*/
#include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
-#include <linux/buffer_head.h>
+#include <linux/buffer_head.h> /* __set_page_dirty_buffers */
#include <linux/pagevec.h>
#include <trace/events/writeback.h>
/*
- * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
- * will look to see if it needs to force writeback or throttling.
+ * Sleep at most 200ms at a time in balance_dirty_pages().
*/
-static long ratelimit_pages = 32;
+#define MAX_PAUSE max(HZ/5, 1)
/*
- * When balance_dirty_pages decides that the caller needs to perform some
- * non-background writeback, this is how many pages it will attempt to write.
- * It should be somewhat larger than dirtied pages to ensure that reasonably
- * large amounts of I/O are submitted.
+ * Try to keep balance_dirty_pages() call intervals higher than this many pages
+ * by raising pause time to max_pause when falls below it.
*/
-static inline long sync_writeback_pages(unsigned long dirtied)
-{
- if (dirtied < ratelimit_pages)
- dirtied = ratelimit_pages;
+#define DIRTY_POLL_THRESH (128 >> (PAGE_SHIFT - 10))
- return dirtied + dirtied / 2;
-}
+/*
+ * Estimate write bandwidth at 200ms intervals.
+ */
+#define BANDWIDTH_INTERVAL max(HZ/5, 1)
+
+#define RATELIMIT_CALC_SHIFT 10
+
+/*
+ * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
+ * will look to see if it needs to force writeback or throttling.
+ */
+static long ratelimit_pages = 32;
/* The following parameters are exported via /proc/sys/vm */
*/
unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */
+EXPORT_SYMBOL_GPL(dirty_writeback_interval);
+
/*
* The longest time for which data is allowed to remain dirty
*/
/* End of sysctl-exported parameters */
+unsigned long global_dirty_limit;
/*
* Scale the writeback cache size proportional to the relative writeout speeds.
*
*/
static struct prop_descriptor vm_completions;
-static struct prop_descriptor vm_dirties;
+
+/*
+ * Work out the current dirty-memory clamping and background writeout
+ * thresholds.
+ *
+ * The main aim here is to lower them aggressively if there is a lot of mapped
+ * memory around. To avoid stressing page reclaim with lots of unreclaimable
+ * pages. It is better to clamp down on writers than to start swapping, and
+ * performing lots of scanning.
+ *
+ * We only allow 1/2 of the currently-unmapped memory to be dirtied.
+ *
+ * We don't permit the clamping level to fall below 5% - that is getting rather
+ * excessive.
+ *
+ * We make sure that the background writeout level is below the adjusted
+ * clamping level.
+ */
+
+/*
+ * In a memory zone, there is a certain amount of pages we consider
+ * available for the page cache, which is essentially the number of
+ * free and reclaimable pages, minus some zone reserves to protect
+ * lowmem and the ability to uphold the zone's watermarks without
+ * requiring writeback.
+ *
+ * This number of dirtyable pages is the base value of which the
+ * user-configurable dirty ratio is the effictive number of pages that
+ * are allowed to be actually dirtied. Per individual zone, or
+ * globally by using the sum of dirtyable pages over all zones.
+ *
+ * Because the user is allowed to specify the dirty limit globally as
+ * absolute number of bytes, calculating the per-zone dirty limit can
+ * require translating the configured limit into a percentage of
+ * global dirtyable memory first.
+ */
+
+static unsigned long highmem_dirtyable_memory(unsigned long total)
+{
+#ifdef CONFIG_HIGHMEM
+ int node;
+ unsigned long x = 0;
+
+ for_each_node_state(node, N_HIGH_MEMORY) {
+ struct zone *z =
+ &NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
+
+ x += zone_page_state(z, NR_FREE_PAGES) +
+ zone_reclaimable_pages(z) - z->dirty_balance_reserve;
+ }
+ /*
+ * Make sure that the number of highmem pages is never larger
+ * than the number of the total dirtyable memory. This can only
+ * occur in very strange VM situations but we want to make sure
+ * that this does not occur.
+ */
+ return min(x, total);
+#else
+ return 0;
+#endif
+}
+
+/**
+ * global_dirtyable_memory - number of globally dirtyable pages
+ *
+ * Returns the global number of pages potentially available for dirty
+ * page cache. This is the base value for the global dirty limits.
+ */
+unsigned long global_dirtyable_memory(void)
+{
+ unsigned long x;
+
+ x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages() -
+ dirty_balance_reserve;
+
+ if (!vm_highmem_is_dirtyable)
+ x -= highmem_dirtyable_memory(x);
+
+ return x + 1; /* Ensure that we never return 0 */
+}
+
+/*
+ * global_dirty_limits - background-writeback and dirty-throttling thresholds
+ *
+ * Calculate the dirty thresholds based on sysctl parameters
+ * - vm.dirty_background_ratio or vm.dirty_background_bytes
+ * - vm.dirty_ratio or vm.dirty_bytes
+ * The dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and
+ * real-time tasks.
+ */
+void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
+{
+ unsigned long background;
+ unsigned long dirty;
+ unsigned long uninitialized_var(available_memory);
+ struct task_struct *tsk;
+
+ if (!vm_dirty_bytes || !dirty_background_bytes)
+ available_memory = global_dirtyable_memory();
+
+ if (vm_dirty_bytes)
+ dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE);
+ else
+ dirty = (vm_dirty_ratio * available_memory) / 100;
+
+ if (dirty_background_bytes)
+ background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE);
+ else
+ background = (dirty_background_ratio * available_memory) / 100;
+
+ if (background >= dirty)
+ background = dirty / 2;
+ tsk = current;
+ if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
+ background += background / 4;
+ dirty += dirty / 4;
+ }
+ *pbackground = background;
+ *pdirty = dirty;
+ trace_global_dirty_state(background, dirty);
+}
+
+/**
+ * zone_dirtyable_memory - number of dirtyable pages in a zone
+ * @zone: the zone
+ *
+ * Returns the zone's number of pages potentially available for dirty
+ * page cache. This is the base value for the per-zone dirty limits.
+ */
+static unsigned long zone_dirtyable_memory(struct zone *zone)
+{
+ /*
+ * The effective global number of dirtyable pages may exclude
+ * highmem as a big-picture measure to keep the ratio between
+ * dirty memory and lowmem reasonable.
+ *
+ * But this function is purely about the individual zone and a
+ * highmem zone can hold its share of dirty pages, so we don't
+ * care about vm_highmem_is_dirtyable here.
+ */
+ return zone_page_state(zone, NR_FREE_PAGES) +
+ zone_reclaimable_pages(zone) -
+ zone->dirty_balance_reserve;
+}
+
+/**
+ * zone_dirty_limit - maximum number of dirty pages allowed in a zone
+ * @zone: the zone
+ *
+ * Returns the maximum number of dirty pages allowed in a zone, based
+ * on the zone's dirtyable memory.
