Currently the proactive compaction order is fixed to
COMPACTION_HPAGE_ORDER(9), it's OK in most machines with lots of
normal 4KB memory, but it's too high for the machines with small
normal memory, for example the machines with most memory configured
as 1GB hugetlbfs huge pages. In these machines the max order of
free pages is often below 9, and it's always below 9 even with hard
compaction. This will lead to proactive compaction be triggered very
frequently. In these machines we only care about order of 3 or 4.
This patch export the oder to proc and let it configurable
by user, and the default value is still COMPACTION_HPAGE_ORDER.
Signed-off-by: chukaiping <[email protected]>
Reported-by: kernel test robot <[email protected]>
---
Changes in v2:
- fix the compile error in ia64 and powerpc
- change the hard coded max order number from 10 to MAX_ORDER - 1
include/linux/compaction.h | 1 +
kernel/sysctl.c | 11 +++++++++++
mm/compaction.c | 14 +++++++++++---
3 files changed, 23 insertions(+), 3 deletions(-)
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index ed4070e..151ccd1 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -83,6 +83,7 @@ static inline unsigned long compact_gap(unsigned int order)
#ifdef CONFIG_COMPACTION
extern int sysctl_compact_memory;
extern unsigned int sysctl_compaction_proactiveness;
+extern unsigned int sysctl_compaction_order;
extern int sysctl_compaction_handler(struct ctl_table *table, int write,
void *buffer, size_t *length, loff_t *ppos);
extern int sysctl_extfrag_threshold;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 62fbd09..a607d4d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -195,6 +195,8 @@ enum sysctl_writes_mode {
#endif /* CONFIG_SMP */
#endif /* CONFIG_SCHED_DEBUG */
+static int max_buddy_zone = MAX_ORDER - 1;
+
#ifdef CONFIG_COMPACTION
static int min_extfrag_threshold;
static int max_extfrag_threshold = 1000;
@@ -2871,6 +2873,15 @@ int proc_do_static_key(struct ctl_table *table, int write,
.extra2 = &one_hundred,
},
{
+ .procname = "compaction_order",
+ .data = &sysctl_compaction_order,
+ .maxlen = sizeof(sysctl_compaction_order),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = &max_buddy_zone,
+ },
+ {
.procname = "extfrag_threshold",
.data = &sysctl_extfrag_threshold,
.maxlen = sizeof(int),
diff --git a/mm/compaction.c b/mm/compaction.c
index e04f447..bfd1d5e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1925,16 +1925,16 @@ static bool kswapd_is_running(pg_data_t *pgdat)
/*
* A zone's fragmentation score is the external fragmentation wrt to the
- * COMPACTION_HPAGE_ORDER. It returns a value in the range [0, 100].
+ * sysctl_compaction_order. It returns a value in the range [0, 100].
*/
static unsigned int fragmentation_score_zone(struct zone *zone)
{
- return extfrag_for_order(zone, COMPACTION_HPAGE_ORDER);
+ return extfrag_for_order(zone, sysctl_compaction_order);
}
/*
* A weighted zone's fragmentation score is the external fragmentation
- * wrt to the COMPACTION_HPAGE_ORDER scaled by the zone's size. It
+ * wrt to the sysctl_compaction_order scaled by the zone's size. It
* returns a value in the range [0, 100].
*
* The scaling factor ensures that proactive compaction focuses on larger
@@ -2666,6 +2666,7 @@ static void compact_nodes(void)
* background. It takes values in the range [0, 100].
