sync_inode - write an inode and its pages to disk.
* @inode: the inode to sync
The function is responsible to synchronize all dirty inodes belongings to a given superblock
task = kthread_create(bdi_writeback_thread, &bdi->wb,
"flush-%s", dev_name(bdi->dev));
root@szx3:/home/szx# ps -ef|grep flush
root 950 2 0 08:55 ? 00:00:00 [flush-8:0]
bdi_writeback_thread
struct bdi_writeback {
struct backing_dev_info *bdi; /* our parent bdi */
unsigned int nr;
unsigned long last_old_flush; /* last old data flush */
unsigned long last_active; /* last time bdi thread was active */
struct task_struct *task; /* writeback thread */
struct timer_list wakeup_timer; /* used for delayed bdi thread wakeup */
struct list_head b_dirty; /* dirty inodes */
struct list_head b_io; /* parked for writeback */
struct list_head b_more_io; /* parked for more writeback */
spinlock_t list_lock; /* protects the b_* lists */
};
struct backing_dev_info {
struct list_head bdi_list;
unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */
unsigned long state; /* Always use atomic bitops on this */
unsigned int capabilities; /* Device capabilities */
congested_fn *congested_fn; /* Function pointer if device is md/dm */
void *congested_data; /* Pointer to aux data for congested func */
char *name;
struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS];
unsigned long bw_time_stamp; /* last time write bw is updated */
unsigned long dirtied_stamp;
unsigned long written_stamp; /* pages written at bw_time_stamp */
unsigned long write_bandwidth; /* the estimated write bandwidth */
unsigned long avg_write_bandwidth; /* further smoothed write bw */
/*
* The base dirty throttle rate, re-calculated on every 200ms.
* All the bdi tasks' dirty rate will be curbed under it.
* @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit
* in small steps and is much more smooth/stable than the latter.
*/
unsigned long dirty_ratelimit;
unsigned long balanced_dirty_ratelimit;
struct prop_local_percpu completions;
int dirty_exceeded;
unsigned int min_ratio;
unsigned int max_ratio, max_prop_frac;
struct bdi_writeback wb; /* default writeback info for this bdi */
spinlock_t wb_lock; /* protects work_list */
struct list_head work_list;
struct device *dev;
struct timer_list laptop_mode_wb_timer;
#ifdef CONFIG_DEBUG_FS
struct dentry *debug_dir;
struct dentry *debug_stats;
#endif
};
/*
* Passed into wb_writeback(), essentially a subset of writeback_control
*/
struct wb_writeback_work {
long nr_pages;
struct super_block *sb;
unsigned long *older_than_this;
enum writeback_sync_modes sync_mode;
unsigned int tagged_writepages:1;
unsigned int for_kupdate:1;
unsigned int range_cyclic:1;
unsigned int for_background:1;
enum wb_reason reason; /* why was writeback initiated? */
struct list_head list; /* pending work list */
struct completion *done; /* set if the caller waits */
};
long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
{
struct backing_dev_info *bdi = wb->bdi;
struct wb_writeback_work *work;
long wrote = 0;
set_bit(BDI_writeback_running, &wb->bdi->state);
while ((work = get_next_work_item(bdi)) != NULL) {
/*
* Override sync mode, in case we must wait for completion
* because this thread is exiting now.
*/
if (force_wait)
work->sync_mode = WB_SYNC_ALL;
trace_writeback_exec(bdi, work);
wrote += wb_writeback(wb, work);
/*
* Notify the caller of completion if this is a synchronous
* work item, otherwise just free it.
*/
if (work->done)
complete(work->done);
else
kfree(work);
}
/*
* Check for periodic writeback, kupdated() style
*/
wrote += wb_check_old_data_flush(wb);
wrote += wb_check_background_flush(wb);
clear_bit(BDI_writeback_running, &wb->bdi->state);
return wrote;
}
the first time one of an inode's pages is dirtied, we mark the dirtying-time in the inode's address_space So this periodic writeback code just walks the superblock inode list, writing back any inodes which are older than a specific point in time.
__wait_on_bit
wait_queue_head_t *bit_waitqueue(void *word, int bit)
{
const int shift = BITS_PER_LONG == 32 ? 5 : 6;
const struct zone *zone = page_zone(virt_to_page(word));
unsigned long val = (unsigned long)word << shift | bit;
return &zone->wait_table[hash_long(val, zone->wait_table_bits)];
}
Zone -> wait_table
Zone -> wait_table_bits
Power-of-2 order of the size of the wait queue hash table array
The purpose of all there is to keep track of the people waiting for a page to become available and make them runnable again when possible . The trouble is that this consumes a lot of space ,especially when so few things wait on pages at a given time.
So instead of using per-page wait-queues , we use a waitqueue hash table.
