linux-sg2042/fs/f2fs/node.h

397 lines
11 KiB
C
Raw Normal View History

/*
* fs/f2fs/node.h
*
* Copyright (c) 2012 Samsung Electronics Co., Ltd.
* http://www.samsung.com/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
/* start node id of a node block dedicated to the given node id */
#define START_NID(nid) ((nid / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK)
/* node block offset on the NAT area dedicated to the given start node id */
#define NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK)
/* # of pages to perform readahead before building free nids */
#define FREE_NID_PAGES 4
/* maximum readahead size for node during getting data blocks */
#define MAX_RA_NODE 128
/* control the memory footprint threshold (10MB per 1GB ram) */
#define DEF_RAM_THRESHOLD 10
/* vector size for gang look-up from nat cache that consists of radix tree */
#define NATVEC_SIZE 64
/* return value for read_node_page */
#define LOCKED_PAGE 1
/*
* For node information
*/
struct node_info {
nid_t nid; /* node id */
nid_t ino; /* inode number of the node's owner */
block_t blk_addr; /* block address of the node */
unsigned char version; /* version of the node */
};
enum {
IS_CHECKPOINTED, /* is it checkpointed before? */
f2fs: fix conditions to remain recovery information in f2fs_sync_file This patch revisited whole the recovery information during the f2fs_sync_file. In this patch, there are three information to make a decision. a) IS_CHECKPOINTED, /* is it checkpointed before? */ b) HAS_FSYNCED_INODE, /* is the inode fsynced before? */ c) HAS_LAST_FSYNC, /* has the latest node fsync mark? */ And, the scenarios for our rule are based on: [Term] F: fsync_mark, D: dentry_mark 1. inode(x) | CP | inode(x) | dnode(F) 2. inode(x) | CP | inode(F) | dnode(F) 3. inode(x) | CP | dnode(F) | inode(x) | inode(F) 4. inode(x) | CP | dnode(F) | inode(F) 5. CP | inode(x) | dnode(F) | inode(DF) 6. CP | inode(DF) | dnode(F) 7. CP | dnode(F) | inode(DF) 8. CP | dnode(F) | inode(x) | inode(DF) For example, #3, the three conditions should be changed as follows. inode(x) | CP | dnode(F) | inode(x) | inode(F) a) x o o o o b) x x x x o c) x o o x o If f2fs_sync_file stops ------^, it should write inode(F) --------------^ So, the need_inode_block_update should return true, since c) get_nat_flag(e, HAS_LAST_FSYNC), is false. For example, #8, CP | alloc | dnode(F) | inode(x) | inode(DF) a) o x x x x b) x x x o c) o o x o If f2fs_sync_file stops -------^, it should write inode(DF) --------------^ Note that, the roll-forward policy should follow this rule, which means, if there are any missing blocks, we doesn't need to recover that inode. Signed-off-by: Huang Ying <ying.huang@intel.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-09-16 05:50:48 +08:00
HAS_FSYNCED_INODE, /* is the inode fsynced before? */
HAS_LAST_FSYNC, /* has the latest node fsync mark? */
IS_DIRTY, /* this nat entry is dirty? */
};
struct nat_entry {
struct list_head list; /* for clean or dirty nat list */
unsigned char flag; /* for node information bits */
struct node_info ni; /* in-memory node information */
};
#define nat_get_nid(nat) (nat->ni.nid)
#define nat_set_nid(nat, n) (nat->ni.nid = n)
#define nat_get_blkaddr(nat) (nat->ni.blk_addr)
#define nat_set_blkaddr(nat, b) (nat->ni.blk_addr = b)
#define nat_get_ino(nat) (nat->ni.ino)
#define nat_set_ino(nat, i) (nat->ni.ino = i)
#define nat_get_version(nat) (nat->ni.version)
#define nat_set_version(nat, v) (nat->ni.version = v)
#define inc_node_version(version) (++version)
static inline void set_nat_flag(struct nat_entry *ne,
unsigned int type, bool set)
{
unsigned char mask = 0x01 << type;
if (set)
ne->flag |= mask;
else
ne->flag &= ~mask;
}
static inline bool get_nat_flag(struct nat_entry *ne, unsigned int type)
{
unsigned char mask = 0x01 << type;
return ne->flag & mask;
}
