seaweedfs/weed/mount/weedfs_file_copy_range.go

100 lines
3 KiB
Go
Raw Normal View History

package mount
import (
2023-09-21 18:08:26 +00:00
"github.com/seaweedfs/seaweedfs/weed/util"
"net/http"
more solid weed mount (#4089) * compare chunks by timestamp * fix slab clearing error * fix test compilation * move oldest chunk to sealed, instead of by fullness * lock on fh.entryViewCache * remove verbose logs * revert slat clearing * less logs * less logs * track write and read by timestamp * remove useless logic * add entry lock on file handle release * use mem chunk only, swap file chunk has problems * comment out code that maybe used later * add debug mode to compare data read and write * more efficient readResolvedChunks with linked list * small optimization * fix test compilation * minor fix on writer * add SeparateGarbageChunks * group chunks into sections * turn off debug mode * fix tests * fix tests * tmp enable swap file chunk * Revert "tmp enable swap file chunk" This reverts commit 985137ec472924e4815f258189f6ca9f2168a0a7. * simple refactoring * simple refactoring * do not re-use swap file chunk. Sealed chunks should not be re-used. * comment out debugging facilities * either mem chunk or swap file chunk is fine now * remove orderedMutex as *semaphore.Weighted not found impactful * optimize size calculation for changing large files * optimize performance to avoid going through the long list of chunks * still problems with swap file chunk * rename * tiny optimization * swap file chunk save only successfully read data * fix * enable both mem and swap file chunk * resolve chunks with range * rename * fix chunk interval list * also change file handle chunk group when adding chunks * pick in-active chunk with time-decayed counter * fix compilation * avoid nil with empty fh.entry * refactoring * rename * rename * refactor visible intervals to *list.List * refactor chunkViews to *list.List * add IntervalList for generic interval list * change visible interval to use IntervalList in generics * cahnge chunkViews to *IntervalList[*ChunkView] * use NewFileChunkSection to create * rename variables * refactor * fix renaming leftover * renaming * renaming * add insert interval * interval list adds lock * incrementally add chunks to readers Fixes: 1. set start and stop offset for the value object 2. clone the value object 3. use pointer instead of copy-by-value when passing to interval.Value 4. use insert interval since adding chunk could be out of order * fix tests compilation * fix tests compilation
2023-01-03 07:20:45 +00:00
"time"
"github.com/hanwen/go-fuse/v2/fuse"
"github.com/seaweedfs/seaweedfs/weed/glog"
)
// CopyFileRange copies data from one file to another from and to specified offsets.
//
// See https://man7.org/linux/man-pages/man2/copy_file_range.2.html
// See https://github.com/libfuse/libfuse/commit/fe4f9428fc403fa8b99051f52d84ea5bd13f3855
/**
* Copy a range of data from one file to another
*
* Niels de Vos: libfuse: add copy_file_range() support
*
* Performs an optimized copy between two file descriptors without the
* additional cost of transferring data through the FUSE kernel module
* to user space (glibc) and then back into the FUSE filesystem again.
*
* In case this method is not implemented, applications are expected to
* fall back to a regular file copy. (Some glibc versions did this
* emulation automatically, but the emulation has been removed from all
* glibc release branches.)
