kernel-ark/mm/backing-dev.c
Peter Zijlstra 189d3c4a94 mm: bdi: allow setting a minimum for the bdi dirty limit
Under normal circumstances each device is given a part of the total write-back
cache that relates to its current avg writeout speed in relation to the other
devices.

min_ratio - allows one to assign a minimum portion of the write-back cache to
a particular device.  This is useful in situations where you might want to
provide a minimum QoS.  (One request for this feature came from flash based
storage people who wanted to avoid writing out at all costs - they of course
needed some pdflush hacks as well)

max_ratio - allows one to assign a maximum portion of the dirty limit to a
particular device.  This is useful in situations where you want to avoid one
device taking all or most of the write-back cache.  Eg.  an NFS mount that is
prone to get stuck, or a FUSE mount which you don't trust to play fair.

Add "min_ratio" to /sys/class/bdi.  This indicates the minimum percentage of
the global dirty threshold allocated to this bdi.

[mszeredi@suse.cz]

 - fix parsing in min_ratio_store()
 - document new sysfs attribute

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-30 08:29:50 -07:00

233 lines
5.1 KiB
C

#include <linux/wait.h>
#include <linux/backing-dev.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/writeback.h>
#include <linux/device.h>
static struct class *bdi_class;
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))
BDI_SHOW(reclaimable_kb, K(bdi_stat(bdi, BDI_RECLAIMABLE)))
BDI_SHOW(writeback_kb, K(bdi_stat(bdi, BDI_WRITEBACK)))
static inline unsigned long get_dirty(struct backing_dev_info *bdi, int i)
{
unsigned long thresh[3];
get_dirty_limits(&thresh[0], &thresh[1], &thresh[2], bdi);
return thresh[i];
}
BDI_SHOW(dirty_kb, K(get_dirty(bdi, 1)))
BDI_SHOW(bdi_dirty_kb, K(get_dirty(bdi, 2)))
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)
#define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store)
static struct device_attribute bdi_dev_attrs[] = {
__ATTR_RW(read_ahead_kb),
__ATTR_RO(reclaimable_kb),
__ATTR_RO(writeback_kb),
__ATTR_RO(dirty_kb),
__ATTR_RO(bdi_dirty_kb),
__ATTR_RW(min_ratio),
__ATTR_NULL,
};
static __init int bdi_class_init(void)
{
bdi_class = class_create(THIS_MODULE, "bdi");
bdi_class->dev_attrs = bdi_dev_attrs;
return 0;
}
core_initcall(bdi_class_init);
int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...)
{
char *name;
va_list args;
int ret = 0;
struct device *dev;
va_start(args, fmt);
name = kvasprintf(GFP_KERNEL, fmt, args);
va_end(args);
if (!name)
return -ENOMEM;
dev = device_create(bdi_class, parent, MKDEV(0, 0), name);
if (IS_ERR(dev)) {
ret = PTR_ERR(dev);
goto exit;
}
bdi->dev = dev;
dev_set_drvdata(bdi->dev, bdi);
exit:
kfree(name);
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) {
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;
for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
err = percpu_counter_init_irq(&bdi->bdi_stat[i], 0);
if (err)
goto err;
}
bdi->dirty_exceeded = 0;
err = prop_local_init_percpu(&bdi->completions);
if (err) {
err:
while (i--)
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]);
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 rw)
{
enum bdi_state bit;
wait_queue_head_t *wqh = &congestion_wqh[rw];
bit = (rw == WRITE) ? BDI_write_congested : BDI_read_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 rw)
{
enum bdi_state bit;
bit = (rw == WRITE) ? BDI_write_congested : BDI_read_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);