summaryrefslogtreecommitdiff
path: root/mm/page-writeback.c
diff options
context:
space:
mode:
authorPeter Zijlstra <a.p.zijlstra@chello.nl>2007-10-16 23:25:50 -0700
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-10-17 08:42:45 -0700
commit04fbfdc14e5f48463820d6b9807daa5e9c92c51f (patch)
treec62905212c8c6373b2258c7f528398d3c831b075 /mm/page-writeback.c
parent145ca25eb2fbd20d4faf1bad4628c7650332058f (diff)
downloadlwn-04fbfdc14e5f48463820d6b9807daa5e9c92c51f.tar.gz
lwn-04fbfdc14e5f48463820d6b9807daa5e9c92c51f.zip
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>
Diffstat (limited to 'mm/page-writeback.c')
-rw-r--r--mm/page-writeback.c203
1 files changed, 171 insertions, 32 deletions
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index f1d201fdcf9c..b0360546ac86 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2,6 +2,7 @@
* mm/page-writeback.c
*
* Copyright (C) 2002, Linus Torvalds.
+ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
*
* Contains functions related to writing back dirty pages at the
* address_space level.
@@ -49,8 +50,6 @@
*/
static long ratelimit_pages = 32;
-static int dirty_exceeded __cacheline_aligned_in_smp; /* Dirty mem may be over limit */
-
/*
* 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.
@@ -103,6 +102,103 @@ EXPORT_SYMBOL(laptop_mode);
static void background_writeout(unsigned long _min_pages);
/*
+ * Scale the writeback cache size proportional to the relative writeout speeds.
+ *
+ * We do this by keeping a floating proportion between BDIs, based on page
+ * writeback completions [end_page_writeback()]. Those devices that write out
+ * pages fastest will get the larger share, while the slower will get a smaller
+ * share.
+ *
+ * We use page writeout completions because we are interested in getting rid of
+ * dirty pages. Having them written out is the primary goal.
+ *
+ * We introduce a concept of time, a period over which we measure these events,
+ * because demand can/will vary over time. The length of this period itself is
+ * measured in page writeback completions.
+ *
+ */
+static struct prop_descriptor vm_completions;
+
+static unsigned long determine_dirtyable_memory(void);
+
+/*
+ * couple the period to the dirty_ratio:
+ *
+ * period/2 ~ roundup_pow_of_two(dirty limit)
+ */
+static int calc_period_shift(void)
+{
+ unsigned long dirty_total;
+
+ dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) / 100;
+ return 2 + ilog2(dirty_total - 1);
+}
+
+/*
+ * update the period when the dirty ratio changes.
+ */
+int dirty_ratio_handler(struct ctl_table *table, int write,
+ struct file *filp, void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int old_ratio = vm_dirty_ratio;
+ int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+ if (ret == 0 && write && vm_dirty_ratio != old_ratio) {
+ int shift = calc_period_shift();
+ prop_change_shift(&vm_completions, shift);
+ }
+ return ret;
+}
+
+/*
+ * Increment the BDI's writeout completion count and the global writeout
+ * completion count. Called from test_clear_page_writeback().
+ */
+static inline void __bdi_writeout_inc(struct backing_dev_info *bdi)
+{
+ __prop_inc_percpu(&vm_completions, &bdi->completions);
+}
+
+/*
+ * 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,
+ numerator, denominator);
+ } else {
+ *numerator = 0;
+ *denominator = 1;
+ }
+}
+
+/*
+ * Clip the earned share of dirty pages to that which is actually available.
+ * This avoids exceeding the total dirty_limit when the floating averages
+ * fluctuate too quickly.
+ */
+static void
+clip_bdi_dirty_limit(struct backing_dev_info *bdi, long dirty, long *pbdi_dirty)
+{
+ long avail_dirty;
+
+ avail_dirty = dirty -
+ (global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_WRITEBACK) +
+ global_page_state(NR_UNSTABLE_NFS));
+
+ if (avail_dirty < 0)
+ avail_dirty = 0;
+
+ avail_dirty += bdi_stat(bdi, BDI_RECLAIMABLE) +
+ bdi_stat(bdi, BDI_WRITEBACK);
+
+ *pbdi_dirty = min(*pbdi_dirty, avail_dirty);
+}
+
+/*
* Work out the current dirty-memory clamping and background writeout
* thresholds.
*
@@ -158,8 +254,8 @@ static unsigned long determine_dirtyable_memory(void)
}
static void
-get_dirty_limits(long *pbackground, long *pdirty,
- struct address_space *mapping)
+get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
+ struct backing_dev_info *bdi)
{
int background_ratio; /* Percentages */
int dirty_ratio;
@@ -193,6 +289,22 @@ get_dirty_limits(long *pbackground, long *pdirty,
}
*pbackground = background;
*pdirty = dirty;
+
+ if (bdi) {
+ u64 bdi_dirty = dirty;
+ long numerator, denominator;
+
+ /*
+ * Calculate this BDI's share of the dirty ratio.
