2006-01-17 00:50:04 +08:00
|
|
|
/*
|
|
|
|
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
|
2006-05-19 03:09:15 +08:00
|
|
|
* Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
|
2006-01-17 00:50:04 +08:00
|
|
|
*
|
|
|
|
* This copyrighted material is made available to anyone wishing to use,
|
|
|
|
* modify, copy, or redistribute it subject to the terms and conditions
|
2006-09-01 23:05:15 +08:00
|
|
|
* of the GNU General Public License version 2.
|
2006-01-17 00:50:04 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/spinlock.h>
|
|
|
|
#include <linux/completion.h>
|
|
|
|
#include <linux/buffer_head.h>
|
2011-09-13 07:15:24 +08:00
|
|
|
#include <linux/blkdev.h>
|
2006-02-28 06:23:27 +08:00
|
|
|
#include <linux/gfs2_ondisk.h>
|
2006-03-29 03:14:04 +08:00
|
|
|
#include <linux/crc32.h>
|
2006-01-17 00:50:04 +08:00
|
|
|
|
|
|
|
#include "gfs2.h"
|
2006-02-28 06:23:27 +08:00
|
|
|
#include "incore.h"
|
2006-01-17 00:50:04 +08:00
|
|
|
#include "bmap.h"
|
|
|
|
#include "glock.h"
|
|
|
|
#include "inode.h"
|
|
|
|
#include "meta_io.h"
|
|
|
|
#include "quota.h"
|
|
|
|
#include "rgrp.h"
|
2013-01-28 17:30:07 +08:00
|
|
|
#include "log.h"
|
2011-02-24 05:11:33 +08:00
|
|
|
#include "super.h"
|
2006-01-17 00:50:04 +08:00
|
|
|
#include "trans.h"
|
2006-02-08 19:50:51 +08:00
|
|
|
#include "dir.h"
|
2006-02-28 06:23:27 +08:00
|
|
|
#include "util.h"
|
2009-06-12 15:49:20 +08:00
|
|
|
#include "trace_gfs2.h"
|
2006-01-17 00:50:04 +08:00
|
|
|
|
|
|
|
/* This doesn't need to be that large as max 64 bit pointers in a 4k
|
|
|
|
* block is 512, so __u16 is fine for that. It saves stack space to
|
|
|
|
* keep it small.
|
|
|
|
*/
|
|
|
|
struct metapath {
|
2008-01-29 17:12:55 +08:00
|
|
|
struct buffer_head *mp_bh[GFS2_MAX_META_HEIGHT];
|
2006-01-17 00:50:04 +08:00
|
|
|
__u16 mp_list[GFS2_MAX_META_HEIGHT];
|
|
|
|
};
|
|
|
|
|
2006-07-26 22:51:20 +08:00
|
|
|
/**
|
|
|
|
* gfs2_unstuffer_page - unstuff a stuffed inode into a block cached by a page
|
|
|
|
* @ip: the inode
|
|
|
|
* @dibh: the dinode buffer
|
|
|
|
* @block: the block number that was allocated
|
2010-08-11 16:37:53 +08:00
|
|
|
* @page: The (optional) page. This is looked up if @page is NULL
|
2006-07-26 22:51:20 +08:00
|
|
|
*
|
|
|
|
* Returns: errno
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
|
2006-09-05 00:49:07 +08:00
|
|
|
u64 block, struct page *page)
|
2006-07-26 22:51:20 +08:00
|
|
|
{
|
|
|
|
struct inode *inode = &ip->i_inode;
|
|
|
|
struct buffer_head *bh;
|
|
|
|
int release = 0;
|
|
|
|
|
|
|
|
if (!page || page->index) {
|
2012-03-20 03:25:50 +08:00
|
|
|
page = find_or_create_page(inode->i_mapping, 0, GFP_NOFS);
|
2006-07-26 22:51:20 +08:00
|
|
|
if (!page)
|
|
|
|
return -ENOMEM;
|
|
|
|
release = 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!PageUptodate(page)) {
|
|
|
|
void *kaddr = kmap(page);
|
2010-03-25 22:32:43 +08:00
|
|
|
u64 dsize = i_size_read(inode);
|
|
|
|
|
|
|
|
if (dsize > (dibh->b_size - sizeof(struct gfs2_dinode)))
|
|
|
|
dsize = dibh->b_size - sizeof(struct gfs2_dinode);
|
2006-07-26 22:51:20 +08:00
|
|
|
|
2010-03-25 22:32:43 +08:00
|
|
|
memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize);
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
memset(kaddr + dsize, 0, PAGE_SIZE - dsize);
|
2006-07-26 22:51:20 +08:00
|
|
|
kunmap(page);
|
|
|
|
|
|
|
|
SetPageUptodate(page);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!page_has_buffers(page))
|
2016-08-03 01:05:27 +08:00
|
|
|
create_empty_buffers(page, BIT(inode->i_blkbits),
|
|
|
|
BIT(BH_Uptodate));
|
2006-07-26 22:51:20 +08:00
|
|
|
|
|
|
|
bh = page_buffers(page);
|
|
|
|
|
|
|
|
if (!buffer_mapped(bh))
|
|
|
|
map_bh(bh, inode->i_sb, block);
|
|
|
|
|
|
|
|
set_buffer_uptodate(bh);
|
2007-08-27 16:49:37 +08:00
|
|
|
if (!gfs2_is_jdata(ip))
|
|
|
|
mark_buffer_dirty(bh);
|
2007-10-17 15:35:19 +08:00
|
|
|
if (!gfs2_is_writeback(ip))
|
2012-12-14 20:36:02 +08:00
|
|
|
gfs2_trans_add_data(ip->i_gl, bh);
|
2006-07-26 22:51:20 +08:00
|
|
|
|
|
|
|
if (release) {
|
|
|
|
unlock_page(page);
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
put_page(page);
|
2006-07-26 22:51:20 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2006-01-17 00:50:04 +08:00
|
|
|
/**
|
|
|
|
* gfs2_unstuff_dinode - Unstuff a dinode when the data has grown too big
|
|
|
|
* @ip: The GFS2 inode to unstuff
|
2010-08-11 16:37:53 +08:00
|
|
|
* @page: The (optional) page. This is looked up if the @page is NULL
|
2006-01-17 00:50:04 +08:00
|
|
|
*
|
|
|
|
* This routine unstuffs a dinode and returns it to a "normal" state such
|
|
|
|
* that the height can be grown in the traditional way.
|
|
|
|
*
|
|
|
|
* Returns: errno
|
|
|
|
*/
|
|
|
|
|
2006-07-26 22:51:20 +08:00
|
|
|
int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page)
|
2006-01-17 00:50:04 +08:00
|
|
|
{
|
|
|
|
struct buffer_head *bh, *dibh;
|
2006-10-03 00:39:19 +08:00
|
|
|
struct gfs2_dinode *di;
|
2006-09-05 00:49:07 +08:00
|
|
|
u64 block = 0;
|
2006-02-08 19:50:51 +08:00
|
|
|
int isdir = gfs2_is_dir(ip);
|
2006-01-17 00:50:04 +08:00
|
|
|
int error;
|
|
|
|
|
|
|
|
down_write(&ip->i_rw_mutex);
|
|
|
|
|
|
|
|
error = gfs2_meta_inode_buffer(ip, &dibh);
|
|
|
|
if (error)
|
|
|
|
goto out;
|
2006-09-25 21:26:04 +08:00
|
|
|
|
2010-08-11 16:53:11 +08:00
|
|
|
if (i_size_read(&ip->i_inode)) {
|
2006-01-17 00:50:04 +08:00
|
|
|
/* Get a free block, fill it with the stuffed data,
|
|
|
|
and write it out to disk */
|
|
|
|
|
2008-02-06 18:11:15 +08:00
|
|
|
unsigned int n = 1;
|
2011-11-18 23:58:32 +08:00
|
|
|
error = gfs2_alloc_blocks(ip, &block, &n, 0, NULL);
|
2009-05-20 17:48:47 +08:00
|
|
|
if (error)
|
|
|
|
goto out_brelse;
|
2006-02-08 19:50:51 +08:00
|
|
|
if (isdir) {
|
2008-02-01 21:16:55 +08:00
|
|
|
gfs2_trans_add_unrevoke(GFS2_SB(&ip->i_inode), block, 1);
|
2006-04-24 22:07:13 +08:00
|
|
|
error = gfs2_dir_get_new_buffer(ip, block, &bh);
|
2006-01-17 00:50:04 +08:00
|
|
|
if (error)
|
|
|
|
goto out_brelse;
|
2006-10-03 00:39:19 +08:00
|
|
|
gfs2_buffer_copy_tail(bh, sizeof(struct gfs2_meta_header),
|
2006-01-17 00:50:04 +08:00
|
|
|
dibh, sizeof(struct gfs2_dinode));
|
|
|
|
brelse(bh);
|
|
|
|
} else {
|
2006-07-26 22:51:20 +08:00
|
|
|
error = gfs2_unstuffer_page(ip, dibh, block, page);
|
2006-01-17 00:50:04 +08:00
|
|
|
if (error)
|
|
|
|
goto out_brelse;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Set up the pointer to the new block */
|
|
|
|
|
2012-12-14 20:36:02 +08:00
|
|
|
gfs2_trans_add_meta(ip->i_gl, dibh);
|
2006-10-03 00:39:19 +08:00
|
|
|
di = (struct gfs2_dinode *)dibh->b_data;
|
2006-01-17 00:50:04 +08:00
|
|
|
gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
|
|
|
|
|
2010-08-11 16:53:11 +08:00
|
|
|
if (i_size_read(&ip->i_inode)) {
|
2006-10-03 00:39:19 +08:00
|
|
|
*(__be64 *)(di + 1) = cpu_to_be64(block);
|
2008-02-12 22:17:27 +08:00
|
|
|
gfs2_add_inode_blocks(&ip->i_inode, 1);
|
|
|
|
di->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
2008-01-28 18:37:35 +08:00
|
|
|
ip->i_height = 1;
|
2006-10-03 00:39:19 +08:00
|
|
|
di->di_height = cpu_to_be16(1);
|
2006-01-17 00:50:04 +08:00
|
|
|
|
2006-09-05 00:04:26 +08:00
|
|
|
out_brelse:
|
2006-01-17 00:50:04 +08:00
|
|
|
brelse(dibh);
|
2006-09-05 00:04:26 +08:00
|
|
|
out:
|
2006-01-17 00:50:04 +08:00
|
|
|
up_write(&ip->i_rw_mutex);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
* find_metapath - Find path through the metadata tree
|
2008-02-23 00:09:31 +08:00
|
|
|
* @sdp: The superblock
|
2006-01-17 00:50:04 +08:00
|
|
|
* @mp: The metapath to return the result in
|
|
|
|
* @block: The disk block to look up
|
2008-02-23 00:09:31 +08:00
|
|
|
* @height: The pre-calculated height of the metadata tree
|
2006-01-17 00:50:04 +08:00
|
|
|
*
|
|
|
|
* This routine returns a struct metapath structure that defines a path
|
|
|
|
* through the metadata of inode "ip" to get to block "block".
|
|
|
|
*
|
|
|
|
* Example:
|
|
|
|
* Given: "ip" is a height 3 file, "offset" is 101342453, and this is a
|
|
|
|
* filesystem with a blocksize of 4096.
|
|
|
|
*
|
|
|
|
* find_metapath() would return a struct metapath structure set to:
|
|
|
|
* mp_offset = 101342453, mp_height = 3, mp_list[0] = 0, mp_list[1] = 48,
|
|
|
|
* and mp_list[2] = 165.
|
|
|
|
*
|
|
|
|
* That means that in order to get to the block containing the byte at
|
|
|
|
* offset 101342453, we would load the indirect block pointed to by pointer
|
|
|
|
* 0 in the dinode. We would then load the indirect block pointed to by
|
|
|
|
* pointer 48 in that indirect block. We would then load the data block
|
|
|
|
* pointed to by pointer 165 in that indirect block.
