kernel_optimize_test/include/linux/slub_def.h
Christoph Lameter 8ff12cfc00 SLUB: Support for performance statistics
The statistics provided here allow the monitoring of allocator behavior but
at the cost of some (minimal) loss of performance. Counters are placed in
SLUB's per cpu data structure. The per cpu structure may be extended by the
statistics to grow larger than one cacheline which will increase the cache
footprint of SLUB.

There is a compile option to enable/disable the inclusion of the runtime
statistics and its off by default.

The slabinfo tool is enhanced to support these statistics via two options:

-D 	Switches the line of information displayed for a slab from size
	mode to activity mode.

-A	Sorts the slabs displayed by activity. This allows the display of
	the slabs most important to the performance of a certain load.

-r	Report option will report detailed statistics on

Example (tbench load):

slabinfo -AD		->Shows the most active slabs

Name                   Objects    Alloc     Free   %Fast
skbuff_fclone_cache         33 111953835 111953835  99  99
:0000192                  2666  5283688  5281047  99  99
:0001024                   849  5247230  5246389  83  83
vm_area_struct            1349   119642   118355  91  22
:0004096                    15    66753    66751  98  98
:0000064                  2067    25297    23383  98  78
dentry                   10259    28635    18464  91  45
:0000080                 11004    18950     8089  98  98
:0000096                  1703    12358    10784  99  98
:0000128                   762    10582     9875  94  18
:0000512                   184     9807     9647  95  81
:0002048                   479     9669     9195  83  65
anon_vma                   777     9461     9002  99  71
kmalloc-8                 6492     9981     5624  99  97
:0000768                   258     7174     6931  58  15

So the skbuff_fclone_cache is of highest importance for the tbench load.
Pretty high load on the 192 sized slab. Look for the aliases

slabinfo -a | grep 000192
:0000192     <- xfs_btree_cur filp kmalloc-192 uid_cache tw_sock_TCP
	request_sock_TCPv6 tw_sock_TCPv6 skbuff_head_cache xfs_ili

Likely skbuff_head_cache.


Looking into the statistics of the skbuff_fclone_cache is possible through

slabinfo skbuff_fclone_cache	->-r option implied if cache name is mentioned


.... Usual output ...

Slab Perf Counter       Alloc     Free %Al %Fr
--------------------------------------------------
Fastpath             111953360 111946981  99  99
Slowpath                 1044     7423   0   0
Page Alloc                272      264   0   0
Add partial                25      325   0   0
Remove partial             86      264   0   0
RemoteObj/SlabFrozen      350     4832   0   0
Total                111954404 111954404

Flushes       49 Refill        0
Deactivate Full=325(92%) Empty=0(0%) ToHead=24(6%) ToTail=1(0%)

Looks good because the fastpath is overwhelmingly taken.


skbuff_head_cache:

Slab Perf Counter       Alloc     Free %Al %Fr
--------------------------------------------------
Fastpath              5297262  5259882  99  99
Slowpath                 4477    39586   0   0
Page Alloc                937      824   0   0
Add partial                 0     2515   0   0
Remove partial           1691      824   0   0
RemoteObj/SlabFrozen     2621     9684   0   0
Total                 5301739  5299468

Deactivate Full=2620(100%) Empty=0(0%) ToHead=0(0%) ToTail=0(0%)


Descriptions of the output:

Total:		The total number of allocation and frees that occurred for a
		slab

Fastpath:	The number of allocations/frees that used the fastpath.

Slowpath:	Other allocations

Page Alloc:	Number of calls to the page allocator as a result of slowpath
		processing

Add Partial:	Number of slabs added to the partial list through free or
		alloc (occurs during cpuslab flushes)

Remove Partial:	Number of slabs removed from the partial list as a result of
		allocations retrieving a partial slab or by a free freeing
		the last object of a slab.

RemoteObj/Froz:	How many times were remotely freed object encountered when a
		slab was about to be deactivated. Frozen: How many times was
		free able to skip list processing because the slab was in use
		as the cpuslab of another processor.

