* filer: remove lock contention during chunk download This addresses issue #7504 where a single weed mount FUSE instance does not fully utilize node network bandwidth when reading large files. The SingleChunkCacher was holding a mutex during the entire HTTP download, causing readers to block until the download completed. This serialized chunk reads even when multiple goroutines were downloading in parallel. Changes: - Add sync.Cond to SingleChunkCacher for efficient waiting - Move HTTP download outside the critical section in startCaching() - Use condition variable in readChunkAt() to wait for download completion - Add isComplete flag to track download state Now multiple chunk downloads can proceed truly in parallel, and readers wait efficiently using the condition variable instead of blocking on a mutex held during I/O operations. Ref: #7504 * filer: parallel chunk fetching within doReadAt This addresses issue #7504 by enabling parallel chunk downloads within a single read operation. Previously, doReadAt() processed chunks sequentially in a loop, meaning each chunk had to be fully downloaded before the next one started. This left significant network bandwidth unused when chunks resided on different volume servers. Changes: - Collect all chunk read tasks upfront - Use errgroup to fetch multiple chunks in parallel - Each chunk reads directly into its correct buffer position - Limit concurrency to prefetchCount (min 4) to avoid overwhelming the system - Handle gaps and zero-filling before parallel fetch - Trigger prefetch after parallel reads complete For a read spanning N chunks on different volume servers, this can now utilize up to N times the bandwidth of a single connection. Ref: #7504 * http: direct buffer read to reduce memory copies This addresses issue #7504 by reducing memory copy overhead during chunk downloads. Previously, RetriedFetchChunkData used ReadUrlAsStream which: 1. Allocated a 64KB intermediate buffer 2. Read data in 64KB chunks 3. Called a callback to copy each chunk to the destination For a 16MB chunk, this meant 256 copy operations plus the callback overhead. Profiling showed significant time spent in memmove. Changes: - Add readUrlDirectToBuffer() that reads directly into the destination - Add retriedFetchChunkDataDirect() for unencrypted, non-gzipped chunks - Automatically use direct read path when possible (cipher=nil, gzip=false) - Use http.NewRequestWithContext for proper cancellation For unencrypted chunks (the common case), this eliminates the intermediate buffer entirely, reading HTTP response bytes directly into the final destination buffer. Ref: #7504 * address review comments - Use channel (done) instead of sync.Cond for download completion signaling This integrates better with context cancellation patterns - Remove redundant groupErr check in reader_at.go (errors are already captured in task.err) - Remove buggy URL encoding logic from retriedFetchChunkDataDirect (The existing url.PathEscape on full URL is a pre-existing bug that should be fixed separately) * address review comments (round 2) - Return io.ErrUnexpectedEOF when HTTP response is truncated This prevents silent data corruption from incomplete reads - Simplify errgroup error handling by using g.Wait() error directly Remove redundant task.err field and manual error aggregation loop - Define minReadConcurrency constant instead of magic number 4 Improves code readability and maintainability Note: Context propagation to startCaching() is intentionally NOT changed. The downloaded chunk is a shared resource that may be used by multiple readers. Using context.Background() ensures the download completes even if one reader cancels, preventing data loss for other waiting readers. * http: inject request ID for observability in direct read path Add request_id.InjectToRequest() call to readUrlDirectToBuffer() for consistency with ReadUrlAsStream path. This ensures full-chunk reads carry the same tracing/correlation headers for server logs and metrics. * filer: consistent timestamp handling in sequential read path Use max(ts, task.chunk.ModifiedTsNs) in sequential path to match parallel path behavior. Also update ts before error check so that on failure, the returned timestamp reflects the max of all chunks processed so far. * filer: document why context.Background() is used in startCaching Add comment explaining the intentional design decision: the downloaded chunk is a shared resource that may be used by multiple concurrent readers. Using context.Background() ensures the download completes even if one reader cancels, preventing errors for other waiting readers. * filer: propagate context for reader cancellation Address review comment: pass context through ReadChunkAt call chain so that a reader can cancel its wait for a download. The key distinction is: - Download uses context.Background() - shared resource, always completes - Reader wait uses request context - can be cancelled individually If a reader cancels, it stops waiting and returns ctx.Err(), but the download continues to completion for other readers waiting on the same chunk. This properly handles the shared resource semantics while still allowing individual reader cancellation. * filer: use defer for close(done) to guarantee signal on panic Move close(s.done) to a defer statement at the start of startCaching() to ensure the completion signal is always sent, even if an unexpected panic occurs. This prevents readers from blocking indefinitely. * filer: remove unnecessary code - Remove close(s.cacheStartedCh) in destroy() - the channel is only used for one-time synchronization, closing it provides no benefit - Remove task := task loop variable capture - Go 1.22+ fixed loop variable semantics, this capture is no longer necessary (go.mod specifies Go 1.24.0) * filer: restore fallback to chunkCache when cacher returns no data Fix critical issue where ReadChunkAt would return 0,nil immediately if SingleChunkCacher couldn't provide data for the requested offset, without trying the chunkCache fallback. Now if cacher.readChunkAt returns n=0 and err=nil, we fall through to try chunkCache. * filer: add comprehensive tests for ReaderCache Tests cover: - Context cancellation while waiting for download - Fallback to chunkCache when cacher returns n=0, err=nil - Multiple concurrent readers waiting for same chunk - Partial reads at different offsets - Downloader cleanup when exceeding cache limit - Done channel signaling (no hangs on completion) * filer: prioritize done channel over context cancellation If data is already available (done channel closed), return it even if the reader's context is also cancelled. This avoids unnecessary errors when the download has already completed. * filer: add lookup error test and document test limitations Add TestSingleChunkCacherLookupError to test error handling when lookup fails. Document that full HTTP integration tests for SingleChunkCacher require global HTTP client initialization which is complex in unit tests. The download path is tested via FUSE integration tests. * filer: add tests that exercise SingleChunkCacher concurrency logic Add tests that use blocking lookupFileIdFn to exercise the actual SingleChunkCacher wait/cancellation logic: - TestSingleChunkCacherContextCancellationDuringLookup: tests reader cancellation while lookup is blocked - TestSingleChunkCacherMultipleReadersWaitForDownload: tests multiple readers waiting on the same download - TestSingleChunkCacherOneReaderCancelsOthersContinue: tests that when one reader cancels, other readers continue waiting These tests properly exercise the done channel wait/cancel logic without requiring HTTP calls - the blocking lookup simulates a slow download.
