mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-26 19:19:32 +03:00
82a37189aa
The current ZFS implementation stores xattrs on disk using a hidden
directory. In this directory a file name represents the xattr name
and the file contexts are the xattr binary data. This approach is
very flexible and allows for arbitrarily large xattrs. However,
it also suffers from a significant performance penalty. Accessing
a single xattr can requires up to three disk seeks.
1) Lookup the dnode object.
2) Lookup the dnodes's xattr directory object.
3) Lookup the xattr object in the directory.
To avoid this performance penalty Linux filesystems such as ext3
and xfs try to store the xattr as part of the inode on disk. When
the xattr is to large to store in the inode then a single external
block is allocated for them. In practice most xattrs are small
and this approach works well.
The addition of System Attributes (SA) to zfs provides us a clean
way to make this optimization. When the dataset property 'xattr=sa'
is set then xattrs will be preferentially stored as System Attributes.
This allows tiny xattrs (~100 bytes) to be stored with the dnode and
up to 64k of xattrs to be stored in the spill block. If additional
xattr space is required, which is unlikely under Linux, they will be
stored using the traditional directory approach.
This optimization results in roughly a 3x performance improvement
when accessing xattrs which brings zfs roughly to parity with ext4
and xfs (see table below). When multiple xattrs are stored per-file
the performance improvements are even greater because all of the
xattrs stored in the spill block will be cached.
However, by default SA based xattrs are disabled in the Linux port
to maximize compatibility with other implementations. If you do
enable SA based xattrs then they will not be visible on platforms
which do not support this feature.
----------------------------------------------------------------------
Time in seconds to get/set one xattr of N bytes on 100,000 files
------+--------------------------------+------------------------------
| setxattr | getxattr
bytes | ext4 xfs zfs-dir zfs-sa | ext4 xfs zfs-dir zfs-sa
------+--------------------------------+------------------------------
1 | 2.33 31.88 21.50 4.57 | 2.35 2.64 6.29 2.43
32 | 2.79 30.68 21.98 4.60 | 2.44 2.59 6.78 2.48
256 | 3.25 31.99 21.36 5.92 | 2.32 2.71 6.22 3.14
1024 | 3.30 32.61 22.83 8.45 | 2.40 2.79 6.24 3.27
4096 | 3.57 317.46 22.52 10.73 | 2.78 28.62 6.90 3.94
16384 | n/a 2342.39 34.30 19.20 | n/a 45.44 145.90 7.55
65536 | n/a 2941.39 128.15 131.32* | n/a 141.92 256.85 262.12*
Legend:
* ext4 - Stock RHEL6.1 ext4 mounted with '-o user_xattr'.
* xfs - Stock RHEL6.1 xfs mounted with default options.
* zfs-dir - Directory based xattrs only.
* zfs-sa - Prefer SAs but spill in to directories as needed, a
trailing * indicates overflow in to directories occured.
NOTE: Ext4 supports 4096 bytes of xattr name/value pairs per file.
NOTE: XFS and ZFS have no limit on xattr name/value pairs per file.
NOTE: Linux limits individual name/value pairs to 65536 bytes.
NOTE: All setattr/getattr's were done after dropping the cache.
NOTE: All tests were run against a single hard drive.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #443
151 lines
4.3 KiB
C
151 lines
4.3 KiB
C
/*
|
|
* CDDL HEADER START
|
|
*
|
|
* The contents of this file are subject to the terms of the
|
|
* Common Development and Distribution License (the "License").
|
|
* You may not use this file except in compliance with the License.
|
|
*
|
|
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
|
|
* or http://www.opensolaris.org/os/licensing.
|
|
* See the License for the specific language governing permissions
|
|
* and limitations under the License.
|
|
*
|
|
* When distributing Covered Code, include this CDDL HEADER in each
|
|
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
|
|
* If applicable, add the following below this CDDL HEADER, with the
|
|
* fields enclosed by brackets "[]" replaced with your own identifying
|
|
* information: Portions Copyright [yyyy] [name of copyright owner]
|
|
*
|
|
* CDDL HEADER END
|
|
*/
|
|
/*
|
|
* Copyright 2010 Sun Microsystems, Inc. All rights reserved.
|
|
* Use is subject to license terms.
|
|
*/
|
|
|
|
#ifndef _SYS_ZFS_SA_H
|
|
#define _SYS_ZFS_SA_H
|
|
|
|
#ifdef _KERNEL
|
|
#include <sys/types32.h>
|
|
#include <sys/list.h>
|
|
#include <sys/dmu.h>
|
|
#include <sys/zfs_acl.h>
|
|
#include <sys/zfs_znode.h>
|
|
#include <sys/sa.h>
|
|
#include <sys/zil.h>
|
|
|
|
|
|
#endif
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
/*
|
|
* This is the list of known attributes
|
|
* to the ZPL. The values of the actual
|
|
* attributes are not defined by the order
|
|
* the enums. It is controlled by the attribute
|
|
* registration mechanism. Two different file system
|
|
* could have different numeric values for the same
|
|
* attributes. this list is only used for dereferencing
|
|
* into the table that will hold the actual numeric value.
