The patch titled
mm: bdi: allow setting a maximum for the bdi dirty limit
has been added to the -mm tree. Its filename is
mm-bdi-allow-setting-a-maximum-for-the-bdi-dirty-limit.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://www.zip.com.au/~akpm/linux/patches/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: mm: bdi: allow setting a maximum for the bdi dirty limit
From: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Add "max_ratio" to /sys/class/bdi. This indicates the maximum percentage of
the global dirty threshold allocated to this bdi.
[mszeredi@xxxxxxx]
- fix parsing in max_ratio_store().
- export bdi_set_max_ratio() to modules
- limit bdi_dirty with bdi->max_ratio
- document new sysfs attribute
Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Signed-off-by: Miklos Szeredi <mszeredi@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
Documentation/ABI/testing/sysfs-class-bdi | 9 +++-
include/linux/backing-dev.h | 2
include/linux/proportions.h | 13 ++++++
lib/proportions.c | 38 +++++++++++++++---
mm/backing-dev.c | 21 ++++++++++
mm/page-writeback.c | 41 +++++++++++++++++---
6 files changed, 111 insertions(+), 13 deletions(-)
diff -puN Documentation/ABI/testing/sysfs-class-bdi~mm-bdi-allow-setting-a-maximum-for-the-bdi-dirty-limit Documentation/ABI/testing/sysfs-class-bdi
--- a/Documentation/ABI/testing/sysfs-class-bdi~mm-bdi-allow-setting-a-maximum-for-the-bdi-dirty-limit
+++ a/Documentation/ABI/testing/sysfs-class-bdi
@@ -53,4 +53,11 @@ min_ratio (read-write)
Minimal percentage of global dirty threshold allocated to this
bdi. If the value written to this file would make the the sum
of all min_ratio values exceed 100, then EINVAL is returned.
- The default is zero
+ If min_ratio would become larger than the current max_ratio,
+ then also EINVAL is returned. The default is zero
+
+max_ratio (read-write)
+
+ Maximal percentage of global dirty threshold allocated to this
+ bdi. If max_ratio would become smaller than the current
+ min_ratio, then EINVAL is returned. The default is 100
diff -puN include/linux/backing-dev.h~mm-bdi-allow-setting-a-maximum-for-the-bdi-dirty-limit include/linux/backing-dev.h
--- a/include/linux/backing-dev.h~mm-bdi-allow-setting-a-maximum-for-the-bdi-dirty-limit
+++ a/include/linux/backing-dev.h
@@ -52,6 +52,7 @@ struct backing_dev_info {
int dirty_exceeded;
unsigned int min_ratio;
+ unsigned int max_ratio, max_prop_frac;
struct device *dev;
};
@@ -139,6 +140,7 @@ static inline unsigned long bdi_stat_err
}
int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio);
+int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
/*
* Flags in backing_dev_info::capability
diff -puN include/linux/proportions.h~mm-bdi-allow-setting-a-maximum-for-the-bdi-dirty-limit include/linux/proportions.h
--- a/include/linux/proportions.h~mm-bdi-allow-setting-a-maximum-for-the-bdi-dirty-limit
+++ a/include/linux/proportions.h
@@ -78,6 +78,19 @@ void prop_inc_percpu(struct prop_descrip
}
/*
+ * Limit the time part in order to ensure there are some bits left for the
+ * cycle counter and fraction multiply.
+ */
+#define PROP_MAX_SHIFT (3*BITS_PER_LONG/4)
+
+#define PROP_FRAC_SHIFT (BITS_PER_LONG - PROP_MAX_SHIFT - 1)
+#define PROP_FRAC_BASE (1UL << PROP_FRAC_SHIFT)
+
+void __prop_inc_percpu_max(struct prop_descriptor *pd,
+ struct prop_local_percpu *pl, long frac);
+
+
+/*
* ----- SINGLE ------
*/
diff -puN lib/proportions.c~mm-bdi-allow-setting-a-maximum-for-the-bdi-dirty-limit lib/proportions.c
--- a/lib/proportions.c~mm-bdi-allow-setting-a-maximum-for-the-bdi-dirty-limit
+++ a/lib/proportions.c
@@ -73,12 +73,6 @@
#include <linux/proportions.h>
#include <linux/rcupdate.h>
-/*
- * Limit the time part in order to ensure there are some bits left for the
- * cycle counter.
- */
-#define PROP_MAX_SHIFT (3*BITS_PER_LONG/4)
-
int prop_descriptor_init(struct prop_descriptor *pd, int shift)
{
int err;
@@ -268,6 +262,38 @@ void __prop_inc_percpu(struct prop_descr
}
/*
+ * identical to __prop_inc_percpu, except that it limits this pl's fraction to
+ * @frac/PROP_FRAC_BASE by ignoring events when this limit has been exceeded.