662 lines
16 KiB
Go
662 lines
16 KiB
Go
package http
|
|
|
|
import (
|
|
"compress/gzip"
|
|
"context"
|
|
"encoding/json"
|
|
"errors"
|
|
"fmt"
|
|
"sync"
|
|
|
|
"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"
|
|
)
|
|
|
|
var ErrNotFound = fmt.Errorf("not found")
|
|
var ErrTooManyRequests = fmt.Errorf("too many requests")
|
|
|
|
var (
|
|
jwtSigningReadKey security.SigningKey
|
|
jwtSigningReadKeyExpires int
|
|
loadJwtConfigOnce sync.Once
|
|
)
|
|
|
|
func loadJwtConfig() {
|
|
v := util.GetViper()
|
|
jwtSigningReadKey = security.SigningKey(v.GetString("jwt.signing.read.key"))
|
|
jwtSigningReadKeyExpires = v.GetInt("jwt.signing.read.expires_after_seconds")
|
|
}
|
|
|
|
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 {
|
|
return nil, true, err
|
|
}
|
|
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", "BEARER "+string(jwt))
|
|
}
|
|
}
|
|
|
|
func Delete(url string, jwt string) error {
|
|
req, err := http.NewRequest(http.MethodDelete, url, nil)
|
|
maybeAddAuth(req, jwt)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
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.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)
|
|
maybeAddAuth(req, jwt)
|
|
if err != nil {
|
|
return
|
|
}
|
|
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) (filename string, header http.Header, resp *http.Response, e error) {
|
|
req, err := http.NewRequest(http.MethodGet, fileUrl, nil)
|
|
if err != nil {
|
|
return "", nil, nil, err
|
|
}
|
|
|
|
maybeAddAuth(req, jwt)
|
|
|
|
response, err := GetGlobalHttpClient().Do(req)
|
|
if err != nil {
|
|
return "", nil, nil, err
|
|
}
|
|
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.NewRequest(http.MethodGet, fileUrl, nil)
|
|
maybeAddAuth(req, jwt)
|
|
if err != nil {
|
|
return false, err
|
|
}
|
|
|
|
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 {
|
|
return true, err
|
|
}
|
|
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)
|
|
defer reader.Close()
|
|
default:
|
|
reader = r.Body
|
|
}
|
|
|
|
var (
|
|
m int
|
|
)
|
|
buf := mem.Allocate(64 * 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
|
|
}
|
|
|
|
func RetriedFetchChunkData(ctx context.Context, buffer []byte, urlStrings []string, cipherKey []byte, isGzipped bool, isFullChunk bool, offset int64, fileId string) (n int, err error) {
|
|
|
|
loadJwtConfigOnce.Do(loadJwtConfig)
|
|
var jwt security.EncodedJwt
|
|
if len(jwtSigningReadKey) > 0 {
|
|
jwt = security.GenJwtForVolumeServer(
|
|
jwtSigningReadKey,
|
|
jwtSigningReadKeyExpires,
|
|
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))
|
|
}
|
|
|
|
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:
|
|
}
|
|
|
|
for _, urlString := range 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, 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 {
|
|
glog.V(0).InfofCtx(ctx, "read %s failed, err: %v", urlString, err)
|
|
} else {
|
|
break
|
|
}
|
|
}
|
|
if err != nil && shouldRetry {
|
|
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 string) (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:
|
|
}
|
|
|
|
for _, urlString := range urlStrings {
|
|
select {
|
|
case <-ctx.Done():
|
|
return 0, ctx.Err()
|
|
default:
|
|
}
|
|
|
|
n, shouldRetry, err = readUrlDirectToBuffer(ctx, urlString+"?readDeleted=true", jwt, buffer)
|
|
if err == nil {
|
|
return n, nil
|
|
}
|
|
if !shouldRetry {
|
|
break
|
|
}
|
|
glog.V(0).InfofCtx(ctx, "read %s failed, err: %v", urlString, err)
|
|
}
|
|
|
|
if err != nil && shouldRetry {
|
|
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 {
|
|
return 0, true, err
|
|
}
|
|
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
|
|
}
|