seaweedfs/weed/util/http/http_global_client_util.go

package http

import (
	"compress/gzip"
	"context"
	"encoding/json"
	"errors"
	"fmt"
	"sync"
	"sync/atomic"

	"github.com/seaweedfs/seaweedfs/weed/util"
	"github.com/seaweedfs/seaweedfs/weed/util/mem"
	"github.com/seaweedfs/seaweedfs/weed/util/request_id"

	"io"
	"net/http"
	"net/url"
	"strings"
	"time"

	"github.com/seaweedfs/seaweedfs/weed/glog"

	"github.com/seaweedfs/seaweedfs/weed/security"
	util_http_client "github.com/seaweedfs/seaweedfs/weed/util/http/client"
)

var ErrNotFound = fmt.Errorf("not found")
var ErrTooManyRequests = fmt.Errorf("too many requests")

type jwtSigningReadConfig struct {
	key     security.SigningKey
	expires int
}

var (
	jwtSigningReadConfigPtr atomic.Pointer[jwtSigningReadConfig]
	loadJwtConfigOnce       sync.Once
)

func AppendQueryParameter(rawURL, key, value string) string {
	encoded := url.Values{key: []string{value}}.Encode()
	fragment := ""
	if fragmentIndex := strings.Index(rawURL, "#"); fragmentIndex >= 0 {
		fragment = rawURL[fragmentIndex:]
		rawURL = rawURL[:fragmentIndex]
	}

	var result string
	switch {
	case strings.Contains(rawURL, "?"):
		if strings.HasSuffix(rawURL, "?") || strings.HasSuffix(rawURL, "&") {
			result = rawURL + encoded
		} else {
			result = rawURL + "&" + encoded
		}
	default:
		result = rawURL + "?" + encoded
	}
	return result + fragment
}

func loadJwtConfig() {
	v := util.GetViper()
	jwtSigningReadConfigPtr.Store(&jwtSigningReadConfig{
		key:     security.SigningKey(v.GetString("jwt.signing.read.key")),
		expires: v.GetInt("jwt.signing.read.expires_after_seconds"),
	})
}

// ReloadJwtSigningReadConfig re-reads the volume read-signing key from the
// already-reloaded security config, so operators can rotate it via SIGHUP
// without restarting the process.
func ReloadJwtSigningReadConfig() {
	loadJwtConfig()
}

func Post(url string, values url.Values) ([]byte, error) {
	r, err := GetGlobalHttpClient().PostForm(url, values)
	if err != nil {
		return nil, err
	}
	defer r.Body.Close()
	b, err := io.ReadAll(r.Body)
	if r.StatusCode >= 400 {
		if err != nil {
			return nil, fmt.Errorf("%s: %d - %s", url, r.StatusCode, string(b))
		} else {
			return nil, fmt.Errorf("%s: %s", url, r.Status)
		}
	}
	if err != nil {
		return nil, err
	}
	return b, nil
}

// github.com/seaweedfs/seaweedfs/unmaintained/repeated_vacuum/repeated_vacuum.go
// may need increasing http.Client.Timeout
func Get(url string) ([]byte, bool, error) {
	return GetAuthenticated(url, "")
}

func GetAuthenticated(url, jwt string) ([]byte, bool, error) {
	request, err := http.NewRequest(http.MethodGet, url, nil)
	if err != nil {
		return nil, true, err
	}
	maybeAddAuth(request, jwt)
	request.Header.Add("Accept-Encoding", "gzip")

	response, err := GetGlobalHttpClient().Do(request)
	if err != nil {
		recordUnreachable(request.URL.Host)
		return nil, true, err
	}
	recordReachable(request.URL.Host)
	defer CloseResponse(response)

	var reader io.ReadCloser
	switch response.Header.Get("Content-Encoding") {
	case "gzip":
		reader, err = gzip.NewReader(response.Body)
		if err != nil {
			return nil, true, err
		}
		defer reader.Close()
	default:
		reader = response.Body
	}

	b, err := io.ReadAll(reader)
	if response.StatusCode >= 400 {
		retryable := response.StatusCode >= 500
		return nil, retryable, fmt.Errorf("%s: %s", url, response.Status)
	}
	if err != nil {
		return nil, false, err
	}
	return b, false, nil
}