|
|
|
|
*
|
|
|
|
* ----------------------------------------
|
|
|
|
* | Dinode | |
|
|
|
|
* | | 4|
|
|
|
|
* | |0 1 2 3 4 5 9|
|
|
|
|
* | | 6|
|
|
|
|
* ----------------------------------------
|
|
|
|
* |
|
|
|
|
* |
|
|
|
|
* V
|
|
|
|
* ----------------------------------------
|
|
|
|
* | Indirect Block |
|
|
|
|
* | 5|
|
|
|
|
* | 4 4 4 4 4 5 5 1|
|
|
|
|
* |0 5 6 7 8 9 0 1 2|
|
|
|
|
* ----------------------------------------
|
|
|
|
* |
|
|
|
|
* |
|
|
|
|
* V
|
|
|
|
* ----------------------------------------
|
|
|
|
* | Indirect Block |
|
|
|
|
* | 1 1 1 1 1 5|
|
|
|
|
* | 6 6 6 6 6 1|
|
|
|
|
* |0 3 4 5 6 7 2|
|
|
|
|
* ----------------------------------------
|
|
|
|
* |
|
|
|
|
* |
|
|
|
|
* V
|
|
|
|
* ----------------------------------------
|
|
|
|
* | Data block containing offset |
|
|
|
|
* | 101342453 |
|
|
|
|
* | |
|
|
|
|
* | |
|
|
|
|
* ----------------------------------------
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
2008-02-23 00:09:31 +08:00
|
|
|
static void find_metapath(const struct gfs2_sbd *sdp, u64 block,
|
|
|
|
struct metapath *mp, unsigned int height)
|
2006-01-17 00:50:04 +08:00
|
|
|
{
|
|
|
|
unsigned int i;
|
|
|
|
|
2008-02-23 00:09:31 +08:00
|
|
|
for (i = height; i--;)
|
2008-01-29 01:24:35 +08:00
|
|
|
mp->mp_list[i] = do_div(block, sdp->sd_inptrs);
|
2006-01-17 00:50:04 +08:00
|
|
|
|
|
|
|
}
|
|
|
|
|
2008-06-25 01:53:38 +08:00
|
|
|
static inline unsigned int metapath_branch_start(const struct metapath *mp)
|
2008-02-23 00:09:31 +08:00
|
|
|
{
|
2008-06-25 01:53:38 +08:00
|
|
|
if (mp->mp_list[0] == 0)
|
|
|
|
return 2;
|
|
|
|
return 1;
|
2008-02-23 00:09:31 +08:00
|
|
|
}
|
|
|
|
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
/**
|
|
|
|
* metaptr1 - Return the first possible metadata pointer in a metaath buffer
|
|
|
|
* @height: The metadata height (0 = dinode)
|
|
|
|
* @mp: The metapath
|
|
|
|
*/
|
|
|
|
static inline __be64 *metaptr1(unsigned int height, const struct metapath *mp)
|
|
|
|
{
|
|
|
|
struct buffer_head *bh = mp->mp_bh[height];
|
|
|
|
if (height == 0)
|
|
|
|
return ((__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)));
|
|
|
|
return ((__be64 *)(bh->b_data + sizeof(struct gfs2_meta_header)));
|
|
|
|
}
|
|
|
|
|
2006-01-17 00:50:04 +08:00
|
|
|
/**
|
|
|
|
* metapointer - Return pointer to start of metadata in a buffer
|
|
|
|
* @height: The metadata height (0 = dinode)
|
|
|
|
* @mp: The metapath
|
|
|
|
*
|
|
|
|
* Return a pointer to the block number of the next height of the metadata
|
|
|
|
* tree given a buffer containing the pointer to the current height of the
|
|
|
|
* metadata tree.
|
|
|
|
*/
|
|
|
|
|
2008-02-23 00:09:31 +08:00
|
|
|
static inline __be64 *metapointer(unsigned int height, const struct metapath *mp)
|
2006-01-17 00:50:04 +08:00
|
|
|
{
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
__be64 *p = metaptr1(height, mp);
|
|
|
|
return p + mp->mp_list[height];
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
2011-09-21 18:05:16 +08:00
|
|
|
static void gfs2_metapath_ra(struct gfs2_glock *gl,
|
|
|
|
const struct buffer_head *bh, const __be64 *pos)
|
|
|
|
{
|
|
|
|
struct buffer_head *rabh;
|
|
|
|
const __be64 *endp = (const __be64 *)(bh->b_data + bh->b_size);
|
|
|
|
const __be64 *t;
|
|
|
|
|
|
|
|
for (t = pos; t < endp; t++) {
|
|
|
|
if (!*t)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
rabh = gfs2_getbuf(gl, be64_to_cpu(*t), CREATE);
|
|
|
|
if (trylock_buffer(rabh)) {
|
|
|
|
if (!buffer_uptodate(rabh)) {
|
|
|
|
rabh->b_end_io = end_buffer_read_sync;
|
gfs2: add flag REQ_PRIO for metadata I/O
When gfs2 does metadata I/O, only REQ_META is used as a metadata hint of
the bio. But flag REQ_META is just a hint for block trace, not for block
layer code to handle a bio as metadata request.
For some of metadata I/Os of gfs2, A REQ_PRIO flag on the metadata bio
would be very informative to block layer code. For example, if bcache is
used as a I/O cache for gfs2, it will be possible for bcache code to get
the hint and cache the pre-fetched metadata blocks on cache device. This
behavior may be helpful to improve metadata I/O performance if the
following requests hit the cache.
Here are the locations in gfs2 code where a REQ_PRIO flag should be added,
- All places where REQ_READAHEAD is used, gfs2 code uses this flag for
metadata read ahead.
- In gfs2_meta_rq() where the first metadata block is read in.
- In gfs2_write_buf_to_page(), read in quota metadata blocks to have them
up to date.
These metadata blocks are probably to be accessed again in future, adding
a REQ_PRIO flag may have bcache to keep such metadata in fast cache
device. For system without a cache layer, REQ_PRIO can still provide hint
to block layer to handle metadata requests more properly.
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-07-21 20:48:22 +08:00
|
|
|
submit_bh(REQ_OP_READ,
|
|
|
|
REQ_RAHEAD | REQ_META | REQ_PRIO,
|
|
|
|
rabh);
|
2011-09-21 18:05:16 +08:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
unlock_buffer(rabh);
|
|
|
|
}
|
|
|
|
brelse(rabh);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
/**
|
|
|
|
* lookup_mp_height - helper function for lookup_metapath
|
|
|
|
* @ip: the inode
|
|
|
|
* @mp: the metapath
|
|
|
|
* @h: the height which needs looking up
|
|
|
|
*/
|
|
|
|
static int lookup_mp_height(struct gfs2_inode *ip, struct metapath *mp, int h)
|
|
|
|
{
|
|
|
|
__be64 *ptr = metapointer(h, mp);
|
|
|
|
u64 dblock = be64_to_cpu(*ptr);
|
|
|
|
|
|
|
|
if (!dblock)
|
|
|
|
return h + 1;
|
|
|
|
|
|
|
|
return gfs2_meta_indirect_buffer(ip, h + 1, dblock, &mp->mp_bh[h + 1]);
|
|
|
|
}
|
|
|
|
|
2006-01-17 00:50:04 +08:00
|
|
|
/**
|
2008-02-23 00:09:31 +08:00
|
|
|
* lookup_metapath - Walk the metadata tree to a specific point
|
|
|
|
* @ip: The inode
|
2006-01-17 00:50:04 +08:00
|
|
|
* @mp: The metapath
|
|
|
|
*
|
2008-02-23 00:09:31 +08:00
|
|
|
* Assumes that the inode's buffer has already been looked up and
|
|
|
|
* hooked onto mp->mp_bh[0] and that the metapath has been initialised
|
|
|
|
* by find_metapath().
|
|
|
|
*
|
|
|
|
* If this function encounters part of the tree which has not been
|
|
|
|
* allocated, it returns the current height of the tree at the point
|
|
|
|
* at which it found the unallocated block. Blocks which are found are
|
|
|
|
* added to the mp->mp_bh[] list.
|
2006-01-17 00:50:04 +08:00
|
|
|
*
|
2008-02-23 00:09:31 +08:00
|
|
|
* Returns: error or height of metadata tree
|
2006-01-17 00:50:04 +08:00
|
|
|
*/
|
|
|
|
|
2008-02-23 00:09:31 +08:00
|
|
|
static int lookup_metapath(struct gfs2_inode *ip, struct metapath *mp)
|
2008-01-28 23:10:29 +08:00
|
|
|
{
|
|
|
|
unsigned int end_of_metadata = ip->i_height - 1;
|
|
|
|
unsigned int x;
|
2008-02-12 22:48:39 +08:00
|
|
|
int ret;
|
2008-01-28 23:10:29 +08:00
|
|
|
|
|
|
|
for (x = 0; x < end_of_metadata; x++) {
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
ret = lookup_mp_height(ip, mp, x);
|
2008-01-28 23:10:29 +08:00
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2008-02-23 00:09:31 +08:00
|
|
|
return ip->i_height;
|
2008-01-29 17:12:55 +08:00
|
|
|
}
|
|
|
|
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
/**
|
|
|
|
* fillup_metapath - fill up buffers for the metadata path to a specific height
|
|
|
|
* @ip: The inode
|
|
|
|
* @mp: The metapath
|
|
|
|
* @h: The height to which it should be mapped
|
|
|
|
*
|
|
|
|
* Similar to lookup_metapath, but does lookups for a range of heights
|
|
|
|
*
|
|
|
|
* Returns: error or height of metadata tree
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int fillup_metapath(struct gfs2_inode *ip, struct metapath *mp, int h)
|
|
|
|
{
|
|
|
|
unsigned int start_h = h - 1;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (h) {
|
|
|
|
/* find the first buffer we need to look up. */
|
|
|
|
while (start_h > 0 && mp->mp_bh[start_h] == NULL)
|
|
|
|
start_h--;
|
|
|
|
for (; start_h < h; start_h++) {
|
|
|
|
ret = lookup_mp_height(ip, mp, start_h);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return ip->i_height;
|
|
|
|
}
|
|
|
|
|
2008-02-23 00:09:31 +08:00
|
|
|
static inline void release_metapath(struct metapath *mp)
|
2008-01-29 17:12:55 +08:00
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
2008-02-23 00:09:31 +08:00
|
|
|
for (i = 0; i < GFS2_MAX_META_HEIGHT; i++) {
|
|
|
|
if (mp->mp_bh[i] == NULL)
|
|
|
|
break;
|
|
|
|
brelse(mp->mp_bh[i]);
|
|
|
|
}
|
2008-01-28 23:10:29 +08:00
|
|
|
}
|
|
|
|
|
2008-02-08 21:18:11 +08:00
|
|
|
/**
|
|
|
|
* gfs2_extent_length - Returns length of an extent of blocks
|
|
|
|
* @start: Start of the buffer
|
|
|
|
* @len: Length of the buffer in bytes
|
|
|
|
* @ptr: Current position in the buffer
|
|
|
|
* @limit: Max extent length to return (0 = unlimited)
|
|
|
|
* @eob: Set to 1 if we hit "end of block"
|
|
|
|
*
|
|
|
|
* If the first block is zero (unallocated) it will return the number of
|
|
|
|
* unallocated blocks in the extent, otherwise it will return the number
|
|
|
|
* of contiguous blocks in the extent.
|
|
|
|
*
|
|
|
|
* Returns: The length of the extent (minimum of one block)
|
|
|
|
*/
|
|
|
|
|
2014-08-06 21:08:36 +08:00
|
|
|
static inline unsigned int gfs2_extent_length(void *start, unsigned int len, __be64 *ptr, size_t limit, int *eob)
|
2008-02-08 21:18:11 +08:00
|
|
|
{
|
|
|
|
const __be64 *end = (start + len);
|
|
|
|
const __be64 *first = ptr;
|
|
|
|
u64 d = be64_to_cpu(*ptr);
|
|
|
|
|
|
|
|
*eob = 0;
|
|
|
|
do {
|
|
|
|
ptr++;
|
|
|
|
if (ptr >= end)
|
|
|
|
break;
|
|
|
|
if (limit && --limit == 0)
|
|
|
|
break;
|
|
|
|
if (d)
|
|
|
|
d++;
|
|
|
|
} while(be64_to_cpu(*ptr) == d);
|
|
|
|
if (ptr >= end)
|
|
|
|
*eob = 1;
|
|
|
|
return (ptr - first);
|
|
|
|
}
|
|
|
|
|
2008-02-23 00:09:31 +08:00
|
|
|
static inline void bmap_lock(struct gfs2_inode *ip, int create)
|
2006-11-16 04:21:06 +08:00
|
|
|
{
|
|
|
|
if (create)
|
|
|
|
down_write(&ip->i_rw_mutex);
|
|
|
|
else
|
|
|
|
down_read(&ip->i_rw_mutex);
|
|
|
|
}
|
|
|
|
|
2008-02-23 00:09:31 +08:00
|
|
|
static inline void bmap_unlock(struct gfs2_inode *ip, int create)
|
2006-11-16 04:21:06 +08:00
|
|
|
{
|
|
|
|
if (create)
|
|
|
|
up_write(&ip->i_rw_mutex);
|
|
|
|
else
|
|
|
|
up_read(&ip->i_rw_mutex);
|
|
|
|
}
|
|
|
|
|
2008-02-23 00:09:31 +08:00
|
|
|
static inline __be64 *gfs2_indirect_init(struct metapath *mp,
|
|
|
|
struct gfs2_glock *gl, unsigned int i,
|
|
|
|
unsigned offset, u64 bn)
|
|
|
|
{
|
|
|
|
__be64 *ptr = (__be64 *)(mp->mp_bh[i - 1]->b_data +
|
|
|
|
((i > 1) ? sizeof(struct gfs2_meta_header) :
|
|
|
|
sizeof(struct gfs2_dinode)));
|
|
|
|
BUG_ON(i < 1);
|
|
|
|
BUG_ON(mp->mp_bh[i] != NULL);
|
|
|
|
mp->mp_bh[i] = gfs2_meta_new(gl, bn);
|
2012-12-14 20:36:02 +08:00
|
|
|
gfs2_trans_add_meta(gl, mp->mp_bh[i]);
|
2008-02-23 00:09:31 +08:00
|
|
|
gfs2_metatype_set(mp->mp_bh[i], GFS2_METATYPE_IN, GFS2_FORMAT_IN);
|
|
|
|
gfs2_buffer_clear_tail(mp->mp_bh[i], sizeof(struct gfs2_meta_header));
|
|
|
|
ptr += offset;
|
|
|
|
*ptr = cpu_to_be64(bn);
|
|
|
|
return ptr;
|
|
|
|
}
|
|
|
|
|
|
|
|
enum alloc_state {
|
|
|
|
ALLOC_DATA = 0,
|
|
|
|
ALLOC_GROW_DEPTH = 1,
|
|
|
|
ALLOC_GROW_HEIGHT = 2,
|
|
|
|
/* ALLOC_UNSTUFF = 3, TBD and rather complicated */
|
|
|
|
};
|
|
|
|
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
static inline unsigned int hptrs(struct gfs2_sbd *sdp, const unsigned int hgt)
|
|
|
|
{
|
|
|
|
if (hgt)
|
|
|
|
return sdp->sd_inptrs;
|
|
|
|
return sdp->sd_diptrs;
|
|
|
|
}
|
|
|
|
|
2008-02-23 00:09:31 +08:00
|
|
|
/**
|
|
|
|
* gfs2_bmap_alloc - Build a metadata tree of the requested height
|
|
|
|
* @inode: The GFS2 inode
|
|
|
|
* @lblock: The logical starting block of the extent
|
|
|
|
* @bh_map: This is used to return the mapping details
|
|
|
|
* @mp: The metapath
|
|
|
|
* @sheight: The starting height (i.e. whats already mapped)
|
|
|
|
* @height: The height to build to
|
|
|
|
* @maxlen: The max number of data blocks to alloc
|
|
|
|
*
|
|
|
|
* In this routine we may have to alloc:
|
|
|
|
* i) Indirect blocks to grow the metadata tree height
|
|
|
|
* ii) Indirect blocks to fill in lower part of the metadata tree
|
|
|
|
* iii) Data blocks
|
|
|
|
*
|
|
|
|
* The function is in two parts. The first part works out the total
|
|
|
|
* number of blocks which we need. The second part does the actual
|
|
|
|
* allocation asking for an extent at a time (if enough contiguous free
|
|
|
|
* blocks are available, there will only be one request per bmap call)
|
|
|
|
* and uses the state machine to initialise the blocks in order.
