mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-09-08 15:41:15 +02:00
* benchmark tool for mounted filesystems * ci: on-demand mount benchmark, native WinFsp vs rclone plus a Linux reference * windows mount: let the Windows cache manager cache file data WinFsp only turns the cache manager on for a file when FileInfoTimeout is infinite; at any finite value every application read and write is a synchronous trip into the mount process at whatever size the application issued. Metadata events already reach FspFileSystemNotify, which purges a changed file's cached pages and attributes, so an infinite timeout stays coherent. The dir listing, volume info and EA timeouts are pinned to one second so they do not silently inherit the infinity. * windows mount: cache resolved paths and attributes in the adapter WinFsp addresses every operation by path and has no FORGET, so the adapter walked the whole path through Lookup on each one, and in a directory the filer has not listed yet every walk was a filer round trip; nothing played the part of the kernel's dentry and attribute caches. The path cache owns one lookup reference per entry the way the kernel holds one until FORGET, serves attribute reads for files without an open handle, and is purged by the mount's own mutations and by metadata events, with the timeout as backstop. * windows mount: keep a closed file's attributes cached Open steals the path's cache entry for its handle and Release returned the reference with a purge, so the stat that follows every copied file walked to the filer again. Reading the handle's final attributes before it goes away and moving the reference back into the cache serves that stat locally, the way the kernel's attribute cache does after a close. Only if the path still names that inode, though: WinFsp reports the path the handle opened with, and after a delete-on-close or a rename caching it would resurrect an entry that is gone. * windows mount: persist entries at create, and let the flush stay at close WinFsp posts the cleanup and close that carry the flush after CloseHandle has returned, so deferring the filer entry to the flush let everything that reads through the filer race an unflushed close: a listing missed just-written files, and a directory rename moved a directory on the filer before its newest child existed there, leaving the straggler flush to recreate the child under the dead path. Flush-at-cleanup is not the answer either: it makes every handle's cleanup flush, and those flushes race the unlinks of delete-on-close, re-inserting the entry the unlink just removed. Persisting the entry at create takes the ordering question away. * mount: flush written pages before a truncate shrinks past them The shrink trims chunks, but written pages that have not become chunks yet are invisible to it, so the next flush wrote them back and the file grew again, resurrecting the truncated bytes. Windows hits this on every write-then-shrink because its flush runs after CloseHandle, but the gap is platform-neutral. * mount: order a file's unlink against its in-flight flush Unlink set the handle's deleted flag bare, so a flush already past its own check of that flag wrote the entry back right after the delete removed it, and a delete-on-close file outlived its last handle. The flag is now set under the handle's flush lock and re-checked under it, so a flush either completes before the delete or sees the flag and skips. An eagerly created handle also starts clean: the dirty mark existed to make the deferred filer create happen at flush, and eager creates have nothing to flush.
155 lines
4.3 KiB
Go
155 lines
4.3 KiB
Go
package mount
|
|
|
|
import (
|
|
"sync"
|
|
"testing"
|
|
|
|
"github.com/seaweedfs/go-fuse/v2/fuse"
|
|
"github.com/seaweedfs/seaweedfs/weed/filer"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/util"
|
|
)
|
|
|
|
// TestAttrChunkRace guards the locking around an open handle's chunk slice.
|
|
//
|
|
// With writebackCache, async upload workers append chunks to an open file
|
|
// handle's shared entry under the LockedEntry lock (FileHandle.AddChunks),
|
|
// while metadata ops compute the file size by iterating entry.Chunks. SetAttr
|
|
// and GetAttr used to read that slice without the LockedEntry lock, so a
|
|
// concurrent append that reallocated the backing array produced a torn slice
|
|
// read and a nil pointer dereference in filer.TotalSize. Run under -race.
|
|
func TestAttrChunkRace(t *testing.T) {
|
|
wfs := &WFS{
|
|
option: &Option{},
|
|
inodeToPath: NewInodeToPath(util.FullPath("/"), 0),
|
|
fhMap: NewFileHandleToInode(),
|
|
openMtimeCache: make(map[uint64][2]int64, 8),
|
|
}
|
|
|
|
const inode = uint64(42)
|
|
fullPath := util.FullPath("/dir/sample.txt")
|
|
wfs.inodeToPath.Lookup(fullPath, 1, false, false, inode, true)
|
|
|
|
entry := &filer_pb.Entry{
|
|
Name: "sample.txt",
|
|
Attributes: &filer_pb.FuseAttributes{FileMode: 0644},
|
|
}
|
|
chunkGroup, err := filer.NewChunkGroup(nil, nil, nil, 1)
|
|
if err != nil {
|
|
t.Fatalf("NewChunkGroup: %v", err)
|
|
}
|
|
fh := &FileHandle{
|
|
fh: FileHandleId(1),
|
|
inode: inode,
|
|
wfs: wfs,
|
|
entry: &LockedEntry{Entry: entry},
|
|
entryChunkGroup: chunkGroup,
|
|
}
|
|
fh.dirtyPages = newPageWriter(fh, 1<<20)
|
|
wfs.fhMap.inode2fh[inode] = fh
|
|
wfs.fhMap.fh2inode[fh.fh] = inode
|
|
|
|
const iterations = 2000
|
|
var wg sync.WaitGroup
|
|
wg.Add(3)
|
|
|
|
// Async uploader: append chunks, reallocating the backing array.