*/
unsigned int __read_mostly sysctl_compaction_proactiveness = 20;
+unsigned int __read_mostly sysctl_compaction_order;
/*
* This is the entry point for compacting all nodes via
@@ -2958,6 +2959,13 @@ static int __init kcompactd_init(void)
int nid;
int ret;
+ /*
+ * move the initialization of sysctl_compaction_order to here to
+ * eliminate compile error in ia64 and powerpc architecture because
+ * COMPACTION_HPAGE_ORDER is a variable in this architecture
+ */
+ sysctl_compaction_order = COMPACTION_HPAGE_ORDER;
+
ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
"mm/compaction:online",
kcompactd_cpu_online, NULL);
--
1.7.1
> -----Original Message-----
> From: chukaiping <[email protected]>
> Sent: Wednesday, April 21, 2021 12:22 AM
> To: [email protected]; [email protected]; [email protected];
> [email protected]; [email protected]; Nitin Gupta
> <[email protected]>; [email protected]; [email protected];
> [email protected]; [email protected]; [email protected]
> Cc: [email protected]; [email protected]; linux-
> [email protected]
> Subject: [PATCH v2] mm/compaction:let proactive compaction order
> configurable
>
> Currently the proactive compaction order is fixed to
> COMPACTION_HPAGE_ORDER(9), it's OK in most machines with lots of
> normal 4KB memory, but it's too high for the machines with small normal
> memory, for example the machines with most memory configured as 1GB
> hugetlbfs huge pages. In these machines the max order of free pages is often
> below 9, and it's always below 9 even with hard compaction. This will lead to
> proactive compaction be triggered very frequently. In these machines we only
> care about order of 3 or 4.
> This patch export the oder to proc and let it configurable by user, and the
> default value is still COMPACTION_HPAGE_ORDER.
>
I agree with the idea of making the target order configurable as you may not
always care about the hugepage order in particular.
> Signed-off-by: chukaiping <[email protected]>
> Reported-by: kernel test robot <[email protected]>
> ---
>
> Changes in v2:
> - fix the compile error in ia64 and powerpc
> - change the hard coded max order number from 10 to MAX_ORDER - 1
>
> include/linux/compaction.h | 1 +
> kernel/sysctl.c | 11 +++++++++++
> mm/compaction.c | 14 +++++++++++---
> 3 files changed, 23 insertions(+), 3 deletions(-)
>
> diff --git a/include/linux/compaction.h b/include/linux/compaction.h index
> ed4070e..151ccd1 100644
> --- a/include/linux/compaction.h
> +++ b/include/linux/compaction.h
> @@ -83,6 +83,7 @@ static inline unsigned long compact_gap(unsigned int
> order) #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory;
> extern unsigned int sysctl_compaction_proactiveness;
> +extern unsigned int sysctl_compaction_order;
> extern int sysctl_compaction_handler(struct ctl_table *table, int write,
> void *buffer, size_t *length, loff_t *ppos); extern int
> sysctl_extfrag_threshold; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index
> 62fbd09..a607d4d 100644
> --- a/kernel/sysctl.c
> +++ b/kernel/sysctl.c
> @@ -195,6 +195,8 @@ enum sysctl_writes_mode { #endif /* CONFIG_SMP
> */ #endif /* CONFIG_SCHED_DEBUG */
>
> +static int max_buddy_zone = MAX_ORDER - 1;
> +
> #ifdef CONFIG_COMPACTION
> static int min_extfrag_threshold;
> static int max_extfrag_threshold = 1000; @@ -2871,6 +2873,15 @@ int
> proc_do_static_key(struct ctl_table *table, int write,
> .extra2 = &one_hundred,
> },
> {
> + .procname = "compaction_order",
> + .data = &sysctl_compaction_order,
> + .maxlen = sizeof(sysctl_compaction_order),
> + .mode = 0644,
> + .proc_handler = proc_dointvec_minmax,
> + .extra1 = SYSCTL_ZERO,
This should be SYSCTL_ONE. Fragmentation wrt order 0 is always going to be 0.
Thanks,
Nitin
On Wed, Apr 21, 2021 at 03:21:53PM +0800, chukaiping wrote:
> Currently the proactive compaction order is fixed to
> COMPACTION_HPAGE_ORDER(9), it's OK in most machines with lots of
> normal 4KB memory, but it's too high for the machines with small
> normal memory, for example the machines with most memory configured
> as 1GB hugetlbfs huge pages. In these machines the max order of
> free pages is often below 9, and it's always below 9 even with hard
> compaction. This will lead to proactive compaction be triggered very
> frequently. In these machines we only care about order of 3 or 4.
> This patch export the oder to proc and let it configurable
> by user, and the default value is still COMPACTION_HPAGE_ORDER.
