diff --git a/include/jemalloc/internal/arena_externs.h b/include/jemalloc/internal/arena_externs.h index 77a2b541..4b3732b4 100644 --- a/include/jemalloc/internal/arena_externs.h +++ b/include/jemalloc/internal/arena_externs.h @@ -16,17 +16,13 @@ extern const char *percpu_arena_mode_names[]; extern const uint64_t h_steps[SMOOTHSTEP_NSTEPS]; extern malloc_mutex_t arenas_lock; -void arena_stats_large_nrequests_add(tsdn_t *tsdn, arena_stats_t *arena_stats, - szind_t szind, uint64_t nrequests); -void arena_stats_mapped_add(tsdn_t *tsdn, arena_stats_t *arena_stats, - size_t size); void arena_basic_stats_merge(tsdn_t *tsdn, arena_t *arena, unsigned *nthreads, const char **dss, ssize_t *dirty_decay_ms, ssize_t *muzzy_decay_ms, size_t *nactive, size_t *ndirty, size_t *nmuzzy); void arena_stats_merge(tsdn_t *tsdn, arena_t *arena, unsigned *nthreads, const char **dss, ssize_t *dirty_decay_ms, ssize_t *muzzy_decay_ms, size_t *nactive, size_t *ndirty, size_t *nmuzzy, arena_stats_t *astats, - malloc_bin_stats_t *bstats, malloc_large_stats_t *lstats); + bin_stats_t *bstats, arena_stats_large_t *lstats); void arena_extents_dirty_dalloc(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks, extent_t *extent); #ifdef JEMALLOC_JET diff --git a/include/jemalloc/internal/arena_stats.h b/include/jemalloc/internal/arena_stats.h new file mode 100644 index 00000000..837d4eb6 --- /dev/null +++ b/include/jemalloc/internal/arena_stats.h @@ -0,0 +1,237 @@ +#ifndef JEMALLOC_INTERNAL_ARENA_STATS_H +#define JEMALLOC_INTERNAL_ARENA_STATS_H + +#include "jemalloc/internal/atomic.h" +#include "jemalloc/internal/mutex.h" +#include "jemalloc/internal/mutex_prof.h" +#include "jemalloc/internal/size_classes.h" + +/* + * In those architectures that support 64-bit atomics, we use atomic updates for + * our 64-bit values. Otherwise, we use a plain uint64_t and synchronize + * externally. + */ +#ifdef JEMALLOC_ATOMIC_U64 +typedef atomic_u64_t arena_stats_u64_t; +#else +/* Must hold the arena stats mutex while reading atomically. */ +typedef uint64_t arena_stats_u64_t; +#endif + +typedef struct arena_stats_large_s arena_stats_large_t; +struct arena_stats_large_s { + /* + * Total number of allocation/deallocation requests served directly by + * the arena. + */ + arena_stats_u64_t nmalloc; + arena_stats_u64_t ndalloc; + + /* + * Number of allocation requests that correspond to this size class. + * This includes requests served by tcache, though tcache only + * periodically merges into this counter. + */ + arena_stats_u64_t nrequests; /* Partially derived. */ + + /* Current number of allocations of this size class. */ + size_t curlextents; /* Derived. */ +}; + +typedef struct arena_stats_decay_s arena_stats_decay_t; +struct arena_stats_decay_s { + /* Total number of purge sweeps. */ + arena_stats_u64_t npurge; + /* Total number of madvise calls made. */ + arena_stats_u64_t nmadvise; + /* Total number of pages purged. */ + arena_stats_u64_t purged; +}; + +/* + * Arena stats. Note that fields marked "derived" are not directly maintained + * within the arena code; rather their values are derived during stats merge + * requests. + */ +typedef struct arena_stats_s arena_stats_t; +struct arena_stats_s { +#ifndef JEMALLOC_ATOMIC_U64 + malloc_mutex_t mtx; +#endif + + /* Number of bytes currently mapped, excluding retained memory. */ + atomic_zu_t mapped; /* Partially derived. */ + + /* + * Number of unused virtual memory bytes currently retained. Retained + * bytes are technically mapped (though always decommitted or purged), + * but they are excluded from the mapped statistic (above). + */ + atomic_zu_t retained; /* Derived. */ + + arena_stats_decay_t decay_dirty; + arena_stats_decay_t decay_muzzy; + + atomic_zu_t base; /* Derived. */ + atomic_zu_t internal; + atomic_zu_t resident; /* Derived. */ + atomic_zu_t metadata_thp; + + atomic_zu_t allocated_large; /* Derived. */ + arena_stats_u64_t nmalloc_large; /* Derived. */ + arena_stats_u64_t ndalloc_large; /* Derived. */ + arena_stats_u64_t nrequests_large; /* Derived. */ + + /* Number of bytes cached in tcache associated with this arena. */ + atomic_zu_t tcache_bytes; /* Derived. */ + + mutex_prof_data_t mutex_prof_data[mutex_prof_num_arena_mutexes]; + + /* One element for each large size class. */ + arena_stats_large_t lstats[NSIZES - NBINS]; + + /* Arena uptime. */ + nstime_t uptime; +}; + +static inline bool +arena_stats_init(tsdn_t *tsdn, arena_stats_t *arena_stats) { + if (config_debug) { + for (size_t i = 0; i < sizeof(arena_stats_t); i++) { + assert(((char *)arena_stats)[i] == 0); + } + } +#ifndef JEMALLOC_ATOMIC_U64 + if (malloc_mutex_init(&arena_stats->mtx, "arena_stats", + WITNESS_RANK_ARENA_STATS, malloc_mutex_rank_exclusive)) { + return true; + } +#endif + /* Memory is zeroed, so there is no need to clear stats. */ + return false; +} + +static inline void +arena_stats_lock(tsdn_t *tsdn, arena_stats_t *arena_stats) { +#ifndef JEMALLOC_ATOMIC_U64 + malloc_mutex_lock(tsdn, &arena_stats->mtx); +#endif +} + +static inline void +arena_stats_unlock(tsdn_t *tsdn, arena_stats_t *arena_stats) { +#ifndef JEMALLOC_ATOMIC_U64 + malloc_mutex_unlock(tsdn, &arena_stats->mtx); +#endif +} + +static inline uint64_t +arena_stats_read_u64(tsdn_t *tsdn, arena_stats_t *arena_stats, + arena_stats_u64_t *p) { +#ifdef JEMALLOC_ATOMIC_U64 + return atomic_load_u64(p, ATOMIC_RELAXED); +#else + malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); + return *p; +#endif +} + +static inline void +arena_stats_add_u64(tsdn_t *tsdn, arena_stats_t *arena_stats, + arena_stats_u64_t *p, uint64_t x) { +#ifdef JEMALLOC_ATOMIC_U64 + atomic_fetch_add_u64(p, x, ATOMIC_RELAXED); +#else + malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); + *p += x; +#endif +} + +UNUSED static inline void +arena_stats_sub_u64(tsdn_t *tsdn, arena_stats_t *arena_stats, + arena_stats_u64_t *p, uint64_t x) { +#ifdef JEMALLOC_ATOMIC_U64 + UNUSED uint64_t r = atomic_fetch_sub_u64(p, x, ATOMIC_RELAXED); + assert(r - x <= r); +#else + malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); + *p -= x; + assert(*p + x >= *p); +#endif +} + +/* + * Non-atomically sets *dst += src. *dst needs external synchronization. + * This lets us avoid the cost of a fetch_add when its unnecessary (note that + * the types here are atomic). + */ +static inline void +arena_stats_accum_u64(arena_stats_u64_t *dst, uint64_t src) { +#ifdef JEMALLOC_ATOMIC_U64 + uint64_t cur_dst = atomic_load_u64(dst, ATOMIC_RELAXED); + atomic_store_u64(dst, src + cur_dst, ATOMIC_RELAXED); +#else + *dst += src; +#endif +} + +static inline size_t +arena_stats_read_zu(tsdn_t *tsdn, arena_stats_t *arena_stats, atomic_zu_t *p) { +#ifdef JEMALLOC_ATOMIC_U64 + return atomic_load_zu(p, ATOMIC_RELAXED); +#else + malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); + return atomic_load_zu(p, ATOMIC_RELAXED); +#endif +} + +static inline void +arena_stats_add_zu(tsdn_t *tsdn, arena_stats_t *arena_stats, atomic_zu_t *p, + size_t x) { +#ifdef JEMALLOC_ATOMIC_U64 + atomic_fetch_add_zu(p, x, ATOMIC_RELAXED); +#else + malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); + size_t cur = atomic_load_zu(p, ATOMIC_RELAXED); + atomic_store_zu(p, cur + x, ATOMIC_RELAXED); +#endif +} + +static inline void +arena_stats_sub_zu(tsdn_t *tsdn, arena_stats_t *arena_stats, atomic_zu_t *p, + size_t x) { +#ifdef JEMALLOC_ATOMIC_U64 + UNUSED size_t r = atomic_fetch_sub_zu(p, x, ATOMIC_RELAXED); + assert(r - x <= r); +#else + malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); + size_t cur = atomic_load_zu(p, ATOMIC_RELAXED); + atomic_store_zu(p, cur - x, ATOMIC_RELAXED); +#endif +} + +/* Like the _u64 variant, needs an externally synchronized *dst. */ +static inline void +arena_stats_accum_zu(atomic_zu_t *dst, size_t src) { + size_t cur_dst = atomic_load_zu(dst, ATOMIC_RELAXED); + atomic_store_zu(dst, src + cur_dst, ATOMIC_RELAXED); +} + +static inline void +arena_stats_large_nrequests_add(tsdn_t *tsdn, arena_stats_t *arena_stats, + szind_t szind, uint64_t nrequests) { + arena_stats_lock(tsdn, arena_stats); + arena_stats_add_u64(tsdn, arena_stats, &arena_stats->lstats[szind - + NBINS].nrequests, nrequests); + arena_stats_unlock(tsdn, arena_stats); +} + +static inline void +arena_stats_mapped_add(tsdn_t *tsdn, arena_stats_t *arena_stats, size_t size) { + arena_stats_lock(tsdn, arena_stats); + arena_stats_add_zu(tsdn, arena_stats, &arena_stats->mapped, size); + arena_stats_unlock(tsdn, arena_stats); +} + + +#endif /* JEMALLOC_INTERNAL_ARENA_STATS_H */ diff --git a/include/jemalloc/internal/arena_structs_b.h b/include/jemalloc/internal/arena_structs_b.h index d843b09b..38bc9596 100644 --- a/include/jemalloc/internal/arena_structs_b.h +++ b/include/jemalloc/internal/arena_structs_b.h @@ -1,6 +1,7 @@ #ifndef JEMALLOC_INTERNAL_ARENA_STRUCTS_B_H #define JEMALLOC_INTERNAL_ARENA_STRUCTS_B_H +#include "jemalloc/internal/arena_stats.h" #include "jemalloc/internal/atomic.h" #include "jemalloc/internal/bin.h" #include "jemalloc/internal/bitmap.h" @@ -11,7 +12,6 @@ #include "jemalloc/internal/ql.h" #include "jemalloc/internal/size_classes.h" #include "jemalloc/internal/smoothstep.h" -#include "jemalloc/internal/stats.h" #include "jemalloc/internal/ticker.h" struct arena_decay_s { @@ -69,7 +69,7 @@ struct arena_decay_s { * arena and ctl code. * * Synchronization: Same as associated arena's stats field. */ - decay_stats_t *stats; + arena_stats_decay_t *stats; /* Peak number of pages in associated extents. Used for debug only. */ uint64_t ceil_npages; }; diff --git a/include/jemalloc/internal/bin.h b/include/jemalloc/internal/bin.h index 89572fa1..9b416ada 100644 --- a/include/jemalloc/internal/bin.h +++ b/include/jemalloc/internal/bin.h @@ -4,7 +4,7 @@ #include "jemalloc/internal/extent_types.h" #include "jemalloc/internal/extent_structs.h" #include "jemalloc/internal/mutex.h" -#include "jemalloc/internal/stats.h" +#include "jemalloc/internal/bin_stats.h" /* * A bin contains a set of extents that are currently being used for slab @@ -75,7 +75,7 @@ struct bin_s { extent_list_t slabs_full; /* Bin statistics. */ - malloc_bin_stats_t stats; + bin_stats_t stats; }; /* Initializes a bin to empty. Returns true on error. */ @@ -88,7 +88,7 @@ void bin_postfork_child(tsdn_t *tsdn, bin_t *bin); /* Stats. */ static inline void -bin_stats_merge(tsdn_t *tsdn, malloc_bin_stats_t *dst_bin_stats, bin_t *bin) { +bin_stats_merge(tsdn_t *tsdn, bin_stats_t *dst_bin_stats, bin_t *bin) { malloc_mutex_lock(tsdn, &bin->lock); malloc_mutex_prof_read(tsdn, &dst_bin_stats->mutex_data, &bin->lock); dst_bin_stats->nmalloc += bin->stats.nmalloc; diff --git a/include/jemalloc/internal/bin_stats.h b/include/jemalloc/internal/bin_stats.h new file mode 100644 index 00000000..86e673ec --- /dev/null +++ b/include/jemalloc/internal/bin_stats.h @@ -0,0 +1,51 @@ +#ifndef JEMALLOC_INTERNAL_BIN_STATS_H +#define JEMALLOC_INTERNAL_BIN_STATS_H + +#include "jemalloc/internal/mutex_prof.h" + +typedef struct bin_stats_s bin_stats_t; +struct bin_stats_s { + /* + * Total number of allocation/deallocation requests served directly by + * the bin. Note that tcache may allocate an object, then recycle it + * many times, resulting many increments to nrequests, but only one + * each to nmalloc and ndalloc. + */ + uint64_t nmalloc; + uint64_t ndalloc; + + /* + * Number of allocation requests that correspond to the size of this + * bin. This includes requests served by