gvisor/pkg/abi/linux/fs.go

102 lines
2.6 KiB
Go
Raw Normal View History

// Copyright 2018 The gVisor Authors.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package linux
// Filesystem types used in statfs(2).
//
// See linux/magic.h.
const (
ANON_INODE_FS_MAGIC = 0x09041934
DEVPTS_SUPER_MAGIC = 0x00001cd1
EXT_SUPER_MAGIC = 0xef53
OVERLAYFS_SUPER_MAGIC = 0x794c7630
PIPEFS_MAGIC = 0x50495045
PROC_SUPER_MAGIC = 0x9fa0
RAMFS_MAGIC = 0x09041934
SOCKFS_MAGIC = 0x534F434B
SYSFS_MAGIC = 0x62656572
TMPFS_MAGIC = 0x01021994
V9FS_MAGIC = 0x01021997
)
// Filesystem path limits, from uapi/linux/limits.h.
const (
NAME_MAX = 255
PATH_MAX = 4096
)
// Statfs is struct statfs, from uapi/asm-generic/statfs.h.
type Statfs struct {
// Type is one of the filesystem magic values, defined above.
Type uint64
// BlockSize is the data block size.
BlockSize int64
// Blocks is the number of data blocks in use.
Blocks uint64
// BlocksFree is the number of free blocks.
BlocksFree uint64
// BlocksAvailable is the number of blocks free for use by
// unprivileged users.
BlocksAvailable uint64
// Files is the number of used file nodes on the filesystem.
Files uint64
// FileFress is the number of free file nodes on the filesystem.
FilesFree uint64
// FSID is the filesystem ID.
FSID [2]int32
// NameLength is the maximum file name length.
NameLength uint64
// FragmentSize is equivalent to BlockSize.
FragmentSize int64
// Flags is the set of filesystem mount flags.
Flags uint64
// Spare is unused.
Spare [4]uint64
}
Sentry virtual filesystem, v2 Major differences from the current ("v1") sentry VFS: - Path resolution is Filesystem-driven (FilesystemImpl methods call vfs.ResolvingPath methods) rather than VFS-driven (fs package owns a Dirent tree and calls fs.InodeOperations methods to populate it). This drastically improves performance, primarily by reducing overhead from inefficient synchronization and indirection. It also makes it possible to implement remote filesystem protocols that translate FS system calls into single RPCs, rather than having to make (at least) one RPC per path component, significantly reducing the latency of remote filesystems (especially during cold starts and for uncacheable shared filesystems). - Mounts are correctly represented as a separate check based on contextual state (current mount) rather than direct replacement in a fs.Dirent tree. This makes it possible to support (non-recursive) bind mounts and mount namespaces. Included in this CL is fsimpl/memfs, an incomplete in-memory filesystem that exists primarily to demonstrate intended filesystem implementation patterns and for benchmarking: BenchmarkVFS1TmpfsStat/1-6 3000000 497 ns/op BenchmarkVFS1TmpfsStat/2-6 2000000 676 ns/op BenchmarkVFS1TmpfsStat/3-6 2000000 904 ns/op BenchmarkVFS1TmpfsStat/8-6 1000000 1944 ns/op BenchmarkVFS1TmpfsStat/64-6 100000 14067 ns/op BenchmarkVFS1TmpfsStat/100-6 50000 21700 ns/op BenchmarkVFS2MemfsStat/1-6 10000000 197 ns/op BenchmarkVFS2MemfsStat/2-6 5000000 233 ns/op BenchmarkVFS2MemfsStat/3-6 5000000 268 ns/op BenchmarkVFS2MemfsStat/8-6 3000000 477 ns/op BenchmarkVFS2MemfsStat/64-6 500000 2592 ns/op BenchmarkVFS2MemfsStat/100-6 300000 4045 ns/op BenchmarkVFS1TmpfsMountStat/1-6 2000000 679 ns/op BenchmarkVFS1TmpfsMountStat/2-6 2000000 912 ns/op BenchmarkVFS1TmpfsMountStat/3-6 1000000 1113 ns/op BenchmarkVFS1TmpfsMountStat/8-6 1000000 2118 ns/op BenchmarkVFS1TmpfsMountStat/64-6 100000 14251 ns/op BenchmarkVFS1TmpfsMountStat/100-6 100000 22397 ns/op BenchmarkVFS2MemfsMountStat/1-6 5000000 317 ns/op BenchmarkVFS2MemfsMountStat/2-6 5000000 361 ns/op BenchmarkVFS2MemfsMountStat/3-6 5000000 387 ns/op BenchmarkVFS2MemfsMountStat/8-6 3000000 582 ns/op BenchmarkVFS2MemfsMountStat/64-6 500000 2699 ns/op BenchmarkVFS2MemfsMountStat/100-6 300000 4133 ns/op From this we can infer that, on this machine: - Constant cost for tmpfs stat() is ~160ns in VFS2 and ~280ns in VFS1. - Per-path-component cost is ~35ns in VFS2 and ~215ns in VFS1, a difference of about 6x. - The cost of crossing a mount boundary is about 80ns in VFS2 (MemfsMountStat/1 does approximately the same amount of work as MemfsStat/2, except that it also crosses a mount boundary). This is an inescapable cost of the separate mount lookup needed to support bind mounts and mount namespaces. PiperOrigin-RevId: 258853946
2019-07-18 22:09:14 +00:00
// Whence argument to lseek(2), from include/uapi/linux/fs.h.
const (
SEEK_SET = 0
SEEK_CUR = 1
SEEK_END = 2
SEEK_DATA = 3
SEEK_HOLE = 4
)
// Sync_file_range flags, from include/uapi/linux/fs.h
const (
SYNC_FILE_RANGE_WAIT_BEFORE = 1
SYNC_FILE_RANGE_WRITE = 2
SYNC_FILE_RANGE_WAIT_AFTER = 4
)
// Flag argument to renameat2(2), from include/uapi/linux/fs.h.
const (
RENAME_NOREPLACE = (1 << 0) // Don't overwrite target.
RENAME_EXCHANGE = (1 << 1) // Exchange src and dst.
RENAME_WHITEOUT = (1 << 2) // Whiteout src.
)