mirror_zfs/include/sys/zfs_vnops.h
Brian Behlendorf 057e8eee35 Improve fstat(2) performance
There is at most a factor of 3x performance improvement to be
had by using the Linux generic_fillattr() helper.  However, to
use it safely we need to ensure the values in a cached inode
are kept rigerously up to date.  Unfortunately, this isn't
the case for the blksize, blocks, and atime fields.  At the
moment the authoritative values are still stored in the znode.

This patch introduces an optimized zfs_getattr_fast() call.
The idea is to use the up to date values from the inode and
the blksize, block, and atime fields from the znode.  At some
latter date we should be able to strictly use the inode values
and further improve performance.

The remaining overhead in the zfs_getattr_fast() call can be
attributed to having to take the znode mutex.  This overhead is
unavoidable until the inode is kept strictly up to date.  The
the careful reader will notice the we do not use the customary
ZFS_ENTER()/ZFS_EXIT() macros.  These macro's are designed to
ensure the filesystem is not torn down in the middle of an
operation.  However, in this case the VFS is holding a
reference on the active inode so we know this is impossible.

=================== Performance Tests ========================

This test calls the fstat(2) system call 10,000,000 times on
an open file description in a tight loop.  The test results
show the zfs stat(2) performance is now only 22% slower than
ext4.  This is a 2.5x improvement and there is a clear long
term plan to get to parity with ext4.

filesystem    | test-1  test-2  test-3  | average | times-ext4
--------------+-------------------------+---------+-----------
ext4          |  7.785s  7.899s  7.284s |  7.656s | 1.000x
zfs-0.6.0-rc4 | 24.052s 22.531s 23.857s | 23.480s | 3.066x
zfs-faststat  |  9.224s  9.398s  9.485s |  9.369s | 1.223x

The second test is to run 'du' of a copy of the /usr tree
which contains 110514 files.  The test is run multiple times
both using both a cold cache (/proc/sys/vm/drop_caches) and
a hot cache.  As expected this change signigicantly improved
the zfs hot cache performance and doesn't quite bring zfs to
parity with ext4.

A little surprisingly the zfs cold cache performance is better
than ext4.  This can probably be attributed to the zfs allocation
policy of co-locating all the meta data on disk which minimizes
seek times.  By default the ext4 allocator will spread the data
over the entire disk only co-locating each directory.

filesystem    | cold    | hot
--------------+---------+--------
ext4          | 13.318s | 1.040s
zfs-0.6.0-rc4 |  4.982s | 1.762s
zfs-faststat  |  4.933s | 1.345s
2011-07-11 09:11:22 -07:00

86 lines
3.6 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 (c) 2010, Oracle and/or its affiliates. All rights reserved.
*/
#ifndef _SYS_FS_ZFS_VNOPS_H
#define _SYS_FS_ZFS_VNOPS_H
#include <sys/vnode.h>
#include <sys/xvattr.h>
#include <sys/uio.h>
#include <sys/cred.h>
#include <sys/fcntl.h>
#include <sys/pathname.h>
#ifdef __cplusplus
extern "C" {
#endif
extern int zfs_open(struct inode *ip, int mode, int flag, cred_t *cr);
extern int zfs_close(struct inode *ip, int flag, cred_t *cr);
extern int zfs_read(struct inode *ip, uio_t *uio, int ioflag, cred_t *cr);
extern int zfs_write(struct inode *ip, uio_t *uio, int ioflag, cred_t *cr);
extern int zfs_access(struct inode *ip, int mode, int flag, cred_t *cr);
extern int zfs_lookup(struct inode *dip, char *nm, struct inode **ipp,
int flags, cred_t *cr, int *direntflags, pathname_t *realpnp);
extern int zfs_create(struct inode *dip, char *name, vattr_t *vap, int excl,
int mode, struct inode **ipp, cred_t *cr, int flag, vsecattr_t *vsecp);
extern int zfs_remove(struct inode *dip, char *name, cred_t *cr);
extern int zfs_mkdir(struct inode *dip, char *dirname, vattr_t *vap,
struct inode **ipp, cred_t *cr, int flags, vsecattr_t *vsecp);
extern int zfs_rmdir(struct inode *dip, char *name, struct inode *cwd,
cred_t *cr, int flags);
extern int zfs_readdir(struct inode *ip, void *dirent, filldir_t filldir,
loff_t *pos, cred_t *cr);
extern int zfs_fsync(struct inode *ip, int syncflag, cred_t *cr);
extern int zfs_getattr(struct inode *ip, vattr_t *vap, int flag, cred_t *cr);
extern int zfs_getattr_fast(struct inode *ip, struct kstat *sp);
extern int zfs_setattr(struct inode *ip, vattr_t *vap, int flag, cred_t *cr);
extern int zfs_rename(struct inode *sdip, char *snm, struct inode *tdip,
char *tnm, cred_t *cr, int flags);
extern int zfs_symlink(struct inode *dip, char *name, vattr_t *vap,
char *link, struct inode **ipp, cred_t *cr, int flags);
extern int zfs_follow_link(struct dentry *dentry, struct nameidata *nd);
extern int zfs_readlink(struct inode *ip, uio_t *uio, cred_t *cr);
extern int zfs_link(struct inode *tdip, struct inode *sip,
char *name, cred_t *cr);
extern void zfs_inactive(struct inode *ip);
extern int zfs_space(struct inode *ip, int cmd, flock64_t *bfp, int flag,
offset_t offset, cred_t *cr);
extern int zfs_fid(struct inode *ip, fid_t *fidp);
extern int zfs_getsecattr(struct inode *ip, vsecattr_t *vsecp, int flag,
cred_t *cr);
extern int zfs_setsecattr(struct inode *ip, vsecattr_t *vsecp, int flag,
cred_t *cr);
extern int zfs_getpage(struct inode *ip, struct page *pl[], int nr_pages);
extern int zfs_putpage(struct page *page, struct writeback_control *wbc,
void *data);
extern int zfs_map(struct inode *ip, offset_t off, caddr_t *addrp,
size_t len, unsigned long vm_flags);
#ifdef __cplusplus
}
#endif
#endif /* _SYS_FS_ZFS_VNOPS_H */