tcache, though tcache only + * periodically merges into this counter. + */ + uint64_t nrequests; + + /* + * Current number of regions of this size class, including regions + * currently cached by tcache. + */ + size_t curregs; + + /* Number of tcache fills from this bin. */ + uint64_t nfills; + + /* Number of tcache flushes to this bin. */ + uint64_t nflushes; + + /* Total number of slabs created for this bin's size class. */ + uint64_t nslabs; + + /* + * Total number of slabs reused by extracting them from the slabs heap + * for this bin's size class. + */ + uint64_t reslabs; + + /* Current number of slabs in this bin. */ + size_t curslabs; + + mutex_prof_data_t mutex_data; +}; + +#endif /* JEMALLOC_INTERNAL_BIN_STATS_H */ diff --git a/include/jemalloc/internal/ctl.h b/include/jemalloc/internal/ctl.h index a36feaff..d927d948 100644 --- a/include/jemalloc/internal/ctl.h +++ b/include/jemalloc/internal/ctl.h @@ -40,8 +40,8 @@ typedef struct ctl_arena_stats_s { uint64_t ndalloc_small; uint64_t nrequests_small; - malloc_bin_stats_t bstats[NBINS]; - malloc_large_stats_t lstats[NSIZES - NBINS]; + bin_stats_t bstats[NBINS]; + arena_stats_large_t lstats[NSIZES - NBINS]; } ctl_arena_stats_t; typedef struct ctl_stats_s { diff --git a/include/jemalloc/internal/stats.h b/include/jemalloc/internal/stats.h index 1da5b024..852e3426 100644 --- a/include/jemalloc/internal/stats.h +++ b/include/jemalloc/internal/stats.h @@ -1,17 +1,6 @@ #ifndef JEMALLOC_INTERNAL_STATS_H #define JEMALLOC_INTERNAL_STATS_H -#include "jemalloc/internal/atomic.h" -#include "jemalloc/internal/mutex_prof.h" -#include "jemalloc/internal/mutex.h" -#include "jemalloc/internal/size_classes.h" - -/* - * The synchronization for stats counters may piggyback on existing - * synchronization in the associated data. Therefore, the merging functions for - * a module's stats will lie in the module, instead of with the stats. - */ - /* OPTION(opt, var_name, default, set_value_to) */ #define STATS_PRINT_OPTIONS \ OPTION('J', json, false, true) \ @@ -38,133 +27,4 @@ extern char opt_stats_print_opts[stats_print_tot_num_options+1]; void stats_print(void (*write_cb)(void *, const char *), void *cbopaque, const char *opts); -/* - * In those architectures that support 64-bit atomics, we use atomic updates for - * our 64-bit values. Otherwise, we use a plain uint64_t and synchronize - * externally. - */ -#ifdef JEMALLOC_ATOMIC_U64 -typedef atomic_u64_t arena_stats_u64_t; -#else -/* Must hold the arena stats mutex while reading atomically. */ -typedef uint64_t arena_stats_u64_t; -#endif - -typedef struct malloc_bin_stats_s { - /* - * Total number of allocation/deallocation requests served directly by - * the bin. Note that tcache may allocate an object, then recycle it - * many times, resulting many increments to nrequests, but only one - * each to nmalloc and ndalloc. - */ - uint64_t nmalloc; - uint64_t ndalloc; - - /* - * Number of allocation requests that correspond to the size of this - * bin. This includes requests served by tcache, though tcache only - * periodically merges into this counter. - */ - uint64_t nrequests; - - /* - * Current number of regions of this size class, including regions - * currently cached by tcache. - */ - size_t curregs; - - /* Number of tcache fills from this bin. */ - uint64_t nfills; - - /* Number of tcache flushes to this bin. */ - uint64_t nflushes; - - /* Total number of slabs created for this bin's size class. */ - uint64_t nslabs; - - /* - * Total number of slabs reused by extracting them from the slabs heap - * for this bin's size class. - */ - uint64_t reslabs; - - /* Current number of slabs in this bin. */ - size_t curslabs; - - mutex_prof_data_t mutex_data; -} malloc_bin_stats_t; - -typedef struct malloc_large_stats_s { - /* - * Total number of