*/
func (wfs *WFS) CopyFileRange(cancel <-chan struct{}, in *fuse.CopyFileRangeIn) (written uint32, code fuse.Status) {
// flags must equal 0 for this syscall as of now
if in.Flags != 0 {
return 0, fuse.EINVAL
}
// files must exist
fhOut := wfs.GetHandle(FileHandleId(in.FhOut))
if fhOut == nil {
return 0, fuse.EBADF
}
fhIn := wfs.GetHandle(FileHandleId(in.FhIn))
if fhIn == nil {
return 0, fuse.EBADF
}
// lock source and target file handles
2023-09-21 18:08:26 +00:00
fhOutActiveLock := fhOut.wfs.fhLockTable.AcquireLock("CopyFileRange", fhOut.fh, util.ExclusiveLock)
defer fhOut.wfs.fhLockTable.ReleaseLock(fhOut.fh, fhOutActiveLock)
if fhOut.entry == nil {
return 0, fuse.ENOENT
}
if fhIn.fh != fhOut.fh {
2023-09-23 17:33:44 +00:00
fhInActiveLock := fhIn.wfs.fhLockTable.AcquireLock("CopyFileRange", fhIn.fh, util.SharedLock)
2023-09-21 18:08:26 +00:00
defer fhIn.wfs.fhLockTable.ReleaseLock(fhIn.fh, fhInActiveLock)
}
// directories are not supported
if fhIn.entry.IsDirectory || fhOut.entry.IsDirectory {
return 0, fuse.EISDIR
}
glog.V(4).Infof(
"CopyFileRange %s fhIn %d -> %s fhOut %d, [%d,%d) -> [%d,%d)",
fhIn.FullPath(), fhIn.fh,
fhOut.FullPath(), fhOut.fh,
in.OffIn, in.OffIn+in.Len,
in.OffOut, in.OffOut+in.Len,
)
data := make([]byte, in.Len)
totalRead, err := readDataByFileHandle(data, fhIn, int64(in.OffIn))
if err != nil {
glog.Warningf("file handle read %s %d: %v", fhIn.FullPath(), totalRead, err)
return 0, fuse.EIO
}
data = data[:totalRead]
if totalRead == 0 {
return 0, fuse.OK
}
// put data at the specified offset in target file
fhOut.dirtyPages.writerPattern.MonitorWriteAt(int64(in.OffOut), int(in.Len))
fhOut.entry.Content = nil
more solid weed mount (#4089) * compare chunks by timestamp * fix slab clearing error * fix test compilation * move oldest chunk to sealed, instead of by fullness * lock on fh.entryViewCache * remove verbose logs * revert slat clearing * less logs * less logs * track write and read by timestamp * remove useless logic * add entry lock on file handle release * use mem chunk only, swap file chunk has problems * comment out code that maybe used later * add debug mode to compare data read and write * more efficient readResolvedChunks with linked list * small optimization * fix test compilation * minor fix on writer * add SeparateGarbageChunks * group chunks into sections * turn off debug mode * fix tests * fix tests * tmp enable swap file chunk * Revert "tmp enable swap file chunk" This reverts commit 985137ec472924e4815f258189f6ca9f2168a0a7. * simple refactoring * simple refactoring * do not re-use swap file chunk. Sealed chunks should not be re-used. * comment out debugging facilities * either mem chunk or swap file chunk is fine now * remove orderedMutex as *semaphore.Weighted not found impactful * optimize size calculation for changing large files * optimize performance to avoid going through the long list of chunks * still problems with swap file chunk * rename * tiny optimization * swap file chunk save only successfully read data * fix * enable both mem and swap file chunk * resolve chunks with range * rename * fix chunk interval list * also change file handle chunk group when adding chunks * pick in-active chunk with time-decayed counter * fix compilation * avoid nil with empty fh.entry * refactoring * rename * rename * refactor visible intervals to *list.List * refactor chunkViews to *list.List * add IntervalList for generic interval list * change visible interval to use IntervalList in generics * cahnge chunkViews to *IntervalList[*ChunkView] * use NewFileChunkSection to create * rename variables * refactor * fix renaming leftover * renaming * renaming * add insert interval * interval list adds lock * incrementally add chunks to readers Fixes: 1. set start and stop offset for the value object 2. clone the value object 3. use pointer instead of copy-by-value when passing to interval.Value 4. use insert interval since adding chunk could be out of order * fix tests compilation * fix tests compilation
2023-01-03 07:20:45 +00:00
fhOut.dirtyPages.AddPage(int64(in.OffOut), data, fhOut.dirtyPages.writerPattern.IsSequentialMode(), time.Now().UnixNano())
fhOut.entry.Attributes.FileSize = uint64(max(int64(in.OffOut)+totalRead, int64(fhOut.entry.Attributes.FileSize)))
fhOut.dirtyMetadata = true
written = uint32(totalRead)
// detect mime type
if written > 0 && in.OffOut <= 512 {
fhOut.contentType = http.DetectContentType(data)
}
return written, fuse.OK
}