|
|
*/
|
|
typedef enum zpl_attr {
|
|
ZPL_ATIME,
|
|
ZPL_MTIME,
|
|
ZPL_CTIME,
|
|
ZPL_CRTIME,
|
|
ZPL_GEN,
|
|
ZPL_MODE,
|
|
ZPL_SIZE,
|
|
ZPL_PARENT,
|
|
ZPL_LINKS,
|
|
ZPL_XATTR,
|
|
ZPL_RDEV,
|
|
ZPL_FLAGS,
|
|
ZPL_UID,
|
|
ZPL_GID,
|
|
ZPL_PAD,
|
|
ZPL_ZNODE_ACL,
|
|
ZPL_DACL_COUNT,
|
|
ZPL_SYMLINK,
|
|
ZPL_SCANSTAMP,
|
|
ZPL_DACL_ACES,
|
|
ZPL_DXATTR,
|
|
ZPL_END
|
|
} zpl_attr_t;
|
|
|
|
#define ZFS_OLD_ZNODE_PHYS_SIZE 0x108
|
|
#define ZFS_SA_BASE_ATTR_SIZE (ZFS_OLD_ZNODE_PHYS_SIZE - \
|
|
sizeof (zfs_acl_phys_t))
|
|
|
|
#define SA_MODE_OFFSET 0
|
|
#define SA_SIZE_OFFSET 8
|
|
#define SA_GEN_OFFSET 16
|
|
#define SA_UID_OFFSET 24
|
|
#define SA_GID_OFFSET 32
|
|
#define SA_PARENT_OFFSET 40
|
|
|
|
extern sa_attr_reg_t zfs_attr_table[ZPL_END + 1];
|
|
extern sa_attr_reg_t zfs_legacy_attr_table[ZPL_END + 1];
|
|
|
|
/*
|
|
* This is a deprecated data structure that only exists for
|
|
* dealing with file systems create prior to ZPL version 5.
|
|
*/
|
|
typedef struct znode_phys {
|
|
uint64_t zp_atime[2]; /* 0 - last file access time */
|
|
uint64_t zp_mtime[2]; /* 16 - last file modification time */
|
|
uint64_t zp_ctime[2]; /* 32 - last file change time */
|
|
uint64_t zp_crtime[2]; /* 48 - creation time */
|
|
uint64_t zp_gen; /* 64 - generation (txg of creation) */
|
|
uint64_t zp_mode; /* 72 - file mode bits */
|
|
uint64_t zp_size; /* 80 - size of file */
|
|
uint64_t zp_parent; /* 88 - directory parent (`..') */
|
|
uint64_t zp_links; /* 96 - number of links to file */
|
|
uint64_t zp_xattr; /* 104 - DMU object for xattrs */
|
|
uint64_t zp_rdev; /* 112 - dev_t for VBLK & VCHR files */
|
|
uint64_t zp_flags; /* 120 - persistent flags */
|
|
uint64_t zp_uid; /* 128 - file owner */
|
|
uint64_t zp_gid; /* 136 - owning group */
|
|
uint64_t zp_zap; /* 144 - extra attributes */
|
|
uint64_t zp_pad[3]; /* 152 - future */
|
|
zfs_acl_phys_t zp_acl; /* 176 - 263 ACL */
|
|
/*
|
|
* Data may pad out any remaining bytes in the znode buffer, eg:
|
|
*
|
|
* |<---------------------- dnode_phys (512) ------------------------>|
|
|
* |<-- dnode (192) --->|<----------- "bonus" buffer (320) ---------->|
|
|
* |<---- znode (264) ---->|<---- data (56) ---->|
|
|
*
|
|
* At present, we use this space for the following:
|
|
* - symbolic links
|
|
* - 32-byte anti-virus scanstamp (regular files only)
|
|
*/
|
|
} znode_phys_t;
|
|
|
|
#ifdef _KERNEL
|
|
|
|
#define DXATTR_MAX_ENTRY_SIZE (32768)
|
|
#define DXATTR_MAX_SA_SIZE (SPA_MAXBLOCKSIZE >> 1)
|
|
|
|
int zfs_sa_readlink(struct znode *, uio_t *);
|
|
void zfs_sa_symlink(struct znode *, char *link, int len, dmu_tx_t *);
|
|
void zfs_sa_get_scanstamp(struct znode *, xvattr_t *);
|
|
void zfs_sa_set_scanstamp(struct znode *, xvattr_t *, dmu_tx_t *);
|
|
int zfs_sa_get_xattr(struct znode *);
|
|
int zfs_sa_set_xattr(struct znode *);
|
|
void zfs_sa_upgrade(struct sa_handle *, dmu_tx_t *);
|
|
void zfs_sa_upgrade_txholds(dmu_tx_t *, struct znode *);
|
|
void zfs_sa_init(void);
|
|
void zfs_sa_fini(void);
|
|
#endif
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_ZFS_SA_H */
|