allocation/deallocation requests served directly by - * the arena. - */ - arena_stats_u64_t nmalloc; - arena_stats_u64_t ndalloc; - - /* - * Number of allocation requests that correspond to this size class. - * This includes requests served by tcache, though tcache only - * periodically merges into this counter. - */ - arena_stats_u64_t nrequests; /* Partially derived. */ - - /* Current number of allocations of this size class. */ - size_t curlextents; /* Derived. */ -} malloc_large_stats_t; - -typedef struct decay_stats_s { - /* Total number of purge sweeps. */ - arena_stats_u64_t npurge; - /* Total number of madvise calls made. */ - arena_stats_u64_t nmadvise; - /* Total number of pages purged. */ - arena_stats_u64_t purged; -} decay_stats_t; - -/* - * Arena stats. Note that fields marked "derived" are not directly maintained - * within the arena code; rather their values are derived during stats merge - * requests. - */ -typedef struct arena_stats_s { -#ifndef JEMALLOC_ATOMIC_U64 - malloc_mutex_t mtx; -#endif - - /* Number of bytes currently mapped, excluding retained memory. */ - atomic_zu_t mapped; /* Partially derived. */ - - /* - * Number of unused virtual memory bytes currently retained. Retained - * bytes are technically mapped (though always decommitted or purged), - * but they are excluded from the mapped statistic (above). - */ - atomic_zu_t retained; /* Derived. */ - - decay_stats_t decay_dirty; - decay_stats_t decay_muzzy; - - atomic_zu_t base; /* Derived. */ - atomic_zu_t internal; - atomic_zu_t resident; /* Derived. */ - atomic_zu_t metadata_thp; - - atomic_zu_t allocated_large; /* Derived. */ - arena_stats_u64_t nmalloc_large; /* Derived. */ - arena_stats_u64_t ndalloc_large; /* Derived. */ - arena_stats_u64_t nrequests_large; /* Derived. */ - - /* Number of bytes cached in tcache associated with this arena. */ - atomic_zu_t tcache_bytes; /* Derived. */ - - mutex_prof_data_t mutex_prof_data[mutex_prof_num_arena_mutexes]; - - /* One element for each large size class. */ - malloc_large_stats_t lstats[NSIZES - NBINS]; - - /* Arena uptime. */ - nstime_t uptime; -} arena_stats_t; - #endif /* JEMALLOC_INTERNAL_STATS_H */ diff --git a/src/arena.c b/src/arena.c index c02dff18..e3693d54 100644 --- a/src/arena.c +++ b/src/arena.c @@ -57,145 +57,6 @@ static void arena_bin_lower_slab(tsdn_t *tsdn, arena_t *arena, extent_t *slab, /******************************************************************************/ -static bool -arena_stats_init(tsdn_t *tsdn, arena_stats_t *arena_stats) { - if (config_debug) { - for (size_t i = 0; i < sizeof(arena_stats_t); i++) { - assert(((char *)arena_stats)[i] == 0); - } - } -#ifndef JEMALLOC_ATOMIC_U64 - if (malloc_mutex_init(&arena_stats->mtx, "arena_stats", - WITNESS_RANK_ARENA_STATS, malloc_mutex_rank_exclusive)) { - return true; - } -#endif - /* Memory is zeroed, so there is no need to clear stats. */ - return false; -} - -static void -arena_stats_lock(tsdn_t *tsdn, arena_stats_t *arena_stats) { -#ifndef JEMALLOC_ATOMIC_U64 - malloc_mutex_lock(tsdn, &arena_stats->mtx); -#endif -} - -static void -arena_stats_unlock(tsdn_t *tsdn, arena_stats_t *arena_stats) { -#ifndef JEMALLOC_ATOMIC_U64 - malloc_mutex_unlock(tsdn, &arena_stats->mtx); -#endif -} - -static uint64_t -arena_stats_read_u64(tsdn_t *tsdn, arena_stats_t *arena_stats, - arena_stats_u64_t *p) { -#ifdef JEMALLOC_ATOMIC_U64 - return atomic_load_u64(p, ATOMIC_RELAXED); -#else - malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); - return *p; -#endif -} - -static void -arena_stats_add_u64(tsdn_t *tsdn, arena_stats_t *arena_stats, - arena_stats_u64_t *p, uint64_t x) { -#ifdef JEMALLOC_ATOMIC_U64 - atomic_fetch_add_u64(p, x, ATOMIC_RELAXED); -#else - malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); - *p += x; -#endif -} - -UNUSED static