|
|
|
|
*
|
|
|
|
* Returns: errno on error
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
|
|
|
|
struct buffer_head *bh_map, struct metapath *mp,
|
|
|
|
const unsigned int sheight,
|
|
|
|
const unsigned int height,
|
2014-08-06 21:08:36 +08:00
|
|
|
const size_t maxlen)
|
2008-02-23 00:09:31 +08:00
|
|
|
{
|
|
|
|
struct gfs2_inode *ip = GFS2_I(inode);
|
|
|
|
struct gfs2_sbd *sdp = GFS2_SB(inode);
|
2011-09-13 07:15:24 +08:00
|
|
|
struct super_block *sb = sdp->sd_vfs;
|
2008-02-23 00:09:31 +08:00
|
|
|
struct buffer_head *dibh = mp->mp_bh[0];
|
|
|
|
u64 bn, dblock = 0;
|
2008-06-25 01:53:38 +08:00
|
|
|
unsigned n, i, blks, alloced = 0, iblks = 0, branch_start = 0;
|
2008-02-23 00:09:31 +08:00
|
|
|
unsigned dblks = 0;
|
|
|
|
unsigned ptrs_per_blk;
|
|
|
|
const unsigned end_of_metadata = height - 1;
|
2011-09-13 07:15:24 +08:00
|
|
|
int ret;
|
2008-02-23 00:09:31 +08:00
|
|
|
int eob = 0;
|
|
|
|
enum alloc_state state;
|
|
|
|
__be64 *ptr;
|
|
|
|
__be64 zero_bn = 0;
|
|
|
|
|
|
|
|
BUG_ON(sheight < 1);
|
|
|
|
BUG_ON(dibh == NULL);
|
|
|
|
|
2012-12-14 20:36:02 +08:00
|
|
|
gfs2_trans_add_meta(ip->i_gl, dibh);
|
2008-02-23 00:09:31 +08:00
|
|
|
|
|
|
|
if (height == sheight) {
|
|
|
|
struct buffer_head *bh;
|
|
|
|
/* Bottom indirect block exists, find unalloced extent size */
|
|
|
|
ptr = metapointer(end_of_metadata, mp);
|
|
|
|
bh = mp->mp_bh[end_of_metadata];
|
|
|
|
dblks = gfs2_extent_length(bh->b_data, bh->b_size, ptr, maxlen,
|
|
|
|
&eob);
|
|
|
|
BUG_ON(dblks < 1);
|
|
|
|
state = ALLOC_DATA;
|
|
|
|
} else {
|
|
|
|
/* Need to allocate indirect blocks */
|
|
|
|
ptrs_per_blk = height > 1 ? sdp->sd_inptrs : sdp->sd_diptrs;
|
2014-08-06 21:08:36 +08:00
|
|
|
dblks = min(maxlen, (size_t)(ptrs_per_blk -
|
|
|
|
mp->mp_list[end_of_metadata]));
|
2008-02-23 00:09:31 +08:00
|
|
|
if (height == ip->i_height) {
|
|
|
|
/* Writing into existing tree, extend tree down */
|
|
|
|
iblks = height - sheight;
|
|
|
|
state = ALLOC_GROW_DEPTH;
|
|
|
|
} else {
|
|
|
|
/* Building up tree height */
|
|
|
|
state = ALLOC_GROW_HEIGHT;
|
|
|
|
iblks = height - ip->i_height;
|
2008-06-25 01:53:38 +08:00
|
|
|
branch_start = metapath_branch_start(mp);
|
|
|
|
iblks += (height - branch_start);
|
2008-02-23 00:09:31 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* start of the second part of the function (state machine) */
|
|
|
|
|
|
|
|
blks = dblks + iblks;
|
|
|
|
i = sheight;
|
|
|
|
do {
|
2009-05-20 17:48:47 +08:00
|
|
|
int error;
|
2008-02-23 00:09:31 +08:00
|
|
|
n = blks - alloced;
|
2011-11-18 23:58:32 +08:00
|
|
|
error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL);
|
2009-05-20 17:48:47 +08:00
|
|
|
if (error)
|
|
|
|
return error;
|
2008-02-23 00:09:31 +08:00
|
|
|
alloced += n;
|
|
|
|
if (state != ALLOC_DATA || gfs2_is_jdata(ip))
|
|
|
|
gfs2_trans_add_unrevoke(sdp, bn, n);
|
|
|
|
switch (state) {
|
|
|
|
/* Growing height of tree */
|
|
|
|
case ALLOC_GROW_HEIGHT:
|
|
|
|
if (i == 1) {
|
|
|
|
ptr = (__be64 *)(dibh->b_data +
|
|
|
|
sizeof(struct gfs2_dinode));
|
|
|
|
zero_bn = *ptr;
|
|
|
|
}
|
|
|
|
for (; i - 1 < height - ip->i_height && n > 0; i++, n--)
|
|
|
|
gfs2_indirect_init(mp, ip->i_gl, i, 0, bn++);
|
|
|
|
if (i - 1 == height - ip->i_height) {
|
|
|
|
i--;
|
|
|
|
gfs2_buffer_copy_tail(mp->mp_bh[i],
|
|
|
|
sizeof(struct gfs2_meta_header),
|
|
|
|
dibh, sizeof(struct gfs2_dinode));
|
|
|
|
gfs2_buffer_clear_tail(dibh,
|
|
|
|
sizeof(struct gfs2_dinode) +
|
|
|
|
sizeof(__be64));
|
|
|
|
ptr = (__be64 *)(mp->mp_bh[i]->b_data +
|
|
|
|
sizeof(struct gfs2_meta_header));
|
|
|
|
*ptr = zero_bn;
|
|
|
|
state = ALLOC_GROW_DEPTH;
|
2008-06-25 01:53:38 +08:00
|
|
|
for(i = branch_start; i < height; i++) {
|
2008-02-23 00:09:31 +08:00
|
|
|
if (mp->mp_bh[i] == NULL)
|
|
|
|
break;
|
|
|
|
brelse(mp->mp_bh[i]);
|
|
|
|
mp->mp_bh[i] = NULL;
|
|
|
|
}
|
2008-06-25 01:53:38 +08:00
|
|
|
i = branch_start;
|
2008-02-23 00:09:31 +08:00
|
|
|
}
|
|
|
|
if (n == 0)
|
|
|
|
break;
|
|
|
|
/* Branching from existing tree */
|
|
|
|
case ALLOC_GROW_DEPTH:
|
|
|
|
if (i > 1 && i < height)
|
2012-12-14 20:36:02 +08:00
|
|
|
gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[i-1]);
|
2008-02-23 00:09:31 +08:00
|
|
|
for (; i < height && n > 0; i++, n--)
|
|
|
|
gfs2_indirect_init(mp, ip->i_gl, i,
|
|
|
|
mp->mp_list[i-1], bn++);
|
|
|
|
if (i == height)
|
|
|
|
state = ALLOC_DATA;
|
|
|
|
if (n == 0)
|
|
|
|
break;
|
|
|
|
/* Tree complete, adding data blocks */
|
|
|
|
case ALLOC_DATA:
|
|
|
|
BUG_ON(n > dblks);
|
|
|
|
BUG_ON(mp->mp_bh[end_of_metadata] == NULL);
|
2012-12-14 20:36:02 +08:00
|
|
|
gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[end_of_metadata]);
|
2008-02-23 00:09:31 +08:00
|
|
|
dblks = n;
|
|
|
|
ptr = metapointer(end_of_metadata, mp);
|
|
|
|
dblock = bn;
|
|
|
|
while (n-- > 0)
|
|
|
|
*ptr++ = cpu_to_be64(bn++);
|
2011-09-13 07:15:24 +08:00
|
|
|
if (buffer_zeronew(bh_map)) {
|
|
|
|
ret = sb_issue_zeroout(sb, dblock, dblks,
|
|
|
|
GFP_NOFS);
|
|
|
|
if (ret) {
|
|
|
|
fs_err(sdp,
|
|
|
|
"Failed to zero data buffers\n");
|
|
|
|
clear_buffer_zeronew(bh_map);
|
|
|
|
}
|
|
|
|
}
|
2008-02-23 00:09:31 +08:00
|
|
|
break;
|
|
|
|
}
|
2010-02-12 18:10:55 +08:00
|
|
|
} while ((state != ALLOC_DATA) || !dblock);
|
2008-02-23 00:09:31 +08:00
|
|
|
|
|
|
|
ip->i_height = height;
|
|
|
|
gfs2_add_inode_blocks(&ip->i_inode, alloced);
|
|
|
|
gfs2_dinode_out(ip, mp->mp_bh[0]->b_data);
|
|
|
|
map_bh(bh_map, inode->i_sb, dblock);
|
|
|
|
bh_map->b_size = dblks << inode->i_blkbits;
|
|
|
|
set_buffer_new(bh_map);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2006-01-17 00:50:04 +08:00
|
|
|
/**
|
2006-11-16 04:21:06 +08:00
|
|
|
* gfs2_block_map - Map a block from an inode to a disk block
|
2006-05-06 04:59:11 +08:00
|
|
|
* @inode: The inode
|
2006-01-17 00:50:04 +08:00
|
|
|
* @lblock: The logical block number
|
2006-11-16 04:21:06 +08:00
|
|
|
* @bh_map: The bh to be mapped
|
2008-02-23 00:09:31 +08:00
|
|
|
* @create: True if its ok to alloc blocks to satify the request
|
2006-01-17 00:50:04 +08:00
|
|
|
*
|
2008-02-23 00:09:31 +08:00
|
|
|
* Sets buffer_mapped() if successful, sets buffer_boundary() if a
|
|
|
|
* read of metadata will be required before the next block can be
|
|
|
|
* mapped. Sets buffer_new() if new blocks were allocated.
