POOL_CACHE(9) NetBSD Kernel Developer's Manual POOL_CACHE(9)
NAME
pool_cache, pool_cache_init, pool_cache_destroy, pool_cache_get_paddr, pool_cache_get, pool_cache_put_paddr, pool_cache_put, pool_cache_destruct_object, pool_cache_invalidate, pool_cache_sethiwat, pool_cache_setlowat, pool_cache_sethardlimit -- resource-pool cache man- ager
SYNOPSIS
#include <sys/pool.h> pool_cache_t pool_cache_init(size_t size, u_int align, u_int align_offset, int flags, const char *name, struct pool_allocator *palloc, int ipl, int (*ctor)(void *, void *, int), void (*dtor)(void *, void *), void *arg); void pool_cache_destroy(pool_cache_t pc); void * pool_cache_get_paddr(pool_cache_t pc, int flags, paddr_t *pap); void * pool_cache_get(pool_cache_t pc, int flags); void pool_cache_put_paddr(pool_cache_t pc, void *object, paddr_t pa); void pool_cache_put(pool_cache_t pc, void *object); void pool_cache_destruct_object(pool_cache_t pc, void *object); void pool_cache_invalidate(pool_cache_t pc); void pool_cache_sethiwat(pool_cache_t pc, int n); void pool_cache_setlowat(pool_cache_t pc, int n); void pool_cache_sethardlimit(pool_cache_t pc, int n, const char *warnmess, int ratecap);
DESCRIPTION
These utility routines provide management of pools of fixed-sized areas of memory. Resource pools set aside an amount of memory for exclusive use by the resource pool owner. This can be used by applications to guarantee the availability of a minimum amount of memory needed to con- tinue operation independent of the memory resources currently available from the system-wide memory allocator. pool_cache follows the pool(9) API closely and offers routines that are functionally equivalent to their pool(9) counterparts. In addition, pool_cache provides object management functions used to manipulate objects allocated from the pool. It also maintains global and per-CPU caches, both levels of cache work together to allow for low overhead allocation and release of objects, and improved L1/L2/L3 hardware cache locality in multiprocessor systems.
FUNCTIONS
pool_cache_init(size, align, align_offset, flags, name, palloc, ipl, ctor, dtor, arg) Allocate and initialize a pool cache. The arguments are: size Specifies the size of the memory items managed by the pool. align Specifies the memory address alignment of the items returned by pool_cache_get(). This argument must be a power of two. If zero, the alignment defaults to an architecture-specific natural alignment. align_offset The offset within an item to which the align parameter applies. flags Should be set to zero, PR_NOTOUCH, or PR_PSERIALIZE. If PR_NOTOUCH is given, free items are never used to keep internal state so that the pool can be used for non memory backed objects. If PR_PSERIALIZE is given, then the allo- cator guarantees that a passive serialization barrier equivalent to ``xc_barrier(0)'' will be performed before either the object's destructor is called or before object's backing store is returned to the system. PR_PSERIALIZE implies PR_NOTOUCH. Because of the guaran- tees provided by PR_PSERIALIZE, objects must never be freed to a pool cache using this option from either hard or soft interrupt context, as doing so may block. name The name used to identify the object in diagnostic output. palloc Should be typically be set to NULL, instructing pool_cache_init() to select an appropriate back-end allo- cator. Alternate allocators can be used to partition space from arbitrary sources. Use of alternate allocators is not documented here as it is not a stable, endorsed part of the API. ipl Specifies an interrupt priority level that will block all interrupt handlers that could potentially access the pool. The pool_cache facility provides its own synchronization. The users of any given pool_cache need not provide addi- tional synchronization for access to it. ctor Specifies a constructor used to initialize newly allocated objects. If no constructor is required, specify NULL. The first argument to ctor is arg, the second is the new object, and the third is flags. dtor Specifies a destructor used to destroy cached objects prior to their release to backing store. If no destructor is required, specify NULL. The first argument to dtor is arg, and the second is the object. arg This value of this argument will be passed to both the constructor and destructor routines. pool_cache_destroy(pc) Destroy a pool cache pc. All other access to the cache must be stopped before this call can be made. pool_cache_get_paddr(pc, flags, pap) Get an object from a pool cache pc. If pap is not NULL, physi- cal address of the object or POOL_PADDR_INVALID will be returned via it. flags will be passed to pool_get() function of the backing pool(9) and the object constructor specified when the pool cache is created by pool_cache_init(). pool_cache_get(pc, flags) pool_cache_get() is the same as pool_cache_get_paddr() with NULL pap argument. It's implemented as a macro. pool_cache_put_paddr(pc, object, pa) Put an object object back to the pool cache pc. pa should be physical address of the object object or POOL_PADDR_INVALID. If the number of available items in the backing pool exceeds the maximum pool size set by pool_cache_sethiwat() and there are no outstanding requests for pool items, the excess items will be returned to the system. pool_cache_put(pc, object) pool_cache_put() is the same as pool_cache_put_paddr() with POOL_PADDR_INVALID pa argument. It's implemented as a macro. pool_cache_destruct_object(pc, object) Force destruction of an object object and release it back into the pool. pool_cache_invalidate(pc) Invalidate a pool cache pc. All objects in the cache will be destructed and freed back to the pool backing the cache. For pool caches that vend constructed objects, consumers of this API must take care to provide proper synchronization between the input to the constructor and cache invalidation. pool_cache_sethiwat(pc, n) A pool will attempt to increase its resource usage to keep up with the demand for its items. Conversely, it will return unused memory to the system should the number of accumulated free items in the pool exceed a programmable limit. The limits for the minimum and maximum number of free items which a pool should try to keep available are known as the high and low watermarks. The function pool_cache_sethiwat() sets the backing pool's high water mark. As items are freed and the number of free items in the pool is larger than the maximum set by this function, any completely unused pages are released immediately. If this func- tion is not used to specify a maximum number of items, the pages will remain associated with the pool until the system runs low on memory, at which point the VM system will try to reclaim unused pages. pool_cache_setlowat(pc, n) Set the minimum number of free items to try to keep in the pool. When the number of free items in the pool drops below this threshold, a non-blocking attempt is made to allocate memory for more items. The number of free items is not guaranteed to remain above this threshold. pool_cache_sethardlimit(pc, n, warnmess, ratecap) Set the maximum number of total items (both free and allocated) for the backing pool(9) to n. When the hard limit is reached, the warning message warnmess will be logged. ratecap represents the minimal interval (in seconds) after which another warning message is issued when the pool hits its hard limit again. pool_cache_prime(pc, n) Set the minimum number of total items (both free and allocated) for the backing pool(9) to n.
CODE REFERENCES
The pool_cache subsystem is implemented within the file sys/kern/subr_pool.c.
SEE ALSO
intro(9), kmem(9), memoryallocators(9), percpu(9), pool(9) NetBSD 10.99 December 21, 2021 NetBSD 10.99
Powered by man-cgi (2024-08-26). Maintained for NetBSD by Kimmo Suominen. Based on man-cgi by Panagiotis Christias.