linux/mm/backing-dev.c

331 lines
7.6 KiB
C
Raw Normal View History

#include <linux/wait.h>
#include <linux/backing-dev.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/writeback.h>
#include <linux/device.h>
void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
{
}
EXPORT_SYMBOL(default_unplug_io_fn);
struct backing_dev_info default_backing_dev_info = {
.ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
.state = 0,
.capabilities = BDI_CAP_MAP_COPY,
.unplug_io_fn = default_unplug_io_fn,
};
EXPORT_SYMBOL_GPL(default_backing_dev_info);
static struct class *bdi_class;
#ifdef CONFIG_DEBUG_FS
#include <linux/debugfs.h>
#include <linux/seq_file.h>
static struct dentry *bdi_debug_root;
static void bdi_debug_init(void)
{
bdi_debug_root = debugfs_create_dir("bdi", NULL);
}
static int bdi_debug_stats_show(struct seq_file *m, void *v)
{
struct backing_dev_info *bdi = m->private;
unsigned long background_thresh;
unsigned long dirty_thresh;
unsigned long bdi_thresh;
get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi);
#define K(x) ((x) << (PAGE_SHIFT - 10))
seq_printf(m,
"BdiWriteback: %8lu kB\n"
"BdiReclaimable: %8lu kB\n"
"BdiDirtyThresh: %8lu kB\n"
"DirtyThresh: %8lu kB\n"
"BackgroundThresh: %8lu kB\n",
(unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),
(unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)),
K(bdi_thresh),
K(dirty_thresh),
K(background_thresh));
#undef K
return 0;
}
static int bdi_debug_stats_open(struct inode *inode, struct file *file)
{
return single_open(file, bdi_debug_stats_show, inode->i_private);
}
static const struct file_operations bdi_debug_stats_fops = {
.open = bdi_debug_stats_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static void bdi_debug_register(struct backing_dev_info *bdi, const char *name)
{
bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root);
bdi->debug_stats = debugfs_create_file("stats", 0444, bdi->debug_dir,
bdi, &bdi_debug_stats_fops);
}
static void bdi_debug_unregister(struct backing_dev_info *bdi)
{
debugfs_remove(bdi->debug_stats);
debugfs_remove(bdi->debug_dir);
}
#else
static inline void bdi_debug_init(void)
{
}
static inline void bdi_debug_register(struct backing_dev_info *bdi,
const char *name)
{
}
static inline void bdi_debug_unregister(struct backing_dev_info *bdi)
{
}
#endif
static ssize_t read_ahead_kb_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct backing_dev_info *bdi = dev_get_drvdata(dev);
char *end;
unsigned long read_ahead_kb;
ssize_t ret = -EINVAL;
read_ahead_kb = simple_strtoul(buf, &end, 10);
if (*buf && (end[0] == '\0' || (end[0] == '\n' && end[1] == '\0'))) {
bdi->ra_pages = read_ahead_kb >> (PAGE_SHIFT - 10);
ret = count;
}
return ret;
}
#define K(pages) ((pages) << (PAGE_SHIFT - 10))
#define BDI_SHOW(name, expr) \
static ssize_t name##_show(struct device *dev, \
struct device_attribute *attr, char *page) \
{ \
struct backing_dev_info *bdi = dev_get_drvdata(dev); \
\
return snprintf(page, PAGE_SIZE-1, "%lld\n", (long long)expr); \
}
BDI_SHOW(read_ahead_kb, K(bdi->ra_pages))
static ssize_t min_ratio_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
struct backing_dev_info *bdi = dev_get_drvdata(dev);
char *end;
unsigned int ratio;
ssize_t ret = -EINVAL;
ratio = simple_strtoul(buf, &end, 10);
if (*buf && (end[0] == '\0' || (end[0] == '\n' && end[1] == '\0'))) {
ret = bdi_set_min_ratio(bdi, ratio);
if (!ret)
ret = count;
}
return ret;
}
BDI_SHOW(min_ratio, bdi->min_ratio)
static ssize_t max_ratio_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
struct backing_dev_info *bdi = dev_get_drvdata(dev);
char *end;
unsigned int ratio;
ssize_t ret = -EINVAL;
ratio = simple_strtoul(buf, &end, 10);
if (*buf && (end[0] == '\0' || (end[0] == '\n' && end[1] == '\0'))) {
ret = bdi_set_max_ratio(bdi, ratio);
if (!ret)
ret = count;
}
return ret;
}
BDI_SHOW(max_ratio, bdi->max_ratio)
#define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store)
static struct device_attribute bdi_dev_attrs[] = {
__ATTR_RW(read_ahead_kb),
__ATTR_RW(min_ratio),
__ATTR_RW(max_ratio),
__ATTR_NULL,
};
static __init int bdi_class_init(void)
{
bdi_class = class_create(THIS_MODULE, "bdi");
bdi_class->dev_attrs = bdi_dev_attrs;
bdi_debug_init();
return 0;
}
postcore_initcall(bdi_class_init);
static int __init default_bdi_init(void)
{
int err;
err = bdi_init(&default_backing_dev_info);
if (!err)
bdi_register(&default_backing_dev_info, NULL, "default");
return err;
}
subsys_initcall(default_bdi_init);
int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...)