|
2006-01-17 00:50:04 +08:00
|
|
|
*
|
|
|
|
* Returns: errno
|
|
|
|
*/
|
|
|
|
|
2007-12-11 04:13:27 +08:00
|
|
|
int gfs2_block_map(struct inode *inode, sector_t lblock,
|
|
|
|
struct buffer_head *bh_map, int create)
|
2006-01-17 00:50:04 +08:00
|
|
|
{
|
2006-06-15 03:32:57 +08:00
|
|
|
struct gfs2_inode *ip = GFS2_I(inode);
|
|
|
|
struct gfs2_sbd *sdp = GFS2_SB(inode);
|
2008-01-28 18:37:35 +08:00
|
|
|
unsigned int bsize = sdp->sd_sb.sb_bsize;
|
2014-08-06 21:08:36 +08:00
|
|
|
const size_t maxlen = bh_map->b_size >> inode->i_blkbits;
|
2008-01-28 18:37:35 +08:00
|
|
|
const u64 *arr = sdp->sd_heightsize;
|
2008-02-23 00:09:31 +08:00
|
|
|
__be64 *ptr;
|
|
|
|
u64 size;
|
|
|
|
struct metapath mp;
|
|
|
|
int ret;
|
|
|
|
int eob;
|
|
|
|
unsigned int len;
|
|
|
|
struct buffer_head *bh;
|
|
|
|
u8 height;
|
2006-09-22 05:05:23 +08:00
|
|
|
|
2008-02-23 00:09:31 +08:00
|
|
|
BUG_ON(maxlen == 0);
|
2006-01-17 00:50:04 +08:00
|
|
|
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
memset(&mp, 0, sizeof(mp));
|
2008-02-23 00:09:31 +08:00
|
|
|
bmap_lock(ip, create);
|
2006-11-16 04:21:06 +08:00
|
|
|
clear_buffer_mapped(bh_map);
|
|
|
|
clear_buffer_new(bh_map);
|
|
|
|
clear_buffer_boundary(bh_map);
|
2009-06-12 15:49:20 +08:00
|
|
|
trace_gfs2_bmap(ip, bh_map, lblock, create, 1);
|
2008-01-28 18:37:35 +08:00
|
|
|
if (gfs2_is_dir(ip)) {
|
|
|
|
bsize = sdp->sd_jbsize;
|
|
|
|
arr = sdp->sd_jheightsize;
|
|
|
|
}
|
2006-11-16 04:21:06 +08:00
|
|
|
|
2008-02-23 00:09:31 +08:00
|
|
|
ret = gfs2_meta_inode_buffer(ip, &mp.mp_bh[0]);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
2006-01-17 00:50:04 +08:00
|
|
|
|
2008-02-23 00:09:31 +08:00
|
|
|
height = ip->i_height;
|
|
|
|
size = (lblock + 1) * bsize;
|
|
|
|
while (size > arr[height])
|
|
|
|
height++;
|
|
|
|
find_metapath(sdp, lblock, &mp, height);
|
|
|
|
ret = 1;
|
|
|
|
if (height > ip->i_height || gfs2_is_stuffed(ip))
|
|
|
|
goto do_alloc;
|
|
|
|
ret = lookup_metapath(ip, &mp);
|
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
|
|
|
if (ret != ip->i_height)
|
|
|
|
goto do_alloc;
|
|
|
|
ptr = metapointer(ip->i_height - 1, &mp);
|
|
|
|
if (*ptr == 0)
|
|
|
|
goto do_alloc;
|
|
|
|
map_bh(bh_map, inode->i_sb, be64_to_cpu(*ptr));
|
|
|
|
bh = mp.mp_bh[ip->i_height - 1];
|
|
|
|
len = gfs2_extent_length(bh->b_data, bh->b_size, ptr, maxlen, &eob);
|
|
|
|
bh_map->b_size = (len << inode->i_blkbits);
|
|
|
|
if (eob)
|
|
|
|
set_buffer_boundary(bh_map);
|
|
|
|
ret = 0;
|
|
|
|
out:
|
|
|
|
release_metapath(&mp);
|
2009-06-12 15:49:20 +08:00
|
|
|
trace_gfs2_bmap(ip, bh_map, lblock, create, ret);
|
2008-02-23 00:09:31 +08:00
|
|
|
bmap_unlock(ip, create);
|
|
|
|
return ret;
|
2008-02-08 21:18:11 +08:00
|
|
|
|
2008-02-23 00:09:31 +08:00
|
|
|
do_alloc:
|
|
|
|
/* All allocations are done here, firstly check create flag */
|
|
|
|
if (!create) {
|
|
|
|
BUG_ON(gfs2_is_stuffed(ip));
|
|
|
|
ret = 0;
|
|
|
|
goto out;
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
2008-02-23 00:09:31 +08:00
|
|
|
|
|
|
|
/* At this point ret is the tree depth of already allocated blocks */
|
|
|
|
ret = gfs2_bmap_alloc(inode, lblock, bh_map, &mp, ret, height, maxlen);
|
|
|
|
goto out;
|
2006-05-06 04:59:11 +08:00
|
|
|
}
|
|
|
|
|
2008-01-28 16:47:38 +08:00
|
|
|
/*
|
|
|
|
* Deprecated: do not use in new code
|
|
|
|
*/
|
2006-05-06 04:59:11 +08:00
|
|
|
int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsigned *extlen)
|
|
|
|
{
|
2006-10-14 05:25:45 +08:00
|
|
|
struct buffer_head bh = { .b_state = 0, .b_blocknr = 0 };
|
2006-09-19 05:18:23 +08:00
|
|
|
int ret;
|
2006-05-06 04:59:11 +08:00
|
|
|
int create = *new;
|
|
|
|
|
|
|
|
BUG_ON(!extlen);
|
|
|
|
BUG_ON(!dblock);
|
|
|
|
BUG_ON(!new);
|
|
|
|
|
2016-08-03 01:05:27 +08:00
|
|
|
bh.b_size = BIT(inode->i_blkbits + (create ? 0 : 5));
|
2007-12-11 04:13:27 +08:00
|
|
|
ret = gfs2_block_map(inode, lblock, &bh, create);
|
2006-09-19 05:18:23 +08:00
|
|
|
*extlen = bh.b_size >> inode->i_blkbits;
|
|
|
|
*dblock = bh.b_blocknr;
|
|
|
|
if (buffer_new(&bh))
|
|
|
|
*new = 1;
|
|
|
|
else
|
|
|
|
*new = 0;
|
|
|
|
return ret;
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
2006-07-26 23:27:10 +08:00
|
|
|
/**
|
|
|
|
* gfs2_block_truncate_page - Deal with zeroing out data for truncate
|
|
|
|
*
|
|
|
|
* This is partly borrowed from ext3.
|
|
|
|
*/
|
2010-08-11 16:37:53 +08:00
|
|
|
static int gfs2_block_truncate_page(struct address_space *mapping, loff_t from)
|
2006-07-26 23:27:10 +08:00
|
|
|
{
|
|
|
|
struct inode *inode = mapping->host;
|
|
|
|
struct gfs2_inode *ip = GFS2_I(inode);
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
unsigned long index = from >> PAGE_SHIFT;
|
|
|
|
unsigned offset = from & (PAGE_SIZE-1);
|
2006-07-26 23:27:10 +08:00
|
|
|
unsigned blocksize, iblock, length, pos;
|
|
|
|
struct buffer_head *bh;
|
|
|
|
struct page *page;
|
|
|
|
int err;
|
|
|
|
|
2012-03-20 03:25:50 +08:00
|
|
|
page = find_or_create_page(mapping, index, GFP_NOFS);
|
2006-07-26 23:27:10 +08:00
|
|
|
if (!page)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
blocksize = inode->i_sb->s_blocksize;
|
|
|
|
length = blocksize - (offset & (blocksize - 1));
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
iblock = index << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits);
|
2006-07-26 23:27:10 +08:00
|
|
|
|
|
|
|
if (!page_has_buffers(page))
|
|
|
|
create_empty_buffers(page, blocksize, 0);
|
|
|
|
|
|
|
|
/* Find the buffer that contains "offset" */
|
|
|
|
bh = page_buffers(page);
|
|
|
|
pos = blocksize;
|
|
|
|
while (offset >= pos) {
|
|
|
|
bh = bh->b_this_page;
|
|
|
|
iblock++;
|
|
|
|
pos += blocksize;
|
|
|
|
}
|
|
|
|
|
|
|
|
err = 0;
|
|
|
|
|
|
|
|
if (!buffer_mapped(bh)) {
|
2007-12-11 04:13:27 +08:00
|
|
|
gfs2_block_map(inode, iblock, bh, 0);
|
2006-07-26 23:27:10 +08:00
|
|
|
/* unmapped? It's a hole - nothing to do */
|
|
|
|
if (!buffer_mapped(bh))
|
|
|
|
goto unlock;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Ok, it's mapped. Make sure it's up-to-date */
|
|
|
|
if (PageUptodate(page))
|
|
|
|
set_buffer_uptodate(bh);
|
|
|
|
|
|
|
|
if (!buffer_uptodate(bh)) {
|
|
|
|
err = -EIO;
|
2016-06-06 03:31:44 +08:00
|
|
|
ll_rw_block(REQ_OP_READ, 0, 1, &bh);
|
2006-07-26 23:27:10 +08:00
|
|
|
wait_on_buffer(bh);
|
|
|
|
/* Uhhuh. Read error. Complain and punt. */
|
|
|
|
if (!buffer_uptodate(bh))
|
|
|
|
goto unlock;
|
2007-06-26 09:14:31 +08:00
|
|
|
err = 0;
|
2006-07-26 23:27:10 +08:00
|
|
|
}
|
|
|
|
|
2007-10-17 15:35:19 +08:00
|
|
|
if (!gfs2_is_writeback(ip))
|
2012-12-14 20:36:02 +08:00
|
|
|
gfs2_trans_add_data(ip->i_gl, bh);
|
2006-07-26 23:27:10 +08:00
|
|
|
|
2008-02-05 14:28:29 +08:00
|
|
|
zero_user(page, offset, length);
|
2009-06-10 16:09:40 +08:00
|
|
|
mark_buffer_dirty(bh);
|
2006-07-26 23:27:10 +08:00
|
|
|
unlock:
|
|
|
|
unlock_page(page);
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
|
|
|
put_page(page);
|
2006-07-26 23:27:10 +08:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2014-05-15 00:32:31 +08:00
|
|
|
#define GFS2_JTRUNC_REVOKES 8192
|
|
|
|
|
2012-11-13 17:50:28 +08:00
|
|
|
/**
|
|
|
|
* gfs2_journaled_truncate - Wrapper for truncate_pagecache for jdata files
|
|
|
|
* @inode: The inode being truncated
|
|
|
|
* @oldsize: The original (larger) size
|
|
|
|
* @newsize: The new smaller size
|
|
|
|
*
|
|
|
|
* With jdata files, we have to journal a revoke for each block which is
|
|
|
|
* truncated. As a result, we need to split this into separate transactions
|
|
|
|
* if the number of pages being truncated gets too large.
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int gfs2_journaled_truncate(struct inode *inode, u64 oldsize, u64 newsize)
|
|
|
|
{
|
|
|
|
struct gfs2_sbd *sdp = GFS2_SB(inode);
|
|
|
|
u64 max_chunk = GFS2_JTRUNC_REVOKES * sdp->sd_vfs->s_blocksize;
|
|
|
|
u64 chunk;
|
|
|
|
int error;
|
|
|
|
|
|
|
|
while (oldsize != newsize) {
|
|
|
|
chunk = oldsize - newsize;
|
|
|
|
if (chunk > max_chunk)
|
|
|
|
chunk = max_chunk;
|
2013-09-13 06:13:56 +08:00
|
|
|
truncate_pagecache(inode, oldsize - chunk);
|
2012-11-13 17:50:28 +08:00
|
|
|
oldsize -= chunk;
|
|
|
|
gfs2_trans_end(sdp);
|
|
|
|
error = gfs2_trans_begin(sdp, RES_DINODE, GFS2_JTRUNC_REVOKES);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2010-08-11 16:37:53 +08:00
|
|
|
static int trunc_start(struct inode *inode, u64 oldsize, u64 newsize)
|
2006-01-17 00:50:04 +08:00
|
|
|
{
|
2010-08-11 16:37:53 +08:00
|
|
|
struct gfs2_inode *ip = GFS2_I(inode);
|
|
|
|
struct gfs2_sbd *sdp = GFS2_SB(inode);
|
|
|
|
struct address_space *mapping = inode->i_mapping;
|
2006-01-17 00:50:04 +08:00
|
|
|
struct buffer_head *dibh;
|
|
|
|
int journaled = gfs2_is_jdata(ip);
|
|
|
|
int error;
|
|
|
|
|
2012-11-13 17:50:28 +08:00
|
|
|
if (journaled)
|
|
|
|
error = gfs2_trans_begin(sdp, RES_DINODE + RES_JDATA, GFS2_JTRUNC_REVOKES);
|
|
|
|
else
|
|
|
|
error = gfs2_trans_begin(sdp, RES_DINODE, 0);
|
2006-01-17 00:50:04 +08:00
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
error = gfs2_meta_inode_buffer(ip, &dibh);
|
|
|
|
if (error)
|
|
|
|
goto out;
|
|
|
|
|
2012-12-14 20:36:02 +08:00
|
|
|
gfs2_trans_add_meta(ip->i_gl, dibh);
|
2010-08-11 16:37:53 +08:00
|
|
|
|
2006-01-17 00:50:04 +08:00
|
|
|
if (gfs2_is_stuffed(ip)) {
|
2010-08-11 16:37:53 +08:00
|
|
|
gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode) + newsize);
|
2006-01-17 00:50:04 +08:00
|
|
|
} else {
|
2010-08-11 16:37:53 +08:00
|
|
|
if (newsize & (u64)(sdp->sd_sb.sb_bsize - 1)) {
|
|
|
|
error = gfs2_block_truncate_page(mapping, newsize);
|
|
|
|
if (error)
|
|
|
|
goto out_brelse;
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
2010-08-11 16:37:53 +08:00
|
|
|
ip->i_diskflags |= GFS2_DIF_TRUNC_IN_PROG;
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
2010-08-11 16:37:53 +08:00
|
|
|
i_size_write(inode, newsize);
|
2016-09-14 22:48:04 +08:00
|
|
|
ip->i_inode.i_mtime = ip->i_inode.i_ctime = current_time(&ip->i_inode);
|
2010-08-11 16:37:53 +08:00
|
|
|
gfs2_dinode_out(ip, dibh->b_data);
|
2006-01-17 00:50:04 +08:00
|
|
|
|
2012-11-13 17:50:28 +08:00
|
|
|
if (journaled)
|
|
|
|
error = gfs2_journaled_truncate(inode, oldsize, newsize);
|
|
|
|
else
|
2013-09-13 06:13:56 +08:00
|
|
|
truncate_pagecache(inode, newsize);
|
2012-11-13 17:50:28 +08:00
|
|
|
|
|
|
|
if (error) {
|
|
|
|
brelse(dibh);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2010-08-11 16:37:53 +08:00
|
|
|
out_brelse:
|
|
|
|
brelse(dibh);
|
2006-09-05 00:04:26 +08:00
|
|
|
out:
|
2006-01-17 00:50:04 +08:00
|
|
|
gfs2_trans_end(sdp);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
/**
|
|
|
|
* sweep_bh_for_rgrps - find an rgrp in a meta buffer and free blocks therein
|
|
|
|
* @ip: inode
|
|
|
|
* @rg_gh: holder of resource group glock
|
|
|
|
* @mp: current metapath fully populated with buffers
|
|
|
|
* @btotal: place to keep count of total blocks freed
|
|
|
|
* @hgt: height we're processing
|
|
|
|
* @first: true if this is the first call to this function for this height
|
|
|
|
*
|
|
|
|
* We sweep a metadata buffer (provided by the metapath) for blocks we need to
|
|
|
|
* free, and free them all. However, we do it one rgrp at a time. If this
|
|
|
|
* block has references to multiple rgrps, we break it into individual
|
|
|
|
* transactions. This allows other processes to use the rgrps while we're
|
|
|
|
* focused on a single one, for better concurrency / performance.
