/*
* Start background writeback (via pdflush) at this percentage
*/
-int dirty_background_ratio = 5;
+int dirty_background_ratio = 10;
+
+/*
+ * dirty_background_bytes starts at 0 (disabled) so that it is a function of
+ * dirty_background_ratio * the amount of dirtyable memory
+ */
+unsigned long dirty_background_bytes;
/*
* free highmem will not be subtracted from the total free memory
/*
* The generator of dirty data starts writeback at this percentage
*/
-int vm_dirty_ratio = 10;
+int vm_dirty_ratio = 20;
+
+/*
+ * vm_dirty_bytes starts at 0 (disabled) so that it is a function of
+ * vm_dirty_ratio * the amount of dirtyable memory
+ */
+unsigned long vm_dirty_bytes;
/*
- * The interval between `kupdate'-style writebacks, in jiffies
+ * The interval between `kupdate'-style writebacks
*/
-int dirty_writeback_interval = 5 * HZ;
+unsigned int dirty_writeback_interval = 5 * 100; /* sentiseconds */
/*
- * The longest number of jiffies for which data is allowed to remain dirty
+ * The longest time for which data is allowed to remain dirty
*/
-int dirty_expire_interval = 30 * HZ;
+unsigned int dirty_expire_interval = 30 * 100; /* sentiseconds */
/*
* Flag that makes the machine dump writes/reads and block dirtyings.
{
unsigned long dirty_total;
- dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) / 100;
+ if (vm_dirty_bytes)
+ dirty_total = vm_dirty_bytes / PAGE_SIZE;
+ else
+ dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) /
+ 100;
return 2 + ilog2(dirty_total - 1);
}
/*
- * update the period when the dirty ratio changes.
+ * update the period when the dirty threshold changes.
*/
+static void update_completion_period(void)
+{
+ int shift = calc_period_shift();
+ prop_change_shift(&vm_completions, shift);
+ prop_change_shift(&vm_dirties, shift);
+}
+
+int dirty_background_ratio_handler(struct ctl_table *table, int write,
+ struct file *filp, void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret;
+
+ ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+ if (ret == 0 && write)
+ dirty_background_bytes = 0;
+ return ret;
+}
+
+int dirty_background_bytes_handler(struct ctl_table *table, int write,
+ struct file *filp, void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret;
+
+ ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+ if (ret == 0 && write)
+ dirty_background_ratio = 0;
+ return ret;
+}
+
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);
+ int ret;
+
+ 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);
- prop_change_shift(&vm_dirties, shift);
+ update_completion_period();
+ vm_dirty_bytes = 0;
+ }
+ return ret;
+}
+
+
+int dirty_bytes_handler(struct ctl_table *table, int write,
+ struct file *filp, void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ unsigned long old_bytes = vm_dirty_bytes;
+ int ret;
+
+ ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+ if (ret == 0 && write && vm_dirty_bytes != old_bytes) {
+ update_completion_period();
+ vm_dirty_ratio = 0;
}
return ret;
}
}
EXPORT_SYMBOL_GPL(bdi_writeout_inc);
-static inline void task_dirty_inc(struct task_struct *tsk)
+void task_dirty_inc(struct task_struct *tsk)
{
prop_inc_single(&vm_dirties, &tsk->dirties);
}
}
void
-get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
- struct backing_dev_info *bdi)
+get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty,
+ unsigned long *pbdi_dirty, struct backing_dev_info *bdi)
{
- int background_ratio; /* Percentages */
- int dirty_ratio;
- long background;
- long dirty;
+ unsigned long background;
+ unsigned long dirty;
unsigned long available_memory = determine_dirtyable_memory();
struct task_struct *tsk;
- dirty_ratio = vm_dirty_ratio;
- if (dirty_ratio < 5)
- dirty_ratio = 5;
+ if (vm_dirty_bytes)
+ dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE);
+ else {
+ int dirty_ratio;
- background_ratio = dirty_background_ratio;
- if (background_ratio >= dirty_ratio)
- background_ratio = dirty_ratio / 2;
+ dirty_ratio = vm_dirty_ratio;
+ if (dirty_ratio < 5)
+ dirty_ratio = 5;
+ dirty = (dirty_ratio * available_memory) / 100;
+ }
- background = (background_ratio * available_memory) / 100;
- dirty = (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;
{
long nr_reclaimable, bdi_nr_reclaimable;
long nr_writeback, bdi_nr_writeback;
- long background_thresh;
- long dirty_thresh;
- long bdi_thresh;
+ unsigned long background_thresh;
+ unsigned long dirty_thresh;
+ unsigned long bdi_thresh;
unsigned long pages_written = 0;
unsigned long write_chunk = sync_writeback_pages();
void throttle_vm_writeout(gfp_t gfp_mask)
{
- long background_thresh;
- long dirty_thresh;
+ unsigned long background_thresh;
+ unsigned long dirty_thresh;
for ( ; ; ) {
get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
};
for ( ; ; ) {
- long background_thresh;
- long dirty_thresh;
+ unsigned long background_thresh;
+ unsigned long dirty_thresh;
get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
if (global_page_state(NR_FILE_DIRTY) +
sync_supers();
- oldest_jif = jiffies - dirty_expire_interval;
+ oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval);
start_jif = jiffies;
- next_jif = start_jif + dirty_writeback_interval;
+ next_jif = start_jif + msecs_to_jiffies(dirty_writeback_interval * 10);
nr_to_write = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS) +
(inodes_stat.nr_inodes - inodes_stat.nr_unused);
int dirty_writeback_centisecs_handler(ctl_table *table, int write,
struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
- proc_dointvec_userhz_jiffies(table, write, file, buffer, length, ppos);
+ proc_dointvec(table, write, file, buffer, length, ppos);
if (dirty_writeback_interval)
- mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
+ mod_timer(&wb_timer, jiffies +
+ msecs_to_jiffies(dirty_writeback_interval * 10));
else
del_timer(&wb_timer);
return 0;
{
int shift;
- mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
+ mod_timer(&wb_timer,
+ jiffies + msecs_to_jiffies(dirty_writeback_interval * 10));
writeback_set_ratelimit();
register_cpu_notifier(&ratelimit_nb);
}
retry:
done_index = index;
- while (!done && (index <= end) &&
- (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
- PAGECACHE_TAG_DIRTY,
- min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
- unsigned i;
+ while (!done && (index <= end)) {
+ int i;
+
+ nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+ PAGECACHE_TAG_DIRTY,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+ if (nr_pages == 0)
+ break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
- done_index = page->index + 1;
-
/*
- * At this point we hold neither mapping->tree_lock nor
- * lock on the page itself: the page may be truncated or
- * invalidated (changing page->mapping to NULL), or even
- * swizzled back from swapper_space to tmpfs file
- * mapping
+ * At this point, the page may be truncated or
+ * invalidated (changing page->mapping to NULL), or
+ * even swizzled back from swapper_space to tmpfs file
+ * mapping. However, page->index will not change
+ * because we have a reference on the page.