func Head(url string) (http.Header, error) {
	r, err := GetGlobalHttpClient().Head(url)
	if err != nil {
		return nil, err
	}
	defer CloseResponse(r)
	if r.StatusCode >= 400 {
		return nil, fmt.Errorf("%s: %s", url, r.Status)
	}
	return r.Header, nil
}

func maybeAddAuth(req *http.Request, jwt string) {
	if jwt != "" {
		req.Header.Set("Authorization", security.BearerPrefix+string(jwt))
	}
}

func Delete(url string, jwt string) error {
	req, err := http.NewRequest(http.MethodDelete, url, nil)
	if err != nil {
		return err
	}
	maybeAddAuth(req, jwt)
	resp, e := GetGlobalHttpClient().Do(req)
	if e != nil {
		return e
	}
	defer resp.Body.Close()
	body, err := io.ReadAll(resp.Body)
	if err != nil {
		return err
	}
	switch resp.StatusCode {
	case http.StatusNotFound, http.StatusNoContent, http.StatusAccepted, http.StatusOK:
		return nil
	}
	m := make(map[string]interface{})
	if e := json.Unmarshal(body, &m); e == nil {
		if s, ok := m["error"].(string); ok {
			return errors.New(s)
		}
	}
	return errors.New(string(body))
}

func DeleteProxied(url string, jwt string) (body []byte, httpStatus int, err error) {
	req, err := http.NewRequest(http.MethodDelete, url, nil)
	if err != nil {
		return
	}
	maybeAddAuth(req, jwt)
	resp, err := GetGlobalHttpClient().Do(req)
	if err != nil {
		return
	}
	defer resp.Body.Close()
	body, err = io.ReadAll(resp.Body)
	if err != nil {
		return
	}
	httpStatus = resp.StatusCode
	return
}

func GetBufferStream(url string, values url.Values, allocatedBytes []byte, eachBuffer func([]byte)) error {
	r, err := GetGlobalHttpClient().PostForm(url, values)
	if err != nil {
		return err
	}
	defer CloseResponse(r)
	if r.StatusCode != 200 {
		return fmt.Errorf("%s: %s", url, r.Status)
	}
	for {
		n, err := r.Body.Read(allocatedBytes)
		if n > 0 {
			eachBuffer(allocatedBytes[:n])
		}
		if err != nil {
			if err == io.EOF {
				return nil
			}
			return err
		}
	}
}

func GetUrlStream(url string, values url.Values, readFn func(io.Reader) error) error {
	r, err := GetGlobalHttpClient().PostForm(url, values)
	if err != nil {
		return err
	}
	defer CloseResponse(r)
	if r.StatusCode != 200 {
		return fmt.Errorf("%s: %s", url, r.Status)
	}
	return readFn(r.Body)
}

func DownloadFile(fileUrl string, jwt string, offset ...int64) (filename string, header http.Header, resp *http.Response, e error) {
	return DownloadFileWithClient(GetGlobalHttpClient(), fileUrl, jwt, offset...)
}

// DownloadFileWithClient is like DownloadFile but uses the provided HTTP client
// instead of the global one. This is used by filer.sync to download from
// remote clusters that use different TLS certificates.
func DownloadFileWithClient(client *util_http_client.HTTPClient, fileUrl string, jwt string, offset ...int64) (filename string, header http.Header, resp *http.Response, e error) {
	if client == nil {
		return "", nil, nil, fmt.Errorf("nil HTTP client in DownloadFileWithClient")
	}
	req, err := http.NewRequest(http.MethodGet, fileUrl, nil)
	if err != nil {
		return "", nil, nil, err
	}

	maybeAddAuth(req, jwt)

	var rangeOffset int64
	if len(offset) > 0 {
		rangeOffset = offset[0]
	}
	if rangeOffset > 0 {
		req.Header.Set("Range", fmt.Sprintf("bytes=%d-", rangeOffset))
	}

	response, err := client.Do(req)
	if err != nil {
		return "", nil, nil, err
	}

	if rangeOffset > 0 {
		expected := fmt.Sprintf("bytes %d-", rangeOffset)
		if response.StatusCode != http.StatusPartialContent ||
			!strings.HasPrefix(response.Header.Get("Content-Range"), expected) {
			CloseResponse(response)
			return "", nil, nil, fmt.Errorf("range request %q to %s returned %s with Content-Range %q",
				req.Header.Get("Range"), fileUrl, response.Status, response.Header.Get("Content-Range"))
		}
	}

