mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-11-15 16:28:30 +01:00
* mount: fail the write when the swap file chunk cannot be created #7957 added a nil check after NewSwapFileChunk so a failed swap file creation returns an error instead of panicking. The result was assigned to pageChunk, a PageChunk interface, before the check, and an interface holding a nil *SwapFileChunk is not nil, so the check never fired: SaveDataAt stored the nil chunk and panicked in WriteDataAt. Check the *SwapFileChunk before converting it. The new test points the swap directory below a regular file; on master it panics in SwapFileChunk.WriteDataAt. Signed-off-by: anant <170962632+antcybersec@users.noreply.github.com> * mount: grow the file only after its write is buffered Write set the new size, times, pending append offset and uncommitted bytes before AddPage. When AddPage failed (now that a swap file chunk that cannot be created returns an error), the write was reported as failed but the larger size stayed on the handle's entry, so the next flush published it with a hole where the data should be. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * mount: report a partly buffered write as a short write PageWriter.AddPage fills one chunk at a time, so when a later chunk cannot be created the earlier chunks already hold their bytes. Return how much was buffered, and let Write grow the size and times over that prefix and report it, instead of failing the whole write while the prefix still reaches the next flush. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * mount: report the bytes a failed copy_file_range already buffered A streaming copy whose page fails partway returned an error even though earlier pages, or the start of the failing one, were already buffered and would reach the next flush with the destination size left short. Count the buffered bytes, grow the destination over them, and return them as a short copy. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * mount: free the copy test's destination pages The buffered memory chunk counts toward the process-wide memory chunk ceiling, so repeated runs of the test pushed later ones onto the unusable swap directory. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * mount: count only the bytes a swap chunk stored A swap chunk whose file write fails stores a prefix or nothing, but SaveDataAt returned no error and AddPage counted the whole span as buffered. SaveDataAt now reports the short write, and AddPage passes the stored count up so a write is never acknowledged past it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * mount: fail a partly buffered writeback write Kernel writeback ignores the count in a WRITE reply, so a short write there drops the unbuffered rest without an error. A write flagged as page-cache writeback now keeps its buffered prefix but returns the error, which the kernel reports on fsync. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Signed-off-by: anant <170962632+antcybersec@users.noreply.github.com> Co-authored-by: anant <170962632+antcybersec@users.noreply.github.com> Co-authored-by: Chris Lu <chrislusf@users.noreply.github.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
96 lines
3.8 KiB
Go
96 lines
3.8 KiB
Go
//go:build !freebsd
|
|
|
|
package mount
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"os"
|
|
"path/filepath"
|
|
"syscall"
|
|
"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"
|
|
"google.golang.org/protobuf/proto"
|
|
)
|
|
|
|
// A write the swap file cannot buffer fails, and must not grow the file: the
|
|
// next flush would publish that size with a hole where its data should be. A
|
|
// write that buffers only its first chunk is a short write of those bytes, or
|
|
// an error for kernel writeback, which would drop the rest silently.
