This change adds a "smart" page scanning mode for KSM. So far all the
candidate pages are continuously scanned to find candidates for
de-duplication. There are a considerably number of pages that cannot be
de-duplicated. This is costly in terms of CPU. By using smart scanning
considerable CPU savings can be achieved.
This change takes the history of scanning pages into account and skips
the page scanning of certain pages for a while if de-deduplication for
this page has not been successful in the past.
To do this it introduces two new fields in the ksm_rmap_item structure:
age and skip_age. age, is the KSM age and skip_age is the age for how
long page scanning of this page is skipped. The age field is incremented
each time the page is scanned and the page cannot be de-duplicated.
How often a page is skipped is dependent how often de-duplication has
been tried so far and the number of skips is currently limited to 8.
This value has shown to be effective with different workloads.
The feature is currently disable by default and can be enabled with the
new smart_scan knob.
The feature has shown to be very effective: upt to 25% of the page scans
can be eliminated; the pages_to_scan rate can be reduced by 40 - 50% and
a similar de-duplication rate can be maintained.
Signed-off-by: Stefan Roesch <[email protected]>
---
mm/ksm.c | 108 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 108 insertions(+)
diff --git a/mm/ksm.c b/mm/ksm.c
index 981af9c72e7a..7a1aa3872cf4 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -56,6 +56,8 @@
#define DO_NUMA(x) do { } while (0)
#endif
+typedef u8 rmap_age_t;
+
/**
* DOC: Overview
*
@@ -193,6 +195,8 @@ struct ksm_stable_node {
* @node: rb node of this rmap_item in the unstable tree
* @head: pointer to stable_node heading this list in the stable tree
* @hlist: link into hlist of rmap_items hanging off that stable_node
+ * @age: number of scan iterations since creation
+ * @skip_age: skip rmap item until age reaches skip_age
*/
struct ksm_rmap_item {
struct ksm_rmap_item *rmap_list;
@@ -212,6 +216,8 @@ struct ksm_rmap_item {
struct hlist_node hlist;
};
};
+ rmap_age_t age;
+ rmap_age_t skip_age;
};
#define SEQNR_MASK 0x0ff /* low bits of unstable tree seqnr */
@@ -281,6 +287,9 @@ static unsigned int zero_checksum __read_mostly;
/* Whether to merge empty (zeroed) pages with actual zero pages */
static bool ksm_use_zero_pages __read_mostly;
+/* Skip pages that couldn't be de-duplicated previously */
+static bool ksm_smart_scan;
+
/* The number of zero pages which is placed by KSM */
unsigned long ksm_zero_pages;
@@ -2305,6 +2314,78 @@ static struct ksm_rmap_item *get_next_rmap_item(struct ksm_mm_slot *mm_slot,
return rmap_item;
}
+/*
+ * Calculate skip age for the ksm page age. The age determines how often
+ * de-duplicating has already been tried unsuccessfully. If the age is
+ * smaller, the scanning of this page is skipped for less scans.
+ *
+ * @age: rmap_item age of page
+ */
+static unsigned int skip_age(rmap_age_t age)
+{
+ if (age <= 3)
+ return 1;
+ if (age <= 5)
+ return 2;
+ if (age <= 8)
+ return 4;
+
+ return 8;
+}
+
+/*
+ * Determines if a page should be skipped for the current scan.
+ *
+ * @page: page to check
+ * @rmap_item: associated rmap_item of page
+ */
+static bool should_skip_rmap_item(struct page *page,
+ struct ksm_rmap_item *rmap_item)
+{
+ rmap_age_t age;
+
+ if (!ksm_smart_scan)
+ return false;
+
+ /*
+ * Never skip pages that are already KSM; pages cmp_and_merge_page()
+ * will essentially ignore them, but we still have to process them
+ * properly.
+ */
+ if (PageKsm(page))
+ return false;
+
+ /*
+ * Smaller ages are not skipped, they need to get a chance to go
+ * through the different phases of the KSM merging.
+ */
+ age = rmap_item->age;
+ rmap_item->age = (rmap_item->age + 1) & 0xFF;
+
+ if (age < 3)
+ return false;
+
+ /*
+ * Page has been skipped and reached its target age to re-enable
+ * scanning the page.
