3c0e5c0f45
While the existing implementation of .writepage()/zpl_putpage() was functional it was not entirely correct. In particular, it would move dirty pages in to a clean state simply after copying them in to the ARC cache. This would result in the pages being lost if the system were to crash enough though the Linux VFS believed them to be safe on stable storage. Since at the moment virtually all I/O, except mmap(2), bypasses the page cache this isn't as bad as it sounds. However, as hopefully start using the page cache more getting this right becomes more important so it's good to improve this now. This patch takes a big step in that direction by updating the code to correctly move dirty pages through a writeback phase before they are marked clean. When a dirty page is copied in to the ARC it will now be set in writeback and a completion callback is registered with the transaction. The page will stay in writeback until the dmu runs the completion callback indicating the page is on stable storage. At this point the page can be safely marked clean. This process is normally entirely asynchronous and will be repeated for every dirty page. This may initially sound inefficient but most of these pages will end up in a few txgs. That means when they are eventually written to disk they should be nicely batched. However, there is room for improvement. It may still be desirable to batch up the pages in to larger writes for the dmu. This would reduce the number of callbacks and small 4k buffer required by the ARC. Finally, if the caller requires that the I/O be done synchronously by setting WB_SYNC_ALL or if ZFS_SYNC_ALWAYS is set. Then the I/O will trigger a zil_commit() to flush the data to stable storage. At which point the registered callbacks will be run leaving the date safe of disk and marked clean before returning from .writepage. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
86 lines
3.6 KiB
C
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 inode *ip, struct page *pp,
|
|
struct writeback_control *wbc);
|
|
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 */
|