Linux Virtualization - Feb 2016 - [PATCH 0/2] export 'available' memory to virtio balloon statistics

Add a new field, VIRTIO_BALLOON_S_AVAIL, to virtio_balloon memory
statistics protocol, corresponding to 'Available' in /proc/meminfo.

It indicates to the hypervisor how big the balloon can be inflated
without pushing the guest system to swap. This metric would be very
useful in VM orchestration software to improve memory management
of different VMs under overcommit.

Signed-off-by: Igor Redko <redkoi at virtuozzo.com>
Reviewed-by: Roman Kagan <rkagan at virtuozzo.com>
Signed-off-by: Denis V. Lunev <den at openvz.org>
CC: Michael S. Tsirkin <mst at redhat.com>
CC: Andrew Morton <akpm at linux-foundation.org>

Igor Redko (2):
  calculate 'available' memory in the separate function
  virtio_balloon: export 'available' memory to balloon statistics

 drivers/virtio/virtio_balloon.c     |  6 ++++++
 fs/proc/meminfo.c                   | 31 +-------------------------
 include/linux/mm.h                  |  1 +
 include/uapi/linux/virtio_balloon.h |  3 ++-
 mm/page_alloc.c                     | 43 +++++++++++++++++++++++++++++++++++++
 5 files changed, 53 insertions(+), 31 deletions(-)

-- 
2.5.0

From: Igor Redko <redkoi at virtuozzo.com>

Factor out calculation of the available memory counter into a separate
exportable function, in order to be able to use it in other parts of
the kernel.

In particular, it appears a relevant metric to report to the
hypervisor via virtio-balloon statistics interface (in a followup
patch).

Signed-off-by: Igor Redko <redkoi at virtuozzo.com>
Reviewed-by: Roman Kagan <rkagan at virtuozzo.com>
Signed-off-by: Denis V. Lunev <den at openvz.org>
CC: Michael S. Tsirkin <mst at redhat.com>
CC: Andrew Morton <akpm at linux-foundation.org>
---
 fs/proc/meminfo.c  | 31 +------------------------------
 include/linux/mm.h |  1 +
 mm/page_alloc.c    | 43 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 45 insertions(+), 30 deletions(-)

diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index df4661a..8372046 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -29,10 +29,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	unsigned long committed;
 	long cached;
 	long available;
-	unsigned long pagecache;
-	unsigned long wmark_low = 0;
 	unsigned long pages[NR_LRU_LISTS];
-	struct zone *zone;
 	int lru;
 
 /*
@@ -51,33 +48,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
 		pages[lru] = global_page_state(NR_LRU_BASE + lru);
 
-	for_each_zone(zone)
-		wmark_low += zone->watermark[WMARK_LOW];
-
-	/*
-	 * Estimate the amount of memory available for userspace allocations,
-	 * without causing swapping.
-	 */
-	available = i.freeram - totalreserve_pages;
-
-	/*
-	 * Not all the page cache can be freed, otherwise the system will
-	 * start swapping. Assume at least half of the page cache, or the
-	 * low watermark worth of cache, needs to stay.
-	 */
-	pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
-	pagecache -= min(pagecache / 2, wmark_low);
-	available += pagecache;
-
-	/*
-	 * Part of the reclaimable slab consists of items that are in use,
-	 * and cannot be freed. Cap this estimate at the low watermark.
-	 */
-	available += global_page_state(NR_SLAB_RECLAIMABLE) -
-		     min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
-
-	if (available < 0)
-		available = 0;
+	available = si_mem_available();
 
 	/*
 	 * Tagged format, for easy grepping and expansion.
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 516e149..a8c4144 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1862,6 +1862,7 @@ extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
 extern void __init mmap_init(void);
 extern void show_mem(unsigned int flags);
+extern long si_mem_available(void);
 extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 838ca8bb..dae813c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3603,6 +3603,49 @@ static inline void show_node(struct zone *zone)
 		printk("Node %d ", zone_to_nid(zone));
 }
 