f2fs: fix conditions to remain recovery information in f2fs_sync_file This patch revisited whole the recovery information during the f2fs_sync_file. In this patch, there are three information to make a decision. a) IS_CHECKPOINTED, /* is it checkpointed before? */ b) HAS_FSYNCED_INODE, /* is the inode fsynced before? */ c) HAS_LAST_FSYNC, /* has the latest node fsync mark? */ And, the scenarios for our rule are based on: [Term] F: fsync_mark, D: dentry_mark 1. inode(x) | CP | inode(x) | dnode(F) 2. inode(x) | CP | inode(F) | dnode(F) 3. inode(x) | CP | dnode(F) | inode(x) | inode(F) 4. inode(x) | CP | dnode(F) | inode(F) 5. CP | inode(x) | dnode(F) | inode(DF) 6. CP | inode(DF) | dnode(F) 7. CP | dnode(F) | inode(DF) 8. CP | dnode(F) | inode(x) | inode(DF) For example, #3, the three conditions should be changed as follows. inode(x) | CP | dnode(F) | inode(x) | inode(F) a) x o o o o b) x x x x o c) x o o x o If f2fs_sync_file stops ------^, it should write inode(F) --------------^ So, the need_inode_block_update should return true, since c) get_nat_flag(e, HAS_LAST_FSYNC), is false. For example, #8, CP | alloc | dnode(F) | inode(x) | inode(DF) a) o x x x x b) x x x o c) o o x o If f2fs_sync_file stops -------^, it should write inode(DF) --------------^ Note that, the roll-forward policy should follow this rule, which means, if there are any missing blocks, we doesn't need to recover that inode. Signed-off-by: Huang Ying <ying.huang@intel.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-09-16 05:50:48 +08:00
static inline void nat_reset_flag(struct nat_entry *ne)
{
/* these states can be set only after checkpoint was done */
set_nat_flag(ne, IS_CHECKPOINTED, true);
set_nat_flag(ne, HAS_FSYNCED_INODE, false);
set_nat_flag(ne, HAS_LAST_FSYNC, true);
}
static inline void node_info_from_raw_nat(struct node_info *ni,
struct f2fs_nat_entry *raw_ne)
{
ni->ino = le32_to_cpu(raw_ne->ino);
ni->blk_addr = le32_to_cpu(raw_ne->block_addr);
ni->version = raw_ne->version;
}
static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne,
struct node_info *ni)
{
raw_ne->ino = cpu_to_le32(ni->ino);
raw_ne->block_addr = cpu_to_le32(ni->blk_addr);
raw_ne->version = ni->version;
}
enum mem_type {
FREE_NIDS, /* indicates the free nid list */
NAT_ENTRIES, /* indicates the cached nat entry */
DIRTY_DENTS /* indicates dirty dentry pages */
};
f2fs: refactor flush_nat_entries codes for reducing NAT writes Although building NAT journal in cursum reduce the read/write work for NAT block, but previous design leave us lower performance when write checkpoint frequently for these cases: 1. if journal in cursum has already full, it's a bit of waste that we flush all nat entries to page for persistence, but not to cache any entries. 2. if journal in cursum is not full, we fill nat entries to journal util journal is full, then flush the left dirty entries to disk without merge journaled entries, so these journaled entries may be flushed to disk at next checkpoint but lost chance to flushed last time. In this patch we merge dirty entries located in same NAT block to nat entry set, and linked all set to list, sorted ascending order by entries' count of set. Later we flush entries in sparse set into journal as many as we can, and then flush merged entries to disk. In this way we can not only gain in performance, but also save lifetime of flash device. In my testing environment, it shows this patch can help to reduce NAT block writes obviously. In hard disk test case: cost time of fsstress is stablely reduced by about 5%. 1. virtual machine + hard disk: fsstress -p 20 -n 200 -l 5 node num cp count nodes/cp based 4599.6 1803.0 2.551 patched 2714.6 1829.6 1.483 2. virtual machine + 32g micro SD card: fsstress -p 20 -n 200 -l 1 -w -f chown=0 -f creat=4 -f dwrite=0 -f fdatasync=4 -f fsync=4 -f link=0 -f mkdir=4 -f mknod=4 -f rename=5 -f rmdir=5 -f symlink=0 -f truncate=4 -f unlink=5 -f write=0 -S node num cp count nodes/cp based 84.5 43.7 1.933 patched 49.2 40.0 1.23 Our latency of merging op shows not bad when handling extreme case like: merging a great number of dirty nats: latency(ns) dirty nat count 3089219 24922 5129423 27422 4000250 24523 change log from v1: o fix wrong logic in add_nat_entry when grab a new nat entry set. o swith to create slab cache in create_node_manager_caches. o use GFP_ATOMIC instead of GFP_NOFS to avoid potential long latency. change log from v2: o make comment position more appropriate suggested by Jaegeuk Kim. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-06-24 09:18:20 +08:00