Flushes:	Number of times the cpuslab was flushed on request
		(kmem_cache_shrink, may result from races in __slab_alloc)

Refill:		Number of times we were able to refill the cpuslab from
		remotely freed objects for the same slab.

Deactivate:	Statistics how slabs were deactivated. Shows how they were
		put onto the partial list.

In general fastpath is very good. Slowpath without partial list processing is
also desirable. Any touching of partial list uses node specific locks which
may potentially cause list lock contention.

Signed-off-by: Christoph Lameter <clameter@sgi.com>
2008-02-07 17:47:41 -08:00

230 lines
6.2 KiB
C

#ifndef _LINUX_SLUB_DEF_H
#define _LINUX_SLUB_DEF_H
/*
* SLUB : A Slab allocator without object queues.
*
* (C) 2007 SGI, Christoph Lameter <clameter@sgi.com>
*/
#include <linux/types.h>
#include <linux/gfp.h>
#include <linux/workqueue.h>
#include <linux/kobject.h>
enum stat_item {
ALLOC_FASTPATH, /* Allocation from cpu slab */
ALLOC_SLOWPATH, /* Allocation by getting a new cpu slab */
FREE_FASTPATH, /* Free to cpu slub */
FREE_SLOWPATH, /* Freeing not to cpu slab */
FREE_FROZEN, /* Freeing to frozen slab */
FREE_ADD_PARTIAL, /* Freeing moves slab to partial list */
FREE_REMOVE_PARTIAL, /* Freeing removes last object */
ALLOC_FROM_PARTIAL, /* Cpu slab acquired from partial list */
ALLOC_SLAB, /* Cpu slab acquired from page allocator */
ALLOC_REFILL, /* Refill cpu slab from slab freelist */
FREE_SLAB, /* Slab freed to the page allocator */
CPUSLAB_FLUSH, /* Abandoning of the cpu slab */
DEACTIVATE_FULL, /* Cpu slab was full when deactivated */
DEACTIVATE_EMPTY, /* Cpu slab was empty when deactivated */
DEACTIVATE_TO_HEAD, /* Cpu slab was moved to the head of partials */
DEACTIVATE_TO_TAIL, /* Cpu slab was moved to the tail of partials */
DEACTIVATE_REMOTE_FREES,/* Slab contained remotely freed objects */
NR_SLUB_STAT_ITEMS };
struct kmem_cache_cpu {
void **freelist; /* Pointer to first free per cpu object */
struct page *page; /* The slab from which we are allocating */
int node; /* The node of the page (or -1 for debug) */
unsigned int offset; /* Freepointer offset (in word units) */
unsigned int objsize; /* Size of an object (from kmem_cache) */
#ifdef CONFIG_SLUB_STATS
unsigned stat[NR_SLUB_STAT_ITEMS];
#endif
};
struct kmem_cache_node {
spinlock_t list_lock; /* Protect partial list and nr_partial */
unsigned long nr_partial;
atomic_long_t nr_slabs;
struct list_head partial;
#ifdef CONFIG_SLUB_DEBUG
struct list_head full;
#endif
};
/*
* Slab cache management.
*/
struct kmem_cache {
/* Used for retriving partial slabs etc */
unsigned long flags;
int size; /* The size of an object including meta data */
int objsize; /* The size of an object without meta data */
int offset; /* Free pointer offset. */
int order;
/*
* Avoid an extra cache line for UP, SMP and for the node local to
* struct kmem_cache.
*/
struct kmem_cache_node local_node;
/* Allocation and freeing of slabs */
int objects; /* Number of objects in slab */
int refcount; /* Refcount for slab cache destroy */
void (*ctor)(struct kmem_cache *, void *);
int inuse; /* Offset to metadata */
int align; /* Alignment */
const char *name; /* Name (only for display!) */
struct list_head list; /* List of slab caches */
#ifdef CONFIG_SLUB_DEBUG
struct kobject kobj; /* For sysfs */
#endif