	header = response.Header
	contentDisposition := response.Header["Content-Disposition"]
	if len(contentDisposition) > 0 {
		idx := strings.Index(contentDisposition[0], "filename=")
		if idx != -1 {
			filename = contentDisposition[0][idx+len("filename="):]
			filename = strings.Trim(filename, "\"")
		}
	}
	resp = response
	return
}

func Do(req *http.Request) (resp *http.Response, err error) {
	return GetGlobalHttpClient().Do(req)
}

func NormalizeUrl(url string) (string, error) {
	return GetGlobalHttpClient().NormalizeHttpScheme(url)
}

func ReadUrl(ctx context.Context, fileUrl string, cipherKey []byte, isContentCompressed bool, isFullChunk bool, offset int64, size int, buf []byte) (int64, error) {

	if cipherKey != nil {
		var n int
		_, err := readEncryptedUrl(ctx, fileUrl, "", cipherKey, isContentCompressed, isFullChunk, offset, size, func(data []byte) {
			n = copy(buf, data)
		})
		return int64(n), err
	}

	req, err := http.NewRequest(http.MethodGet, fileUrl, nil)
	if err != nil {
		return 0, err
	}
	if !isFullChunk {
		req.Header.Add("Range", fmt.Sprintf("bytes=%d-%d", offset, offset+int64(size)-1))
	} else {
		req.Header.Set("Accept-Encoding", "gzip")
	}

	r, err := GetGlobalHttpClient().Do(req)
	if err != nil {
		return 0, err
	}
	defer CloseResponse(r)

	if r.StatusCode >= 400 {
		return 0, fmt.Errorf("%s: %s", fileUrl, r.Status)
	}

	var reader io.ReadCloser
	contentEncoding := r.Header.Get("Content-Encoding")
	switch contentEncoding {
	case "gzip":
		reader, err = gzip.NewReader(r.Body)
		if err != nil {
			return 0, err
		}
		defer reader.Close()
	default:
		reader = r.Body
	}

	var (
		i, m int
		n    int64
	)

	// refers to https://github.com/golang/go/blob/master/src/bytes/buffer.go#L199
	// commit id c170b14c2c1cfb2fd853a37add92a82fd6eb4318
	for {
		m, err = reader.Read(buf[i:])
		i += m
		n += int64(m)
		if err == io.EOF {
			return n, nil
		}
		if err != nil {
			return n, err
		}
		if n == int64(len(buf)) {
			break
		}
	}
	// drains the response body to avoid memory leak
	data, _ := io.ReadAll(reader)
	if len(data) != 0 {
		glog.V(1).InfofCtx(ctx, "%s reader has remaining %d bytes", contentEncoding, len(data))
	}
	return n, err
}

func ReadUrlAsStream(ctx context.Context, fileUrl, jwt string, cipherKey []byte, isContentGzipped bool, isFullChunk bool, offset int64, size int, fn func(data []byte)) (retryable bool, err error) {
	if cipherKey != nil {
		return readEncryptedUrl(ctx, fileUrl, jwt, cipherKey, isContentGzipped, isFullChunk, offset, size, fn)
	}

	req, err := http.NewRequestWithContext(ctx, http.MethodGet, fileUrl, nil)
	if err != nil {
		return false, err
	}
	maybeAddAuth(req, jwt)

	if isFullChunk {
		req.Header.Add("Accept-Encoding", "gzip")
	} else {
		req.Header.Add("Range", fmt.Sprintf("bytes=%d-%d", offset, offset+int64(size)-1))
	}
	request_id.InjectToRequest(ctx, req)

	r, err := GetGlobalHttpClient().Do(req)
	if err != nil {
		if ctx.Err() == nil {
			recordUnreachable(req.URL.Host)
		}
		return true, err
	}
	recordReachable(req.URL.Host)
	defer CloseResponse(r)
	if r.StatusCode >= 400 {
		if r.StatusCode == http.StatusNotFound {
			return true, fmt.Errorf("%s: %s: %w", fileUrl, r.Status, ErrNotFound)
		}
		if r.StatusCode == http.StatusTooManyRequests {
			return false, fmt.Errorf("%s: %s: %w", fileUrl, r.Status, ErrTooManyRequests)
		}
		retryable = r.StatusCode >= 499
		return retryable, fmt.Errorf("%s: %s", fileUrl, r.Status)
	}