+ */
+static unsigned long zone_dirty_limit(struct zone *zone)
+{
+ unsigned long zone_memory = zone_dirtyable_memory(zone);
+ struct task_struct *tsk = current;
+ unsigned long dirty;
+
+ if (vm_dirty_bytes)
+ dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) *
+ zone_memory / global_dirtyable_memory();
+ else
+ dirty = vm_dirty_ratio * zone_memory / 100;
+
+ if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk))
+ dirty += dirty / 4;
+
+ return dirty;
+}
+
+/**
+ * zone_dirty_ok - tells whether a zone is within its dirty limits
+ * @zone: the zone to check
+ *
+ * Returns %true when the dirty pages in @zone are within the zone's
+ * dirty limit, %false if the limit is exceeded.
+ */
+bool zone_dirty_ok(struct zone *zone)
+{
+ unsigned long limit = zone_dirty_limit(zone);
+
+ return zone_page_state(zone, NR_FILE_DIRTY) +
+ zone_page_state(zone, NR_UNSTABLE_NFS) +
+ zone_page_state(zone, NR_WRITEBACK) <= limit;
+}
/*
* couple the period to the dirty_ratio:
if (vm_dirty_bytes)
dirty_total = vm_dirty_bytes / PAGE_SIZE;
else
- dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) /
+ dirty_total = (vm_dirty_ratio * global_dirtyable_memory()) /
100;
return 2 + ilog2(dirty_total - 1);
}
{
int shift = calc_period_shift();
prop_change_shift(&vm_completions, shift);
- prop_change_shift(&vm_dirties, shift);
+
+ writeback_set_ratelimit();
}
int dirty_background_ratio_handler(struct ctl_table *table, int write,
return ret;
}
-
int dirty_bytes_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
*/
static inline void __bdi_writeout_inc(struct backing_dev_info *bdi)
{
+ __inc_bdi_stat(bdi, BDI_WRITTEN);
__prop_inc_percpu_max(&vm_completions, &bdi->completions,
bdi->max_prop_frac);
}
}
EXPORT_SYMBOL_GPL(bdi_writeout_inc);
-void task_dirty_inc(struct task_struct *tsk)
-{
- prop_inc_single(&vm_dirties, &tsk->dirties);
-}
-
/*
* Obtain an accurate fraction of the BDI's portion.
*/
static void bdi_writeout_fraction(struct backing_dev_info *bdi,
long *numerator, long *denominator)
{
- if (bdi_cap_writeback_dirty(bdi)) {
- prop_fraction_percpu(&vm_completions, &bdi->completions,
+ prop_fraction_percpu(&vm_completions, &bdi->completions,
numerator, denominator);
- } else {
- *numerator = 0;
- *denominator = 1;
- }
-}
-
-static inline void task_dirties_fraction(struct task_struct *tsk,
- long *numerator, long *denominator)
-{
- prop_fraction_single(&vm_dirties, &tsk->dirties,
- numerator, denominator);
-}
-
-/*
- * task_dirty_limit - scale down dirty throttling threshold for one task
- *
- * task specific dirty limit:
- *
- * dirty -= (dirty/8) * p_{t}
- *
- * To protect light/slow dirtying tasks from heavier/fast ones, we start
- * throttling individual tasks before reaching the bdi dirty limit.
- * Relatively low thresholds will be allocated to heavy dirtiers. So when
- * dirty pages grow large, heavy dirtiers will be throttled first, which will
- * effectively curb the growth of dirty pages. Light dirtiers with high enough
- * dirty threshold may never get throttled.
- */
-static unsigned long task_dirty_limit(struct task_struct *tsk,
- unsigned long bdi_dirty)
-{
- long numerator, denominator;
- unsigned long dirty = bdi_dirty;
- u64 inv = dirty >> 3;
-
- task_dirties_fraction(tsk, &numerator, &denominator);
- inv *= numerator;
- do_div(inv, denominator);
-
- dirty -= inv;
-
- return max(dirty, bdi_dirty/2);
}
/*
- *
+ * bdi_min_ratio keeps the sum of the minimum dirty shares of all
+ * registered backing devices, which, for obvious reasons, can not
+ * exceed 100%.
*/
static unsigned int bdi_min_ratio;
}
EXPORT_SYMBOL(bdi_set_max_ratio);
-/*
- * Work out the current dirty-memory clamping and background writeout
- * thresholds.
+static unsigned long dirty_freerun_ceiling(unsigned long thresh,
+ unsigned long bg_thresh)
+{
+ return (thresh + bg_thresh) / 2;
+}
+
+static unsigned long hard_dirty_limit(unsigned long thresh)
+{
+ return max(thresh, global_dirty_limit);
+}
+
+/**
+ * bdi_dirty_limit - @bdi's share of dirty throttling threshold
+ * @bdi: the backing_dev_info to query
+ * @dirty: global dirty limit in pages
*
- * The main aim here is to lower them aggressively if there is a lot of mapped
- * memory around. To avoid stressing page reclaim with lots of unreclaimable
- * pages. It is better to clamp down on writers than to start swapping, and
- * performing lots of scanning.
+ * Returns @bdi's dirty limit in pages. The term "dirty" in the context of
+ * dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages.
*
- * We only allow 1/2 of the currently-unmapped memory to be dirtied.
+ * Note that balance_dirty_pages() will only seriously take it as a hard limit
+ * when sleeping max_pause per page is not enough to keep the dirty pages under
+ * control. For example, when the device is completely stalled due to some error
+ * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key.
+ * In the other normal situations, it acts more gently by throttling the tasks
+ * more (rather than completely block them) when the bdi dirty pages go high.
*
- * We don't permit the clamping level to fall below 5% - that is getting rather
- * excessive.
+ * It allocates high/low dirty limits to fast/slow devices, in order to prevent
+ * - starving fast devices
+ * - piling up dirty pages (that will take long time to sync) on slow devices
*
- * We make sure that the background writeout level is below the adjusted
- * clamping level.
+ * The bdi's share of dirty limit will be adapting to its throughput and
+ * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set.
*/
+unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty)
+{
+ u64 bdi_dirty;
+ long numerator, denominator;
-static unsigned long highmem_dirtyable_memory(unsigned long total)
+ /*
+ * Calculate this BDI's share of the dirty ratio.
+ */
+ bdi_writeout_fraction(bdi, &numerator, &denominator);
+
+ bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100;
+ bdi_dirty *= numerator;
+ do_div(bdi_dirty, denominator);
+
+ bdi_dirty += (dirty * bdi->min_ratio) / 100;
+ if (bdi_dirty > (dirty * bdi->max_ratio) / 100)
+ bdi_dirty = dirty * bdi->max_ratio / 100;
+
+ return bdi_dirty;
+}
+
+/*
+ * Dirty position control.
+ *
+ * (o) global/bdi setpoints
+ *
+ * We want the dirty pages be balanced around the global/bdi setpoints.
+ * When the number of dirty pages is higher/lower than the setpoint, the
+ * dirty position control ratio (and hence task dirty ratelimit) will be
+ * decreased/increased to bring the dirty pages back to the setpoint.