#ifdef CONFIG_NUMA
/*
* Defragmentation by allocating from a remote node.
*/
int remote_node_defrag_ratio;
struct kmem_cache_node *node[MAX_NUMNODES];
#endif
#ifdef CONFIG_SMP
struct kmem_cache_cpu *cpu_slab[NR_CPUS];
#else
struct kmem_cache_cpu cpu_slab;
#endif
};
/*
* Kmalloc subsystem.
*/
#if defined(ARCH_KMALLOC_MINALIGN) && ARCH_KMALLOC_MINALIGN > 8
#define KMALLOC_MIN_SIZE ARCH_KMALLOC_MINALIGN
#else
#define KMALLOC_MIN_SIZE 8
#endif
#define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE)
/*
* We keep the general caches in an array of slab caches that are used for
* 2^x bytes of allocations.
*/
extern struct kmem_cache kmalloc_caches[PAGE_SHIFT];
/*
* Sorry that the following has to be that ugly but some versions of GCC
* have trouble with constant propagation and loops.
*/
static __always_inline int kmalloc_index(size_t size)
{
if (!size)
return 0;
if (size <= KMALLOC_MIN_SIZE)
return KMALLOC_SHIFT_LOW;
if (size > 64 && size <= 96)
return 1;
if (size > 128 && size <= 192)
return 2;
if (size <= 8) return 3;
if (size <= 16) return 4;
if (size <= 32) return 5;
if (size <= 64) return 6;
if (size <= 128) return 7;
if (size <= 256) return 8;
if (size <= 512) return 9;
if (size <= 1024) return 10;
if (size <= 2 * 1024) return 11;
/*
* The following is only needed to support architectures with a larger page
* size than 4k.
*/
if (size <= 4 * 1024) return 12;
if (size <= 8 * 1024) return 13;
if (size <= 16 * 1024) return 14;
if (size <= 32 * 1024) return 15;
if (size <= 64 * 1024) return 16;
if (size <= 128 * 1024) return 17;
if (size <= 256 * 1024) return 18;
if (size <= 512 * 1024) return 19;
if (size <= 1024 * 1024) return 20;
if (size <= 2 * 1024 * 1024) return 21;
return -1;
/*
* What we really wanted to do and cannot do because of compiler issues is:
* int i;
* for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++)
* if (size <= (1 << i))
* return i;
*/
}
/*
* Find the slab cache for a given combination of allocation flags and size.
*
* This ought to end up with a global pointer to the right cache
* in kmalloc_caches.
*/
static __always_inline struct kmem_cache *kmalloc_slab(size_t size)
{
int index = kmalloc_index(size);
if (index == 0)
return NULL;
return &kmalloc_caches[index];
}
#ifdef CONFIG_ZONE_DMA
#define SLUB_DMA __GFP_DMA
#else
/* Disable DMA functionality */
#define SLUB_DMA (__force gfp_t)0
#endif
void *kmem_cache_alloc(struct kmem_cache *, gfp_t);
void *__kmalloc(size_t size, gfp_t flags);
static __always_inline void *kmalloc(size_t size, gfp_t flags)
{
if (__builtin_constant_p(size)) {
if (size > PAGE_SIZE / 2)
return (void *)__get_free_pages(flags | __GFP_COMP,
get_order(size));
if (!(flags & SLUB_DMA)) {
struct kmem_cache *s = kmalloc_slab(size);
if (!s)
return ZERO_SIZE_PTR;
return kmem_cache_alloc(s, flags);
}
}
return __kmalloc(size, flags);
}
#ifdef CONFIG_NUMA
void *__kmalloc_node(size_t size, gfp_t flags, int node);
void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node);
static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
{
if (__builtin_constant_p(size) &&
size <= PAGE_SIZE / 2 && !(flags & SLUB_DMA)) {
struct kmem_cache *s = kmalloc_slab(size);
if (!s)
return ZERO_SIZE_PTR;
return kmem_cache_alloc_node(s, flags, node);
}
return __kmalloc_node(size, flags, node);
}
#endif
#endif /* _LINUX_SLUB_DEF_H */