struct nat_entry_set {
struct list_head set_list; /* link with other nat sets */
f2fs: refactor flush_nat_entries codes for reducing NAT writes Although building NAT journal in cursum reduce the read/write work for NAT block, but previous design leave us lower performance when write checkpoint frequently for these cases: 1. if journal in cursum has already full, it's a bit of waste that we flush all nat entries to page for persistence, but not to cache any entries. 2. if journal in cursum is not full, we fill nat entries to journal util journal is full, then flush the left dirty entries to disk without merge journaled entries, so these journaled entries may be flushed to disk at next checkpoint but lost chance to flushed last time. In this patch we merge dirty entries located in same NAT block to nat entry set, and linked all set to list, sorted ascending order by entries' count of set. Later we flush entries in sparse set into journal as many as we can, and then flush merged entries to disk. In this way we can not only gain in performance, but also save lifetime of flash device. In my testing environment, it shows this patch can help to reduce NAT block writes obviously. In hard disk test case: cost time of fsstress is stablely reduced by about 5%. 1. virtual machine + hard disk: fsstress -p 20 -n 200 -l 5 node num cp count nodes/cp based 4599.6 1803.0 2.551 patched 2714.6 1829.6 1.483 2. virtual machine + 32g micro SD card: fsstress -p 20 -n 200 -l 1 -w -f chown=0 -f creat=4 -f dwrite=0 -f fdatasync=4 -f fsync=4 -f link=0 -f mkdir=4 -f mknod=4 -f rename=5 -f rmdir=5 -f symlink=0 -f truncate=4 -f unlink=5 -f write=0 -S node num cp count nodes/cp based 84.5 43.7 1.933 patched 49.2 40.0 1.23 Our latency of merging op shows not bad when handling extreme case like: merging a great number of dirty nats: latency(ns) dirty nat count 3089219 24922 5129423 27422 4000250 24523 change log from v1: o fix wrong logic in add_nat_entry when grab a new nat entry set. o swith to create slab cache in create_node_manager_caches. o use GFP_ATOMIC instead of GFP_NOFS to avoid potential long latency. change log from v2: o make comment position more appropriate suggested by Jaegeuk Kim. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-06-24 09:18:20 +08:00
struct list_head entry_list; /* link with dirty nat entries */
nid_t set; /* set number*/
f2fs: refactor flush_nat_entries codes for reducing NAT writes Although building NAT journal in cursum reduce the read/write work for NAT block, but previous design leave us lower performance when write checkpoint frequently for these cases: 1. if journal in cursum has already full, it's a bit of waste that we flush all nat entries to page for persistence, but not to cache any entries. 2. if journal in cursum is not full, we fill nat entries to journal util journal is full, then flush the left dirty entries to disk without merge journaled entries, so these journaled entries may be flushed to disk at next checkpoint but lost chance to flushed last time. In this patch we merge dirty entries located in same NAT block to nat entry set, and linked all set to list, sorted ascending order by entries' count of set. Later we flush entries in sparse set into journal as many as we can, and then flush merged entries to disk. In this way we can not only gain in performance, but also save lifetime of flash device. In my testing environment, it shows this patch can help to reduce NAT block writes obviously. In hard disk test case: cost time of fsstress is stablely reduced by about 5%. 1. virtual machine + hard disk: fsstress -p 20 -n 200 -l 5 node num cp count nodes/cp based 4599.6 1803.0 2.551 patched 2714.6 1829.6 1.483 2. virtual machine + 32g micro SD card: fsstress -p 20 -n 200 -l 1 -w -f chown=0 -f creat=4 -f dwrite=0 -f fdatasync=4 -f fsync=4 -f link=0 -f mkdir=4 -f mknod=4 -f rename=5 -f rmdir=5 -f symlink=0 -f truncate=4 -f unlink=5 -f write=0 -S node num cp count nodes/cp based 84.5 43.7 1.933 patched 49.2 40.0 1.23 Our latency of merging op shows not bad when handling extreme case like: merging a great number of dirty nats: latency(ns) dirty nat count 3089219 24922 5129423 27422 4000250 24523 change log from v1: o fix wrong logic in add_nat_entry when grab a new nat entry set. o swith to create slab cache in create_node_manager_caches. o use GFP_ATOMIC instead of GFP_NOFS to avoid potential long latency. change log from v2: o make comment position more appropriate suggested by Jaegeuk Kim. Signed-off-by: Chao Yu <chao2.yu@samsung.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