+ */
+ if (rmap_item->skip_age == age) {
+ rmap_item->skip_age = 0;
+ return false;
+ }
+
+ /*
+ * Skip the page and calculate skip_age on when to re-enable scanning
+ * for this page.
+ */
+ if (rmap_item->skip_age == 0) {
+ rmap_item->skip_age = (age + skip_age(age)) & 0xFF;
+ remove_rmap_item_from_tree(rmap_item);
+ }
+
+ return true;
+}
+
static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
{
struct mm_struct *mm;
@@ -2409,6 +2490,10 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
if (rmap_item) {
ksm_scan.rmap_list =
&rmap_item->rmap_list;
+
+ if (should_skip_rmap_item(*page, rmap_item))
+ goto next_page;
+
ksm_scan.address += PAGE_SIZE;
} else
put_page(*page);
@@ -3449,6 +3534,28 @@ static ssize_t full_scans_show(struct kobject *kobj,
}
KSM_ATTR_RO(full_scans);
+static ssize_t smart_scan_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sysfs_emit(buf, "%u\n", ksm_smart_scan);
+}
+
+static ssize_t smart_scan_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ int err;
+ bool value;
+
+ err = kstrtobool(buf, &value);
+ if (err)
+ return -EINVAL;
+
+ ksm_smart_scan = value;
+ return count;
+}
+KSM_ATTR(smart_scan);
+
static struct attribute *ksm_attrs[] = {
&sleep_millisecs_attr.attr,
&pages_to_scan_attr.attr,
@@ -3469,6 +3576,7 @@ static struct attribute *ksm_attrs[] = {
&stable_node_chains_prune_millisecs_attr.attr,
&use_zero_pages_attr.attr,
&general_profit_attr.attr,
+ &smart_scan_attr.attr,
NULL,
};
--
2.39.3
> +typedef u8 rmap_age_t;
> +
> /**
> * DOC: Overview
> *
> @@ -193,6 +195,8 @@ struct ksm_stable_node {
> * @node: rb node of this rmap_item in the unstable tree
> * @head: pointer to stable_node heading this list in the stable tree
> * @hlist: link into hlist of rmap_items hanging off that stable_node
> + * @age: number of scan iterations since creation
> + * @skip_age: skip rmap item until age reaches skip_age
> */
> struct ksm_rmap_item {
> struct ksm_rmap_item *rmap_list;
> @@ -212,6 +216,8 @@ struct ksm_rmap_item {
> struct hlist_node hlist;
> };
> };
> + rmap_age_t age;
> + rmap_age_t skip_age;
I *think* of you move that after "oldchecksum", the size of the struct
might not necessarily increase.
[...]
>
> +/*
> + * Calculate skip age for the ksm page age. The age determines how often
> + * de-duplicating has already been tried unsuccessfully. If the age is
> + * smaller, the scanning of this page is skipped for less scans.
> + *
> + * @age: rmap_item age of page
> + */
> +static unsigned int skip_age(rmap_age_t age)
> +{
> + if (age <= 3)
> + return 1;
> + if (age <= 5)
> + return 2;
> + if (age <= 8)
> + return 4;
> +
> + return 8;
> +}
> +
> +/*
> + * Determines if a page should be skipped for the current scan.
> + *
> + * @page: page to check
> + * @rmap_item: associated rmap_item of page
> + */
> +static bool should_skip_rmap_item(struct page *page,
> + struct ksm_rmap_item *rmap_item)
> +{
> + rmap_age_t age;
> +
> + if (!ksm_smart_scan)
> + return false;
> +
> + /*
> + * Never skip pages that are already KSM; pages cmp_and_merge_page()
> + * will essentially ignore them, but we still have to process them
> + * properly.
> + */
> + if (PageKsm(page))
> + return false;
> +
> + /*
> + * Smaller ages are not skipped, they need to get a chance to go
> + * through the different phases of the KSM merging.
> + */
Sorry, had to set some time aside to think this through. Wouldn't it be
cleaner to just not rely on this overflow?
Instead, we could track the page age (which we would freeze at U8_MAX)
and simply track how much more often we are allowed to skip.
