*
* 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.
- * And the "limit" in the name is not seriously taken as hard limit in
- * balance_dirty_pages().
+ *
+ * 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.
*
* It allocates high/low dirty limits to fast/slow devices, in order to prevent
* - starving fast devices
* => fast response on large errors; small oscillation near setpoint
*/
setpoint = (freerun + limit) / 2;
- x = div_s64((setpoint - dirty) << RATELIMIT_CALC_SHIFT,
- limit - setpoint + 1);
+ x = div64_s64(((s64)setpoint - (s64)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;
*/
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);
+ 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
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);
+ pos_ratio = div64_u64(pos_ratio * (x_intercept - bdi_dirty),
+ (x_intercept - bdi_setpoint) | 1);
} else
pos_ratio /= 4;
* bw * elapsed + write_bandwidth * (period - elapsed)
* write_bandwidth = ---------------------------------------------------
* period
+ *
+ * @written may have decreased due to account_page_redirty().
+ * Avoid underflowing @bw calculation.
*/
- bw = written - bdi->written_stamp;
+ bw = written - min(written, bdi->written_stamp);
bw *= HZ;
if (unlikely(elapsed > period)) {
do_div(bw, elapsed);
unsigned long now)
{
static DEFINE_SPINLOCK(dirty_lock);
- static unsigned long update_time;
+ static unsigned long update_time = INITIAL_JIFFIES;
/*
* check locklessly first to optimize away locking for the most time
*
* 8 serves as the safety ratio.
*/
- if (bdi_dirty)
- t = min(t, bdi_dirty * HZ / (8 * bw + 1));
+ t = min(t, bdi_dirty * HZ / (8 * bw + 1));
/*
* The pause time will be settled within range (max_pause/4, max_pause).
if (task_ratelimit)
break;
+ /*
+ * 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.
+ */
+ if (bdi_dirty <= bdi_stat_error(bdi))
+ break;
+
if (fatal_signal_pending(current))
break;
}
bdi_start_background_writeback(bdi);
}
-void set_page_dirty_balance(struct page *page, int page_mkwrite)
-{
- if (set_page_dirty(page) || page_mkwrite) {
- struct address_space *mapping = page_mapping(page);
-
- if (mapping)
- balance_dirty_pages_ratelimited(mapping);
- }
-}
-
static DEFINE_PER_CPU(int, bdp_ratelimits);
/**
* page dirty in that case, but not all the buffers. This is a "bottom-up"
* dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
*
- * Most callers have locked the page, which pins the address_space in memory.
- * But zap_pte_range() does not lock the page, however in that case the
- * mapping is pinned by the vma's ->vm_file reference.
- *
- * We take care to handle the case where the page was truncated from the
- * mapping by re-checking page_mapping() inside tree_lock.
+ * The caller must ensure this doesn't race with truncation. Most will simply
+ * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and
+ * the pte lock held, which also locks out truncation.
*/
int __set_page_dirty_nobuffers(struct page *page)
{
if (!TestSetPageDirty(page)) {
struct address_space *mapping = page_mapping(page);
- struct address_space *mapping2;
+ unsigned long flags;
if (!mapping)
return 1;
- spin_lock_irq(&mapping->tree_lock);
- mapping2 = page_mapping(page);
- if (mapping2) { /* Race with truncate? */
- BUG_ON(mapping2 != mapping);
- WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
- account_page_dirtied(page, mapping);
- radix_tree_tag_set(&mapping->page_tree,
- page_index(page), PAGECACHE_TAG_DIRTY);
- }
- spin_unlock_irq(&mapping->tree_lock);
+ spin_lock_irqsave(&mapping->tree_lock, flags);
+ BUG_ON(page_mapping(page) != mapping);
+ WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
+ account_page_dirtied(page, mapping);
+ radix_tree_tag_set(&mapping->page_tree, page_index(page),
+ PAGECACHE_TAG_DIRTY);
+ spin_unlock_irqrestore(&mapping->tree_lock, flags);
if (mapping->host) {
/* !PageAnon && !swapper_space */
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
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
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);
/*
* We carefully synchronise fault handlers against
* installing a dirty pte and marking the page dirty
- * at this point. We do this by having them hold the
- * page lock at some point after installing their
- * pte, but before marking the page dirty.
- * Pages are always locked coming in here, so we get
- * the desired exclusion. See mm/memory.c:do_wp_page()
- * for more comments.
+ * at this point. We do this by having them hold the
+ * page lock while dirtying the page, and pages are
+ * always locked coming in here, so we get the desired
+ * exclusion.
*/
if (TestClearPageDirty(page)) {
dec_zone_page_state(page, NR_FILE_DIRTY);
git.openpandora.org / pandora-kernel.git / blobdiff