+long si_mem_available(void)
+{
+	long available;
+	unsigned long pagecache;
+	unsigned long wmark_low = 0;
+	unsigned long pages[NR_LRU_LISTS];
+	struct zone *zone;
+	int lru;
+
+	for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
+		pages[lru] = global_page_state(NR_LRU_BASE + lru);
+
+	for_each_zone(zone)
+		wmark_low += zone->watermark[WMARK_LOW];
+
+	/*
+	 * Estimate the amount of memory available for userspace allocations,
+	 * without causing swapping.
+	 */
+	available = global_page_state(NR_FREE_PAGES) - totalreserve_pages;
+
+	/*
+	 * Not all the page cache can be freed, otherwise the system will
+	 * start swapping. Assume at least half of the page cache, or the
+	 * low watermark worth of cache, needs to stay.
+	 */
+	pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
+	pagecache -= min(pagecache / 2, wmark_low);
+	available += pagecache;
+
+	/*
+	 * Part of the reclaimable slab consists of items that are in use,
+	 * and cannot be freed. Cap this estimate at the low watermark.
+	 */
+	available += global_page_state(NR_SLAB_RECLAIMABLE) -
+		     min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
+
+	if (available < 0)
+		available = 0;
+	return available;
+}
+EXPORT_SYMBOL_GPL(si_mem_available);
+
 void si_meminfo(struct sysinfo *val)
 {
 	val->totalram = totalram_pages;
-- 
2.5.0

From: Igor Redko <redkoi at virtuozzo.com>

Add a new field, VIRTIO_BALLOON_S_AVAIL, to virtio_balloon memory
statistics protocol, corresponding to 'Available' in /proc/meminfo.

It indicates to the hypervisor how big the balloon can be inflated
without pushing the guest system to swap.

Signed-off-by: Igor Redko <redkoi at virtuozzo.com>
Reviewed-by: Roman Kagan <rkagan at virtuozzo.com>
Signed-off-by: Denis V. Lunev <den at openvz.org>
CC: Michael S. Tsirkin <mst at redhat.com>
CC: Andrew Morton <akpm at linux-foundation.org>
---
 drivers/virtio/virtio_balloon.c     | 6 ++++++
 include/uapi/linux/virtio_balloon.h | 3 ++-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 0c3691f..f2b77de 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -30,6 +30,7 @@
 #include <linux/balloon_compaction.h>
 #include <linux/oom.h>
 #include <linux/wait.h>
+#include <linux/mm.h>
 
 /*
  * Balloon device works in 4K page units.  So each page is pointed to by
@@ -229,10 +230,13 @@ static void update_balloon_stats(struct virtio_balloon
*vb)
 	unsigned long events[NR_VM_EVENT_ITEMS];
 	struct sysinfo i;
 	int idx = 0;
+	long available;
 
 	all_vm_events(events);
 	si_meminfo(&i);
 
+	available = si_mem_available();
+
 	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_IN,
 				pages_to_bytes(events[PSWPIN]));
 	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_OUT,
@@ -243,6 +247,8 @@ static void update_balloon_stats(struct virtio_balloon *vb)
 				pages_to_bytes(i.freeram));
 	update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMTOT,
 				pages_to_bytes(i.totalram));
+	update_stat(vb, idx++, VIRTIO_BALLOON_S_AVAIL,
+				pages_to_bytes(available));
 }
 
 /*
diff --git a/include/uapi/linux/virtio_balloon.h
b/include/uapi/linux/virtio_balloon.h
index d7f1cbc..343d7dd 100644
--- a/include/uapi/linux/virtio_balloon.h
+++ b/include/uapi/linux/virtio_balloon.h
@@ -51,7 +51,8 @@ struct virtio_balloon_config {
 #define VIRTIO_BALLOON_S_MINFLT   3   /* Number of minor faults */
 #define VIRTIO_BALLOON_S_MEMFREE  4   /* Total amount of free memory */
 #define VIRTIO_BALLOON_S_MEMTOT   5   /* Total amount of memory */
-#define VIRTIO_BALLOON_S_NR       6
+#define VIRTIO_BALLOON_S_AVAIL    6   /* Available memory as in /proc */
+#define VIRTIO_BALLOON_S_NR       7
 