{
va_list args;
int ret = 0;
struct device *dev;
if (bdi->dev) /* The driver needs to use separate queues per device */
goto exit;
va_start(args, fmt);
dev = device_create_vargs(bdi_class, parent, MKDEV(0, 0), bdi, fmt, args);
va_end(args);
if (IS_ERR(dev)) {
ret = PTR_ERR(dev);
goto exit;
}
bdi->dev = dev;
bdi_debug_register(bdi, dev_name(dev));
exit:
return ret;
}
EXPORT_SYMBOL(bdi_register);
int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev)
{
return bdi_register(bdi, NULL, "%u:%u", MAJOR(dev), MINOR(dev));
}
EXPORT_SYMBOL(bdi_register_dev);
void bdi_unregister(struct backing_dev_info *bdi)
{
if (bdi->dev) {
bdi_debug_unregister(bdi);
device_unregister(bdi->dev);
bdi->dev = NULL;
}
}
EXPORT_SYMBOL(bdi_unregister);
int bdi_init(struct backing_dev_info *bdi)
{
int i;
int err;
bdi->dev = NULL;
bdi->min_ratio = 0;
bdi->max_ratio = 100;
bdi->max_prop_frac = PROP_FRAC_BASE;
for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
err = percpu_counter_init(&bdi->bdi_stat[i], 0);
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
if (err)
goto err;
}
bdi->dirty_exceeded = 0;
err = prop_local_init_percpu(&bdi->completions);
if (err) {
err:
while (i--)
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
percpu_counter_destroy(&bdi->bdi_stat[i]);
}
return err;
}
EXPORT_SYMBOL(bdi_init);
void bdi_destroy(struct backing_dev_info *bdi)
{
int i;
bdi_unregister(bdi);
for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
percpu_counter_destroy(&bdi->bdi_stat[i]);
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00
prop_local_destroy_percpu(&bdi->completions);
}
EXPORT_SYMBOL(bdi_destroy);
static wait_queue_head_t congestion_wqh[2] = {
__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
};
void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
{
enum bdi_state bit;
wait_queue_head_t *wqh = &congestion_wqh[sync];
bit = sync ? BDI_sync_congested : BDI_async_congested;
clear_bit(bit, &bdi->state);
smp_mb__after_clear_bit();
if (waitqueue_active(wqh))
wake_up(wqh);
}
EXPORT_SYMBOL(clear_bdi_congested);
void set_bdi_congested(struct backing_dev_info *bdi, int sync)
{
enum bdi_state bit;
bit = sync ? BDI_sync_congested : BDI_async_congested;
set_bit(bit, &bdi->state);
}
EXPORT_SYMBOL(set_bdi_congested);
/**
* congestion_wait - wait for a backing_dev to become uncongested
* @rw: READ or WRITE
* @timeout: timeout in jiffies
*
* Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit
* write congestion. If no backing_devs are congested then just wait for the
* next write to be completed.
*/
long congestion_wait(int rw, long timeout)
{
long ret;
DEFINE_WAIT(wait);
wait_queue_head_t *wqh = &congestion_wqh[rw];
prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
ret = io_schedule_timeout(timeout);
finish_wait(wqh, &wait);
return ret;
}
EXPORT_SYMBOL(congestion_wait);
mm: per device dirty threshold Scale writeback cache per backing device, proportional to its writeout speed. By decoupling the BDI dirty thresholds a number of problems we currently have will go away, namely: - mutual interference starvation (for any number of BDIs); - deadlocks with stacked BDIs (loop, FUSE and local NFS mounts). It might be that all dirty pages are for a single BDI while other BDIs are idling. By giving each BDI a 'fair' share of the dirty limit, each one can have dirty pages outstanding and make progress. A global threshold also creates a deadlock for stacked BDIs; when A writes to B, and A generates enough dirty pages to get throttled, B will never start writeback until the dirty pages go away. Again, by giving each BDI its own 'independent' dirty limit, this problem is avoided. So the problem is to determine how to distribute the total dirty limit across the BDIs fairly and efficiently. A DBI that has a large dirty limit but does not have any dirty pages outstanding is a waste. What is done is to keep a floating proportion between the DBIs based on writeback completions. This way faster/more active devices get a larger share than slower/idle devices. [akpm@linux-foundation.org: fix warnings] [hugh@veritas.com: Fix occasional hang when a task couldn't get out of balance_dirty_pages] Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-17 10:25:50 +04:00