|
|
go func() {
|
|
defer wg.Done()
|
|
for i := 0; i < iterations; i++ {
|
|
fh.AddChunks([]*filer_pb.FileChunk{{FileId: "x", Offset: int64(i), Size: 1}})
|
|
}
|
|
}()
|
|
|
|
// SetAttr: mtime-only recomputes FileSize by iterating chunks; a shrinking
|
|
// size takes the truncate path that rewrites entry.Chunks under the lock.
|
|
go func() {
|
|
defer wg.Done()
|
|
for i := 0; i < iterations; i++ {
|
|
in := &fuse.SetAttrIn{}
|
|
in.NodeId = inode
|
|
if i%2 == 0 {
|
|
in.Valid = fuse.FATTR_MTIME
|
|
in.Mtime = uint64(i)
|
|
} else {
|
|
in.Valid = fuse.FATTR_SIZE
|
|
in.Size = uint64(i % 8)
|
|
}
|
|
var out fuse.AttrOut
|
|
wfs.SetAttr(nil, in, &out)
|
|
}
|
|
}()
|
|
|
|
// GetAttr also computes FileSize by iterating chunks.
|
|
go func() {
|
|
defer wg.Done()
|
|
for i := 0; i < iterations; i++ {
|
|
in := &fuse.GetAttrIn{}
|
|
in.NodeId = inode
|
|
var out fuse.AttrOut
|
|
wfs.GetAttr(nil, in, &out)
|
|
}
|
|
}()
|
|
|
|
wg.Wait()
|
|
}
|
|
|
|
// TestReadFromChunksRace guards the read path's chunk-slice access. The read
|
|
// path holds fh.entryLock (which excludes SetAttr) but not the LockedEntry lock
|
|
// the async uploader appends under, so readFromChunks used to compute FileSize
|
|
// and walk entry.Chunks while AddChunks reallocated the slice. Run under -race.
|
|
func TestReadFromChunksRace(t *testing.T) {
|
|
wfs := &WFS{
|
|
option: &Option{},
|
|
inodeToPath: NewInodeToPath(util.FullPath("/"), 0),
|
|
fhMap: NewFileHandleToInode(),
|
|
}
|
|
|
|
const inode = uint64(42)
|
|
fullPath := util.FullPath("/dir/sample.txt")
|
|
wfs.inodeToPath.Lookup(fullPath, 1, false, false, inode, true)
|
|
|
|
// FileSize 0 forces readFromChunks down the filer.FileSize(chunks) branch.
|
|
entry := &filer_pb.Entry{
|
|
Name: "sample.txt",
|
|
Attributes: &filer_pb.FuseAttributes{FileMode: 0644},
|
|
}
|
|
chunkGroup, err := filer.NewChunkGroup(nil, nil, nil, 1)
|
|
if err != nil {
|
|
t.Fatalf("NewChunkGroup: %v", err)
|
|
}
|
|
fh := &FileHandle{
|
|
fh: FileHandleId(1),
|
|
inode: inode,
|
|
wfs: wfs,
|
|
entry: &LockedEntry{Entry: entry},
|
|
entryChunkGroup: chunkGroup,
|
|
}
|
|
fh.dirtyPages = newPageWriter(fh, 1<<20)
|
|
wfs.fhMap.inode2fh[inode] = fh
|
|
wfs.fhMap.fh2inode[fh.fh] = inode
|
|
|
|
const iterations = 2000
|
|
var wg sync.WaitGroup
|
|
wg.Add(2)
|
|
|
|
go func() {
|
|
defer wg.Done()
|
|
for i := 0; i < iterations; i++ {
|
|
fh.AddChunks([]*filer_pb.FileChunk{{FileId: "x", Offset: int64(i), Size: 1}})
|
|
}
|
|
}()
|
|
|
|
// A read past EOF returns before touching the volume tier, but only after
|
|
// the racy size/chunk snapshot has run.
|
|
go func() {
|
|
defer wg.Done()
|
|
buff := make([]byte, 16)
|
|
for i := 0; i < iterations; i++ {
|
|
fh.readFromChunks(buff, 1<<62)
|
|
}
|
|
}()
|
|
|
|
wg.Wait()
|
|
}
|