|
|
|
|
* At every transaction boundary, we rewrite the inode into the journal.
|
|
|
|
* That way the bitmaps are kept consistent with the inode and we can recover
|
|
|
|
* if we're interrupted by power-outages.
|
|
|
|
*
|
|
|
|
* Returns: 0, or return code if an error occurred.
|
|
|
|
* *btotal has the total number of blocks freed
|
|
|
|
*/
|
|
|
|
static int sweep_bh_for_rgrps(struct gfs2_inode *ip, struct gfs2_holder *rd_gh,
|
|
|
|
const struct metapath *mp, u32 *btotal, int hgt,
|
|
|
|
bool preserve1)
|
2006-01-17 00:50:04 +08:00
|
|
|
{
|
2008-02-23 00:09:31 +08:00
|
|
|
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
struct gfs2_rgrpd *rgd;
|
|
|
|
struct gfs2_trans *tr;
|
|
|
|
struct buffer_head *bh = mp->mp_bh[hgt];
|
|
|
|
__be64 *top, *bottom, *p;
|
|
|
|
int blks_outside_rgrp;
|
|
|
|
u64 bn, bstart, isize_blks;
|
|
|
|
s64 blen; /* needs to be s64 or gfs2_add_inode_blocks breaks */
|
|
|
|
int meta = ((hgt != ip->i_height - 1) ? 1 : 0);
|
|
|
|
int ret = 0;
|
|
|
|
bool buf_in_tr = false; /* buffer was added to transaction */
|
|
|
|
|
|
|
|
if (gfs2_metatype_check(sdp, bh,
|
|
|
|
(hgt ? GFS2_METATYPE_IN : GFS2_METATYPE_DI)))
|
|
|
|
return -EIO;
|
|
|
|
|
|
|
|
more_rgrps:
|
|
|
|
blks_outside_rgrp = 0;
|
|
|
|
bstart = 0;
|
|
|
|
blen = 0;
|
|
|
|
top = metapointer(hgt, mp); /* first ptr from metapath */
|
|
|
|
/* If we're keeping some data at the truncation point, we've got to
|
|
|
|
preserve the metadata tree by adding 1 to the starting metapath. */
|
|
|
|
if (preserve1)
|
|
|
|
top++;
|
|
|
|
|
|
|
|
bottom = (__be64 *)(bh->b_data + bh->b_size);
|
|
|
|
|
|
|
|
for (p = top; p < bottom; p++) {
|
|
|
|
if (!*p)
|
|
|
|
continue;
|
|
|
|
bn = be64_to_cpu(*p);
|
|
|
|
if (gfs2_holder_initialized(rd_gh)) {
|
2017-06-30 20:55:08 +08:00
|
|
|
rgd = gfs2_glock2rgrp(rd_gh->gh_gl);
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
gfs2_assert_withdraw(sdp,
|
|
|
|
gfs2_glock_is_locked_by_me(rd_gh->gh_gl));
|
|
|
|
} else {
|
|
|
|
rgd = gfs2_blk2rgrpd(sdp, bn, false);
|
|
|
|
ret = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
|
|
|
|
0, rd_gh);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
/* Must be done with the rgrp glock held: */
|
|
|
|
if (gfs2_rs_active(&ip->i_res) &&
|
|
|
|
rgd == ip->i_res.rs_rbm.rgd)
|
|
|
|
gfs2_rs_deltree(&ip->i_res);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!rgrp_contains_block(rgd, bn)) {
|
|
|
|
blks_outside_rgrp++;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* The size of our transactions will be unknown until we
|
|
|
|
actually process all the metadata blocks that relate to
|
|
|
|
the rgrp. So we estimate. We know it can't be more than
|
|
|
|
the dinode's i_blocks and we don't want to exceed the
|
|
|
|
journal flush threshold, sd_log_thresh2. */
|
|
|
|
if (current->journal_info == NULL) {
|
|
|
|
unsigned int jblocks_rqsted, revokes;
|
|
|
|
|
|
|
|
jblocks_rqsted = rgd->rd_length + RES_DINODE +
|
|
|
|
RES_INDIRECT;
|
|
|
|
isize_blks = gfs2_get_inode_blocks(&ip->i_inode);
|
|
|
|
if (isize_blks > atomic_read(&sdp->sd_log_thresh2))
|
|
|
|
jblocks_rqsted +=
|
|
|
|
atomic_read(&sdp->sd_log_thresh2);
|
|
|
|
else
|
|
|
|
jblocks_rqsted += isize_blks;
|
|
|
|
revokes = jblocks_rqsted;
|
|
|
|
if (meta)
|
|
|
|
revokes += hptrs(sdp, hgt);
|
|
|
|
else if (ip->i_depth)
|
|
|
|
revokes += sdp->sd_inptrs;
|
|
|
|
ret = gfs2_trans_begin(sdp, jblocks_rqsted, revokes);
|
|
|
|
if (ret)
|
|
|
|
goto out_unlock;
|
|
|
|
down_write(&ip->i_rw_mutex);
|
|
|
|
}
|
|
|
|
/* check if we will exceed the transaction blocks requested */
|
|
|
|
tr = current->journal_info;
|
|
|
|
if (tr->tr_num_buf_new + RES_STATFS +
|
|
|
|
RES_QUOTA >= atomic_read(&sdp->sd_log_thresh2)) {
|
|
|
|
/* We set blks_outside_rgrp to ensure the loop will
|
|
|
|
be repeated for the same rgrp, but with a new
|
|
|
|
transaction. */
|
|
|
|
blks_outside_rgrp++;
|
|
|
|
/* This next part is tricky. If the buffer was added
|
|
|
|
to the transaction, we've already set some block
|
|
|
|
pointers to 0, so we better follow through and free
|
|
|
|
them, or we will introduce corruption (so break).
|
|
|
|
This may be impossible, or at least rare, but I
|
|
|
|
decided to cover the case regardless.
|
|
|
|
|
|
|
|
If the buffer was not added to the transaction
|
|
|
|
(this call), doing so would exceed our transaction
|
|
|
|
size, so we need to end the transaction and start a
|
|
|
|
new one (so goto). */
|
|
|
|
|
|
|
|
if (buf_in_tr)
|
|
|
|
break;
|
|
|
|
goto out_unlock;
|
|
|
|
}
|
|
|
|
|
|
|
|
gfs2_trans_add_meta(ip->i_gl, bh);
|
|
|
|
buf_in_tr = true;
|
|
|
|
*p = 0;
|
|
|
|
if (bstart + blen == bn) {
|
|
|
|
blen++;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
if (bstart) {
|
|
|
|
__gfs2_free_blocks(ip, bstart, (u32)blen, meta);
|
|
|
|
(*btotal) += blen;
|
|
|
|
gfs2_add_inode_blocks(&ip->i_inode, -blen);
|
|
|
|
}
|
|
|
|
bstart = bn;
|
|
|
|
blen = 1;
|
|
|
|
}
|
|
|
|
if (bstart) {
|
|
|
|
__gfs2_free_blocks(ip, bstart, (u32)blen, meta);
|
|
|
|
(*btotal) += blen;
|
|
|
|
gfs2_add_inode_blocks(&ip->i_inode, -blen);
|
|
|
|
}
|
|
|
|
out_unlock:
|
|
|
|
if (!ret && blks_outside_rgrp) { /* If buffer still has non-zero blocks
|
|
|
|
outside the rgrp we just processed,
|
|
|
|
do it all over again. */
|
|
|
|
if (current->journal_info) {
|
|
|
|
struct buffer_head *dibh = mp->mp_bh[0];
|
|
|
|
|
|
|
|
/* Every transaction boundary, we rewrite the dinode
|
|
|
|
to keep its di_blocks current in case of failure. */
|
|
|
|
ip->i_inode.i_mtime = ip->i_inode.i_ctime =
|
2017-05-09 06:59:34 +08:00
|
|
|
current_time(&ip->i_inode);
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
gfs2_trans_add_meta(ip->i_gl, dibh);
|
|
|
|
gfs2_dinode_out(ip, dibh->b_data);
|
|
|
|
up_write(&ip->i_rw_mutex);
|
|
|
|
gfs2_trans_end(sdp);
|
|
|
|
}
|
|
|
|
gfs2_glock_dq_uninit(rd_gh);
|
|
|
|
cond_resched();
|
|
|
|
goto more_rgrps;
|
|
|
|
}
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* find_nonnull_ptr - find a non-null pointer given a metapath and height
|
|
|
|
* assumes the metapath is valid (with buffers) out to height h
|
|
|
|
* @mp: starting metapath
|
|
|
|
* @h: desired height to search
|
|
|
|
*
|
|
|
|
* Returns: true if a non-null pointer was found in the metapath buffer
|
|
|
|
* false if all remaining pointers are NULL in the buffer
|
|
|
|
*/
|
|
|
|
static bool find_nonnull_ptr(struct gfs2_sbd *sdp, struct metapath *mp,
|
|
|
|
unsigned int h)
|
|
|
|
{
|
|
|
|
__be64 *ptr;
|
|
|
|
unsigned int ptrs = hptrs(sdp, h) - 1;
|
|
|
|
|
|
|
|
while (true) {
|
|
|
|
ptr = metapointer(h, mp);
|
GFS2: Fix non-recursive truncate bug
Before this patch if you truncated a file to a smaller size it
wasn't freeing all the blocks properly. There are two reasons.
First, the metapath comparison was not comparing previous heights.
I added a function, mp_eq_to_hgt, which checks the metapath at
all heights prior to the target height.
Second, in function find_nonnull_ptr, it needed to zero out all
pointers for heights following the target height. Translated into
decimal integer terms, this way a number like 299, when incremented,
becomes 300, not 399. The 2 gets incremented to 3, and the following
digits need to be reset.
These two things allow the truncate state machine to properly find
the blocks it needs to delete.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-08-30 22:26:09 +08:00
|
|
|
if (*ptr) { /* if we have a non-null pointer */
|
|
|
|
/* Now zero the metapath after the current height. */
|
|
|
|
h++;
|
|
|
|
if (h < GFS2_MAX_META_HEIGHT)
|
|
|
|
memset(&mp->mp_list[h], 0,
|
|
|
|
(GFS2_MAX_META_HEIGHT - h) *
|
|
|
|
sizeof(mp->mp_list[0]));
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
return true;
|
GFS2: Fix non-recursive truncate bug
Before this patch if you truncated a file to a smaller size it
wasn't freeing all the blocks properly. There are two reasons.
First, the metapath comparison was not comparing previous heights.
I added a function, mp_eq_to_hgt, which checks the metapath at
all heights prior to the target height.
Second, in function find_nonnull_ptr, it needed to zero out all
pointers for heights following the target height. Translated into
decimal integer terms, this way a number like 299, when incremented,
becomes 300, not 399. The 2 gets incremented to 3, and the following
digits need to be reset.