	var reader io.ReadCloser
	contentEncoding := r.Header.Get("Content-Encoding")
	switch contentEncoding {
	case "gzip":
		reader, err = gzip.NewReader(r.Body)
		if err != nil {
			return true, err
		}
		defer reader.Close()
	default:
		reader = r.Body
	}

	var (
		m int
	)
	buf := mem.Allocate(256 * 1024)
	defer mem.Free(buf)

	for {
		// Check for context cancellation before each read
		select {
		case <-ctx.Done():
			return false, ctx.Err()
		default:
		}

		m, err = reader.Read(buf)
		if m > 0 {
			fn(buf[:m])
		}
		if err == io.EOF {
			return false, nil
		}
		if err != nil {
			return true, err
		}
	}

}

func readEncryptedUrl(ctx context.Context, fileUrl, jwt string, cipherKey []byte, isContentCompressed bool, isFullChunk bool, offset int64, size int, fn func(data []byte)) (bool, error) {
	encryptedData, retryable, err := GetAuthenticated(fileUrl, jwt)
	if err != nil {
		return retryable, fmt.Errorf("fetch %s: %v", fileUrl, err)
	}
	decryptedData, err := util.Decrypt(encryptedData, util.CipherKey(cipherKey))
	if err != nil {
		return false, fmt.Errorf("decrypt %s: %v", fileUrl, err)
	}
	if isContentCompressed {
		decryptedData, err = util.DecompressData(decryptedData)
		if err != nil {
			glog.V(0).InfofCtx(ctx, "unzip decrypt %s: %v", fileUrl, err)
		}
	}
	if len(decryptedData) < int(offset)+size {
		return false, fmt.Errorf("read decrypted %s size %d [%d, %d)", fileUrl, len(decryptedData), offset, int(offset)+size)
	}
	if isFullChunk {
		fn(decryptedData)
	} else {
		sliceEnd := int(offset) + size
		fn(decryptedData[int(offset):sliceEnd])
	}
	return false, nil
}

func ReadUrlAsReaderCloser(fileUrl string, jwt string, rangeHeader string) (*http.Response, io.ReadCloser, error) {

	req, err := http.NewRequest(http.MethodGet, fileUrl, nil)
	if err != nil {
		return nil, nil, err
	}
	if rangeHeader != "" {
		req.Header.Add("Range", rangeHeader)
	} else {
		req.Header.Add("Accept-Encoding", "gzip")
	}

	maybeAddAuth(req, jwt)

	r, err := GetGlobalHttpClient().Do(req)
	if err != nil {
		return nil, nil, err
	}
	if r.StatusCode >= 400 {
		CloseResponse(r)
		return nil, nil, fmt.Errorf("%s: %s", fileUrl, r.Status)
	}

	var reader io.ReadCloser
	contentEncoding := r.Header.Get("Content-Encoding")
	switch contentEncoding {
	case "gzip":
		reader, err = gzip.NewReader(r.Body)
		if err != nil {
			return nil, nil, err
		}
	default:
		reader = r.Body
	}

	return r, reader, nil
}

func CloseResponse(resp *http.Response) {
	if resp == nil || resp.Body == nil {
		return
	}
	reader := &CountingReader{reader: resp.Body}
	io.Copy(io.Discard, reader)
	resp.Body.Close()
	if reader.BytesRead > 0 {
		glog.V(1).Infof("response leftover %d bytes", reader.BytesRead)
	}
}

func CloseRequest(req *http.Request) {
	reader := &CountingReader{reader: req.Body}
	io.Copy(io.Discard, reader)
	req.Body.Close()
	if reader.BytesRead > 0 {
		glog.V(1).Infof("request leftover %d bytes", reader.BytesRead)
	}
}

type CountingReader struct {
	reader    io.Reader
	BytesRead int
}

func (r *CountingReader) Read(p []byte) (n int, err error) {
	n, err = r.reader.Read(p)
	r.BytesRead += n
	return n, err
}