2014-06-24 09:18:20 +08:00
unsigned int entry_cnt; /* the # of nat entries in set */
};
/*
* For free nid mangement
*/
enum nid_state {
NID_NEW, /* newly added to free nid list */
NID_ALLOC /* it is allocated */
};
struct free_nid {
struct list_head list; /* for free node id list */
nid_t nid; /* node id */
int state; /* in use or not: NID_NEW or NID_ALLOC */
};
static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *fnid;
spin_lock(&nm_i->free_nid_list_lock);
if (nm_i->fcnt <= 0) {
spin_unlock(&nm_i->free_nid_list_lock);
return;
}
fnid = list_entry(nm_i->free_nid_list.next, struct free_nid, list);
*nid = fnid->nid;
spin_unlock(&nm_i->free_nid_list_lock);
}
/*
* inline functions
*/
static inline void get_nat_bitmap(struct f2fs_sb_info *sbi, void *addr)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
memcpy(addr, nm_i->nat_bitmap, nm_i->bitmap_size);
}
static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
pgoff_t block_off;
pgoff_t block_addr;
int seg_off;
block_off = NAT_BLOCK_OFFSET(start);
seg_off = block_off >> sbi->log_blocks_per_seg;
block_addr = (pgoff_t)(nm_i->nat_blkaddr +
(seg_off << sbi->log_blocks_per_seg << 1) +
(block_off & ((1 << sbi->log_blocks_per_seg) - 1)));
if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
block_addr += sbi->blocks_per_seg;
return block_addr;
}
static inline pgoff_t next_nat_addr(struct f2fs_sb_info *sbi,
pgoff_t block_addr)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
block_addr -= nm_i->nat_blkaddr;
if ((block_addr >> sbi->log_blocks_per_seg) % 2)
block_addr -= sbi->blocks_per_seg;
else
block_addr += sbi->blocks_per_seg;
return block_addr + nm_i->nat_blkaddr;
}
static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
{
unsigned int block_off = NAT_BLOCK_OFFSET(start_nid);
if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
f2fs_clear_bit(block_off, nm_i->nat_bitmap);
else
f2fs_set_bit(block_off, nm_i->nat_bitmap);
}
static inline void fill_node_footer(struct page *page, nid_t nid,
nid_t ino, unsigned int ofs, bool reset)
{
struct f2fs_node *rn = F2FS_NODE(page);
if (reset)
memset(rn, 0, sizeof(*rn));
rn->footer.nid = cpu_to_le32(nid);
rn->footer.ino = cpu_to_le32(ino);
rn->footer.flag = cpu_to_le32(ofs << OFFSET_BIT_SHIFT);
}
static inline void copy_node_footer(struct page *dst, struct page *src)
{
struct f2fs_node *src_rn = F2FS_NODE(src);
struct f2fs_node *dst_rn = F2FS_NODE(dst);
memcpy(&dst_rn->footer, &src_rn->footer, sizeof(struct node_footer));
}
static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
struct f2fs_node *rn = F2FS_NODE(page);
rn->footer.cp_ver = ckpt->checkpoint_ver;
rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
}
static inline nid_t ino_of_node(struct page *node_page)
{
struct f2fs_node *rn = F2FS_NODE(node_page);
return le32_to_cpu(rn->footer.ino);
}
static inline nid_t nid_of_node(struct page *node_page)
{
struct f2fs_node *rn = F2FS_NODE(node_page);
return le32_to_cpu(rn->footer.nid);
}
static inline unsigned int ofs_of_node(struct page *node_page)
{
struct f2fs_node *rn = F2FS_NODE(node_page);
unsigned flag = le32_to_cpu(rn->footer.flag);
return flag >> OFFSET_BIT_SHIFT;
}
static inline unsigned long long cpver_of_node(struct page *node_page)
{
struct f2fs_node *rn = F2FS_NODE(node_page);
return le64_to_cpu(rn->footer.cp_ver);
}
static inline block_t next_blkaddr_of_node(struct page *node_page)
{
struct f2fs_node *rn = F2FS_NODE(node_page);
return le32_to_cpu(rn->footer.next_blkaddr);
}
/*
* f2fs assigns the following node offsets described as (num).