 /*
  * Memory statistics structure.
-- 
2.5.0

On Tue, Feb 16, 2016 at 06:50:52PM +0300, Denis V. Lunev
wrote:
> From: Igor Redko <redkoi at virtuozzo.com>
> 
> Add a new field, VIRTIO_BALLOON_S_AVAIL, to virtio_balloon memory
> statistics protocol, corresponding to 'Available' in /proc/meminfo.
> 
> It indicates to the hypervisor how big the balloon can be inflated
> without pushing the guest system to swap.
> 
> Signed-off-by: Igor Redko <redkoi at virtuozzo.com>
> Reviewed-by: Roman Kagan <rkagan at virtuozzo.com>
> Signed-off-by: Denis V. Lunev <den at openvz.org>
> CC: Michael S. Tsirkin <mst at redhat.com>
> CC: Andrew Morton <akpm at linux-foundation.org>
Oops - I missed the fact that this affects host/guest ABI.

Can you please submit ABI update proposal to virtio tc?
Spec patch would be even better.

This is important to ensure there are no conflicts
with other features being developed in parallel.
> ---
>  drivers/virtio/virtio_balloon.c     | 6 ++++++
>  include/uapi/linux/virtio_balloon.h | 3 ++-
>  2 files changed, 8 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/virtio/virtio_balloon.c
b/drivers/virtio/virtio_balloon.c
> index 0c3691f..f2b77de 100644
> --- a/drivers/virtio/virtio_balloon.c
> +++ b/drivers/virtio/virtio_balloon.c
> @@ -30,6 +30,7 @@
>  #include <linux/balloon_compaction.h>
>  #include <linux/oom.h>
>  #include <linux/wait.h>
> +#include <linux/mm.h>
>  
>  /*
>   * Balloon device works in 4K page units.  So each page is pointed to by
> @@ -229,10 +230,13 @@ static void update_balloon_stats(struct
virtio_balloon *vb)
>  	unsigned long events[NR_VM_EVENT_ITEMS];
>  	struct sysinfo i;
>  	int idx = 0;
> +	long available;
>  
>  	all_vm_events(events);
>  	si_meminfo(&i);
>  
> +	available = si_mem_available();
> +
>  	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_IN,
>  				pages_to_bytes(events[PSWPIN]));
>  	update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_OUT,
> @@ -243,6 +247,8 @@ static void update_balloon_stats(struct virtio_balloon
*vb)
>  				pages_to_bytes(i.freeram));
>  	update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMTOT,
>  				pages_to_bytes(i.totalram));
> +	update_stat(vb, idx++, VIRTIO_BALLOON_S_AVAIL,
> +				pages_to_bytes(available));
>  }
>  
>  /*
> diff --git a/include/uapi/linux/virtio_balloon.h
b/include/uapi/linux/virtio_balloon.h
> index d7f1cbc..343d7dd 100644
> --- a/include/uapi/linux/virtio_balloon.h
> +++ b/include/uapi/linux/virtio_balloon.h
> @@ -51,7 +51,8 @@ struct virtio_balloon_config {
>  #define VIRTIO_BALLOON_S_MINFLT   3   /* Number of minor faults */
>  #define VIRTIO_BALLOON_S_MEMFREE  4   /* Total amount of free memory */
>  #define VIRTIO_BALLOON_S_MEMTOT   5   /* Total amount of memory */
> -#define VIRTIO_BALLOON_S_NR       6
> +#define VIRTIO_BALLOON_S_AVAIL    6   /* Available memory as in /proc */
> +#define VIRTIO_BALLOON_S_NR       7
>  
>  /*
>   * Memory statistics structure.
> -- 
> 2.5.0