OpenVZ Forum


Home » Mailing lists » Devel » [PATCH] BC: resource beancounters (v2)
[PATCH 5/6] BC: kernel memory accounting (core) [message #5547 is a reply to message #5542] Wed, 23 August 2006 11:04 Go to previous messageGo to previous message
dev is currently offline  dev
Messages: 1693
Registered: September 2005
Location: Moscow
Senior Member
Introduce BC_KMEMSIZE resource which accounts kernel
objects allocated by task's request.

Reference to BC is kept on struct page or slab object.
For slabs each struct slab contains a set of pointers
corresponding objects are charged to.

Allocation charge rules:
1. Pages - if allocation is performed with __GFP_BC flag - page
is charged to current's exec_bc.
2. Slabs - kmem_cache may be created with SLAB_BC flag - in this
case each allocation is charged. Caches used by kmalloc are
created with SLAB_BC | SLAB_BC_NOCHARGE flags. In this case
only __GFP_BC allocations are charged.

Signed-off-by: Pavel Emelianov <xemul@sw.ru>
Signed-off-by: Kirill Korotaev <dev@sw.ru>

---

include/linux/gfp.h | 8 ++-
include/linux/mm.h | 6 ++
include/linux/slab.h | 4 +
include/linux/vmalloc.h | 1
include/bc/beancounter.h | 4 +
include/bc/kmem.h | 33 ++++++++++++
kernel/bc/Makefile | 1
kernel/bc/beancounter.c | 3 +
kernel/bc/kmem.c | 89 ++++++++++++++++++++++++++++++++++
mm/mempool.c | 2
mm/page_alloc.c | 11 ++++
mm/slab.c | 121 ++++++++++++++++++++++++++++++++++++++---------
mm/vmalloc.c | 6 ++
13 files changed, 264 insertions(+), 25 deletions(-)

--- ./include/linux/gfp.h.bckmem 2006-07-28 18:43:52.000000000 +0400
+++ ./include/linux/gfp.h 2006-07-31 16:32:22.000000000 +0400
@@ -46,8 +46,10 @@ struct vm_area_struct;
#define __GFP_NOMEMALLOC ((__force gfp_t)0x10000u) /* Don't use emergency reserves */
#define __GFP_HARDWALL ((__force gfp_t)0x20000u) /* Enforce hardwall cpuset memory allocs */
#define __GFP_THISNODE ((__force gfp_t)0x40000u)/* No fallback, no policies */
+#define __GFP_BC ((__force gfp_t)0x80000u) /* Charge allocation with BC */
+#define __GFP_BC_LIMIT ((__force gfp_t)0x100000u) /* Charge against BC limit */

-#define __GFP_BITS_SHIFT 20 /* Room for 20 __GFP_FOO bits */
+#define __GFP_BITS_SHIFT 21 /* Room for 21 __GFP_FOO bits */
#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))

/* if you forget to add the bitmask here kernel will crash, period */
@@ -54,7 +56,8 @@ struct vm_area_struct;
#define GFP_LEVEL_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS| \
__GFP_COLD|__GFP_NOWARN|__GFP_REPEAT| \
__GFP_NOFAIL|__GFP_NORETRY|__GFP_NO_GROW|__GFP_COMP| \
- __GFP_NOMEMALLOC|__GFP_HARDWALL|__GFP_THISNODE)
+ __GFP_NOMEMALLOC|__GFP_HARDWALL|__GFP_THISNODE| \
+ __GFP_BC|__GFP_BC_LIMIT)

/* This equals 0, but use constants in case they ever change */
#define GFP_NOWAIT (GFP_ATOMIC & ~__GFP_HIGH)
@@ -63,6 +66,7 @@ struct vm_area_struct;
#define GFP_NOIO (__GFP_WAIT)
#define GFP_NOFS (__GFP_WAIT | __GFP_IO)
#define GFP_KERNEL (__GFP_WAIT | __GFP_IO | __GFP_FS)
+#define GFP_KERNEL_BC (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_BC)
#define GFP_USER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
#define GFP_HIGHUSER (__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL | \
__GFP_HIGHMEM)
--- ./include/linux/mm.h.bckmem 2006-07-28 18:43:52.000000000 +0400
+++ ./include/linux/mm.h 2006-07-31 17:50:29.000000000 +0400
@@ -267,8 +267,14 @@ struct page {
unsigned int gfp_mask;
unsigned long trace[8];
#endif
+#ifdef CONFIG_BEANCOUNTERS
+ union {
+ struct beancounter *page_bc;
+ } bc;
+#endif
};

+#define page_bc(page) ((page)->bc.page_bc)
#define page_private(page) ((page)->private)
#define set_page_private(page, v) ((page)->private = (v))