Something like the following (which, I am sure, is completely broken,
but should express what I have in mind)
age = rmap_item->age;
if (age != U8_MAX)
rmap_item->age++;
/*
* Smaller ages are not skipped, they need to get a chance to go
* through the different phases of the KSM merging.
*/
if (age < 3)
return false;
/*
* Are we still allowed to skip? If not, then don't skip it
* and determine how much more often we are allowed to skip next.
*/
if (!rmap_item->remaining_skips) {
rmap_item->remaining_skips = skip_age(age);
return false;
}
/* Skip this page. */
rmap_item->remaining_skips--;
remove_rmap_item_from_tree(rmap_item);
return true;
Would that miss anything important? Was the overflow handling (and
scanning more often one we overflow again IIUC) important?
--
Cheers,
David / dhildenb
David Hildenbrand <[email protected]> writes:
>> +typedef u8 rmap_age_t;
>> +
>> /**
>> * DOC: Overview
>> *
>> @@ -193,6 +195,8 @@ struct ksm_stable_node {
>> * @node: rb node of this rmap_item in the unstable tree
>> * @head: pointer to stable_node heading this list in the stable tree
>> * @hlist: link into hlist of rmap_items hanging off that stable_node
>> + * @age: number of scan iterations since creation
>> + * @skip_age: skip rmap item until age reaches skip_age
>> */
>> struct ksm_rmap_item {
>> struct ksm_rmap_item *rmap_list;
>> @@ -212,6 +216,8 @@ struct ksm_rmap_item {
>> struct hlist_node hlist;
>> };
>> };
>> + rmap_age_t age;
>> + rmap_age_t skip_age;
>
> I *think* of you move that after "oldchecksum", the size of the struct might not
> necessarily increase.
>
> [...]
>
>> +/*
>> + * Calculate skip age for the ksm page age. The age determines how often
>> + * de-duplicating has already been tried unsuccessfully. If the age is
>> + * smaller, the scanning of this page is skipped for less scans.
>> + *
>> + * @age: rmap_item age of page
>> + */
>> +static unsigned int skip_age(rmap_age_t age)
>> +{
>> + if (age <= 3)
>> + return 1;
>> + if (age <= 5)
>> + return 2;
>> + if (age <= 8)
>> + return 4;
>> +
>> + return 8;
>> +}
>> +
>> +/*
>> + * Determines if a page should be skipped for the current scan.
>> + *
>> + * @page: page to check
>> + * @rmap_item: associated rmap_item of page
>> + */
>> +static bool should_skip_rmap_item(struct page *page,
>> + struct ksm_rmap_item *rmap_item)
>> +{
>> + rmap_age_t age;
>> +
>> + if (!ksm_smart_scan)
>> + return false;
>> +
>> + /*
>> + * Never skip pages that are already KSM; pages cmp_and_merge_page()
>> + * will essentially ignore them, but we still have to process them
>> + * properly.
>> + */
>> + if (PageKsm(page))
>> + return false;
>> +
>> + /*
>> + * Smaller ages are not skipped, they need to get a chance to go
>> + * through the different phases of the KSM merging.
>> + */
>
> Sorry, had to set some time aside to think this through. Wouldn't it be cleaner
> to just not rely on this overflow?
>
> Instead, we could track the page age (which we would freeze at U8_MAX) and
> simply track how much more often we are allowed to skip.
>
> Something like the following (which, I am sure, is completely broken, but should
> express what I have in mind)
>
>
>
> age = rmap_item->age;
> if (age != U8_MAX)
> rmap_item->age++;
>
> /*
> * Smaller ages are not skipped, they need to get a chance to go
> * through the different phases of the KSM merging.
> */
> if (age < 3)
> return false;
>
> /*
> * Are we still allowed to skip? If not, then don't skip it
> * and determine how much more often we are allowed to skip next.
> */
> if (!rmap_item->remaining_skips) {
> rmap_item->remaining_skips = skip_age(age);
> return false;
> }
>
> /* Skip this page. */
> rmap_item->remaining_skips--;
> remove_rmap_item_from_tree(rmap_item);
> return true;
>
>
>
> Would that miss anything important? Was the overflow handling (and scanning more
> often one we overflow again IIUC) important?
>
That sounds reasonable. I'll incorporate the two suggestions in the next version.