These two things allow the truncate state machine to properly find
the blocks it needs to delete.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-08-30 22:26:09 +08:00
|
|
|
}
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
|
|
|
|
if (mp->mp_list[h] < ptrs)
|
|
|
|
mp->mp_list[h]++;
|
|
|
|
else
|
|
|
|
return false; /* no more pointers in this buffer */
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
enum dealloc_states {
|
|
|
|
DEALLOC_MP_FULL = 0, /* Strip a metapath with all buffers read in */
|
|
|
|
DEALLOC_MP_LOWER = 1, /* lower the metapath strip height */
|
|
|
|
DEALLOC_FILL_MP = 2, /* Fill in the metapath to the given height. */
|
|
|
|
DEALLOC_DONE = 3, /* process complete */
|
|
|
|
};
|
2006-01-17 00:50:04 +08:00
|
|
|
|
GFS2: Fix non-recursive truncate bug
Before this patch if you truncated a file to a smaller size it
wasn't freeing all the blocks properly. There are two reasons.
First, the metapath comparison was not comparing previous heights.
I added a function, mp_eq_to_hgt, which checks the metapath at
all heights prior to the target height.
Second, in function find_nonnull_ptr, it needed to zero out all
pointers for heights following the target height. Translated into
decimal integer terms, this way a number like 299, when incremented,
becomes 300, not 399. The 2 gets incremented to 3, and the following
digits need to be reset.
These two things allow the truncate state machine to properly find
the blocks it needs to delete.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-08-30 22:26:09 +08:00
|
|
|
static bool mp_eq_to_hgt(struct metapath *mp, __u16 *nbof, unsigned int h)
|
|
|
|
{
|
|
|
|
if (memcmp(mp->mp_list, nbof, h * sizeof(mp->mp_list[0])))
|
|
|
|
return false;
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
/**
|
|
|
|
* trunc_dealloc - truncate a file down to a desired size
|
|
|
|
* @ip: inode to truncate
|
|
|
|
* @newsize: The desired size of the file
|
|
|
|
*
|
|
|
|
* This function truncates a file to newsize. It works from the
|
|
|
|
* bottom up, and from the right to the left. In other words, it strips off
|
|
|
|
* the highest layer (data) before stripping any of the metadata. Doing it
|
|
|
|
* this way is best in case the operation is interrupted by power failure, etc.
|
|
|
|
* The dinode is rewritten in every transaction to guarantee integrity.
|
|
|
|
*/
|
|
|
|
static int trunc_dealloc(struct gfs2_inode *ip, u64 newsize)
|
|
|
|
{
|
|
|
|
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
|
|
|
|
struct metapath mp;
|
|
|
|
struct buffer_head *dibh, *bh;
|
|
|
|
struct gfs2_holder rd_gh;
|
|
|
|
u64 lblock;
|
|
|
|
__u16 nbof[GFS2_MAX_META_HEIGHT]; /* new beginning of truncation */
|
|
|
|
unsigned int strip_h = ip->i_height - 1;
|
|
|
|
u32 btotal = 0;
|
|
|
|
int ret, state;
|
|
|
|
int mp_h; /* metapath buffers are read in to this height */
|
|
|
|
sector_t last_ra = 0;
|
|
|
|
u64 prev_bnr = 0;
|
|
|
|
bool preserve1; /* need to preserve the first meta pointer? */
|
|
|
|
|
|
|
|
if (!newsize)
|
2006-01-17 00:50:04 +08:00
|
|
|
lblock = 0;
|
2006-02-08 19:50:51 +08:00
|
|
|
else
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
lblock = (newsize - 1) >> sdp->sd_sb.sb_bsize_shift;
|
2006-01-17 00:50:04 +08:00
|
|
|
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
memset(&mp, 0, sizeof(mp));
|
2008-02-23 00:09:31 +08:00
|
|
|
find_metapath(sdp, lblock, &mp, ip->i_height);
|
2006-01-17 00:50:04 +08:00
|
|
|
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
memcpy(&nbof, &mp.mp_list, sizeof(nbof));
|
|
|
|
|
|
|
|
ret = gfs2_meta_inode_buffer(ip, &dibh);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
2006-01-17 00:50:04 +08:00
|
|
|
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
mp.mp_bh[0] = dibh;
|
|
|
|
ret = lookup_metapath(ip, &mp);
|
|
|
|
if (ret == ip->i_height)
|
|
|
|
state = DEALLOC_MP_FULL; /* We have a complete metapath */
|
|
|
|
else
|
|
|
|
state = DEALLOC_FILL_MP; /* deal with partial metapath */
|
2006-01-17 00:50:04 +08:00
|
|
|
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
ret = gfs2_rindex_update(sdp);
|
|
|
|
if (ret)
|
|
|
|
goto out_metapath;
|
|
|
|
|
|
|
|
ret = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
|
|
|
|
if (ret)
|
|
|
|
goto out_metapath;
|
|
|
|
gfs2_holder_mark_uninitialized(&rd_gh);
|
|
|
|
|
|
|
|
mp_h = strip_h;
|
|
|
|
|
|
|
|
while (state != DEALLOC_DONE) {
|
|
|
|
switch (state) {
|
|
|
|
/* Truncate a full metapath at the given strip height.
|
|
|
|
* Note that strip_h == mp_h in order to be in this state. */
|
|
|
|
case DEALLOC_MP_FULL:
|
|
|
|
if (mp_h > 0) { /* issue read-ahead on metadata */
|
|
|
|
__be64 *top;
|
|
|
|
|
|
|
|
bh = mp.mp_bh[mp_h - 1];
|
|
|
|
if (bh->b_blocknr != last_ra) {
|
|
|
|
last_ra = bh->b_blocknr;
|
|
|
|
top = metaptr1(mp_h - 1, &mp);
|
|
|
|
gfs2_metapath_ra(ip->i_gl, bh, top);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
/* If we're truncating to a non-zero size and the mp is
|
|
|
|
at the beginning of file for the strip height, we
|
|
|
|
need to preserve the first metadata pointer. */
|
GFS2: Fix non-recursive truncate bug
Before this patch if you truncated a file to a smaller size it
wasn't freeing all the blocks properly. There are two reasons.
First, the metapath comparison was not comparing previous heights.
I added a function, mp_eq_to_hgt, which checks the metapath at
all heights prior to the target height.
Second, in function find_nonnull_ptr, it needed to zero out all
pointers for heights following the target height. Translated into
decimal integer terms, this way a number like 299, when incremented,
becomes 300, not 399. The 2 gets incremented to 3, and the following
digits need to be reset.
These two things allow the truncate state machine to properly find
the blocks it needs to delete.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-08-30 22:26:09 +08:00
|
|
|
preserve1 = (newsize && mp_eq_to_hgt(&mp, nbof, mp_h));
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
bh = mp.mp_bh[mp_h];
|
|
|
|
gfs2_assert_withdraw(sdp, bh);
|
|
|
|
if (gfs2_assert_withdraw(sdp,
|
|
|
|
prev_bnr != bh->b_blocknr)) {
|
|
|
|
printk(KERN_EMERG "GFS2: fsid=%s:inode %llu, "
|
|
|
|
"block:%llu, i_h:%u, s_h:%u, mp_h:%u\n",
|
|
|
|
sdp->sd_fsname,
|
|
|
|
(unsigned long long)ip->i_no_addr,
|
|
|
|
prev_bnr, ip->i_height, strip_h, mp_h);
|
|
|
|
}
|
|
|
|
prev_bnr = bh->b_blocknr;
|
|
|
|
ret = sweep_bh_for_rgrps(ip, &rd_gh, &mp, &btotal,
|
|
|
|
mp_h, preserve1);
|
|
|
|
/* If we hit an error or just swept dinode buffer,
|
|
|
|
just exit. */
|
|
|
|
if (ret || !mp_h) {
|
|
|
|
state = DEALLOC_DONE;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
state = DEALLOC_MP_LOWER;
|
|
|
|
break;
|
|
|
|
|
|
|
|
/* lower the metapath strip height */
|
|
|
|
case DEALLOC_MP_LOWER:
|
|
|
|
/* We're done with the current buffer, so release it,
|
|
|
|
unless it's the dinode buffer. Then back up to the
|
|
|
|
previous pointer. */
|
|
|
|
if (mp_h) {
|
|
|
|
brelse(mp.mp_bh[mp_h]);
|
|
|
|
mp.mp_bh[mp_h] = NULL;
|
|
|
|
}
|
|
|
|
/* If we can't get any lower in height, we've stripped
|
|
|
|
off all we can. Next step is to back up and start
|
|
|
|
stripping the previous level of metadata. */
|
|
|
|
if (mp_h == 0) {
|
|
|
|
strip_h--;
|
|
|
|
memcpy(&mp.mp_list, &nbof, sizeof(nbof));
|
|
|
|
mp_h = strip_h;
|
|
|
|
state = DEALLOC_FILL_MP;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
mp.mp_list[mp_h] = 0;
|
|
|
|
mp_h--; /* search one metadata height down */
|
|
|
|
if (mp.mp_list[mp_h] >= hptrs(sdp, mp_h) - 1)
|
|
|
|
break; /* loop around in the same state */
|
|
|
|
mp.mp_list[mp_h]++;
|
|
|
|
/* Here we've found a part of the metapath that is not
|
|
|
|
* allocated. We need to search at that height for the
|
|
|
|
* next non-null pointer. */
|
|
|
|
if (find_nonnull_ptr(sdp, &mp, mp_h)) {
|
|
|
|
state = DEALLOC_FILL_MP;
|
|
|
|
mp_h++;
|
|
|
|
}
|
|
|
|
/* No more non-null pointers at this height. Back up
|
|
|
|
to the previous height and try again. */
|
|
|
|
break; /* loop around in the same state */
|
|
|
|
|
|
|
|
/* Fill the metapath with buffers to the given height. */
|
|
|
|
case DEALLOC_FILL_MP:
|
|
|
|
/* Fill the buffers out to the current height. */
|
|
|
|
ret = fillup_metapath(ip, &mp, mp_h);
|
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
/* If buffers found for the entire strip height */
|
|
|
|
if ((ret == ip->i_height) && (mp_h == strip_h)) {
|
|
|
|
state = DEALLOC_MP_FULL;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (ret < ip->i_height) /* We have a partial height */
|
|
|
|
mp_h = ret - 1;
|
|
|
|
|
|
|
|
/* If we find a non-null block pointer, crawl a bit
|
|
|
|
higher up in the metapath and try again, otherwise
|
|
|
|
we need to look lower for a new starting point. */
|
|
|
|
if (find_nonnull_ptr(sdp, &mp, mp_h))
|
|
|
|
mp_h++;
|
|
|
|
else
|
|
|
|
state = DEALLOC_MP_LOWER;
|
2006-01-17 00:50:04 +08:00
|
|
|
break;
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
}
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
if (btotal) {
|
|
|
|
if (current->journal_info == NULL) {
|
|
|
|
ret = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS +
|
|
|
|
RES_QUOTA, 0);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
down_write(&ip->i_rw_mutex);
|
|
|
|
}
|
|
|
|
gfs2_statfs_change(sdp, 0, +btotal, 0);
|
|
|
|
gfs2_quota_change(ip, -(s64)btotal, ip->i_inode.i_uid,
|
|
|
|
ip->i_inode.i_gid);
|
2017-05-09 06:59:34 +08:00
|
|
|
ip->i_inode.i_mtime = ip->i_inode.i_ctime = current_time(&ip->i_inode);
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
gfs2_trans_add_meta(ip->i_gl, dibh);
|
|
|
|
gfs2_dinode_out(ip, dibh->b_data);
|
|
|
|
up_write(&ip->i_rw_mutex);
|
|
|
|
gfs2_trans_end(sdp);
|
|
|
|
}
|
2006-01-17 00:50:04 +08:00
|
|
|
|
GFS2: Non-recursive delete
Implement truncate/delete as a non-recursive algorithm. The older
algorithm was implemented with recursion to strip off each layer
at a time (going by height, starting with the maximum height.
This version tries to do the same thing but without recursion,
and without needing to allocate new structures or lists in memory.
For example, say you want to truncate a very large file to 1 byte,
and its end-of-file metapath is: 0.505.463.428. The starting
metapath would be 0.0.0.0. Since it's a truncate to non-zero, it
needs to preserve that byte, and all metadata pointing to it.
So it would start at 0.0.0.0, look up all its metadata buffers,
then free all data blocks pointed to at the highest level.
After that buffer is "swept", it moves on to 0.0.0.1, then
0.0.0.2, etc., reading in buffers and sweeping them clean.
When it gets to the end of the 0.0.0 metadata buffer (for 4K
blocks the last valid one is 0.0.0.508), it backs up to the
previous height and starts working on 0.0.1.0, then 0.0.1.1,
and so forth. After it reaches the end and sweeps 0.0.1.508,
it continues with 0.0.2.0, and so on. When that height is
exhausted, and it reaches 0.0.508.508 it backs up another level,
to 0.1.0.0, then 0.1.0.1, through 0.1.0.508. So it has to keep
marching backwards and forwards through the metadata until it's
all swept clean. Once it has all the data blocks freed, it
lowers the strip height, and begins the process all over again,
but with one less height. This time it sweeps 0.0.0 through
0.505.463. When that's clean, it lowers the strip height again
and works to free 0.505. Eventually it strips the lowest height, 0.
