defer conn.Close()
+
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	resp, err := client.BatchDelete(ctx, &volume_server_pb.BatchDeleteRequest{FileIds: []string{"bad-fid"}})
+	if err != nil {
+		t.Fatalf("BatchDelete invalid fid should return response, got error: %v", err)
+	}
+	if len(resp.GetResults()) != 1 {
+		t.Fatalf("expected one batch delete result, got %d", len(resp.GetResults()))
+	}
+	if got := resp.GetResults()[0].GetStatus(); got != 400 {
+		t.Fatalf("invalid fid expected status 400, got %d", got)
+	}
+
+	stateResp, err := client.GetState(ctx, &volume_server_pb.GetStateRequest{})
+	if err != nil {
+		t.Fatalf("GetState failed: %v", err)
+	}
+	_, err = client.SetState(ctx, &volume_server_pb.SetStateRequest{
+		State: &volume_server_pb.VolumeServerState{Maintenance: true, Version: stateResp.GetState().GetVersion()},
+	})
+	if err != nil {
+		t.Fatalf("SetState maintenance=true failed: %v", err)
+	}
+
+	_, err = client.BatchDelete(ctx, &volume_server_pb.BatchDeleteRequest{FileIds: []string{"1,1234567890ab"}})
+	if err == nil {
+		t.Fatalf("BatchDelete should fail when maintenance mode is enabled")
+	}
+	if !strings.Contains(err.Error(), "maintenance mode") {
+		t.Fatalf("expected maintenance mode error, got: %v", err)
+	}
+}
+
+func TestBatchDeleteCookieMismatchAndSkipCheck(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	cluster := framework.StartSingleVolumeCluster(t, matrix.P1())
+	conn, client := framework.DialVolumeServer(t, cluster.VolumeGRPCAddress())
+	defer conn.Close()
+
+	const volumeID = uint32(31)
+	const needleID = uint64(900001)
+	const correctCookie = uint32(0x1122AABB)
+	const wrongCookie = uint32(0x1122AABC)
+	framework.AllocateVolume(t, client, volumeID, "")
+
+	httpClient := framework.NewHTTPClient()
+	fid := framework.NewFileID(volumeID, needleID, correctCookie)
+	uploadResp := framework.UploadBytes(t, httpClient, cluster.VolumeAdminURL(), fid, []byte("batch-delete-cookie-check"))
+	_ = framework.ReadAllAndClose(t, uploadResp)
+	if uploadResp.StatusCode != http.StatusCreated {
+		t.Fatalf("upload expected 201, got %d", uploadResp.StatusCode)
+	}
+
+	wrongCookieFid := framework.NewFileID(volumeID, needleID, wrongCookie)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	mismatchResp, err := client.BatchDelete(ctx, &volume_server_pb.BatchDeleteRequest{
+		FileIds:         []string{wrongCookieFid},
+		SkipCookieCheck: false,
+	})
+	if err != nil {
+		t.Fatalf("BatchDelete with cookie check failed: %v", err)
+	}
+	if len(mismatchResp.GetResults()) != 1 {
+		t.Fatalf("BatchDelete cookie mismatch expected 1 result, got %d", len(mismatchResp.GetResults()))
+	}
+	if mismatchResp.GetResults()[0].GetStatus() != http.StatusBadRequest {
+		t.Fatalf("BatchDelete cookie mismatch expected status 400, got %d", mismatchResp.GetResults()[0].GetStatus())
+	}
+
+	skipCheckResp, err := client.BatchDelete(ctx, &volume_server_pb.BatchDeleteRequest{
+		FileIds:         []string{wrongCookieFid},
+		SkipCookieCheck: true,
+	})
+	if err != nil {
+		t.Fatalf("BatchDelete skip cookie check failed: %v", err)
+	}
+	if len(skipCheckResp.GetResults()) != 1 {
+		t.Fatalf("BatchDelete skip check expected 1 result, got %d", len(skipCheckResp.GetResults()))