|
|
func TestFailedWriteDoesNotGrowFile(t *testing.T) {
|
|
t.Run("short write", func(t *testing.T) { testFailedWriteDoesNotGrowFile(t, 0) })
|
|
t.Run("kernel writeback", func(t *testing.T) { testFailedWriteDoesNotGrowFile(t, fuse.WRITE_CACHE) })
|
|
}
|
|
|
|
func testFailedWriteDoesNotGrowFile(t *testing.T, writeFlags uint32) {
|
|
base := attributeAppendEntry(1)
|
|
base.CommitTsNs = 100
|
|
peer := &g6ConditionalPeer{entry: proto.Clone(base).(*filer_pb.Entry)}
|
|
peer.blobs = map[string][]byte{base.Chunks[0].GetFileIdString(): bytes.Repeat([]byte{'O'}, 256)}
|
|
|
|
w := newInvalidateTestWFS(t)
|
|
notADir := filepath.Join(t.TempDir(), "file")
|
|
if err := os.WriteFile(notADir, nil, 0600); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
w.option.uniqueCacheDirForWrite = filepath.Join(notADir, "swap")
|
|
w.option.DefaultPermissions = true
|
|
w.posixLocks = NewPosixLockTable()
|
|
w.option.ConcurrentWriters = 1
|
|
w.concurrentWriters = util.NewLimitedConcurrentExecutor(1)
|
|
startFakeFiler(t, w, peer)
|
|
w.inodeToPath.Lookup("/dir", 1, true, false, 0, false)
|
|
w.inodeToPath.Lookup("/dir/file", 1, false, false, 42, true)
|
|
w.inodeToPath.MarkChildrenCached("/dir")
|
|
if err := w.metaCache.InsertEntry(context.Background(), filer.FromPbEntry("/dir", proto.Clone(base).(*filer_pb.Entry)), 1); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
out := &fuse.OpenOut{}
|
|
if code := w.Open(nil, &fuse.OpenIn{InHeader: fuse.InHeader{NodeId: 42}, Flags: syscall.O_WRONLY}, out); code != fuse.OK {
|
|
t.Fatal(code)
|
|
}
|
|
fh := w.GetHandle(FileHandleId(out.Fh))
|
|
g6AppendUploader(t, fh, 100, peer)
|
|
|
|
write := func(offset uint64, size int, value byte) (uint32, fuse.Status) {
|
|
return w.Write(nil, &fuse.WriteIn{InHeader: fuse.InHeader{NodeId: 42}, Fh: out.Fh, Offset: offset, Size: uint32(size), WriteFlags: writeFlags}, bytes.Repeat([]byte{value}, size))
|
|
}
|
|
if _, code := write(256, 256, 'A'); code != fuse.OK {
|
|
t.Fatalf("buffered write: %v", code)
|
|
}
|
|
// The only writable chunk slot is taken, so this write needs the swap file.
|
|
if _, code := write(4096, 256, 'B'); code == fuse.OK {
|
|
t.Fatal("write through an unusable swap directory succeeded")
|
|
}
|
|
if size := fh.GetEntry().GetEntry().Attributes.FileSize; size != 512 {
|
|
t.Fatalf("file size after the failed write = %d, want 512", size)
|
|
}
|
|
// The first 24 bytes fit the existing chunk; the next chunk needs the swap file.
|
|
n, code := write(1000, 48, 'C')
|
|
if writeFlags == 0 && (code != fuse.OK || n != 24) {
|
|
t.Fatalf("boundary-crossing write = %d, %v; want a short write of 24", n, code)
|
|
}
|
|
if writeFlags != 0 && code == fuse.OK {
|
|
t.Fatalf("boundary-crossing writeback = %d, OK; want an error", n)
|
|
}
|
|
if size := fh.GetEntry().GetEntry().Attributes.FileSize; size != 1024 {
|
|
t.Fatalf("file size after the short write = %d, want 1024", size)
|
|
}
|
|
if code := w.Fsync(nil, &fuse.FsyncIn{InHeader: fuse.InHeader{NodeId: 42}, Fh: out.Fh}); code != fuse.OK {
|
|
t.Fatal(code)
|
|
}
|
|
|
|
peer.mu.Lock()
|
|
defer peer.mu.Unlock()
|
|
want := append(bytes.Repeat([]byte{'O'}, 256), bytes.Repeat([]byte{'A'}, 256)...)
|
|
want = append(want, make([]byte, 1000-512)...)
|
|
want = append(want, bytes.Repeat([]byte{'C'}, 24)...)
|
|
if got := g6StoredBytes(t, peer); peer.entry.Attributes.FileSize != 1024 || !bytes.Equal(got, want) {
|
|
t.Fatalf("stored size %d, want 1024 with the original and buffered bytes", peer.entry.Attributes.FileSize)
|
|
}
|
|
}
|