For a delete or truncate to 0, all metadata for all heights of
0.0.0.0 would be freed. For a truncate to 1 byte, 0.0.0.0 would
be preserved.
This isn't much different from normal integer incrementing,
where an integer gets incremented from 0000 (0.0.0.0) to 3021
(3.0.2.1). So 0000 gets increments to 0001, 0002, up to 0009,
then on to 0010, 0011 up to 0099, then 0100 and so forth. It's
just that each "digit" goes from 0 to 508 (for a total of 509
pointers) rather than from 0 to 9.
Note that the dinode will only have 483 pointers due to the
dinode structure itself.
Also note: this is just an example. These numbers (509 and 483)
are based on a standard 4K block size. Smaller block sizes will
yield smaller numbers of indirect pointers accordingly.
The truncation process is accomplished with the help of two
major functions and a few helper functions.
Functions do_strip and recursive_scan are obsolete, so removed.
New function sweep_bh_for_rgrps cleans a buffer_head pointed to
by the given metapath and height. By cleaning, I mean it frees
all blocks starting at the offset passed in metapath. It starts
at the first block in the buffer pointed to by the metapath and
identifies its resource group (rgrp). From there it frees all
subsequent block pointers that lie within that rgrp. If it's
already inside a transaction, it stays within it as long as it
can. In other words, it doesn't close a transaction until it knows
it's freed what it can from the resource group. In this way,
multiple buffers may be cleaned in a single transaction, as long
as those blocks in the buffer all lie within the same rgrp.
If it's not in a transaction, it starts one. If the buffer_head
has references to blocks within multiple rgrps, it frees all the
blocks inside the first rgrp it finds, then closes the
transaction. Then it repeats the cycle: identifies the next
unfreed block, uses it to find its rgrp, then starts a new
transaction for that set. It repeats this process repeatedly
until the buffer_head contains no more references to any blocks
past the given metapath.
Function trunc_dealloc has been reworked into a finite state
automaton. It has basically 3 active states:
DEALLOC_MP_FULL, DEALLOC_MP_LOWER, and DEALLOC_FILL_MP:
The DEALLOC_MP_FULL state implies the metapath has a full set
of buffers out to the "shrink height", and therefore, it can
call function sweep_bh_for_rgrps to free the blocks within the
highest height of the metapath. If it's just swept the lowest
level (or an error has occurred) the state machine is ended.
Otherwise it proceeds to the DEALLOC_MP_LOWER state.
The DEALLOC_MP_LOWER state implies we are finished with a given
buffer_head, which may now be released, and therefore we are
then missing some buffer information from the metapath. So we
need to find more buffers to read in. In most cases, this is
just a matter of releasing the buffer_head and moving to the
next pointer from the previous height, so it may be read in and
swept as well. If it can't find another non-null pointer to
process, it checks whether it's reached the end of a height
and needs to lower the strip height, or whether it still needs
move forward through the previous height's metadata. In this
state, all zero-pointers are skipped. From this state, it can
only loop around (once more backing up another height) or,
once a valid metapath is found (one that has non-zero
pointers), proceed to state DEALLOC_FILL_MP.
The DEALLOC_FILL_MP state implies that we have a metapath
but not all its buffers are read in. So we must proceed to read
in buffer_heads until the metapath has a valid buffer for every
height. If the previous state backed us up 3 heights, we may
need to read in a buffer, increment the height, then repeat the
process until buffers have been read in for all required heights.
If it's successful reading a buffer, and it's at the highest
height we need, it proceeds back to the DEALLOC_MP_FULL state.
If it's unable to fill in a buffer, (encounters a hole, etc.)
it tries to find another non-zero block pointer. If they're all
zero, it lowers the height and returns to the DEALLOC_MP_LOWER
state. If it finds a good non-null pointer, it loops around and
reads it in, while keeping the metapath in lock-step with the
pointers it examines.
The state machine runs until the truncation request is
satisfied. Then any transactions are ended, the quota and
statfs data are updated, and the function is complete.
Helper function metaptr1 was introduced to be an easy way to
determine the start of a buffer_head's indirect pointers.
Helper function lookup_mp_height was introduced to find a
metapath index and read in the buffer that corresponds to it.
In this way, function lookup_metapath becomes a simple loop to
call it for every height.
Helper function fillup_metapath is similar to lookup_metapath
except it can do partial lookups. If the state machine
backed up multiple levels (like 2999 wrapping to 3000) it
needs to find out the next starting point and start issuing
metadata reads at that point.
Helper function hptrs is a shortcut to determine how many
pointers should be expected in a buffer. Height 0 is the dinode
which has fewer pointers than the others.
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
2017-02-06 21:28:32 +08:00
|
|
|
out:
|
|
|
|
if (gfs2_holder_initialized(&rd_gh))
|
|
|
|
gfs2_glock_dq_uninit(&rd_gh);
|
|
|
|
if (current->journal_info) {
|
|
|
|
up_write(&ip->i_rw_mutex);
|
|
|
|
gfs2_trans_end(sdp);
|
|
|
|
cond_resched();
|
|
|
|
}
|
|
|
|
gfs2_quota_unhold(ip);
|
|
|
|
out_metapath:
|
|
|
|
release_metapath(&mp);
|
|
|
|
return ret;
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int trunc_end(struct gfs2_inode *ip)
|
|
|
|
{
|
2006-06-15 03:32:57 +08:00
|
|
|
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
|
2006-01-17 00:50:04 +08:00
|
|
|
struct buffer_head *dibh;
|
|
|
|
int error;
|
|
|
|
|
|
|
|
error = gfs2_trans_begin(sdp, RES_DINODE, 0);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
down_write(&ip->i_rw_mutex);
|
|
|
|
|
|
|
|
error = gfs2_meta_inode_buffer(ip, &dibh);
|
|
|
|
if (error)
|
|
|
|
goto out;
|
|
|
|
|
2010-08-11 16:53:11 +08:00
|
|
|
if (!i_size_read(&ip->i_inode)) {
|
2008-01-28 18:37:35 +08:00
|
|
|
ip->i_height = 0;
|
2008-02-06 17:25:45 +08:00
|
|
|
ip->i_goal = ip->i_no_addr;
|
2006-01-17 00:50:04 +08:00
|
|
|
gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
|
2013-01-28 17:30:07 +08:00
|
|
|
gfs2_ordered_del_inode(ip);
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
2016-09-14 22:48:04 +08:00
|
|
|
ip->i_inode.i_mtime = ip->i_inode.i_ctime = current_time(&ip->i_inode);
|
2008-11-04 18:05:22 +08:00
|
|
|
ip->i_diskflags &= ~GFS2_DIF_TRUNC_IN_PROG;
|
2006-01-17 00:50:04 +08:00
|
|
|
|
2012-12-14 20:36:02 +08:00
|
|
|
gfs2_trans_add_meta(ip->i_gl, dibh);
|
2006-11-01 04:07:05 +08:00
|
|
|
gfs2_dinode_out(ip, dibh->b_data);
|
2006-01-17 00:50:04 +08:00
|
|
|
brelse(dibh);
|
|
|
|
|
2006-09-05 00:04:26 +08:00
|
|
|
out:
|
2006-01-17 00:50:04 +08:00
|
|
|
up_write(&ip->i_rw_mutex);
|
|
|
|
gfs2_trans_end(sdp);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* do_shrink - make a file smaller
|
2010-08-11 16:37:53 +08:00
|
|
|
* @inode: the inode
|
|
|
|
* @oldsize: the current inode size
|
|
|
|
* @newsize: the size to make the file
|
2006-01-17 00:50:04 +08:00
|
|
|
*
|
2010-08-11 16:37:53 +08:00
|
|
|
* Called with an exclusive lock on @inode. The @size must
|
|
|
|
* be equal to or smaller than the current inode size.
|
2006-01-17 00:50:04 +08:00
|
|
|
*
|
|
|
|
* Returns: errno
|
|
|
|
*/
|
|
|
|
|
2010-08-11 16:37:53 +08:00
|
|
|
static int do_shrink(struct inode *inode, u64 oldsize, u64 newsize)
|
2006-01-17 00:50:04 +08:00
|
|
|
{
|
2010-08-11 16:37:53 +08:00
|
|
|
struct gfs2_inode *ip = GFS2_I(inode);
|
2006-01-17 00:50:04 +08:00
|
|
|
int error;
|
|
|
|
|
2010-08-11 16:37:53 +08:00
|
|
|
error = trunc_start(inode, oldsize, newsize);
|
2006-01-17 00:50:04 +08:00
|
|
|
if (error < 0)
|
|
|
|
return error;
|
2010-08-11 16:37:53 +08:00
|
|
|
if (gfs2_is_stuffed(ip))
|
2006-01-17 00:50:04 +08:00
|
|
|
return 0;
|
|
|
|
|
2010-08-11 16:37:53 +08:00
|
|
|
error = trunc_dealloc(ip, newsize);
|
|
|
|
if (error == 0)
|
2006-01-17 00:50:04 +08:00
|
|
|
error = trunc_end(ip);
|
|
|
|
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2010-08-11 16:37:53 +08:00
|
|
|
void gfs2_trim_blocks(struct inode *inode)
|
2007-08-20 21:29:53 +08:00
|
|
|
{
|
2010-08-11 16:37:53 +08:00
|
|
|
u64 size = inode->i_size;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
ret = do_shrink(inode, size, size);
|
|
|
|
WARN_ON(ret != 0);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* do_grow - Touch and update inode size
|
|
|
|
* @inode: The inode
|
|
|
|
* @size: The new size
|
|
|
|
*
|
|
|
|
* This function updates the timestamps on the inode and
|
|
|
|
* may also increase the size of the inode. This function
|
|
|
|
* must not be called with @size any smaller than the current
|
|
|
|
* inode size.
|
|
|
|
*
|
|
|
|
* Although it is not strictly required to unstuff files here,
|
|
|
|
* earlier versions of GFS2 have a bug in the stuffed file reading
|
|
|
|
* code which will result in a buffer overrun if the size is larger
|
|
|
|
* than the max stuffed file size. In order to prevent this from
|
2011-03-31 09:57:33 +08:00
|
|
|
* occurring, such files are unstuffed, but in other cases we can
|
2010-08-11 16:37:53 +08:00
|
|
|
* just update the inode size directly.
|
|
|
|
*
|
|
|
|
* Returns: 0 on success, or -ve on error
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int do_grow(struct inode *inode, u64 size)
|
|
|
|
{
|
|
|
|
struct gfs2_inode *ip = GFS2_I(inode);
|
|
|
|
struct gfs2_sbd *sdp = GFS2_SB(inode);
|
2013-10-02 18:13:25 +08:00
|
|
|
struct gfs2_alloc_parms ap = { .target = 1, };
|
2007-08-20 21:29:53 +08:00
|
|
|
struct buffer_head *dibh;
|
|
|
|
int error;
|
2012-04-12 21:19:30 +08:00
|
|
|
int unstuff = 0;
|
2007-08-20 21:29:53 +08:00
|
|
|
|
2010-08-11 16:37:53 +08:00
|
|
|
if (gfs2_is_stuffed(ip) &&
|
|
|
|
(size > (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)))) {
|
2015-03-19 01:03:41 +08:00
|
|
|
error = gfs2_quota_lock_check(ip, &ap);
|
2010-08-11 16:37:53 +08:00
|
|
|
if (error)
|
2012-05-18 21:28:23 +08:00
|
|
|
return error;
|
2010-08-11 16:37:53 +08:00
|
|
|
|
2013-10-02 18:13:25 +08:00
|
|
|
error = gfs2_inplace_reserve(ip, &ap);
|
2010-08-11 16:37:53 +08:00
|
|
|
if (error)
|
|
|
|
goto do_grow_qunlock;
|
2012-04-12 21:19:30 +08:00
|
|
|
unstuff = 1;
|
2010-08-11 16:37:53 +08:00
|
|
|
}
|
|
|
|
|
2013-06-28 00:47:51 +08:00
|
|
|
error = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS + RES_RG_BIT +
|
|
|
|
(sdp->sd_args.ar_quota == GFS2_QUOTA_OFF ?