--- ./include/linux/slab.h.bckmem 2006-07-10 12:39:19.000000000 +0400
+++ ./include/linux/slab.h 2006-07-31 17:02:08.000000000 +0400
@@ -46,6 +46,8 @@ typedef struct kmem_cache kmem_cache_t;
#define SLAB_PANIC 0x00040000UL /* panic if kmem_cache_create() fails */
#define SLAB_DESTROY_BY_RCU 0x00080000UL /* defer freeing pages to RCU */
#define SLAB_MEM_SPREAD 0x00100000UL /* Spread some memory over cpuset */
+#define SLAB_BC 0x00200000UL /* Account with BC */
+#define SLAB_BC_NOCHARGE 0x00400000UL /* Explicit accounting */

/* flags passed to a constructor func */
#define SLAB_CTOR_CONSTRUCTOR 0x001UL /* if not set, then deconstructor */
@@ -265,6 +267,8 @@ extern kmem_cache_t *bio_cachep;

extern atomic_t slab_reclaim_pages;

+struct beancounter;
+struct beancounter **kmem_cache_bcp(kmem_cache_t *cachep, void *obj);
#endif /* __KERNEL__ */

#endif /* _LINUX_SLAB_H */
--- ./include/linux/vmalloc.h.bckmem 2006-07-17 17:01:12.000000000 +0400
+++ ./include/linux/vmalloc.h 2006-08-01 13:21:59.000000000 +0400
@@ -36,6 +36,7 @@ struct vm_struct {
* Highlevel APIs for driver use
*/
extern void *vmalloc(unsigned long size);
+extern void *vmalloc_bc(unsigned long size);
extern void *vmalloc_user(unsigned long size);
extern void *vmalloc_node(unsigned long size, int node);
extern void *vmalloc_exec(unsigned long size);
--- ./include/bc/beancounter.h.bckmem 2006-07-28 18:43:52.000000000 +0400
+++ ./include/bc/beancounter.h 2006-08-03 16:03:01.000000000 +0400
@@ -14,7 +14,9 @@
* Resource list.
*/

-#define BC_RESOURCES 0
+#define BC_KMEMSIZE 0
+
+#define BC_RESOURCES 1

struct resource_parm {
/*
--- ./include/bc/kmem.h.bckmem 2006-07-28 18:43:52.000000000 +0400
+++ ./include/bc/kmem.h 2006-07-31 17:37:05.000000000 +0400
@@ -0,0 +1,33 @@
+/*
+ * include/bc/kmem.h
+ *
+ * Copyright (C) 2006 OpenVZ. SWsoft Inc
+ *
+ */
+
+#ifndef __BC_KMEM_H_
+#define __BC_KMEM_H_
+
+#include <linux/config.h>
+
+/*
+ * BC_KMEMSIZE accounting
+ */
+
+struct mm_struct;
+struct page;
+struct beancounter;
+
+#ifdef CONFIG_BEANCOUNTERS
+int bc_page_charge(struct page *page, int order, gfp_t flags);
+void bc_page_uncharge(struct page *page, int order);
+
+int bc_slab_charge(kmem_cache_t *cachep, void *obj, gfp_t flags);
+void bc_slab_uncharge(kmem_cache_t *cachep, void *obj);
+#else
+#define bc_page_charge(pg, o, mask) (0)
+#define bc_page_uncharge(pg, o) do { } while (0)
+#define bc_slab_charge(cachep, o, f) (0)
+#define bc_slab_uncharge(cachep, o) do { } while (0)
+#endif
+#endif /* __BC_SLAB_H_ */
--- ./kernel/bc/Makefile.bcsys 2006-07-28 14:08:37.000000000 +0400
+++ ./kernel/bc/Makefile 2006-08-01 11:08:39.000000000 +0400
@@ -7,3 +7,4 @@
obj-$(CONFIG_BEANCOUNTERS) += beancounter.o
obj-$(CONFIG_BEANCOUNTERS) += misc.o
obj-$(CONFIG_BEANCOUNTERS) += sys.o
+obj-$(CONFIG_BEANCOUNTERS) += kmem.o
--- ./kernel/bc/beancounter.c.bckmem 2006-07-28 18:43:52.000000000 +0400
+++ ./kernel/bc/beancounter.c 2006-08-03 16:14:17.000000000 +0400
@@ -19,6 +19,7 @@ static void init_beancounter_struct(stru
struct beancounter init_bc;

const char *bc_rnames[] = {
+ "kmemsize", /* 0 */
};

#define bc_hash_fun(x) ((((x) >> 8) ^ (x)) & (BC_HASH_SIZE - 1))
@@ -348,6 +378,8 @@ static void init_beancounter_syslimits(s
{
int k;