+ *
+ * pos_ratio = 1 << RATELIMIT_CALC_SHIFT
+ *
+ * if (dirty < setpoint) scale up pos_ratio
+ * if (dirty > setpoint) scale down pos_ratio
+ *
+ * if (bdi_dirty < bdi_setpoint) scale up pos_ratio
+ * if (bdi_dirty > bdi_setpoint) scale down pos_ratio
+ *
+ * task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT
+ *
+ * (o) global control line
+ *
+ * ^ pos_ratio
+ * |
+ * | |<===== global dirty control scope ======>|
+ * 2.0 .............*
+ * | .*
+ * | . *
+ * | . *
+ * | . *
+ * | . *
+ * | . *
+ * 1.0 ................................*
+ * | . . *
+ * | . . *
+ * | . . *
+ * | . . *
+ * | . . *
+ * 0 +------------.------------------.----------------------*------------->
+ * freerun^ setpoint^ limit^ dirty pages
+ *
+ * (o) bdi control line
+ *
+ * ^ pos_ratio
+ * |
+ * | *
+ * | *
+ * | *
+ * | *
+ * | * |<=========== span ============>|
+ * 1.0 .......................*
+ * | . *
+ * | . *
+ * | . *
+ * | . *
+ * | . *
+ * | . *
+ * | . *
+ * | . *
+ * | . *
+ * | . *
+ * | . *
+ * 1/4 ...............................................* * * * * * * * * * * *
+ * | . .
+ * | . .
+ * | . .
+ * 0 +----------------------.-------------------------------.------------->
+ * bdi_setpoint^ x_intercept^
+ *
+ * The bdi control line won't drop below pos_ratio=1/4, so that bdi_dirty can
+ * be smoothly throttled down to normal if it starts high in situations like
+ * - start writing to a slow SD card and a fast disk at the same time. The SD
+ * card's bdi_dirty may rush to many times higher than bdi_setpoint.
+ * - the bdi dirty thresh drops quickly due to change of JBOD workload
+ */
+static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
+ unsigned long thresh,
+ unsigned long bg_thresh,
+ unsigned long dirty,
+ unsigned long bdi_thresh,
+ unsigned long bdi_dirty)
{
-#ifdef CONFIG_HIGHMEM
- int node;
- unsigned long x = 0;
+ unsigned long write_bw = bdi->avg_write_bandwidth;
+ unsigned long freerun = dirty_freerun_ceiling(thresh, bg_thresh);
+ unsigned long limit = hard_dirty_limit(thresh);
+ unsigned long x_intercept;
+ unsigned long setpoint; /* dirty pages' target balance point */
+ unsigned long bdi_setpoint;
+ unsigned long span;
+ long long pos_ratio; /* for scaling up/down the rate limit */
+ long x;
+
+ if (unlikely(dirty >= limit))
+ return 0;
- for_each_node_state(node, N_HIGH_MEMORY) {
- struct zone *z =
- &NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
+ /*
+ * global setpoint
+ *
+ * setpoint - dirty 3
+ * f(dirty) := 1.0 + (----------------)
+ * limit - setpoint
+ *
+ * it's a 3rd order polynomial that subjects to
+ *
+ * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast
+ * (2) f(setpoint) = 1.0 => the balance point
+ * (3) f(limit) = 0 => the hard limit
+ * (4) df/dx <= 0 => negative feedback control
+ * (5) the closer to setpoint, the smaller |df/dx| (and the reverse)
+ * => fast response on large errors; small oscillation near setpoint
+ */
+ setpoint = (freerun + limit) / 2;
+ x = div_s64((setpoint - dirty) << RATELIMIT_CALC_SHIFT,
+ limit - setpoint + 1);
+ pos_ratio = x;
+ pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
+ pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
+ pos_ratio += 1 << RATELIMIT_CALC_SHIFT;
- x += zone_page_state(z, NR_FREE_PAGES) +
- zone_reclaimable_pages(z);
+ /*
+ * We have computed basic pos_ratio above based on global situation. If
+ * the bdi is over/under its share of dirty pages, we want to scale
+ * pos_ratio further down/up. That is done by the following mechanism.
+ */
+
+ /*
+ * bdi setpoint
+ *
+ * f(bdi_dirty) := 1.0 + k * (bdi_dirty - bdi_setpoint)
+ *
+ * x_intercept - bdi_dirty
+ * := --------------------------
+ * x_intercept - bdi_setpoint
+ *
+ * The main bdi control line is a linear function that subjects to
+ *
+ * (1) f(bdi_setpoint) = 1.0
+ * (2) k = - 1 / (8 * write_bw) (in single bdi case)
+ * or equally: x_intercept = bdi_setpoint + 8 * write_bw
+ *
+ * For single bdi case, the dirty pages are observed to fluctuate
+ * regularly within range
+ * [bdi_setpoint - write_bw/2, bdi_setpoint + write_bw/2]
+ * for various filesystems, where (2) can yield in a reasonable 12.5%
+ * fluctuation range for pos_ratio.
+ *
+ * For JBOD case, bdi_thresh (not bdi_dirty!) could fluctuate up to its
+ * own size, so move the slope over accordingly and choose a slope that
+ * yields 100% pos_ratio fluctuation on suddenly doubled bdi_thresh.
+ */
+ if (unlikely(bdi_thresh > thresh))
+ bdi_thresh = thresh;
+ /*
+ * It's very possible that bdi_thresh is close to 0 not because the
+ * device is slow, but that it has remained inactive for long time.
+ * Honour such devices a reasonable good (hopefully IO efficient)
+ * threshold, so that the occasional writes won't be blocked and active
+ * writes can rampup the threshold quickly.
+ */
+ bdi_thresh = max(bdi_thresh, (limit - dirty) / 8);
+ /*
+ * scale global setpoint to bdi's:
+ * bdi_setpoint = setpoint * bdi_thresh / thresh
+ */
+ x = div_u64((u64)bdi_thresh << 16, thresh + 1);
+ bdi_setpoint = setpoint * (u64)x >> 16;
+ /*
+ * Use span=(8*write_bw) in single bdi case as indicated by
+ * (thresh - bdi_thresh ~= 0) and transit to bdi_thresh in JBOD case.
+ *
+ * bdi_thresh thresh - bdi_thresh
+ * span = ---------- * (8 * write_bw) + ------------------- * bdi_thresh
+ * thresh thresh
+ */
+ span = (thresh - bdi_thresh + 8 * write_bw) * (u64)x >> 16;
+ x_intercept = bdi_setpoint + span;
+
+ if (bdi_dirty < x_intercept - span / 4) {
+ pos_ratio = div_u64(pos_ratio * (x_intercept - bdi_dirty),
+ x_intercept - bdi_setpoint + 1);
+ } else
+ pos_ratio /= 4;
+
+ /*
+ * bdi reserve area, safeguard against dirty pool underrun and disk idle
+ * It may push the desired control point of global dirty pages higher
+ * than setpoint.
+ */
+ x_intercept = bdi_thresh / 2;
+ if (bdi_dirty < x_intercept) {
+ if (bdi_dirty > x_intercept / 8)
+ pos_ratio = div_u64(pos_ratio * x_intercept, bdi_dirty);
+ else
+ pos_ratio *= 8;
}
+
+ return pos_ratio;
+}
+
+static void bdi_update_write_bandwidth(struct backing_dev_info *bdi,
+ unsigned long elapsed,
+ unsigned long written)
+{
+ const unsigned long period = roundup_pow_of_two(3 * HZ);
+ unsigned long avg = bdi->avg_write_bandwidth;
+ unsigned long old = bdi->write_bandwidth;
+ u64 bw;
+
/*
- * Make sure that the number of highmem pages is never larger
- * than the number of the total dirtyable memory. This can only
- * occur in very strange VM situations but we want to make sure
- * that this does not occur.