+ */
+void __prop_inc_percpu_max(struct prop_descriptor *pd,
+ struct prop_local_percpu *pl, long frac)
+{
+ struct prop_global *pg = prop_get_global(pd);
+
+ prop_norm_percpu(pg, pl);
+
+ if (unlikely(frac != PROP_FRAC_BASE)) {
+ unsigned long period_2 = 1UL << (pg->shift - 1);
+ unsigned long counter_mask = period_2 - 1;
+ unsigned long global_count;
+ long numerator, denominator;
+
+ numerator = percpu_counter_read_positive(&pl->events);
+ global_count = percpu_counter_read(&pg->events);
+ denominator = period_2 + (global_count & counter_mask);
+
+ if (numerator > ((denominator * frac) >> PROP_FRAC_SHIFT))
+ goto out_put;
+ }
+
+ percpu_counter_add(&pl->events, 1);
+ percpu_counter_add(&pg->events, 1);
+
+out_put:
+ prop_put_global(pd, pg);
+}
+
+/*
* Obtain a fraction of this proportion
*
* p_{j} = x_{j} / (period/2 + t % period/2)
diff -puN mm/backing-dev.c~mm-bdi-allow-setting-a-maximum-for-the-bdi-dirty-limit mm/backing-dev.c
--- a/mm/backing-dev.c~mm-bdi-allow-setting-a-maximum-for-the-bdi-dirty-limit
+++ a/mm/backing-dev.c
@@ -68,6 +68,24 @@ static ssize_t min_ratio_store(struct de
}
BDI_SHOW(min_ratio, bdi->min_ratio)
+static ssize_t max_ratio_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t count)
+{
+ struct backing_dev_info *bdi = dev_get_drvdata(dev);
+ char *end;
+ unsigned int ratio;
+ ssize_t ret = -EINVAL;
+
+ ratio = simple_strtoul(buf, &end, 10);
+ if (*buf && (end[0] == '\0' || (end[0] == '\n' && end[1] == '\0'))) {
+ ret = bdi_set_max_ratio(bdi, ratio);
+ if (!ret)
+ ret = count;
+ }
+ return ret;
+}
+BDI_SHOW(max_ratio, bdi->max_ratio)
+
#define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store)
static struct device_attribute bdi_dev_attrs[] = {
@@ -77,6 +95,7 @@ static struct device_attribute bdi_dev_a
__ATTR_RO(dirty_kb),
__ATTR_RO(bdi_dirty_kb),
__ATTR_RW(min_ratio),
+ __ATTR_RW(max_ratio),
__ATTR_NULL,
};
@@ -136,6 +155,8 @@ int bdi_init(struct backing_dev_info *bd
bdi->dev = NULL;
bdi->min_ratio = 0;
+ bdi->max_ratio = 100;
+ bdi->max_prop_frac = PROP_FRAC_BASE;
for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
err = percpu_counter_init_irq(&bdi->bdi_stat[i], 0);
diff -puN mm/page-writeback.c~mm-bdi-allow-setting-a-maximum-for-the-bdi-dirty-limit mm/page-writeback.c
--- a/mm/page-writeback.c~mm-bdi-allow-setting-a-maximum-for-the-bdi-dirty-limit
+++ a/mm/page-writeback.c
@@ -164,7 +164,8 @@ int dirty_ratio_handler(struct ctl_table
*/
static inline void __bdi_writeout_inc(struct backing_dev_info *bdi)
{
- __prop_inc_percpu(&vm_completions, &bdi->completions);
+ __prop_inc_percpu_max(&vm_completions, &bdi->completions,
+ bdi->max_prop_frac);
}
static inline void task_dirty_inc(struct task_struct *tsk)
@@ -254,17 +255,43 @@ int bdi_set_min_ratio(struct backing_dev
unsigned long flags;
spin_lock_irqsave(&bdi_lock, flags);
- min_ratio -= bdi->min_ratio;
- if (bdi_min_ratio + min_ratio < 100) {
- bdi_min_ratio += min_ratio;
- bdi->min_ratio += min_ratio;
- } else
+ if (min_ratio > bdi->max_ratio) {
ret = -EINVAL;
+ } else {
+ min_ratio -= bdi->min_ratio;
+ if (bdi_min_ratio + min_ratio < 100) {
+ bdi_min_ratio += min_ratio;
+ bdi->min_ratio += min_ratio;
+ } else {
+ ret = -EINVAL;
+ }
+ }
spin_unlock_irqrestore(&bdi_lock, flags);
return ret;
}
+int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
+{
+ unsigned long flags;
+ int ret = 0;
+
+ if (max_ratio > 100)
+ return -EINVAL;
+
+ spin_lock_irqsave(&bdi_lock, flags);
+ if (bdi->min_ratio > max_ratio) {
+ ret = -EINVAL;
+ } else {
+ bdi->max_ratio = max_ratio;
+ bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
+ }
+ spin_unlock_irqrestore(&bdi_lock, flags);
+
+ return 0;
+}
+EXPORT_SYMBOL(bdi_set_max_ratio);
+
/*
* Work out the current dirty-memory clamping and background writeout
* thresholds.