void -arena_stats_sub_u64(tsdn_t *tsdn, arena_stats_t *arena_stats, - arena_stats_u64_t *p, uint64_t x) { -#ifdef JEMALLOC_ATOMIC_U64 - UNUSED uint64_t r = atomic_fetch_sub_u64(p, x, ATOMIC_RELAXED); - assert(r - x <= r); -#else - malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); - *p -= x; - assert(*p + x >= *p); -#endif -} - -/* - * Non-atomically sets *dst += src. *dst needs external synchronization. - * This lets us avoid the cost of a fetch_add when its unnecessary (note that - * the types here are atomic). - */ -static void -arena_stats_accum_u64(arena_stats_u64_t *dst, uint64_t src) { -#ifdef JEMALLOC_ATOMIC_U64 - uint64_t cur_dst = atomic_load_u64(dst, ATOMIC_RELAXED); - atomic_store_u64(dst, src + cur_dst, ATOMIC_RELAXED); -#else - *dst += src; -#endif -} - -static size_t -arena_stats_read_zu(tsdn_t *tsdn, arena_stats_t *arena_stats, atomic_zu_t *p) { -#ifdef JEMALLOC_ATOMIC_U64 - return atomic_load_zu(p, ATOMIC_RELAXED); -#else - malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); - return atomic_load_zu(p, ATOMIC_RELAXED); -#endif -} - -static void -arena_stats_add_zu(tsdn_t *tsdn, arena_stats_t *arena_stats, atomic_zu_t *p, - size_t x) { -#ifdef JEMALLOC_ATOMIC_U64 - atomic_fetch_add_zu(p, x, ATOMIC_RELAXED); -#else - malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); - size_t cur = atomic_load_zu(p, ATOMIC_RELAXED); - atomic_store_zu(p, cur + x, ATOMIC_RELAXED); -#endif -} - -static void -arena_stats_sub_zu(tsdn_t *tsdn, arena_stats_t *arena_stats, atomic_zu_t *p, - size_t x) { -#ifdef JEMALLOC_ATOMIC_U64 - UNUSED size_t r = atomic_fetch_sub_zu(p, x, ATOMIC_RELAXED); - assert(r - x <= r); -#else - malloc_mutex_assert_owner(tsdn, &arena_stats->mtx); - size_t cur = atomic_load_zu(p, ATOMIC_RELAXED); - atomic_store_zu(p, cur - x, ATOMIC_RELAXED); -#endif -} - -/* Like the _u64 variant, needs an externally synchronized *dst. */ -static void -arena_stats_accum_zu(atomic_zu_t *dst, size_t src) { - size_t cur_dst = atomic_load_zu(dst, ATOMIC_RELAXED); - atomic_store_zu(dst, src + cur_dst, ATOMIC_RELAXED); -} - -void -arena_stats_large_nrequests_add(tsdn_t *tsdn, arena_stats_t *arena_stats, - szind_t szind, uint64_t nrequests) { - arena_stats_lock(tsdn, arena_stats); - arena_stats_add_u64(tsdn, arena_stats, &arena_stats->lstats[szind - - NBINS].nrequests, nrequests); - arena_stats_unlock(tsdn, arena_stats); -} - -void -arena_stats_mapped_add(tsdn_t *tsdn, arena_stats_t *arena_stats, size_t size) { - arena_stats_lock(tsdn, arena_stats); - arena_stats_add_zu(tsdn, arena_stats, &arena_stats->mapped, size); - arena_stats_unlock(tsdn, arena_stats); -} - void arena_basic_stats_merge(tsdn_t *tsdn, arena_t *arena, unsigned *nthreads, const char **dss, ssize_t *dirty_decay_ms, ssize_t *muzzy_decay_ms, @@ -213,7 +74,7 @@ void arena_stats_merge(tsdn_t *tsdn, arena_t *arena, unsigned *nthreads, const char **dss, ssize_t *dirty_decay_ms, ssize_t *muzzy_decay_ms, size_t *nactive, size_t *ndirty, size_t *nmuzzy, arena_stats_t *astats, - malloc_bin_stats_t *bstats, malloc_large_stats_t *lstats) { + bin_stats_t *bstats, arena_stats_large_t *lstats) { cassert(config_stats); arena_basic_stats_merge(tsdn, arena, nthreads, dss, dirty_decay_ms, @@ -729,7 +590,7 @@ arena_decay_reinit(arena_decay_t *decay, extents_t *extents, ssize_t decay_ms) { static bool arena_decay_init(arena_decay_t *decay, extents_t *extents, ssize_t decay_ms, - decay_stats_t *stats) { + arena_stats_decay_t *stats) { if (config_debug) { for (size_t i = 0; i < sizeof(arena_decay_t); i++) { assert(((char *)decay)[i] == 0); diff --git a/src/bin.c b/src/bin.c index 931a76e2..0886bc4e 100644 --- a/src/bin.c +++ b/src/bin.c @@ -29,7 +29,7 @@ bin_init(bin_t *bin) { extent_heap_new(&bin->slabs_nonfull); extent_list_init(&bin->slabs_full); if (config_stats) { - memset(&bin->stats, 