*/
- lock_page(page);
-
- if (unlikely(page->mapping != mapping)) {
- unlock_page(page);
- continue;
- }
-
if (page->index > end) {
/*
* can't be range_cyclic (1st pass) because
* end == -1 in that case.
*/
done = 1;
- unlock_page(page);
- continue;
+ break;
}
- if (wbc->sync_mode != WB_SYNC_NONE)
- wait_on_page_writeback(page);
+ done_index = page->index + 1;
+
+ lock_page(page);
- if (PageWriteback(page) ||
- !clear_page_dirty_for_io(page)) {
+ /*
+ * Page truncated or invalidated. We can freely skip it
+ * then, even for data integrity operations: the page
+ * has disappeared concurrently, so there could be no
+ * real expectation of this data interity operation
+ * even if there is now a new, dirty page at the same
+ * pagecache address.
+ */
+ if (unlikely(page->mapping != mapping)) {
+continue_unlock:
unlock_page(page);
continue;
}
+ if (!PageDirty(page)) {
+ /* someone wrote it for us */
+ goto continue_unlock;
+ }
+
+ if (PageWriteback(page)) {
+ if (wbc->sync_mode != WB_SYNC_NONE)
+ wait_on_page_writeback(page);
+ else
+ goto continue_unlock;
+ }
+
+ BUG_ON(PageWriteback(page));
+ if (!clear_page_dirty_for_io(page))
+ goto continue_unlock;
+
ret = (*writepage)(page, wbc, data);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
}
}
- if (wbc->sync_mode == WB_SYNC_NONE) {
- if (--wbc->nr_to_write <= 0)
+ if (nr_to_write > 0) {
+ nr_to_write--;
+ if (nr_to_write == 0 &&
+ wbc->sync_mode == WB_SYNC_NONE) {
+ /*
+ * We stop writing back only if we are
+ * not doing integrity sync. In case of
+ * integrity sync we have to keep going
+ * because someone may be concurrently
+ * dirtying pages, and we might have
+ * synced a lot of newly appeared dirty
+ * pages, but have not synced all of the
+ * old dirty pages.
+ */
done = 1;
+ break;
+ }
}
+
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
done = 1;
+ break;
}
}
pagevec_release(&pvec);
cond_resched();
}
- if (!cycled) {
+ if (!cycled && !done) {
/*
* range_cyclic:
* We hit the last page and there is more work to be done: wrap
}
/*
+ * Helper function for set_page_dirty family.
+ * NOTE: This relies on being atomic wrt interrupts.
+ */
+void account_page_dirtied(struct page *page, struct address_space *mapping)
+{
+ if (mapping_cap_account_dirty(mapping)) {
+ __inc_zone_page_state(page, NR_FILE_DIRTY);
+ __inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
+ task_dirty_inc(current);
+ task_io_account_write(PAGE_CACHE_SIZE);
+ }
+}
+
+/*
* For address_spaces which do not use buffers. Just tag the page as dirty in
* its radix tree.
*
if (mapping2) { /* Race with truncate? */
BUG_ON(mapping2 != mapping);
WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
- if (mapping_cap_account_dirty(mapping)) {
- __inc_zone_page_state(page, NR_FILE_DIRTY);
- __inc_bdi_stat(mapping->backing_dev_info,
- BDI_RECLAIMABLE);
- task_io_account_write(PAGE_CACHE_SIZE);
- }
+ account_page_dirtied(page, mapping);
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
}
* If the mapping doesn't provide a set_page_dirty a_op, then
* just fall through and assume that it wants buffer_heads.
*/
-static int __set_page_dirty(struct page *page)
+int set_page_dirty(struct page *page)
{
struct address_space *mapping = page_mapping(page);
}
return 0;
}
-
-int set_page_dirty(struct page *page)
-{
- int ret = __set_page_dirty(page);
- if (ret)
- task_dirty_inc(current);
- return ret;
-}
EXPORT_SYMBOL(set_page_dirty);
/*