* N = NIDS_PER_BLOCK
*
* Inode block (0)
* |- direct node (1)
* |- direct node (2)
* |- indirect node (3)
* | `- direct node (4 => 4 + N - 1)
* |- indirect node (4 + N)
* | `- direct node (5 + N => 5 + 2N - 1)
* `- double indirect node (5 + 2N)
* `- indirect node (6 + 2N)
* `- direct node
* ......
* `- indirect node ((6 + 2N) + x(N + 1))
* `- direct node
* ......
* `- indirect node ((6 + 2N) + (N - 1)(N + 1))
* `- direct node
*/
static inline bool IS_DNODE(struct page *node_page)
{
unsigned int ofs = ofs_of_node(node_page);
if (f2fs_has_xattr_block(ofs))
return false;
if (ofs == 3 || ofs == 4 + NIDS_PER_BLOCK ||
ofs == 5 + 2 * NIDS_PER_BLOCK)
return false;
if (ofs >= 6 + 2 * NIDS_PER_BLOCK) {
ofs -= 6 + 2 * NIDS_PER_BLOCK;
if (!((long int)ofs % (NIDS_PER_BLOCK + 1)))
return false;
}
return true;
}
static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
{
struct f2fs_node *rn = F2FS_NODE(p);
f2fs_wait_on_page_writeback(p, NODE);
if (i)
rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);
else
rn->in.nid[off] = cpu_to_le32(nid);
set_page_dirty(p);
}
static inline nid_t get_nid(struct page *p, int off, bool i)
{
struct f2fs_node *rn = F2FS_NODE(p);
if (i)
return le32_to_cpu(rn->i.i_nid[off - NODE_DIR1_BLOCK]);
return le32_to_cpu(rn->in.nid[off]);
}
/*
* Coldness identification:
* - Mark cold files in f2fs_inode_info
* - Mark cold node blocks in their node footer
* - Mark cold data pages in page cache
*/
static inline int is_file(struct inode *inode, int type)
{
return F2FS_I(inode)->i_advise & type;
}
static inline void set_file(struct inode *inode, int type)
{
F2FS_I(inode)->i_advise |= type;
}
static inline void clear_file(struct inode *inode, int type)
{
F2FS_I(inode)->i_advise &= ~type;
}
#define file_is_cold(inode) is_file(inode, FADVISE_COLD_BIT)
#define file_wrong_pino(inode) is_file(inode, FADVISE_LOST_PINO_BIT)
#define file_set_cold(inode) set_file(inode, FADVISE_COLD_BIT)
#define file_lost_pino(inode) set_file(inode, FADVISE_LOST_PINO_BIT)
#define file_clear_cold(inode) clear_file(inode, FADVISE_COLD_BIT)
#define file_got_pino(inode) clear_file(inode, FADVISE_LOST_PINO_BIT)
static inline int is_cold_data(struct page *page)
{
return PageChecked(page);
}
static inline void set_cold_data(struct page *page)
{
SetPageChecked(page);
}
static inline void clear_cold_data(struct page *page)
{
ClearPageChecked(page);
}
static inline int is_node(struct page *page, int type)
{
struct f2fs_node *rn = F2FS_NODE(page);
return le32_to_cpu(rn->footer.flag) & (1 << type);
}
#define is_cold_node(page) is_node(page, COLD_BIT_SHIFT)
#define is_fsync_dnode(page) is_node(page, FSYNC_BIT_SHIFT)
#define is_dent_dnode(page) is_node(page, DENT_BIT_SHIFT)
static inline void set_cold_node(struct inode *inode, struct page *page)
{
struct f2fs_node *rn = F2FS_NODE(page);
unsigned int flag = le32_to_cpu(rn->footer.flag);
if (S_ISDIR(inode->i_mode))
flag &= ~(0x1 << COLD_BIT_SHIFT);
else
flag |= (0x1 << COLD_BIT_SHIFT);
rn->footer.flag = cpu_to_le32(flag);
}
static inline void set_mark(struct page *page, int mark, int type)
{
struct f2fs_node *rn = F2FS_NODE(page);
unsigned int flag = le32_to_cpu(rn->footer.flag);
if (mark)
flag |= (0x1 << type);
else
flag &= ~(0x1 << type);
rn->footer.flag = cpu_to_le32(flag);
}
#define set_dentry_mark(page, mark) set_mark(page, mark, DENT_BIT_SHIFT)
#define set_fsync_mark(page, mark) set_mark(page, mark, FSYNC_BIT_SHIFT)