The patch titled
writeback: avoid unnecessary calculation of bdi dirty thresholds
has been added to the -mm tree. Its filename is
writeback-avoid-unnecessary-calculation-of-bdi-dirty-thresholds.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: writeback: avoid unnecessary calculation of bdi dirty thresholds
From: Wu Fengguang <fengguang.wu@xxxxxxxxx>
Split get_dirty_limits() into global_dirty_limits()+bdi_dirty_limit(), so
that the latter can be avoided when under global dirty background
threshold (which is the normal state for most systems).
Signed-off-by: Wu Fengguang <fengguang.wu@xxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/fs-writeback.c | 2
include/linux/writeback.h | 5 +-
mm/backing-dev.c | 3 -
mm/page-writeback.c | 74 ++++++++++++++++++------------------
4 files changed, 43 insertions(+), 41 deletions(-)
diff -puN fs/fs-writeback.c~writeback-avoid-unnecessary-calculation-of-bdi-dirty-thresholds fs/fs-writeback.c
--- a/fs/fs-writeback.c~writeback-avoid-unnecessary-calculation-of-bdi-dirty-thresholds
+++ a/fs/fs-writeback.c
@@ -593,7 +593,7 @@ static inline bool over_bground_thresh(v
{
unsigned long background_thresh, dirty_thresh;
- get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
+ global_dirty_limits(&background_thresh, &dirty_thresh);
return (global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS) >= background_thresh);
diff -puN include/linux/writeback.h~writeback-avoid-unnecessary-calculation-of-bdi-dirty-thresholds include/linux/writeback.h
--- a/include/linux/writeback.h~writeback-avoid-unnecessary-calculation-of-bdi-dirty-thresholds
+++ a/include/linux/writeback.h
@@ -124,8 +124,9 @@ struct ctl_table;
int dirty_writeback_centisecs_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
-void get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty,
- unsigned long *pbdi_dirty, struct backing_dev_info *bdi);
+void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
+unsigned long bdi_dirty_limit(struct backing_dev_info *bdi,
+ unsigned long dirty);
void page_writeback_init(void);
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
diff -puN mm/backing-dev.c~writeback-avoid-unnecessary-calculation-of-bdi-dirty-thresholds mm/backing-dev.c
--- a/mm/backing-dev.c~writeback-avoid-unnecessary-calculation-of-bdi-dirty-thresholds
+++ a/mm/backing-dev.c
@@ -83,7 +83,8 @@ static int bdi_debug_stats_show(struct s
nr_more_io++;
spin_unlock(&inode_lock);
- get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi);
+ global_dirty_limits(&background_thresh, &dirty_thresh);
+ bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
#define K(x) ((x) << (PAGE_SHIFT - 10))
seq_printf(m,
diff -puN mm/page-writeback.c~writeback-avoid-unnecessary-calculation-of-bdi-dirty-thresholds mm/page-writeback.c
--- a/mm/page-writeback.c~writeback-avoid-unnecessary-calculation-of-bdi-dirty-thresholds
+++ a/mm/page-writeback.c
@@ -267,10 +267,11 @@ static inline void task_dirties_fraction
*
* dirty -= (dirty/8) * p_{t}
*/
-static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty)
+static unsigned long task_dirty_limit(struct task_struct *tsk,
+ unsigned long bdi_dirty)
{
long numerator, denominator;
- unsigned long dirty = *pdirty;
+ unsigned long dirty = bdi_dirty;
u64 inv = dirty >> 3;
task_dirties_fraction(tsk, &numerator, &denominator);
@@ -278,10 +279,8 @@ static void task_dirty_limit(struct task
do_div(inv, denominator);
dirty -= inv;
- if (dirty < *pdirty/2)
- dirty = *pdirty/2;
- *pdirty = dirty;
+ return max(dirty, bdi_dirty/2);
}
/*
@@ -391,9 +390,7 @@ unsigned long determine_dirtyable_memory
return x + 1; /* Ensure that we never return 0 */
}
-void
-get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty,
- unsigned long *pbdi_dirty, struct backing_dev_info *bdi)
+void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
{
unsigned long background;
unsigned long dirty;
@@ -425,26 +422,28 @@ get_dirty_limits(unsigned long *pbackgro
}
*pbackground = background;
*pdirty = dirty;
+}
- if (bdi) {
- u64 bdi_dirty;
- long numerator, denominator;
+unsigned long bdi_dirty_limit(struct backing_dev_info *bdi,
+ unsigned long dirty)
+{
+ u64 bdi_dirty;
+ long numerator, denominator;
- /*
- * Calculate this BDI's share of the dirty ratio.
