mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-09-11 17:10:40 +02:00
Chris Lu
194dce27bf
* fix(mount): preserve user-set mtime through async/periodic flush (#9363) flushMetadataToFiler and flushFileMetadata both stamped time.Now() onto the entry before sending it to the filer, clobbering any mtime SetAttr had stored from utimes()/touch -m -d. The reproducer hit this ~1s after touch because the writebackCache deferred close from the prior write ran flushMetadataToFiler after the user's utimes call. Flush has no business inventing timestamps. Move the write-time stamp into Write (where it always belonged for POSIX correctness) and let flush persist whatever Write or SetAttr already put on the entry. * test(mount): tighten mtime regression test, drop tautological one - userMtime now has non-zero nanoseconds, so the *Ns assertions catch a regression that would zero the field. - Add CtimeNs assertion (was missing). - Drop TestWriteStampsEntryMtime: it duplicated the implementation it was supposed to test, so a regression in Write would not have failed it. Driving the real Write path needs a full PageWriter, which is out of scope for this fix; TestFlushFileMetadataPreservesUserMtime is the meaningful regression for #9363.
115 lines
3.2 KiB
Go
115 lines
3.2 KiB
Go
package mount
|
|
|
|
import (
|
|
"net/http"
|
|
"syscall"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/go-fuse/v2/fuse"
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/util"
|
|
)
|
|
|
|
/**
|
|
* Write data
|
|
*
|
|
* Write should return exactly the number of bytes requested
|
|
* except on error. An exception to this is when the file has
|
|
* been opened in 'direct_io' mode, in which case the return value
|
|
* of the write system call will reflect the return value of this
|
|
* operation.
|
|
*
|
|
* Unless FUSE_CAP_HANDLE_KILLPRIV is disabled, this method is
|
|
* expected to reset the setuid and setgid bits.
|
|
*
|
|
* fi->fh will contain the value set by the open method, or will
|
|
* be undefined if the open method didn't set any value.
|
|
*
|
|
* Valid replies:
|
|
* fuse_reply_write
|
|
* fuse_reply_err
|
|
*
|
|
* @param req request handle
|
|
* @param ino the inode number
|
|
* @param buf data to write
|
|
* @param size number of bytes to write
|
|
* @param off offset to write to
|
|
* @param fi file information
|
|
*/
|
|
func (wfs *WFS) Write(cancel <-chan struct{}, in *fuse.WriteIn, data []byte) (written uint32, code fuse.Status) {
|
|
|
|
// Check quota including uncommitted writes for real-time enforcement
|
|
if wfs.IsOverQuotaWithUncommitted() {
|
|
return 0, fuse.Status(syscall.ENOSPC)
|
|
}
|
|
|
|
fh := wfs.GetHandle(FileHandleId(in.Fh))
|
|
if fh == nil {
|
|
return 0, fuse.ENOENT
|
|
}
|
|
|
|
fh.dirtyPages.writerPattern.MonitorWriteAt(int64(in.Offset), int(in.Size))
|
|
|
|
tsNs := time.Now().UnixNano()
|
|
|
|
fhActiveLock := fh.wfs.fhLockTable.AcquireLock("Write", fh.fh, util.ExclusiveLock)
|
|
defer fh.wfs.fhLockTable.ReleaseLock(fh.fh, fhActiveLock)
|
|
|
|
entry := fh.GetEntry()
|
|
if entry == nil {
|
|
return 0, fuse.OK
|
|
}
|
|
|
|
entry.Content = nil
|
|
offset := int64(in.Offset)
|
|
oldFileSize := int64(entry.Attributes.FileSize)
|
|
newFileSize := max(offset+int64(len(data)), oldFileSize)
|
|
entry.Attributes.FileSize = uint64(newFileSize)
|
|
|
|
// POSIX: writes update mtime and ctime. Stamp the entry now so the
|
|
// flush path persists the write time rather than overwriting any
|
|
// user-set mtime (e.g., utimes/touch -m -d) at flush time.
|
|
writeNow := time.Unix(0, tsNs)
|
|
entry.Attributes.Mtime = writeNow.Unix()
|
|
entry.Attributes.MtimeNs = int32(writeNow.Nanosecond())
|
|
entry.Attributes.Ctime = writeNow.Unix()
|
|
entry.Attributes.CtimeNs = int32(writeNow.Nanosecond())
|
|
|
|
// Track uncommitted bytes for real-time quota enforcement.
|
|
// Only count the new bytes being added beyond the current file size.
|
|
if newFileSize > oldFileSize {
|
|
wfs.AddUncommittedBytes(newFileSize - oldFileSize)
|
|
}
|
|
|
|
// glog.V(4).Infof("%v write [%d,%d) %d", fh.f.fullpath(), req.Offset, req.Offset+int64(len(req.Data)), len(req.Data))
|
|
|
|
if err := fh.dirtyPages.AddPage(offset, data, fh.dirtyPages.writerPattern.IsSequentialMode(), tsNs); err != nil {
|
|
glog.Errorf("AddPage error: %v", err)
|
|
return 0, fuse.EIO
|
|
}
|
|
|
|
written = uint32(len(data))
|
|
|
|
if offset == 0 {
|
|
// detect mime type
|
|
fh.contentType = http.DetectContentType(data)
|
|
}
|
|
|
|
fh.dirtyMetadata = true
|
|
|
|
// Invalidate the mtime cache so the next Open will not set FOPEN_KEEP_CACHE.
|
|
wfs.invalidateOpenMtimeCache(in.NodeId)
|
|
|
|
// POSIX: clear SUID/SGID bits on write by non-root users.
|
|
if in.Uid != 0 {
|
|
entry.Attributes.FileMode &^= 0o6000
|
|
}
|
|
|
|
if IsDebugFileReadWrite {
|
|
// print("+")
|
|
fh.mirrorFile.WriteAt(data, offset)
|
|
}
|
|
|
|
return written, fuse.OK
|
|
}
|