+ bc->bc_parms[BC_KMEMSIZE].limit = 32 * 1024 * 1024;
+
for (k = 0; k < BC_RESOURCES; k++)
bc->bc_parms[k].barrier = bc->bc_parms[k].limit;
}
--- ./kernel/bc/kmem.c.bckmem 2006-07-31 16:32:22.000000000 +0400
+++ ./kernel/bc/kmem.c 2006-07-31 17:51:27.000000000 +0400
@@ -0,0 +1,89 @@
+/*
+ * kernel/bc/kmem.c
+ *
+ * Copyright (C) 2006 OpenVZ. SWsoft Inc
+ *
+ */
+
+#include <linux/sched.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+
+#include <bc/beancounter.h>
+#include <bc/kmem.h>
+#include <bc/task.h>
+
+/*
+ * Slab accounting
+ */
+
+int bc_slab_charge(kmem_cache_t *cachep, void *objp, gfp_t flags)
+{
+ unsigned int size;
+ struct beancounter *bc, **slab_bcp;
+
+ bc = get_exec_bc();
+ if (bc == NULL)
+ return 0;
+
+ size = kmem_cache_size(cachep);
+ if (bc_charge(bc, BC_KMEMSIZE, size,
+ (flags & __GFP_BC_LIMIT ? BC_LIMIT : BC_BARRIER)))
+ return -ENOMEM;
+
+ slab_bcp = kmem_cache_bcp(cachep, objp);
+ *slab_bcp = get_beancounter(bc);
+ return 0;
+}
+
+void bc_slab_uncharge(kmem_cache_t *cachep, void *objp)
+{
+ unsigned int size;
+ struct beancounter *bc, **slab_bcp;
+
+ slab_bcp = kmem_cache_bcp(cachep, objp);
+ if (*slab_bcp == NULL)
+ return;
+
+ bc = *slab_bcp;
+ size = kmem_cache_size(cachep);
+ bc_uncharge(bc, BC_KMEMSIZE, size);
+ put_beancounter(bc);
+ *slab_bcp = NULL;
+}
+
+/*
+ * Pages accounting
+ */
+
+int bc_page_charge(struct page *page, int order, gfp_t flags)
+{
+ struct beancounter *bc;
+
+ BUG_ON(page_bc(page) != NULL);
+
+ bc = get_exec_bc();
+ if (bc == NULL)
+ return 0;
+
+ if (bc_charge(bc, BC_KMEMSIZE, PAGE_SIZE << order,
+ (flags & __GFP_BC_LIMIT ? BC_LIMIT : BC_BARRIER)))
+ return -ENOMEM;
+
+ page_bc(page) = get_beancounter(bc);
+ return 0;
+}
+
+void bc_page_uncharge(struct page *page, int order)
+{
+ struct beancounter *bc;
+
+ bc = page_bc(page);
+ if (bc == NULL)
+ return;
+
+ bc_uncharge(bc, BC_KMEMSIZE, PAGE_SIZE << order);
+ put_beancounter(bc);
+ page_bc(page) = NULL;
+}
--- ./mm/mempool.c.bckmem 2006-04-21 11:59:36.000000000 +0400
+++ ./mm/mempool.c 2006-08-01 13:25:26.000000000 +0400
@@ -119,6 +119,7 @@ int mempool_resize(mempool_t *pool, int
unsigned long flags;

BUG_ON(new_min_nr <= 0);
+ gfp_mask &= ~__GFP_BC;

spin_lock_irqsave(&pool->lock, flags);
if (new_min_nr <= pool->min_nr) {
@@ -212,6 +213,7 @@ void * mempool_alloc(mempool_t *pool, gf
gfp_mask |= __GFP_NOMEMALLOC; /* don't allocate emergency reserves */
gfp_mask |= __GFP_NORETRY; /* don't loop in __alloc_pages */
gfp_mask |= __GFP_NOWARN; /* failures are OK */
+ gfp_mask &= ~__GFP_BC; /* do not charge */

gfp_temp = gfp_mask & ~(__GFP_WAIT|__GFP_IO);

--- ./mm/page_alloc.c.bckmem 2006-07-28 18:43:52.000000000 +0400
+++ ./mm/page_alloc.c 2006-07-31 19:52:08.000000000 +0400
@@ -38,6 +38,8 @@
#include <linux/mempolicy.h>
#include <linux/stop_machine.h>

+#include <bc/kmem.h>
+
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include "internal.h"
@@ -453,6 +455,8 @@ static void __free_pages_ok(st ...

[ Show the rest of the message ]

Report message to a moderator

[Message index]
 
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Read Message
Previous Topic: Re: pspace child_reaper
Next Topic: Re: pspace child_reaper
Goto Forum:
  

[ Syndicate this forum (XML) ] [ RSS ] [ PDF ]

Current Time: Sat Jul 12 05:28:46 GMT 2025

Total time taken to generate the page: 0.01627 seconds
Powered by FUDforum Powered by Virtuozzo Containers