+	}
+	if skipCheckResp.GetResults()[0].GetStatus() != http.StatusAccepted {
+		t.Fatalf("BatchDelete skip check expected status 202, got %d", skipCheckResp.GetResults()[0].GetStatus())
+	}
+
+	readAfterDelete := framework.ReadBytes(t, httpClient, cluster.VolumeAdminURL(), fid)
+	_ = framework.ReadAllAndClose(t, readAfterDelete)
+	if readAfterDelete.StatusCode != http.StatusNotFound {
+		t.Fatalf("read after skip-check batch delete expected 404, got %d", readAfterDelete.StatusCode)
+	}
+}
+
+func TestBatchDeleteMixedStatusesAndMismatchStopsProcessing(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	cluster := framework.StartSingleVolumeCluster(t, matrix.P1())
+	conn, client := framework.DialVolumeServer(t, cluster.VolumeGRPCAddress())
+	defer conn.Close()
+
+	const volumeID = uint32(32)
+	framework.AllocateVolume(t, client, volumeID, "")
+
+	const needleA = uint64(910001)
+	const needleB = uint64(910002)
+	const needleC = uint64(910003)
+	const cookieA = uint32(0x11111111)
+	const cookieB = uint32(0x22222222)
+	const cookieC = uint32(0x33333333)
+
+	httpClient := framework.NewHTTPClient()
+	fidA := framework.NewFileID(volumeID, needleA, cookieA)
+	fidB := framework.NewFileID(volumeID, needleB, cookieB)
+	fidC := framework.NewFileID(volumeID, needleC, cookieC)
+
+	for _, tc := range []struct {
+		fid  string
+		body string
+	}{
+		{fid: fidA, body: "batch-delete-mixed-a"},
+		{fid: fidB, body: "batch-delete-mixed-b"},
+		{fid: fidC, body: "batch-delete-mixed-c"},
+	} {
+		uploadResp := framework.UploadBytes(t, httpClient, cluster.VolumeAdminURL(), tc.fid, []byte(tc.body))
+		_ = framework.ReadAllAndClose(t, uploadResp)
+		if uploadResp.StatusCode != http.StatusCreated {
+			t.Fatalf("upload %s expected 201, got %d", tc.fid, uploadResp.StatusCode)
+		}
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	missingFid := framework.NewFileID(volumeID, 919999, 0x44444444)
+	mixedResp, err := client.BatchDelete(ctx, &volume_server_pb.BatchDeleteRequest{
+		FileIds: []string{"bad-fid", fidA, missingFid},
+	})
+	if err != nil {
+		t.Fatalf("BatchDelete mixed status request failed: %v", err)
+	}
+	if len(mixedResp.GetResults()) != 3 {
+		t.Fatalf("BatchDelete mixed status expected 3 results, got %d", len(mixedResp.GetResults()))
+	}
+	if mixedResp.GetResults()[0].GetStatus() != http.StatusBadRequest {
+		t.Fatalf("BatchDelete mixed result[0] expected 400, got %d", mixedResp.GetResults()[0].GetStatus())
+	}
+	if mixedResp.GetResults()[1].GetStatus() != http.StatusAccepted {
+		t.Fatalf("BatchDelete mixed result[1] expected 202, got %d", mixedResp.GetResults()[1].GetStatus())
+	}
+	if mixedResp.GetResults()[2].GetStatus() != http.StatusNotFound {
+		t.Fatalf("BatchDelete mixed result[2] expected 404, got %d", mixedResp.GetResults()[2].GetStatus())
+	}
+
+	readDeletedA := framework.ReadBytes(t, httpClient, cluster.VolumeAdminURL(), fidA)
+	_ = framework.ReadAllAndClose(t, readDeletedA)
+	if readDeletedA.StatusCode != http.StatusNotFound {
+		t.Fatalf("fidA should be deleted after batch delete, got status %d", readDeletedA.StatusCode)
+	}
+
+	wrongCookieB := framework.NewFileID(volumeID, needleB, cookieB+1)