// refreshedUrls asks for a fresh location list and reports whether it is worth
// retrying on: a list that comes back empty, or identical to the one that just
// failed everywhere, says the locations were never the problem.
func refreshedUrls(ctx context.Context, refreshUrls RefreshUrlsFunc, current []string, fileId string) ([]string, bool) {
	if refreshUrls == nil {
		return nil, false
	}
	fresh := refreshUrls()
	if len(fresh) == 0 || SameUrls(current, fresh) {
		return nil, false
	}
	glog.V(0).InfofCtx(ctx, "chunk %s failed on every known location, retrying on %d fresh ones", fileId, len(fresh))
	return fresh, true
}

// SameUrls reports whether two location lists hold the same URLs, regardless of
// order: lookups shuffle the locations they return, so comparing positionally
// would read a reshuffle of the very same replicas as a fresh set.
func SameUrls(a, b []string) bool {
	if len(a) != len(b) {
		return false
	}
	counts := make(map[string]int, len(a))
	for _, url := range a {
		counts[url]++
	}
	for _, url := range b {
		if counts[url] == 0 {
			return false
		}
		counts[url]--
	}
	return true
}

// RefreshUrlsFunc supplies a fresh location list for a chunk. The retry loops
// call it at most once: after every location in the list failed, to retry on
// the fresh list at once, or after a later location answered for one that
// failed, so the next read starts from what the cluster knows now instead of
// trying the same dead replica again. Returning nil or the same list leaves
// the caller on the original locations.
type RefreshUrlsFunc func() []string

// RetriedFetchChunkData reads a chunk, trying every location before backing off
// and trying them again. refreshUrls may be nil; when it is not, a pass in which
// every location failed is treated as a stale list rather than a slow cluster,
// and the fresh list is tried immediately instead of after the next backoff.
// A pass that failed on one location and succeeded on another refreshes the
// list for the reads that follow.
func RetriedFetchChunkData(ctx context.Context, buffer []byte, urlStrings []string, cipherKey []byte, isGzipped bool, isFullChunk bool, offset int64, fileId string, refreshUrls RefreshUrlsFunc) (n int, err error) {

	loadJwtConfigOnce.Do(loadJwtConfig)
	var jwt security.EncodedJwt
	if cfg := jwtSigningReadConfigPtr.Load(); cfg != nil && len(cfg.key) > 0 {
		jwt = security.GenJwtForVolumeServer(cfg.key, cfg.expires, fileId)
	}

	// For unencrypted, non-gzipped full chunks, use direct buffer read
	// This avoids the 64KB intermediate buffer and callback overhead
	if cipherKey == nil && !isGzipped && isFullChunk {
		return retriedFetchChunkDataDirect(ctx, buffer, urlStrings, string(jwt), fileId, refreshUrls)
	}

	var shouldRetry bool

	for waitTime := time.Second; waitTime < util.RetryWaitTime; waitTime += waitTime / 2 {
		// Check for context cancellation before starting retry loop
		select {
		case <-ctx.Done():
			return n, ctx.Err()
		default:
		}

		var failed bool
		for _, urlString := range ReachableFirst(urlStrings) {
			// Check for context cancellation before each volume server request
			select {
			case <-ctx.Done():
				return n, ctx.Err()
			default:
			}

			n = 0
			if strings.Contains(urlString, "%") {
				urlString = url.PathEscape(urlString)
			}
			shouldRetry, err = ReadUrlAsStream(ctx, AppendQueryParameter(urlString, "readDeleted", "true"), string(jwt), cipherKey, isGzipped, isFullChunk, offset, len(buffer), func(data []byte) {
				// Check for context cancellation during data processing
				select {
				case <-ctx.Done():
					// Stop processing data when context is cancelled
					return
				default:
				}

				if n < len(buffer) {
					x := copy(buffer[n:], data)
					n += x
				}
			})
			if !shouldRetry {
				break
			}
			if err != nil {
				failed = true
				glog.V(0).InfofCtx(ctx, "read %s failed, err: %v", urlString, err)
			} else {
				break
			}
		}
		if err == nil && failed && refreshUrls != nil {
			refreshUrls()
		}
		if err != nil && shouldRetry {
			if fresh, ok := refreshedUrls(ctx, refreshUrls, urlStrings, fileId); ok {
				urlStrings, refreshUrls = fresh, nil
				continue
			}
			refreshUrls = nil
			glog.V(0).InfofCtx(ctx, "retry reading in %v", waitTime)
			// Sleep with proper context cancellation and timer cleanup
			timer := time.NewTimer(waitTime)
			select {
			case <-ctx.Done():
				timer.Stop()
				return n, ctx.Err()
			case <-timer.C:
				// Continue with retry
			}
		} else {
			break
		}
	}