|
|
|
|
0 : RES_QUOTA), 0);
|
2007-08-20 21:29:53 +08:00
|
|
|
if (error)
|
2010-08-11 16:37:53 +08:00
|
|
|
goto do_grow_release;
|
2007-08-20 21:29:53 +08:00
|
|
|
|
2012-04-12 21:19:30 +08:00
|
|
|
if (unstuff) {
|
2010-08-11 16:37:53 +08:00
|
|
|
error = gfs2_unstuff_dinode(ip, NULL);
|
|
|
|
if (error)
|
|
|
|
goto do_end_trans;
|
|
|
|
}
|
2007-08-20 21:29:53 +08:00
|
|
|
|
|
|
|
error = gfs2_meta_inode_buffer(ip, &dibh);
|
|
|
|
if (error)
|
2010-08-11 16:37:53 +08:00
|
|
|
goto do_end_trans;
|
2007-08-20 21:29:53 +08:00
|
|
|
|
2010-08-11 16:37:53 +08:00
|
|
|
i_size_write(inode, size);
|
2016-09-14 22:48:04 +08:00
|
|
|
ip->i_inode.i_mtime = ip->i_inode.i_ctime = current_time(&ip->i_inode);
|
2012-12-14 20:36:02 +08:00
|
|
|
gfs2_trans_add_meta(ip->i_gl, dibh);
|
2007-08-20 21:29:53 +08:00
|
|
|
gfs2_dinode_out(ip, dibh->b_data);
|
|
|
|
brelse(dibh);
|
|
|
|
|
2010-08-11 16:37:53 +08:00
|
|
|
do_end_trans:
|
2007-08-20 21:29:53 +08:00
|
|
|
gfs2_trans_end(sdp);
|
2010-08-11 16:37:53 +08:00
|
|
|
do_grow_release:
|
2012-04-12 21:19:30 +08:00
|
|
|
if (unstuff) {
|
2010-08-11 16:37:53 +08:00
|
|
|
gfs2_inplace_release(ip);
|
|
|
|
do_grow_qunlock:
|
|
|
|
gfs2_quota_unlock(ip);
|
|
|
|
}
|
2007-08-20 21:29:53 +08:00
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2006-01-17 00:50:04 +08:00
|
|
|
/**
|
2010-08-11 16:37:53 +08:00
|
|
|
* gfs2_setattr_size - make a file a given size
|
|
|
|
* @inode: the inode
|
|
|
|
* @newsize: the size to make the file
|
2006-01-17 00:50:04 +08:00
|
|
|
*
|
2010-08-11 16:37:53 +08:00
|
|
|
* The file size can grow, shrink, or stay the same size. This
|
|
|
|
* is called holding i_mutex and an exclusive glock on the inode
|
|
|
|
* in question.
|
2006-01-17 00:50:04 +08:00
|
|
|
*
|
|
|
|
* Returns: errno
|
|
|
|
*/
|
|
|
|
|
2010-08-11 16:37:53 +08:00
|
|
|
int gfs2_setattr_size(struct inode *inode, u64 newsize)
|
2006-01-17 00:50:04 +08:00
|
|
|
{
|
2013-09-27 19:49:33 +08:00
|
|
|
struct gfs2_inode *ip = GFS2_I(inode);
|
2010-08-11 16:37:53 +08:00
|
|
|
int ret;
|
|
|
|
u64 oldsize;
|
2006-01-17 00:50:04 +08:00
|
|
|
|
2010-08-11 16:37:53 +08:00
|
|
|
BUG_ON(!S_ISREG(inode->i_mode));
|
2006-01-17 00:50:04 +08:00
|
|
|
|
2010-08-11 16:37:53 +08:00
|
|
|
ret = inode_newsize_ok(inode, newsize);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
2006-01-17 00:50:04 +08:00
|
|
|
|
2011-06-25 02:29:45 +08:00
|
|
|
inode_dio_wait(inode);
|
|
|
|
|
2015-10-26 23:40:28 +08:00
|
|
|
ret = gfs2_rsqa_alloc(ip);
|
2013-02-02 01:03:02 +08:00
|
|
|
if (ret)
|
2013-05-28 22:04:44 +08:00
|
|
|
goto out;
|
2013-02-02 01:03:02 +08:00
|
|
|
|
2010-08-11 16:37:53 +08:00
|
|
|
oldsize = inode->i_size;
|
2013-05-28 22:04:44 +08:00
|
|
|
if (newsize >= oldsize) {
|
|
|
|
ret = do_grow(inode, newsize);
|
|
|
|
goto out;
|
|
|
|
}
|
2010-08-11 16:37:53 +08:00
|
|
|
|
2013-05-28 22:04:44 +08:00
|
|
|
ret = do_shrink(inode, oldsize, newsize);
|
|
|
|
out:
|
2015-07-16 21:28:04 +08:00
|
|
|
gfs2_rsqa_delete(ip, NULL);
|
2013-05-28 22:04:44 +08:00
|
|
|
return ret;
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
int gfs2_truncatei_resume(struct gfs2_inode *ip)
|
|
|
|
{
|
|
|
|
int error;
|
2010-08-11 16:53:11 +08:00
|
|
|
error = trunc_dealloc(ip, i_size_read(&ip->i_inode));
|
2006-01-17 00:50:04 +08:00
|
|
|
if (!error)
|
|
|
|
error = trunc_end(ip);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
int gfs2_file_dealloc(struct gfs2_inode *ip)
|
|
|
|
{
|
|
|
|
return trunc_dealloc(ip, 0);
|
|
|
|
}
|
|
|
|
|
2014-03-03 21:35:57 +08:00
|
|
|
/**
|
|
|
|
* gfs2_free_journal_extents - Free cached journal bmap info
|
|
|
|
* @jd: The journal
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
void gfs2_free_journal_extents(struct gfs2_jdesc *jd)
|
|
|
|
{
|
|
|
|
struct gfs2_journal_extent *jext;
|
|
|
|
|
|
|
|
while(!list_empty(&jd->extent_list)) {
|
|
|
|
jext = list_entry(jd->extent_list.next, struct gfs2_journal_extent, list);
|
|
|
|
list_del(&jext->list);
|
|
|
|
kfree(jext);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* gfs2_add_jextent - Add or merge a new extent to extent cache
|
|
|
|
* @jd: The journal descriptor
|
|
|
|
* @lblock: The logical block at start of new extent
|
2014-05-15 00:32:31 +08:00
|
|
|
* @dblock: The physical block at start of new extent
|
2014-03-03 21:35:57 +08:00
|
|
|
* @blocks: Size of extent in fs blocks
|
|
|
|
*
|
|
|
|
* Returns: 0 on success or -ENOMEM
|
|
|
|
*/
|
|
|
|
|
|
|
|
static int gfs2_add_jextent(struct gfs2_jdesc *jd, u64 lblock, u64 dblock, u64 blocks)
|
|
|
|
{
|
|
|
|
struct gfs2_journal_extent *jext;
|
|
|
|
|
|
|
|
if (!list_empty(&jd->extent_list)) {
|
|
|
|
jext = list_entry(jd->extent_list.prev, struct gfs2_journal_extent, list);
|
|
|
|
if ((jext->dblock + jext->blocks) == dblock) {
|
|
|
|
jext->blocks += blocks;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
jext = kzalloc(sizeof(struct gfs2_journal_extent), GFP_NOFS);
|
|
|
|
if (jext == NULL)
|
|
|
|
return -ENOMEM;
|
|
|
|
jext->dblock = dblock;
|
|
|
|
jext->lblock = lblock;
|
|
|
|
jext->blocks = blocks;
|
|
|
|
list_add_tail(&jext->list, &jd->extent_list);
|
|
|
|
jd->nr_extents++;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* gfs2_map_journal_extents - Cache journal bmap info
|
|
|
|
* @sdp: The super block
|
|
|
|
* @jd: The journal to map
|
|
|
|
*
|
|
|
|
* Create a reusable "extent" mapping from all logical
|
|
|
|
* blocks to all physical blocks for the given journal. This will save
|
|
|
|
* us time when writing journal blocks. Most journals will have only one
|
|
|
|
* extent that maps all their logical blocks. That's because gfs2.mkfs
|
|
|
|
* arranges the journal blocks sequentially to maximize performance.
|
|
|
|
* So the extent would map the first block for the entire file length.
|
|
|
|
* However, gfs2_jadd can happen while file activity is happening, so
|
|
|
|
* those journals may not be sequential. Less likely is the case where
|
|
|
|
* the users created their own journals by mounting the metafs and
|
|
|
|
* laying it out. But it's still possible. These journals might have
|
|
|
|
* several extents.
|
|
|
|
*
|
|
|
|
* Returns: 0 on success, or error on failure
|
|
|
|
*/
|
|
|
|
|
|
|
|
int gfs2_map_journal_extents(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd)
|
|
|
|
{
|
|
|
|
u64 lblock = 0;
|
|
|
|
u64 lblock_stop;
|
|
|
|
struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
|
|
|
|
struct buffer_head bh;
|
|
|
|
unsigned int shift = sdp->sd_sb.sb_bsize_shift;
|
|
|
|
u64 size;
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
lblock_stop = i_size_read(jd->jd_inode) >> shift;
|
|
|
|
size = (lblock_stop - lblock) << shift;
|
|
|
|
jd->nr_extents = 0;
|
|
|
|
WARN_ON(!list_empty(&jd->extent_list));
|
|
|
|
|
|
|
|
do {
|
|
|
|
bh.b_state = 0;
|
|
|
|
bh.b_blocknr = 0;
|
|
|
|
bh.b_size = size;
|
|
|
|
rc = gfs2_block_map(jd->jd_inode, lblock, &bh, 0);
|
|
|
|
if (rc || !buffer_mapped(&bh))
|
|
|
|
goto fail;
|
|
|
|
rc = gfs2_add_jextent(jd, lblock, bh.b_blocknr, bh.b_size >> shift);
|
|
|
|
if (rc)
|
|
|
|
goto fail;
|
|
|
|
size -= bh.b_size;
|
|
|
|
lblock += (bh.b_size >> ip->i_inode.i_blkbits);
|
|
|
|
} while(size > 0);
|
|
|
|
|
|
|
|
fs_info(sdp, "journal %d mapped with %u extents\n", jd->jd_jid,
|
|
|
|
jd->nr_extents);
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
fail:
|
|
|
|
fs_warn(sdp, "error %d mapping journal %u at offset %llu (extent %u)\n",
|
|
|
|
rc, jd->jd_jid,
|
|
|
|
(unsigned long long)(i_size_read(jd->jd_inode) - size),
|
|
|
|
jd->nr_extents);
|
|
|
|
fs_warn(sdp, "bmap=%d lblock=%llu block=%llu, state=0x%08lx, size=%llu\n",
|
|
|
|
rc, (unsigned long long)lblock, (unsigned long long)bh.b_blocknr,
|
|
|
|
bh.b_state, (unsigned long long)bh.b_size);
|
|
|
|
gfs2_free_journal_extents(jd);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
2006-01-17 00:50:04 +08:00
|
|
|
/**
|
|
|
|
* gfs2_write_alloc_required - figure out if a write will require an allocation
|
|
|
|
* @ip: the file being written to
|
|
|
|
* @offset: the offset to write to
|
|
|
|
* @len: the number of bytes being written
|
|
|
|
*
|
2010-06-25 07:21:20 +08:00
|
|
|
* Returns: 1 if an alloc is required, 0 otherwise
|
2006-01-17 00:50:04 +08:00
|
|
|
*/
|
|
|
|
|
2006-09-05 00:49:07 +08:00
|
|
|
int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
|
2010-06-25 07:21:20 +08:00
|
|
|
unsigned int len)
|
2006-01-17 00:50:04 +08:00
|
|
|
{
|
2006-06-15 03:32:57 +08:00
|
|
|
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
|
2008-01-28 16:47:38 +08:00
|
|
|
struct buffer_head bh;
|
|
|
|
unsigned int shift;
|
|
|
|
u64 lblock, lblock_stop, size;
|
2008-12-10 18:28:10 +08:00
|
|
|
u64 end_of_file;
|
2006-01-17 00:50:04 +08:00
|
|
|
|
|
|
|
if (!len)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if (gfs2_is_stuffed(ip)) {
|
|
|
|
if (offset + len >
|
|
|
|
sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode))
|
2010-06-25 07:21:20 +08:00
|
|
|
return 1;
|
2006-01-17 00:50:04 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2008-01-28 16:47:38 +08:00
|
|
|
shift = sdp->sd_sb.sb_bsize_shift;
|
2008-12-10 18:28:10 +08:00
|
|
|
BUG_ON(gfs2_is_dir(ip));
|
2010-08-11 16:53:11 +08:00
|
|
|
end_of_file = (i_size_read(&ip->i_inode) + sdp->sd_sb.sb_bsize - 1) >> shift;
|
2008-12-10 18:28:10 +08:00
|
|
|
lblock = offset >> shift;
|
|
|
|
lblock_stop = (offset + len + sdp->sd_sb.sb_bsize - 1) >> shift;
|
|
|
|
if (lblock_stop > end_of_file)
|
2010-06-25 07:21:20 +08:00
|
|
|
return 1;
|
2006-01-17 00:50:04 +08:00
|
|
|
|
2008-01-28 16:47:38 +08:00
|
|
|
size = (lblock_stop - lblock) << shift;
|
|
|
|
do {
|
|
|
|
bh.b_state = 0;
|
|
|
|
bh.b_size = size;
|
|
|
|
gfs2_block_map(&ip->i_inode, lblock, &bh, 0);
|
|
|
|
if (!buffer_mapped(&bh))
|
2010-06-25 07:21:20 +08:00
|
|
|
return 1;
|
2008-01-28 16:47:38 +08:00
|
|
|
size -= bh.b_size;
|
|
|
|
lblock += (bh.b_size >> ip->i_inode.i_blkbits);
|
|
|
|
} while(size > 0);
|
2006-01-17 00:50:04 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|