+ * bw = written * HZ / elapsed
+ *
+ * bw * elapsed + write_bandwidth * (period - elapsed)
+ * write_bandwidth = ---------------------------------------------------
+ * period
*/
- return min(x, total);
-#else
- return 0;
-#endif
+ bw = written - bdi->written_stamp;
+ bw *= HZ;
+ if (unlikely(elapsed > period)) {
+ do_div(bw, elapsed);
+ avg = bw;
+ goto out;
+ }
+ bw += (u64)bdi->write_bandwidth * (period - elapsed);
+ bw >>= ilog2(period);
+
+ /*
+ * one more level of smoothing, for filtering out sudden spikes
+ */
+ if (avg > old && old >= (unsigned long)bw)
+ avg -= (avg - old) >> 3;
+
+ if (avg < old && old <= (unsigned long)bw)
+ avg += (old - avg) >> 3;
+
+out:
+ bdi->write_bandwidth = bw;
+ bdi->avg_write_bandwidth = avg;
}
-/**
- * determine_dirtyable_memory - amount of memory that may be used
- *
- * Returns the numebr of pages that can currently be freed and used
- * by the kernel for direct mappings.
+/*
+ * The global dirtyable memory and dirty threshold could be suddenly knocked
+ * down by a large amount (eg. on the startup of KVM in a swapless system).
+ * This may throw the system into deep dirty exceeded state and throttle
+ * heavy/light dirtiers alike. To retain good responsiveness, maintain
+ * global_dirty_limit for tracking slowly down to the knocked down dirty
+ * threshold.
*/
-unsigned long determine_dirtyable_memory(void)
+static void update_dirty_limit(unsigned long thresh, unsigned long dirty)
{
- unsigned long x;
+ unsigned long limit = global_dirty_limit;
+
+ /*
+ * Follow up in one step.
+ */
+ if (limit < thresh) {
+ limit = thresh;
+ goto update;
+ }
- x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
+ /*
+ * Follow down slowly. Use the higher one as the target, because thresh
+ * may drop below dirty. This is exactly the reason to introduce
+ * global_dirty_limit which is guaranteed to lie above the dirty pages.
+ */
+ thresh = max(thresh, dirty);
+ if (limit > thresh) {
+ limit -= (limit - thresh) >> 5;
+ goto update;
+ }
+ return;
+update:
+ global_dirty_limit = limit;
+}
- if (!vm_highmem_is_dirtyable)
- x -= highmem_dirtyable_memory(x);
+static void global_update_bandwidth(unsigned long thresh,
+ unsigned long dirty,
+ unsigned long now)
+{
+ static DEFINE_SPINLOCK(dirty_lock);
+ static unsigned long update_time;
- return x + 1; /* Ensure that we never return 0 */
+ /*
+ * check locklessly first to optimize away locking for the most time
+ */
+ if (time_before(now, update_time + BANDWIDTH_INTERVAL))
+ return;
+
+ spin_lock(&dirty_lock);
+ if (time_after_eq(now, update_time + BANDWIDTH_INTERVAL)) {
+ update_dirty_limit(thresh, dirty);
+ update_time = now;
+ }
+ spin_unlock(&dirty_lock);
}
/*
- * global_dirty_limits - background-writeback and dirty-throttling thresholds
+ * Maintain bdi->dirty_ratelimit, the base dirty throttle rate.
*
- * Calculate the dirty thresholds based on sysctl parameters
- * - vm.dirty_background_ratio or vm.dirty_background_bytes
- * - vm.dirty_ratio or vm.dirty_bytes
- * The dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and
- * real-time tasks.
+ * Normal bdi tasks will be curbed at or below it in long term.
+ * Obviously it should be around (write_bw / N) when there are N dd tasks.
*/
-void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
+static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi,
+ unsigned long thresh,
+ unsigned long bg_thresh,
+ unsigned long dirty,
+ unsigned long bdi_thresh,
+ unsigned long bdi_dirty,
+ unsigned long dirtied,
+ unsigned long elapsed)
{
- unsigned long background;
- unsigned long dirty;
- unsigned long uninitialized_var(available_memory);
- struct task_struct *tsk;
+ unsigned long freerun = dirty_freerun_ceiling(thresh, bg_thresh);
+ unsigned long limit = hard_dirty_limit(thresh);
+ unsigned long setpoint = (freerun + limit) / 2;
+ unsigned long write_bw = bdi->avg_write_bandwidth;
+ unsigned long dirty_ratelimit = bdi->dirty_ratelimit;
+ unsigned long dirty_rate;
+ unsigned long task_ratelimit;
+ unsigned long balanced_dirty_ratelimit;
+ unsigned long pos_ratio;
+ unsigned long step;
+ unsigned long x;
- if (!vm_dirty_bytes || !dirty_background_bytes)
- available_memory = determine_dirtyable_memory();
+ /*
+ * The dirty rate will match the writeout rate in long term, except
+ * when dirty pages are truncated by userspace or re-dirtied by FS.
+ */
+ dirty_rate = (dirtied - bdi->dirtied_stamp) * HZ / elapsed;
- if (vm_dirty_bytes)
- dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE);
- else
- dirty = (vm_dirty_ratio * available_memory) / 100;
+ pos_ratio = bdi_position_ratio(bdi, thresh, bg_thresh, dirty,
+ bdi_thresh, bdi_dirty);
+ /*
+ * task_ratelimit reflects each dd's dirty rate for the past 200ms.
+ */
+ task_ratelimit = (u64)dirty_ratelimit *
+ pos_ratio >> RATELIMIT_CALC_SHIFT;
+ task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */
- if (dirty_background_bytes)
- background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE);
+ /*
+ * A linear estimation of the "balanced" throttle rate. The theory is,
+ * if there are N dd tasks, each throttled at task_ratelimit, the bdi's
+ * dirty_rate will be measured to be (N * task_ratelimit). So the below
+ * formula will yield the balanced rate limit (write_bw / N).
+ *
+ * Note that the expanded form is not a pure rate feedback:
+ * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) (1)
+ * but also takes pos_ratio into account:
+ * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) * pos_ratio (2)
+ *
+ * (1) is not realistic because pos_ratio also takes part in balancing
+ * the dirty rate. Consider the state
+ * pos_ratio = 0.5 (3)
+ * rate = 2 * (write_bw / N) (4)
+ * If (1) is used, it will stuck in that state! Because each dd will
+ * be throttled at
+ * task_ratelimit = pos_ratio * rate = (write_bw / N) (5)
+ * yielding
+ * dirty_rate = N * task_ratelimit = write_bw (6)
+ * put (6) into (1) we get
+ * rate_(i+1) = rate_(i) (7)
+ *
+ * So we end up using (2) to always keep
+ * rate_(i+1) ~= (write_bw / N) (8)
+ * regardless of the value of pos_ratio. As long as (8) is satisfied,
+ * pos_ratio is able to drive itself to 1.0, which is not only where
+ * the dirty count meet the setpoint, but also where the slope of
+ * pos_ratio is most flat and hence task_ratelimit is least fluctuated.