+	stopResp, err := client.BatchDelete(ctx, &volume_server_pb.BatchDeleteRequest{
+		FileIds: []string{wrongCookieB, fidC},
+	})
+	if err != nil {
+		t.Fatalf("BatchDelete mismatch-stop request failed: %v", err)
+	}
+	if len(stopResp.GetResults()) != 1 {
+		t.Fatalf("BatchDelete mismatch-stop expected 1 result due early break, got %d", len(stopResp.GetResults()))
+	}
+	if stopResp.GetResults()[0].GetStatus() != http.StatusBadRequest {
+		t.Fatalf("BatchDelete mismatch-stop expected 400, got %d", stopResp.GetResults()[0].GetStatus())
+	}
+
+	readB := framework.ReadBytes(t, httpClient, cluster.VolumeAdminURL(), fidB)
+	_ = framework.ReadAllAndClose(t, readB)
+	if readB.StatusCode != http.StatusOK {
+		t.Fatalf("fidB should remain after cookie mismatch path, got %d", readB.StatusCode)
+	}
+
+	readC := framework.ReadBytes(t, httpClient, cluster.VolumeAdminURL(), fidC)
+	_ = framework.ReadAllAndClose(t, readC)
+	if readC.StatusCode != http.StatusOK {
+		t.Fatalf("fidC should remain when batch processing stops on mismatch, got %d", readC.StatusCode)
+	}
+}
+
+func TestBatchDeleteRejectsChunkManifestNeedles(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping integration test in short mode")
+	}
+
+	cluster := framework.StartSingleVolumeCluster(t, matrix.P1())
+	conn, client := framework.DialVolumeServer(t, cluster.VolumeGRPCAddress())
+	defer conn.Close()
+
+	const volumeID = uint32(33)
+	framework.AllocateVolume(t, client, volumeID, "")
+
+	httpClient := framework.NewHTTPClient()
+	fid := framework.NewFileID(volumeID, 920001, 0x5555AAAA)
+	req, err := http.NewRequest(http.MethodPost, cluster.VolumeAdminURL()+"/"+fid+"?cm=true", bytes.NewReader([]byte("manifest-placeholder-payload")))
+	if err != nil {
+		t.Fatalf("create chunk manifest upload request: %v", err)
+	}
+	req.Header.Set("Content-Type", "application/octet-stream")
+	uploadResp := framework.DoRequest(t, httpClient, req)
+	_ = framework.ReadAllAndClose(t, uploadResp)
+	if uploadResp.StatusCode != http.StatusCreated {
+		t.Fatalf("chunk manifest upload expected 201, got %d", uploadResp.StatusCode)
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	resp, err := client.BatchDelete(ctx, &volume_server_pb.BatchDeleteRequest{FileIds: []string{fid}})
+	if err != nil {
+		t.Fatalf("BatchDelete chunk manifest should return response, got grpc error: %v", err)
+	}
+	if len(resp.GetResults()) != 1 {
+		t.Fatalf("BatchDelete chunk manifest expected one result, got %d", len(resp.GetResults()))
+	}
+	if resp.GetResults()[0].GetStatus() != http.StatusNotAcceptable {
+		t.Fatalf("BatchDelete chunk manifest expected status 406, got %d", resp.GetResults()[0].GetStatus())
+	}
+	if !strings.Contains(resp.GetResults()[0].GetError(), "ChunkManifest") {
+		t.Fatalf("BatchDelete chunk manifest expected error mentioning ChunkManifest, got %q", resp.GetResults()[0].GetError())
+	}
+
+	readResp := framework.ReadBytes(t, httpClient, cluster.VolumeAdminURL(), fid)
+	_ = framework.ReadAllAndClose(t, readResp)
+	if readResp.StatusCode != http.StatusOK {
+		t.Fatalf("chunk manifest should not be deleted by BatchDelete reject path, got %d", readResp.StatusCode)
+	}
+}