	return n, err

}

// retriedFetchChunkDataDirect reads chunk data directly into the buffer without
// intermediate buffering. This reduces memory copies and improves throughput
// for large chunk reads.
func retriedFetchChunkDataDirect(ctx context.Context, buffer []byte, urlStrings []string, jwt, fileId string, refreshUrls RefreshUrlsFunc) (n int, err error) {
	var shouldRetry bool

	for waitTime := time.Second; waitTime < util.RetryWaitTime; waitTime += waitTime / 2 {
		select {
		case <-ctx.Done():
			return 0, ctx.Err()
		default:
		}

		var failed bool
		for _, urlString := range ReachableFirst(urlStrings) {
			select {
			case <-ctx.Done():
				return 0, ctx.Err()
			default:
			}

			n, shouldRetry, err = readUrlDirectToBuffer(ctx, AppendQueryParameter(urlString, "readDeleted", "true"), jwt, buffer)
			if err == nil {
				if failed && refreshUrls != nil {
					refreshUrls()
				}
				return n, nil
			}
			if !shouldRetry {
				break
			}
			failed = true
			glog.V(0).InfofCtx(ctx, "read %s failed, err: %v", urlString, err)
		}

		if err != nil && shouldRetry {
			if fresh, ok := refreshedUrls(ctx, refreshUrls, urlStrings, fileId); ok {
				urlStrings, refreshUrls = fresh, nil
				continue
			}
			refreshUrls = nil
			glog.V(0).InfofCtx(ctx, "retry reading in %v", waitTime)
			timer := time.NewTimer(waitTime)
			select {
			case <-ctx.Done():
				timer.Stop()
				return 0, ctx.Err()
			case <-timer.C:
			}
		} else {
			break
		}
	}

	return n, err
}

// readUrlDirectToBuffer reads HTTP response directly into the provided buffer,
// avoiding intermediate buffer allocations and copies.
func readUrlDirectToBuffer(ctx context.Context, fileUrl, jwt string, buffer []byte) (n int, retryable bool, err error) {
	req, err := http.NewRequestWithContext(ctx, http.MethodGet, fileUrl, nil)
	if err != nil {
		return 0, false, err
	}
	maybeAddAuth(req, jwt)
	request_id.InjectToRequest(ctx, req)

	r, err := GetGlobalHttpClient().Do(req)
	if err != nil {
		if ctx.Err() == nil {
			recordUnreachable(req.URL.Host)
		}
		return 0, true, err
	}
	recordReachable(req.URL.Host)
	defer CloseResponse(r)

	if r.StatusCode >= 400 {
		if r.StatusCode == http.StatusNotFound {
			return 0, true, fmt.Errorf("%s: %s: %w", fileUrl, r.Status, ErrNotFound)
		}
		if r.StatusCode == http.StatusTooManyRequests {
			return 0, false, fmt.Errorf("%s: %s: %w", fileUrl, r.Status, ErrTooManyRequests)
		}
		retryable = r.StatusCode >= 499
		return 0, retryable, fmt.Errorf("%s: %s", fileUrl, r.Status)
	}

	// Read directly into the buffer without intermediate copying
	// This is significantly faster for large chunks (16MB+)
	var totalRead int
	for totalRead < len(buffer) {
		select {
		case <-ctx.Done():
			return totalRead, false, ctx.Err()
		default:
		}

		m, readErr := r.Body.Read(buffer[totalRead:])
		totalRead += m
		if readErr != nil {
			if readErr == io.EOF {
				// Return io.ErrUnexpectedEOF if we haven't filled the buffer
				// This prevents silent data corruption from truncated responses
				if totalRead < len(buffer) {
					return totalRead, true, io.ErrUnexpectedEOF
				}
				return totalRead, false, nil
			}
			return totalRead, true, readErr
		}
	}

	return totalRead, false, nil
}