+ */
+ balanced_dirty_ratelimit = div_u64((u64)task_ratelimit * write_bw,
+ dirty_rate | 1);
+ /*
+ * balanced_dirty_ratelimit ~= (write_bw / N) <= write_bw
+ */
+ if (unlikely(balanced_dirty_ratelimit > write_bw))
+ balanced_dirty_ratelimit = write_bw;
+
+ /*
+ * We could safely do this and return immediately:
+ *
+ * bdi->dirty_ratelimit = balanced_dirty_ratelimit;
+ *
+ * However to get a more stable dirty_ratelimit, the below elaborated
+ * code makes use of task_ratelimit to filter out sigular points and
+ * limit the step size.
+ *
+ * The below code essentially only uses the relative value of
+ *
+ * task_ratelimit - dirty_ratelimit
+ * = (pos_ratio - 1) * dirty_ratelimit
+ *
+ * which reflects the direction and size of dirty position error.
+ */
+
+ /*
+ * dirty_ratelimit will follow balanced_dirty_ratelimit iff
+ * task_ratelimit is on the same side of dirty_ratelimit, too.
+ * For example, when
+ * - dirty_ratelimit > balanced_dirty_ratelimit
+ * - dirty_ratelimit > task_ratelimit (dirty pages are above setpoint)
+ * lowering dirty_ratelimit will help meet both the position and rate
+ * control targets. Otherwise, don't update dirty_ratelimit if it will
+ * only help meet the rate target. After all, what the users ultimately
+ * feel and care are stable dirty rate and small position error.
+ *
+ * |task_ratelimit - dirty_ratelimit| is used to limit the step size
+ * and filter out the sigular points of balanced_dirty_ratelimit. Which
+ * keeps jumping around randomly and can even leap far away at times
+ * due to the small 200ms estimation period of dirty_rate (we want to
+ * keep that period small to reduce time lags).
+ */
+ step = 0;
+ if (dirty < setpoint) {
+ x = min(bdi->balanced_dirty_ratelimit,
+ min(balanced_dirty_ratelimit, task_ratelimit));
+ if (dirty_ratelimit < x)
+ step = x - dirty_ratelimit;
+ } else {
+ x = max(bdi->balanced_dirty_ratelimit,
+ max(balanced_dirty_ratelimit, task_ratelimit));
+ if (dirty_ratelimit > x)
+ step = dirty_ratelimit - x;
+ }
+
+ /*
+ * Don't pursue 100% rate matching. It's impossible since the balanced
+ * rate itself is constantly fluctuating. So decrease the track speed
+ * when it gets close to the target. Helps eliminate pointless tremors.
+ */
+ step >>= dirty_ratelimit / (2 * step + 1);
+ /*
+ * Limit the tracking speed to avoid overshooting.
+ */
+ step = (step + 7) / 8;
+
+ if (dirty_ratelimit < balanced_dirty_ratelimit)
+ dirty_ratelimit += step;
else
- background = (dirty_background_ratio * available_memory) / 100;
+ dirty_ratelimit -= step;
- if (background >= dirty)
- background = dirty / 2;
- tsk = current;
- if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
- background += background / 4;
- dirty += dirty / 4;
+ bdi->dirty_ratelimit = max(dirty_ratelimit, 1UL);
+ bdi->balanced_dirty_ratelimit = balanced_dirty_ratelimit;
+
+ trace_bdi_dirty_ratelimit(bdi, dirty_rate, task_ratelimit);
+}
+
+void __bdi_update_bandwidth(struct backing_dev_info *bdi,
+ unsigned long thresh,
+ unsigned long bg_thresh,
+ unsigned long dirty,
+ unsigned long bdi_thresh,
+ unsigned long bdi_dirty,
+ unsigned long start_time)
+{
+ unsigned long now = jiffies;
+ unsigned long elapsed = now - bdi->bw_time_stamp;
+ unsigned long dirtied;
+ unsigned long written;
+
+ /*
+ * rate-limit, only update once every 200ms.
+ */
+ if (elapsed < BANDWIDTH_INTERVAL)
+ return;
+
+ dirtied = percpu_counter_read(&bdi->bdi_stat[BDI_DIRTIED]);
+ written = percpu_counter_read(&bdi->bdi_stat[BDI_WRITTEN]);
+
+ /*
+ * Skip quiet periods when disk bandwidth is under-utilized.
+ * (at least 1s idle time between two flusher runs)
+ */
+ if (elapsed > HZ && time_before(bdi->bw_time_stamp, start_time))
+ goto snapshot;
+
+ if (thresh) {
+ global_update_bandwidth(thresh, dirty, now);
+ bdi_update_dirty_ratelimit(bdi, thresh, bg_thresh, dirty,
+ bdi_thresh, bdi_dirty,
+ dirtied, elapsed);
}
- *pbackground = background;
- *pdirty = dirty;
+ bdi_update_write_bandwidth(bdi, elapsed, written);
+
+snapshot:
+ bdi->dirtied_stamp = dirtied;
+ bdi->written_stamp = written;
+ bdi->bw_time_stamp = now;
+}
+
+static void bdi_update_bandwidth(struct backing_dev_info *bdi,
+ unsigned long thresh,
+ unsigned long bg_thresh,
+ unsigned long dirty,
+ unsigned long bdi_thresh,
+ unsigned long bdi_dirty,
+ unsigned long start_time)
+{
+ if (time_is_after_eq_jiffies(bdi->bw_time_stamp + BANDWIDTH_INTERVAL))
+ return;
+ spin_lock(&bdi->wb.list_lock);
+ __bdi_update_bandwidth(bdi, thresh, bg_thresh, dirty,
+ bdi_thresh, bdi_dirty, start_time);
+ spin_unlock(&bdi->wb.list_lock);
}
/*
- * bdi_dirty_limit - @bdi's share of dirty throttling threshold
+ * After a task dirtied this many pages, balance_dirty_pages_ratelimited_nr()
+ * will look to see if it needs to start dirty throttling.
*
- * Allocate high/low dirty limits to fast/slow devices, in order to prevent
- * - starving fast devices
- * - piling up dirty pages (that will take long time to sync) on slow devices
- *
- * The bdi's share of dirty limit will be adapting to its throughput and
- * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set.
+ * If dirty_poll_interval is too low, big NUMA machines will call the expensive
+ * global_page_state() too often. So scale it near-sqrt to the safety margin
+ * (the number of pages we may dirty without exceeding the dirty limits).
*/
-unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty)
+static unsigned long dirty_poll_interval(unsigned long dirty,
+ unsigned long thresh)
{
- u64 bdi_dirty;
- long numerator, denominator;
+ if (thresh > dirty)
+ return 1UL << (ilog2(thresh - dirty) >> 1);
+
+ return 1;
+}
+
+static long bdi_max_pause(struct backing_dev_info *bdi,
+ unsigned long bdi_dirty)
+{
+ long bw = bdi->avg_write_bandwidth;
+ long t;
/*
- * Calculate this BDI's share of the dirty ratio.
+ * Limit pause time for small memory systems. If sleeping for too long
+ * time, a small pool of dirty/writeback pages may go empty and disk go
+ * idle.