0, sizeof(malloc_bin_stats_t)); + memset(&bin->stats, 0, sizeof(bin_stats_t)); } return false; } diff --git a/src/ctl.c b/src/ctl.c index aae8b6ec..3a22423b 100644 --- a/src/ctl.c +++ b/src/ctl.c @@ -560,7 +560,7 @@ static const ctl_named_node_t super_root_node[] = { * synchronized by the ctl mutex. */ static void -accum_arena_stats_u64(arena_stats_u64_t *dst, arena_stats_u64_t *src) { +ctl_accum_arena_stats_u64(arena_stats_u64_t *dst, arena_stats_u64_t *src) { #ifdef JEMALLOC_ATOMIC_U64 uint64_t cur_dst = atomic_load_u64(dst, ATOMIC_RELAXED); uint64_t cur_src = atomic_load_u64(src, ATOMIC_RELAXED); @@ -572,7 +572,7 @@ accum_arena_stats_u64(arena_stats_u64_t *dst, arena_stats_u64_t *src) { /* Likewise: with ctl mutex synchronization, reading is simple. */ static uint64_t -arena_stats_read_u64(arena_stats_u64_t *p) { +ctl_arena_stats_read_u64(arena_stats_u64_t *p) { #ifdef JEMALLOC_ATOMIC_U64 return atomic_load_u64(p, ATOMIC_RELAXED); #else @@ -580,7 +580,8 @@ arena_stats_read_u64(arena_stats_u64_t *p) { #endif } -static void accum_atomic_zu(atomic_zu_t *dst, atomic_zu_t *src) { +static void +accum_atomic_zu(atomic_zu_t *dst, atomic_zu_t *src) { size_t cur_dst = atomic_load_zu(dst, ATOMIC_RELAXED); size_t cur_src = atomic_load_zu(src, ATOMIC_RELAXED); atomic_store_zu(dst, cur_dst + cur_src, ATOMIC_RELAXED); @@ -690,9 +691,9 @@ ctl_arena_clear(ctl_arena_t *ctl_arena) { ctl_arena->astats->ndalloc_small = 0; ctl_arena->astats->nrequests_small = 0; memset(ctl_arena->astats->bstats, 0, NBINS * - sizeof(malloc_bin_stats_t)); + sizeof(bin_stats_t)); memset(ctl_arena->astats->lstats, 0, (NSIZES - NBINS) * - sizeof(malloc_large_stats_t)); + sizeof(arena_stats_large_t)); } } @@ -755,18 +756,18 @@ ctl_arena_stats_sdmerge(ctl_arena_t *ctl_sdarena, ctl_arena_t *ctl_arena, &astats->astats.retained); } - accum_arena_stats_u64(&sdstats->astats.decay_dirty.npurge, + ctl_accum_arena_stats_u64(&sdstats->astats.decay_dirty.npurge, &astats->astats.decay_dirty.npurge); - accum_arena_stats_u64(&sdstats->astats.decay_dirty.nmadvise, + ctl_accum_arena_stats_u64(&sdstats->astats.decay_dirty.nmadvise, &astats->astats.decay_dirty.nmadvise); - accum_arena_stats_u64(&sdstats->astats.decay_dirty.purged, + ctl_accum_arena_stats_u64(&sdstats->astats.decay_dirty.purged, &astats->astats.decay_dirty.purged); - accum_arena_stats_u64(&sdstats->astats.decay_muzzy.npurge, + ctl_accum_arena_stats_u64(&sdstats->astats.decay_muzzy.npurge, &astats->astats.decay_muzzy.npurge); - accum_arena_stats_u64(&sdstats->astats.decay_muzzy.nmadvise, + ctl_accum_arena_stats_u64(&sdstats->astats.decay_muzzy.nmadvise, &astats->astats.decay_muzzy.nmadvise); - accum_arena_stats_u64(&sdstats->astats.decay_muzzy.purged, + ctl_accum_arena_stats_u64(&sdstats->astats.decay_muzzy.purged, &astats->astats.decay_muzzy.purged); #define OP(mtx) malloc_mutex_prof_merge( \ @@ -806,11 +807,11 @@ MUTEX_PROF_ARENA_MUTEXES assert(atomic_load_zu(&astats->astats.allocated_large, ATOMIC_RELAXED) == 0); } - accum_arena_stats_u64(&sdstats->astats.nmalloc_large, + ctl_accum_arena_stats_u64(&sdstats->astats.nmalloc_large, &astats->astats.nmalloc_large); - accum_arena_stats_u64(&sdstats->astats.ndalloc_large, + ctl_accum_arena_stats_u64(&sdstats->astats.ndalloc_large, &astats->astats.ndalloc_large); - accum_arena_stats_u64(&sdstats->astats.nrequests_large, + ctl_accum_arena_stats_u64(&sdstats->astats.nrequests_large, &astats->astats.nrequests_large); accum_atomic_zu(&sdstats->astats.tcache_bytes, @@ -847,11 +848,11 @@ MUTEX_PROF_ARENA_MUTEXES } for (i = 0; i < NSIZES - NBINS; i++) { - accum_arena_stats_u64(&sdstats->lstats[i].nmalloc, + ctl_accum_arena_stats_u64(&sdstats->lstats[i].nmalloc, &astats->lstats[i].nmalloc); - accum_arena_stats_u64(&sdstats->lstats[i].ndalloc, + ctl_accum_arena_stats_u64(&sdstats->lstats[i].ndalloc, &astats->lstats[i].ndalloc); - accum_arena_stats_u64(&sdstats->lstats[i].nrequests, + ctl_accum_arena_stats_u64(&sdstats->lstats[i].nrequests, &astats->lstats[i].nrequests); if (!destroyed) { sdstats->lstats[i].curlextents += @@ -2545,24 +2546,24 @@ CTL_RO_CGEN(config_stats, stats_arenas_i_retained, size_t) CTL_RO_CGEN(config_stats, stats_arenas_i_dirty_npurge, - arena_stats_read_u64(&arenas_i(mib[2])->astats->astats.decay_dirty.npurge), - uint64_t) + ctl_arena_stats_read_u64( + &arenas_i(mib[2])->astats->astats.decay_dirty.npurge), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_dirty_nmadvise, - arena_stats_read_u64( + ctl_arena_stats_read_u64( &arenas_i(mib[2])->astats->astats.decay_dirty.nmadvise), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_dirty_purged, - arena_stats_read_u64(&arenas_i(mib[2])->astats->astats.decay_dirty.purged), - uint64_t) + ctl_arena_stats_read_u64( + &arenas_i(mib[2])->astats->astats.decay_dirty.purged), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_muzzy_npurge, - arena_stats_read_u64(&arenas_i(mib[2])->astats->astats.decay_muzzy.npurge), - uint64_t) + ctl_arena_stats_read_u64( + &arenas_i(mib[2])->astats->astats.decay_muzzy.npurge), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_muzzy_nmadvise, - arena_stats_read_u64( + ctl_arena_stats_read_u64( &arenas_i(mib[2])->astats->astats.decay_muzzy.nmadvise), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_muzzy_purged, - arena_stats_read_u64(&arenas_i(mib[2])->astats->astats.decay_muzzy.purged), - uint64_t) + ctl_arena_stats_read_u64( + &arenas_i(mib[2])->astats->astats.decay_muzzy.purged), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_base, atomic_load_zu(&arenas_i(mib[2])->astats->astats.base, ATOMIC_RELAXED), @@ -2592,14 +2593,17 @@ CTL_RO_CGEN(config_stats, stats_arenas_i_large_allocated, atomic_load_zu(&arenas_i(mib[2])->astats->astats.allocated_large, ATOMIC_RELAXED), size_t) CTL_RO_CGEN(config_stats, stats_arenas_i_large_nmalloc, - arena_stats_read_u64(&arenas_i(mib[2])->astats->astats.nmalloc_large), - uint64_t) + ctl_arena_stats_read_u64( + &arenas_i(mib[2])->astats->astats.nmalloc_large), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_large_ndalloc, - arena_stats_read_u64(&arenas_i(mib[2])->astats->astats.ndalloc_large), - uint64_t) + ctl_arena_stats_read_u64( + &arenas_i(mib[2])->astats->astats.ndalloc_large), uint64_t) +/* + * Note: "nmalloc" here instead of "nrequests" in the read. This is intentional. + */ CTL_RO_CGEN(config_stats, stats_arenas_i_large_nrequests, - arena_stats_read_u64(&arenas_i(mib[2])->astats->astats.nmalloc_large), - uint64_t) /* Intentional. */ + ctl_arena_stats_read_u64( + &arenas_i(mib[2])->astats->astats.nmalloc_large), uint64_t) /* Intentional. */ /* Lock profiling related APIs below. */ #define RO_MUTEX_CTL_GEN(n, l) \ @@ -2717,14 +2721,14 @@ stats_arenas_i_bins_j_index(tsdn_t *tsdn, const size_t *mib, size_t miblen, } CTL_RO_CGEN(config_stats, stats_arenas_i_lextents_j_nmalloc, - arena_stats_read_u64(&arenas_i(mib[2])->astats->lstats[mib[4]].nmalloc), - uint64_t) + ctl_arena_stats_read_u64( + &arenas_i(mib[2])->astats->lstats[mib[4]].nmalloc), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_lextents_j_ndalloc, - arena_stats_read_u64(&arenas_i(mib[2])->astats->lstats[mib[4]].ndalloc), - uint64_t) + ctl_arena_stats_read_u64( + &arenas_i(mib[2])->astats->lstats[mib[4]].ndalloc), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_lextents_j_nrequests, - arena_stats_read_u64(&arenas_i(mib[2])->astats->lstats[mib[4]].nrequests), - uint64_t) + ctl_arena_stats_read_u64( + &arenas_i(mib[2])->astats->lstats[mib[4]].nrequests), uint64_t) CTL_RO_CGEN(config_stats, stats_arenas_i_lextents_j_curlextents, arenas_i(mib[2])->astats->lstats[mib[4]].curlextents, size_t)