>
> Signed-off-by: chukaiping <[email protected]>
> Reported-by: kernel test robot <[email protected]>
> ---
>
> Changes in v2:
> - fix the compile error in ia64 and powerpc
> - change the hard coded max order number from 10 to MAX_ORDER - 1
>
> include/linux/compaction.h | 1 +
> kernel/sysctl.c | 11 +++++++++++
> mm/compaction.c | 14 +++++++++++---
> 3 files changed, 23 insertions(+), 3 deletions(-)
>
> diff --git a/include/linux/compaction.h b/include/linux/compaction.h
> index ed4070e..151ccd1 100644
> --- a/include/linux/compaction.h
> +++ b/include/linux/compaction.h
> @@ -83,6 +83,7 @@ static inline unsigned long compact_gap(unsigned int order)
> #ifdef CONFIG_COMPACTION
> extern int sysctl_compact_memory;
> extern unsigned int sysctl_compaction_proactiveness;
> +extern unsigned int sysctl_compaction_order;
> extern int sysctl_compaction_handler(struct ctl_table *table, int write,
> void *buffer, size_t *length, loff_t *ppos);
> extern int sysctl_extfrag_threshold;
> diff --git a/kernel/sysctl.c b/kernel/sysctl.c
> index 62fbd09..a607d4d 100644
> --- a/kernel/sysctl.c
> +++ b/kernel/sysctl.c
> @@ -195,6 +195,8 @@ enum sysctl_writes_mode {
> #endif /* CONFIG_SMP */
> #endif /* CONFIG_SCHED_DEBUG */
>
> +static int max_buddy_zone = MAX_ORDER - 1;
> +
This should go into the #ifdef CONFIG_COMPACTION section
below
> #ifdef CONFIG_COMPACTION
> static int min_extfrag_threshold;
> static int max_extfrag_threshold = 1000;
> @@ -2871,6 +2873,15 @@ int proc_do_static_key(struct ctl_table *table, int write,
> .extra2 = &one_hundred,
> },
> {
> + .procname = "compaction_order",
> + .data = &sysctl_compaction_order,
> + .maxlen = sizeof(sysctl_compaction_order),
> + .mode = 0644,
> + .proc_handler = proc_dointvec_minmax,
> + .extra1 = SYSCTL_ZERO,
> + .extra2 = &max_buddy_zone,
> + },
> + {
> .procname = "extfrag_threshold",
> .data = &sysctl_extfrag_threshold,
> .maxlen = sizeof(int),
> diff --git a/mm/compaction.c b/mm/compaction.c
> index e04f447..bfd1d5e 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -1925,16 +1925,16 @@ static bool kswapd_is_running(pg_data_t *pgdat)
>
> /*
> * A zone's fragmentation score is the external fragmentation wrt to the
> - * COMPACTION_HPAGE_ORDER. It returns a value in the range [0, 100].
> + * sysctl_compaction_order. It returns a value in the range [0, 100].
> */
> static unsigned int fragmentation_score_zone(struct zone *zone)
> {
> - return extfrag_for_order(zone, COMPACTION_HPAGE_ORDER);
> + return extfrag_for_order(zone, sysctl_compaction_order);
> }
>
> /*
> * A weighted zone's fragmentation score is the external fragmentation
> - * wrt to the COMPACTION_HPAGE_ORDER scaled by the zone's size. It
> + * wrt to the sysctl_compaction_order scaled by the zone's size. It
> * returns a value in the range [0, 100].
> *
> * The scaling factor ensures that proactive compaction focuses on larger
> @@ -2666,6 +2666,7 @@ static void compact_nodes(void)
> * background. It takes values in the range [0, 100].
> */
> unsigned int __read_mostly sysctl_compaction_proactiveness = 20;
> +unsigned int __read_mostly sysctl_compaction_order;
>
> /*
> * This is the entry point for compacting all nodes via
> @@ -2958,6 +2959,13 @@ static int __init kcompactd_init(void)
> int nid;
> int ret;
>
> + /*
> + * move the initialization of sysctl_compaction_order to here to
> + * eliminate compile error in ia64 and powerpc architecture because
> + * COMPACTION_HPAGE_ORDER is a variable in this architecture
> + */
This comment block belongs to your commit log, instead.
Cheers,
-- Rafael
> + sysctl_compaction_order = COMPACTION_HPAGE_ORDER;
> +
> ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
> "mm/compaction:online",
> kcompactd_cpu_online, NULL);
> --
> 1.7.1
>
>