+ *
+ * 8 serves as the safety ratio.
*/
- bdi_writeout_fraction(bdi, &numerator, &denominator);
+ t = bdi_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8));
+ t++;
- bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100;
- bdi_dirty *= numerator;
- do_div(bdi_dirty, denominator);
+ return min_t(long, t, MAX_PAUSE);
+}
- bdi_dirty += (dirty * bdi->min_ratio) / 100;
- if (bdi_dirty > (dirty * bdi->max_ratio) / 100)
- bdi_dirty = dirty * bdi->max_ratio / 100;
+static long bdi_min_pause(struct backing_dev_info *bdi,
+ long max_pause,
+ unsigned long task_ratelimit,
+ unsigned long dirty_ratelimit,
+ int *nr_dirtied_pause)
+{
+ long hi = ilog2(bdi->avg_write_bandwidth);
+ long lo = ilog2(bdi->dirty_ratelimit);
+ long t; /* target pause */
+ long pause; /* estimated next pause */
+ int pages; /* target nr_dirtied_pause */
- return bdi_dirty;
+ /* target for 10ms pause on 1-dd case */
+ t = max(1, HZ / 100);
+
+ /*
+ * Scale up pause time for concurrent dirtiers in order to reduce CPU
+ * overheads.
+ *
+ * (N * 10ms) on 2^N concurrent tasks.
+ */
+ if (hi > lo)
+ t += (hi - lo) * (10 * HZ) / 1024;
+
+ /*
+ * This is a bit convoluted. We try to base the next nr_dirtied_pause
+ * on the much more stable dirty_ratelimit. However the next pause time
+ * will be computed based on task_ratelimit and the two rate limits may
+ * depart considerably at some time. Especially if task_ratelimit goes
+ * below dirty_ratelimit/2 and the target pause is max_pause, the next
+ * pause time will be max_pause*2 _trimmed down_ to max_pause. As a
+ * result task_ratelimit won't be executed faithfully, which could
+ * eventually bring down dirty_ratelimit.
+ *
+ * We apply two rules to fix it up:
+ * 1) try to estimate the next pause time and if necessary, use a lower
+ * nr_dirtied_pause so as not to exceed max_pause. When this happens,
+ * nr_dirtied_pause will be "dancing" with task_ratelimit.
+ * 2) limit the target pause time to max_pause/2, so that the normal
+ * small fluctuations of task_ratelimit won't trigger rule (1) and
+ * nr_dirtied_pause will remain as stable as dirty_ratelimit.
+ */
+ t = min(t, 1 + max_pause / 2);
+ pages = dirty_ratelimit * t / roundup_pow_of_two(HZ);
+
+ /*
+ * Tiny nr_dirtied_pause is found to hurt I/O performance in the test
+ * case fio-mmap-randwrite-64k, which does 16*{sync read, async write}.
+ * When the 16 consecutive reads are often interrupted by some dirty
+ * throttling pause during the async writes, cfq will go into idles
+ * (deadline is fine). So push nr_dirtied_pause as high as possible
+ * until reaches DIRTY_POLL_THRESH=32 pages.
+ */
+ if (pages < DIRTY_POLL_THRESH) {
+ t = max_pause;
+ pages = dirty_ratelimit * t / roundup_pow_of_two(HZ);
+ if (pages > DIRTY_POLL_THRESH) {
+ pages = DIRTY_POLL_THRESH;
+ t = HZ * DIRTY_POLL_THRESH / dirty_ratelimit;
+ }
+ }
+
+ pause = HZ * pages / (task_ratelimit + 1);
+ if (pause > max_pause) {
+ t = max_pause;
+ pages = task_ratelimit * t / roundup_pow_of_two(HZ);
+ }
+
+ *nr_dirtied_pause = pages;
+ /*
+ * The minimal pause time will normally be half the target pause time.
+ */
+ return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t;
}
/*
* balance_dirty_pages() must be called by processes which are generating dirty
* data. It looks at the number of dirty pages in the machine and will force
- * the caller to perform writeback if the system is over `vm_dirty_ratio'.
+ * the caller to wait once crossing the (background_thresh + dirty_thresh) / 2.
* If we're over `background_thresh' then the writeback threads are woken to
* perform some writeout.
*/
static void balance_dirty_pages(struct address_space *mapping,
- unsigned long write_chunk)
+ unsigned long pages_dirtied)
{
- long nr_reclaimable, bdi_nr_reclaimable;
- long nr_writeback, bdi_nr_writeback;
+ unsigned long nr_reclaimable; /* = file_dirty + unstable_nfs */
+ unsigned long bdi_reclaimable;
+ unsigned long nr_dirty; /* = file_dirty + writeback + unstable_nfs */
+ unsigned long bdi_dirty;
+ unsigned long freerun;
unsigned long background_thresh;
unsigned long dirty_thresh;
unsigned long bdi_thresh;
- unsigned long pages_written = 0;
- unsigned long pause = 1;
+ long period;
+ long pause;
+ long max_pause;
+ long min_pause;
+ int nr_dirtied_pause;
bool dirty_exceeded = false;
+ unsigned long task_ratelimit;
+ unsigned long dirty_ratelimit;
+ unsigned long pos_ratio;
struct backing_dev_info *bdi = mapping->backing_dev_info;
+ unsigned long start_time = jiffies;
for (;;) {
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_NONE,
- .older_than_this = NULL,
- .nr_to_write = write_chunk,
- .range_cyclic = 1,
- };
+ unsigned long now = jiffies;
+ /*
+ * Unstable writes are a feature of certain networked
+ * filesystems (i.e. NFS) in which data may have been
+ * written to the server's write cache, but has not yet
+ * been flushed to permanent storage.
+ */
nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
- nr_writeback = global_page_state(NR_WRITEBACK);
+ nr_dirty = nr_reclaimable + global_page_state(NR_WRITEBACK);
global_dirty_limits(&background_thresh, &dirty_thresh);
* catch-up. This avoids (excessively) small writeouts
* when the bdi limits are ramping up.
*/
- if (nr_reclaimable + nr_writeback <=
- (background_thresh + dirty_thresh) / 2)
+ freerun = dirty_freerun_ceiling(dirty_thresh,
+ background_thresh);
+ if (nr_dirty <= freerun) {
+ current->dirty_paused_when = now;
+ current->nr_dirtied = 0;
+ current->nr_dirtied_pause =
+ dirty_poll_interval(nr_dirty, dirty_thresh);
break;
+ }
+
+ if (unlikely(!writeback_in_progress(bdi)))
+ bdi_start_background_writeback(bdi);
+ /*
+ * bdi_thresh is not treated as some limiting factor as
+ * dirty_thresh, due to reasons
+ * - in JBOD setup, bdi_thresh can fluctuate a lot
+ * - in a system with HDD and USB key, the USB key may somehow
+ * go into state (bdi_dirty >> bdi_thresh) either because
+ * bdi_dirty starts high, or because bdi_thresh drops low.
+ * In this case we don't want to hard throttle the USB key
+ * dirtiers for 100 seconds until bdi_dirty drops under
+ * bdi_thresh. Instead the auxiliary bdi control line in
+ * bdi_position_ratio() will let the dirtier task progress
+ * at some rate <= (write_bw / 2) for bringing down bdi_dirty.