- */
- bdi_writeout_fraction(bdi, &numerator, &denominator);
+ /*
+ * 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;
+ bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100;
+ bdi_dirty *= numerator;
+ do_div(bdi_dirty, denominator);
- *pbdi_dirty = bdi_dirty;
- task_dirty_limit(current, pbdi_dirty);
- }
+ bdi_dirty += (dirty * bdi->min_ratio) / 100;
+ if (bdi_dirty > (dirty * bdi->max_ratio) / 100)
+ bdi_dirty = dirty * bdi->max_ratio / 100;
+
+ return task_dirty_limit(current, bdi_dirty);
}
/*
@@ -475,14 +474,24 @@ static void balance_dirty_pages(struct a
.range_cyclic = 1,
};
- get_dirty_limits(&background_thresh, &dirty_thresh,
- &bdi_thresh, bdi);
-
nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
nr_writeback = global_page_state(NR_WRITEBACK) +
global_page_state(NR_WRITEBACK_TEMP);
+ global_dirty_limits(&background_thresh, &dirty_thresh);
+
+ /*
+ * Throttle it only when the background writeback cannot
+ * catch-up. This avoids (excessively) small writeouts
+ * when the bdi limits are ramping up.
+ */
+ if (nr_reclaimable + nr_writeback <
+ (background_thresh + dirty_thresh) / 2)
+ break;
+
+ bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
+
/*
* In order to avoid the stacked BDI deadlock we need
* to ensure we accurately count the 'dirty' pages when
@@ -514,15 +523,6 @@ static void balance_dirty_pages(struct a
if (!dirty_exceeded)
break;
- /*
- * Throttle it only when the background writeback cannot
- * catch-up. This avoids (excessively) small writeouts
- * when the bdi limits are ramping up.
- */
- if (nr_reclaimable + nr_writeback <
- (background_thresh + dirty_thresh) / 2)
- break;
-
if (!bdi->dirty_exceeded)
bdi->dirty_exceeded = 1;
@@ -635,7 +635,7 @@ void throttle_vm_writeout(gfp_t gfp_mask
unsigned long dirty_thresh;
for ( ; ; ) {
- get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
+ global_dirty_limits(&background_thresh, &dirty_thresh);
/*
* Boost the allowable dirty threshold a bit for page
_
Patches currently in -mm which might be from fengguang.wu@xxxxxxxxx are
origin.patch
linux-next.patch
include-linux-fsh-complete-hexification-of-fmode_-constants.patch
vfs-o_-bit-numbers-uniqueness-check.patch
vfs-introduce-fmode_neg_offset-for-allowing-negative-f_pos.patch
writeback-take-account-of-nr_writeback_temp-in-balance_dirty_pages.patch
writeback-reduce-calls-to-global_page_state-in-balance_dirty_pages.patch
writeback-avoid-unnecessary-calculation-of-bdi-dirty-thresholds.patch
writeback-dont-redirty-tail-an-inode-with-dirty-pages.patch
writeback-fix-queue_io-ordering.patch
writeback-merge-for_kupdate-and-for_kupdate-cases.patch
vfs-add-super-operation-writeback_inodes.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