BSF - Bit Scan Forward (386+)
Usage: BSF dest,src
Modifies flags: ZF
Scans source operand for first bit set. Sets ZF if a bit is found set and loads the destination with an index to first set bit. Clears ZF is no bits are found set. BSF scans forward across bit pattern (0-n) while BSR scans in reverse (n-0).
int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
{
int i;
struct pglist_data *pgdat = zone->zone_pgdat;
size_t alloc_size;
/*
* The per-page waitqueue mechanism uses hashed waitqueues
* per zone.
*/
zone->wait_table_hash_nr_entries =
wait_table_hash_nr_entries(zone_size_pages);
zone->wait_table_bits =
wait_table_bits(zone->wait_table_hash_nr_entries);
//....
}
从 低位 开始搜索
static inline unsigned long __ffs(unsigned long word)
{
asm("bsf %1,%0"
: "=r" (word)
: "rm" (word));
return word;
}
*/
static void inode_wait_for_writeback(struct inode *inode,
struct bdi_writeback *wb)
{
DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC);
wait_queue_head_t *wqh;
wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
while (inode->i_state & I_SYNC) {
spin_unlock(&inode->i_lock);
spin_unlock(&wb->list_lock);
__wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE);
spin_lock(&wb->list_lock);
spin_lock(&inode->i_lock);
}
}
The kernel can start to synchronize data from various different places , but all paths save one end up in
[sysc_sb_inodes] The function is responsible to synchronize all dirty inodes belonging to a given superblock ,
[writeback_single_inode ] is used for each inode .
static int
writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
struct writeback_control *wbc)
{
struct address_space *mapping = inode->i_mapping;
long nr_to_write = wbc->nr_to_write;
unsigned dirty;
int ret;
assert_spin_locked(&wb->list_lock);
assert_spin_locked(&inode->i_lock);
if (!atomic_read(&inode->i_count))
WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
else
WARN_ON(inode->i_state & I_WILL_FREE);
if (inode->i_state & I_SYNC) {
/*
* If this inode is locked for writeback and we are not doing
* writeback-for-data-integrity, move it to b_more_io so that
* writeback can proceed with the other inodes on s_io.
*
* We'll have another go at writing back this inode when we
* completed a full scan of b_io.
*/
if (wbc->sync_mode != WB_SYNC_ALL) {
requeue_io(inode, wb);
trace_writeback_single_inode_requeue(inode, wbc,
nr_to_write);
return 0;
}
/*
* It's a data-integrity sync. We must wait.
*/
inode_wait_for_writeback(inode, wb);
}
BUG_ON(inode->i_state & I_SYNC);
/* Set I_SYNC, reset I_DIRTY_PAGES */
inode->i_state |= I_SYNC;
inode->i_state &= ~I_DIRTY_PAGES;
spin_unlock(&inode->i_lock);
spin_unlock(&wb->list_lock);
ret = do_writepages(mapping, wbc);
/*
* Make sure to wait on the data before writing out the metadata.
* This is important for filesystems that modify metadata on data
* I/O completion.
*/
if (wbc->sync_mode == WB_SYNC_ALL) {
int err = filemap_fdatawait(mapping);
if (ret == 0)
ret = err;
}
/*
* Some filesystems may redirty the inode during the writeback
* due to delalloc, clear dirty metadata flags right before
* write_inode()
*/
spin_lock(&inode->i_lock);
dirty = inode->i_state & I_DIRTY;
inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC);
spin_unlock(&inode->i_lock);
/* Don't write the inode if only I_DIRTY_PAGES was set */
if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
int err = write_inode(inode, wbc);
if (ret == 0)
ret = err;
}
spin_lock(&wb->list_lock);
spin_lock(&inode->i_lock);
inode->i_state &= ~I_SYNC;
if (!(inode->i_state & I_FREEING)) {
/*
* Sync livelock prevention. Each inode is tagged and synced in
* one shot. If still dirty, it will be redirty_tail()'ed below.
* Update the dirty time to prevent enqueue and sync it again.
*/
if ((inode->i_state & I_DIRTY) &&
(wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages))
inode->dirtied_when = jiffies;
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
/*
* We didn't write back all the pages. nfs_writepages()
* sometimes bales out without doing anything.
*/
inode->i_state |= I_DIRTY_PAGES;
if (wbc->nr_to_write <= 0) {
/*
* slice used up: queue for next turn
*/
requeue_io(inode, wb);
} else {
/*
* Writeback blocked by something other than
* congestion. Delay the inode for some time to
* avoid spinning on the CPU (100% iowait)
* retrying writeback of the dirty page/inode
* that cannot be performed immediately.
*/
redirty_tail(inode, wb);
}
} else if (inode->i_state & I_DIRTY) {
/*
* Filesystems can dirty the inode during writeback
* operations, such as delayed allocation during
* submission or metadata updates after data IO
* completion.
*/
redirty_tail(inode, wb);
} else {
/*
* The inode is clean. At this point we either have
* a reference to the inode or it's on it's way out.
* No need to add it back to the LRU.
*/
list_del_init(&inode->i_wb_list);
}
}
inode_sync_complete(inode);
trace_writeback_single_inode(inode, wbc, nr_to_write);
return ret;
}