+ */
bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
- bdi_thresh = task_dirty_limit(current, bdi_thresh);
/*
* In order to avoid the stacked BDI deadlock we need
* actually dirty; with m+n sitting in the percpu
* deltas.
*/
- if (bdi_thresh < 2*bdi_stat_error(bdi)) {
- bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE);
- bdi_nr_writeback = bdi_stat_sum(bdi, BDI_WRITEBACK);
+ if (bdi_thresh < 2 * bdi_stat_error(bdi)) {
+ bdi_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE);
+ bdi_dirty = bdi_reclaimable +
+ bdi_stat_sum(bdi, BDI_WRITEBACK);
} else {
- bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
- bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);
+ bdi_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
+ bdi_dirty = bdi_reclaimable +
+ bdi_stat(bdi, BDI_WRITEBACK);
}
+ dirty_exceeded = (bdi_dirty > bdi_thresh) &&
+ (nr_dirty > dirty_thresh);
+ if (dirty_exceeded && !bdi->dirty_exceeded)
+ bdi->dirty_exceeded = 1;
+
+ bdi_update_bandwidth(bdi, dirty_thresh, background_thresh,
+ nr_dirty, bdi_thresh, bdi_dirty,
+ start_time);
+
+ dirty_ratelimit = bdi->dirty_ratelimit;
+ pos_ratio = bdi_position_ratio(bdi, dirty_thresh,
+ background_thresh, nr_dirty,
+ bdi_thresh, bdi_dirty);
+ task_ratelimit = ((u64)dirty_ratelimit * pos_ratio) >>
+ RATELIMIT_CALC_SHIFT;
+ max_pause = bdi_max_pause(bdi, bdi_dirty);
+ min_pause = bdi_min_pause(bdi, max_pause,
+ task_ratelimit, dirty_ratelimit,
+ &nr_dirtied_pause);
+
+ if (unlikely(task_ratelimit == 0)) {
+ period = max_pause;
+ pause = max_pause;
+ goto pause;
+ }
+ period = HZ * pages_dirtied / task_ratelimit;
+ pause = period;
+ if (current->dirty_paused_when)
+ pause -= now - current->dirty_paused_when;
/*
- * The bdi thresh is somehow "soft" limit derived from the
- * global "hard" limit. The former helps to prevent heavy IO
- * bdi or process from holding back light ones; The latter is
- * the last resort safeguard.
+ * For less than 1s think time (ext3/4 may block the dirtier
+ * for up to 800ms from time to time on 1-HDD; so does xfs,
+ * however at much less frequency), try to compensate it in
+ * future periods by updating the virtual time; otherwise just
+ * do a reset, as it may be a light dirtier.
*/
- dirty_exceeded =
- (bdi_nr_reclaimable + bdi_nr_writeback > bdi_thresh)
- || (nr_reclaimable + nr_writeback > dirty_thresh);
-
- if (!dirty_exceeded)
+ if (pause < min_pause) {
+ trace_balance_dirty_pages(bdi,
+ dirty_thresh,
+ background_thresh,
+ nr_dirty,
+ bdi_thresh,
+ bdi_dirty,
+ dirty_ratelimit,
+ task_ratelimit,
+ pages_dirtied,
+ period,
+ min(pause, 0L),
+ start_time);
+ if (pause < -HZ) {
+ current->dirty_paused_when = now;
+ current->nr_dirtied = 0;
+ } else if (period) {
+ current->dirty_paused_when += period;
+ current->nr_dirtied = 0;
+ } else if (current->nr_dirtied_pause <= pages_dirtied)
+ current->nr_dirtied_pause += pages_dirtied;
break;
+ }
+ if (unlikely(pause > max_pause)) {
+ /* for occasional dropped task_ratelimit */
+ now += min(pause - max_pause, max_pause);
+ pause = max_pause;
+ }
- if (!bdi->dirty_exceeded)
- bdi->dirty_exceeded = 1;
+pause:
+ trace_balance_dirty_pages(bdi,
+ dirty_thresh,
+ background_thresh,
+ nr_dirty,
+ bdi_thresh,
+ bdi_dirty,
+ dirty_ratelimit,
+ task_ratelimit,
+ pages_dirtied,
+ period,
+ pause,
+ start_time);
+ __set_current_state(TASK_KILLABLE);
+ io_schedule_timeout(pause);
- /* Note: nr_reclaimable denotes nr_dirty + nr_unstable.
- * Unstable writes are a feature of certain networked
- * filesystems (i.e. NFS) in which data may have been
- * written to the server's write cache, but has not yet
- * been flushed to permanent storage.
- * Only move pages to writeback if this bdi is over its
- * threshold otherwise wait until the disk writes catch
- * up.
+ current->dirty_paused_when = now + pause;
+ current->nr_dirtied = 0;
+ current->nr_dirtied_pause = nr_dirtied_pause;
+
+ /*
+ * This is typically equal to (nr_dirty < dirty_thresh) and can
+ * also keep "1000+ dd on a slow USB stick" under control.
*/
- trace_wbc_balance_dirty_start(&wbc, bdi);
- if (bdi_nr_reclaimable > bdi_thresh) {
- writeback_inodes_wb(&bdi->wb, &wbc);
- pages_written += write_chunk - wbc.nr_to_write;
- trace_wbc_balance_dirty_written(&wbc, bdi);
- if (pages_written >= write_chunk)
- break; /* We've done our duty */
- }
- trace_wbc_balance_dirty_wait(&wbc, bdi);
- __set_current_state(TASK_UNINTERRUPTIBLE);
- io_schedule_timeout(pause);
+ if (task_ratelimit)
+ break;
/*
- * Increase the delay for each loop, up to our previous
- * default of taking a 100ms nap.
+ * In the case of an unresponding NFS server and the NFS dirty
+ * pages exceeds dirty_thresh, give the other good bdi's a pipe
+ * to go through, so that tasks on them still remain responsive.
+ *
+ * In theory 1 page is enough to keep the comsumer-producer
+ * pipe going: the flusher cleans 1 page => the task dirties 1
+ * more page. However bdi_dirty has accounting errors. So use
+ * the larger and more IO friendly bdi_stat_error.
*/
- pause <<= 1;
- if (pause > HZ / 10)
- pause = HZ / 10;
+ if (bdi_dirty <= bdi_stat_error(bdi))
+ break;
+
+ if (fatal_signal_pending(current))
+ break;
}
if (!dirty_exceeded && bdi->dirty_exceeded)
* In normal mode, we start background writeout at the lower
* background_thresh, to keep the amount of dirty memory low.
*/
- if ((laptop_mode && pages_written) ||
- (!laptop_mode && (nr_reclaimable > background_thresh)))
+ if (laptop_mode)
+ return;
+
+ if (nr_reclaimable > background_thresh)
bdi_start_background_writeback(bdi);
}
}
}
-static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0;
+static DEFINE_PER_CPU(int, bdp_ratelimits);
+
+/*
+ * Normal tasks are throttled by
+ * loop {
+ * dirty tsk->nr_dirtied_pause pages;
+ * take a snap in balance_dirty_pages();
+ * }
+ * However there is a worst case. If every task exit immediately when dirtied
+ * (tsk->nr_dirtied_pause - 1) pages, balance_dirty_pages() will never be
+ * called to throttle the page dirties. The solution is to save the not yet
+ * throttled page dirties in dirty_throttle_leaks on task exit and charge them
+ * randomly into the running tasks. This works well for the above worst case,
+ * as the new task will pick up and accumulate the old task's leaked dirty
+ * count and eventually get throttled.