+ */
+ bdi_writeout_fraction(bdi, &numerator, &denominator);
+
+ bdi_dirty *= numerator;
+ do_div(bdi_dirty, denominator);
+
+ *pbdi_dirty = bdi_dirty;
+ clip_bdi_dirty_limit(bdi, dirty, pbdi_dirty);
+ }
}
/*
@@ -204,9 +316,11 @@ get_dirty_limits(long *pbackground, long *pdirty,
*/
static void balance_dirty_pages(struct address_space *mapping)
{
- long nr_reclaimable;
+ long bdi_nr_reclaimable;
+ long bdi_nr_writeback;
long background_thresh;
long dirty_thresh;
+ long bdi_thresh;
unsigned long pages_written = 0;
unsigned long write_chunk = sync_writeback_pages();
@@ -221,15 +335,15 @@ static void balance_dirty_pages(struct address_space *mapping)
.range_cyclic = 1,
};
- get_dirty_limits(&background_thresh, &dirty_thresh, mapping);
- nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS);
- if (nr_reclaimable + global_page_state(NR_WRITEBACK) <=
- dirty_thresh)
- break;
+ get_dirty_limits(&background_thresh, &dirty_thresh,
+ &bdi_thresh, bdi);
+ bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
+ bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);
+ if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh)
+ break;
- if (!dirty_exceeded)
- dirty_exceeded = 1;
+ if (!bdi->dirty_exceeded)
+ bdi->dirty_exceeded = 1;
/* Note: nr_reclaimable denotes nr_dirty + nr_unstable.
* Unstable writes are a feature of certain networked
@@ -237,26 +351,42 @@ static void balance_dirty_pages(struct address_space *mapping)
* written to the server's write cache, but has not yet
* been flushed to permanent storage.
*/
- if (nr_reclaimable) {
+ if (bdi_nr_reclaimable) {
writeback_inodes(&wbc);
- get_dirty_limits(&background_thresh,
- &dirty_thresh, mapping);
- nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS);
- if (nr_reclaimable +
- global_page_state(NR_WRITEBACK)
- <= dirty_thresh)
- break;
pages_written += write_chunk - wbc.nr_to_write;
- if (pages_written >= write_chunk)
- break; /* We've done our duty */
+ get_dirty_limits(&background_thresh, &dirty_thresh,
+ &bdi_thresh, bdi);
+ }
+
+ /*
+ * In order to avoid the stacked BDI deadlock we need
+ * to ensure we accurately count the 'dirty' pages when
+ * the threshold is low.
+ *
+ * Otherwise it would be possible to get thresh+n pages
+ * reported dirty, even though there are thresh-m pages
+ * 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);
+ } else if (bdi_nr_reclaimable) {
+ bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
+ bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);
}
+
+ if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh)
+ break;
+ if (pages_written >= write_chunk)
+ break; /* We've done our duty */
+
congestion_wait(WRITE, HZ/10);
}
- if (nr_reclaimable + global_page_state(NR_WRITEBACK)
- <= dirty_thresh && dirty_exceeded)
- dirty_exceeded = 0;
+ if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
+ bdi->dirty_exceeded)
+ bdi->dirty_exceeded = 0;
if (writeback_in_progress(bdi))
return; /* pdflush is already working this queue */
@@ -270,7 +400,9 @@ static void balance_dirty_pages(struct address_space *mapping)
* background_thresh, to keep the amount of dirty memory low.
*/
if ((laptop_mode && pages_written) ||
- (!laptop_mode && (nr_reclaimable > background_thresh)))
+ (!laptop_mode && (global_page_state(NR_FILE_DIRTY)
+ + global_page_state(NR_UNSTABLE_NFS)
+ > background_thresh)))
pdflush_operation(background_writeout, 0);
}
@@ -306,7 +438,7 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
unsigned long *p;
ratelimit = ratelimit_pages;
- if (dirty_exceeded)
+ if (mapping->backing_dev_info->dirty_exceeded)
ratelimit = 8;
/*
@@ -342,7 +474,7 @@ void throttle_vm_writeout(gfp_t gfp_mask)
}
for ( ; ; ) {
- get_dirty_limits(&background_thresh, &dirty_thresh, NULL);
+ get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
/*
* Boost the allowable dirty threshold a bit for page
@@ -377,7 +509,7 @@ static void background_writeout(unsigned long _min_pages)
long background_thresh;
long dirty_thresh;
- get_dirty_limits(&background_thresh, &dirty_thresh, NULL);
+ get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
if (global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS) < background_thresh
&& min_pages <= 0)
@@ -580,9 +712,14 @@ static struct notifier_block __cpuinitdata ratelimit_nb = {
*/
void __init page_writeback_init(void)
{
+ int shift;
+
mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
writeback_set_ratelimit();
register_cpu_notifier(&ratelimit_nb);
+
+ shift = calc_period_shift();
+ prop_descriptor_init(&vm_completions, shift);
}
/**
@@ -988,8 +1125,10 @@ int test_clear_page_writeback(struct page *page)
radix_tree_tag_clear(&mapping->page_tree,
page_index(page),
PAGECACHE_TAG_WRITEBACK);
- if (bdi_cap_writeback_dirty(bdi))
+ if (bdi_cap_writeback_dirty(bdi)) {
__dec_bdi_stat(bdi, BDI_WRITEBACK);
+ __bdi_writeout_inc(bdi);
+ }
}
write_unlock_irqrestore(&mapping->tree_lock, flags);
} else {