@@ -365,6 +392,8 @@ get_dirty_limits(long *pbackground, long
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;
*pbdi_dirty = bdi_dirty;
clip_bdi_dirty_limit(bdi, dirty, pbdi_dirty);
_
Patches currently in -mm which might be from a.p.zijlstra@xxxxxxxxx are
origin.patch
lockdep-annotate-epoll.patch
slub-move-kmem_cache_node-determination-into-add_full-and-add_partial-slub-workaround-for-lockdep-confusion.patch
swapin-needs-gfp_mask-for-loop-on-tmpfs.patch
mm-page-writeback-highmem_is_dirtyable-option.patch
mm-page-writeback-highmem_is_dirtyable-option-fix.patch
skip-writing-data-pages-when-inode-is-under-i_sync.patch
fix-dirty-page-accounting-leak-with-ext3-data=journal.patch
kernel-add-mutex_lock_killable.patch
vfs-use-mutex_lock_killable-in-vfs_readdir.patch
memory-controller-add-documentation.patch
memory-controller-resource-counters-v7.patch
memory-controller-containers-setup-v7.patch
memory-controller-accounting-setup-v7.patch
memory-controller-memory-accounting-v7.patch
memory-controller-task-migration-v7.patch
memory-controller-add-per-container-lru-and-reclaim-v7.patch
memory-controller-improve-user-interface.patch
memory-controller-oom-handling-v7.patch
memory-controller-add-switch-to-control-what-type-of-pages-to-limit-v7.patch
memory-controller-make-page_referenced-container-aware-v7.patch
memory-controller-make-charging-gfp-mask-aware.patch
memcgroup-reinstate-swapoff-mod.patch
bugfix-for-memory-cgroup-controller-charge-refcnt-race-fix.patch
bugfix-for-memory-cgroup-controller-fix-error-handling-path-in-mem_charge_cgroup.patch
bugfix-for-memory-controller-add-helper-function-for-assigning-cgroup-to-page.patch
bugfix-for-memory-cgroup-controller-migration-under-memory-controller-fix.patch
bugfix-for-memory-cgroup-controller-avoid-pagelru-page-in-mem_cgroup_isolate_pages.patch
bugfix-for-memory-cgroup-controller-avoid-pagelru-page-in-mem_cgroup_isolate_pages-fix.patch
memcgroup-fix-zone-isolation-oom.patch
memcgroup-revert-swap_state-mods.patch
memory-cgroup-enhancements-fix-zone-handling-in-try_to_free_mem_cgroup_page.patch
memory-cgroup-enhancements-force_empty-interface-for-dropping-all-account-in-empty-cgroup.patch
memory-cgroup-enhancements-remember-a-page-is-charged-as-page-cache.patch
memory-cgroup-enhancements-remember-a-page-is-on-active-list-of-cgroup-or-not.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup.patch
memory-cgroup-enhancements-add-memorystat-file.patch
memory-cgroup-enhancements-add-pre_destroy-handler.patch
memory-cgroup-enhancements-implicit-force_empty-at-rmdir.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-add-scan_global_lru-macro.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-nid-zid-helper-function-for-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-active-inactive-counter.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-calculate-mapper_ratio-per-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-calculate-active-inactive-imbalance-per-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-remember-reclaim-priority-in-memory-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-calculate-the-number-of-pages-to-be-scanned-per-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-modifies-vmscanc-for-isolate-globa-cgroup-lru-activity.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-lru-for-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-lock-for-cgroup.patch
mm-bdi-export-bdi-attributes-in-sysfs.patch
mm-bdi-expose-the-bdi-object-in-sysfs-for-nfs.patch
mm-bdi-expose-the-bdi-object-in-sysfs-for-fuse.patch
mm-bdi-allow-setting-a-minimum-for-the-bdi-dirty-limit.patch
mm-bdi-allow-setting-a-maximum-for-the-bdi-dirty-limit.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
