seaweedfs/weed/mount/weedfs_file_read.go
Chris Lu d4566d4aaa
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 985137ec47.

* 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
2023-01-02 23:20:45 -08:00

90 lines
2.5 KiB
Go

package mount
import (
"bytes"
"fmt"
"io"
"github.com/hanwen/go-fuse/v2/fuse"
"github.com/seaweedfs/seaweedfs/weed/glog"
)
/**
* Read data
*
* Read should send exactly the number of bytes requested except
* on EOF or error, otherwise the rest of the data will be
* substituted with zeroes. An exception to this is when the file
* has been opened in 'direct_io' mode, in which case the return
* value of the read system call will reflect the return value of
* this operation.
*
* 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_buf
* fuse_reply_iov
* fuse_reply_data
* fuse_reply_err
*
* @param req request handle
* @param ino the inode number
* @param size number of bytes to read
* @param off offset to read from
* @param fi file information
*/
func (wfs *WFS) Read(cancel <-chan struct{}, in *fuse.ReadIn, buff []byte) (fuse.ReadResult, fuse.Status) {
fh := wfs.GetHandle(FileHandleId(in.Fh))
if fh == nil {
return nil, fuse.ENOENT
}
fh.Lock()
defer fh.Unlock()
offset := int64(in.Offset)
totalRead, err := readDataByFileHandle(buff, fh, offset)
if err != nil {
glog.Warningf("file handle read %s %d: %v", fh.FullPath(), totalRead, err)
return nil, fuse.EIO
}
if IsDebugFileReadWrite {
// print(".")
mirrorData := make([]byte, totalRead)
fh.mirrorFile.ReadAt(mirrorData, offset)
if bytes.Compare(mirrorData, buff[:totalRead]) != 0 {
againBuff := make([]byte, len(buff))
againRead, _ := readDataByFileHandle(buff, fh, offset)
againCorrect := bytes.Compare(mirrorData, againBuff[:againRead]) == 0
againSame := bytes.Compare(buff[:totalRead], againBuff[:againRead]) == 0
fmt.Printf("\ncompare %v [%d,%d) size:%d againSame:%v againCorrect:%v\n", fh.mirrorFile.Name(), offset, offset+totalRead, totalRead, againSame, againCorrect)
//fmt.Printf("read mirrow data: %v\n", mirrorData)
//fmt.Printf("read actual data: %v\n", buff[:totalRead])
}
}
return fuse.ReadResultData(buff[:totalRead]), fuse.OK
}
func readDataByFileHandle(buff []byte, fhIn *FileHandle, offset int64) (int64, error) {
// read data from source file
size := len(buff)
fhIn.lockForRead(offset, size)
defer fhIn.unlockForRead(offset, size)
n, tsNs, err := fhIn.readFromChunks(buff, offset)
if err == nil || err == io.EOF {
maxStop := fhIn.readFromDirtyPages(buff, offset, tsNs)
n = max(maxStop-offset, n)
}
if err == io.EOF {
err = nil
}
return n, err
}