+ */
+DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
/**
* balance_dirty_pages_ratelimited_nr - balance dirty memory state
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
unsigned long nr_pages_dirtied)
{
- unsigned long ratelimit;
- unsigned long *p;
+ struct backing_dev_info *bdi = mapping->backing_dev_info;
+ int ratelimit;
+ int *p;
+
+ if (!bdi_cap_account_dirty(bdi))
+ return;
- ratelimit = ratelimit_pages;
- if (mapping->backing_dev_info->dirty_exceeded)
- ratelimit = 8;
+ ratelimit = current->nr_dirtied_pause;
+ if (bdi->dirty_exceeded)
+ ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10));
+ preempt_disable();
/*
- * Check the rate limiting. Also, we do not want to throttle real-time
- * tasks in balance_dirty_pages(). Period.
+ * This prevents one CPU to accumulate too many dirtied pages without
+ * calling into balance_dirty_pages(), which can happen when there are
+ * 1000+ tasks, all of them start dirtying pages at exactly the same
+ * time, hence all honoured too large initial task->nr_dirtied_pause.
*/
- preempt_disable();
p = &__get_cpu_var(bdp_ratelimits);
- *p += nr_pages_dirtied;
- if (unlikely(*p >= ratelimit)) {
- ratelimit = sync_writeback_pages(*p);
+ if (unlikely(current->nr_dirtied >= ratelimit))
*p = 0;
- preempt_enable();
- balance_dirty_pages(mapping, ratelimit);
- return;
+ else if (unlikely(*p >= ratelimit_pages)) {
+ *p = 0;
+ ratelimit = 0;
+ }
+ /*
+ * Pick up the dirtied pages by the exited tasks. This avoids lots of
+ * short-lived tasks (eg. gcc invocations in a kernel build) escaping
+ * the dirty throttling and livelock other long-run dirtiers.
+ */
+ p = &__get_cpu_var(dirty_throttle_leaks);
+ if (*p > 0 && current->nr_dirtied < ratelimit) {
+ nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied);
+ *p -= nr_pages_dirtied;
+ current->nr_dirtied += nr_pages_dirtied;
}
preempt_enable();
+
+ if (unlikely(current->nr_dirtied >= ratelimit))
+ balance_dirty_pages(mapping, current->nr_dirtied);
}
EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
for ( ; ; ) {
global_dirty_limits(&background_thresh, &dirty_thresh);
+ dirty_thresh = hard_dirty_limit(dirty_thresh);
/*
* Boost the allowable dirty threshold a bit for page
* threshold
*/
if (bdi_has_dirty_io(&q->backing_dev_info))
- bdi_start_writeback(&q->backing_dev_info, nr_pages);
+ bdi_start_writeback(&q->backing_dev_info, nr_pages,
+ WB_REASON_LAPTOP_TIMER);
}
/*
*
* Here we set ratelimit_pages to a level which ensures that when all CPUs are
* dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory
- * thresholds before writeback cuts in.
- *
- * But the limit should not be set too high. Because it also controls the
- * amount of memory which the balance_dirty_pages() caller has to write back.
- * If this is too large then the caller will block on the IO queue all the
- * time. So limit it to four megabytes - the balance_dirty_pages() caller
- * will write six megabyte chunks, max.
+ * thresholds.
*/
void writeback_set_ratelimit(void)
{
- ratelimit_pages = vm_total_pages / (num_online_cpus() * 32);
+ unsigned long background_thresh;
+ unsigned long dirty_thresh;
+ global_dirty_limits(&background_thresh, &dirty_thresh);
+ ratelimit_pages = dirty_thresh / (num_online_cpus() * 32);
if (ratelimit_pages < 16)
ratelimit_pages = 16;
- if (ratelimit_pages * PAGE_CACHE_SIZE > 4096 * 1024)
- ratelimit_pages = (4096 * 1024) / PAGE_CACHE_SIZE;
}
static int __cpuinit
shift = calc_period_shift();
prop_descriptor_init(&vm_completions, shift);
- prop_descriptor_init(&vm_dirties, shift);
}
/**
range_whole = 1;
cycled = 1; /* ignore range_cyclic tests */
}
- if (wbc->sync_mode == WB_SYNC_ALL)
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
- if (wbc->sync_mode == WB_SYNC_ALL)
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && (index <= end)) {
__inc_zone_page_state(page, NR_FILE_DIRTY);
__inc_zone_page_state(page, NR_DIRTIED);
__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
- task_dirty_inc(current);
+ __inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
task_io_account_write(PAGE_CACHE_SIZE);
+ current->nr_dirtied++;
+ this_cpu_inc(bdp_ratelimits);
}
}
EXPORT_SYMBOL(account_page_dirtied);
void account_page_writeback(struct page *page)
{
inc_zone_page_state(page, NR_WRITEBACK);
- inc_zone_page_state(page, NR_WRITTEN);
}
EXPORT_SYMBOL(account_page_writeback);
EXPORT_SYMBOL(__set_page_dirty_nobuffers);
/*
+ * Call this whenever redirtying a page, to de-account the dirty counters
+ * (NR_DIRTIED, BDI_DIRTIED, tsk->nr_dirtied), so that they match the written
+ * counters (NR_WRITTEN, BDI_WRITTEN) in long term. The mismatches will lead to
+ * systematic errors in balanced_dirty_ratelimit and the dirty pages position
+ * control.
+ */
+void account_page_redirty(struct page *page)
+{
+ struct address_space *mapping = page->mapping;
+ if (mapping && mapping_cap_account_dirty(mapping)) {
+ current->nr_dirtied--;
+ dec_zone_page_state(page, NR_DIRTIED);
+ dec_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
+ }
+}
+EXPORT_SYMBOL(account_page_redirty);
+
+/*
* When a writepage implementation decides that it doesn't want to write this
* page for some reason, it should redirty the locked page via
* redirty_page_for_writepage() and it should then unlock the page and return 0
int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
{
wbc->pages_skipped++;
+ account_page_redirty(page);
return __set_page_dirty_nobuffers(page);
}
EXPORT_SYMBOL(redirty_page_for_writepage);
} else {
ret = TestClearPageWriteback(page);
}
- if (ret)
+ if (ret) {
dec_zone_page_state(page, NR_WRITEBACK);
+ inc_zone_page_state(page, NR_WRITTEN);
+ }
return ret;
}
*/
int mapping_tagged(struct address_space *mapping, int tag)
{
- int ret;
- rcu_read_lock();
- ret = radix_tree_tagged(&mapping->page_tree, tag);
- rcu_read_unlock();
- return ret;
+ return radix_tree_tagged(&mapping->page_tree, tag);
}
EXPORT_SYMBOL(mapping_tagged);
projects / linux-flexiantxendom0-3.2.10.git / blobdiff