project-base/server-skynet-source-3rd-jemalloc
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
b4b4a77848
server-skynet-source-3rd-je.../include/jemalloc/internal/arena.h

647 lines
19 KiB
C
Raw Normal View History

Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
/******************************************************************************/
#ifdef JEMALLOC_H_TYPES
Normalize size classes. Normalize size classes to use the same number of size classes per size doubling (currently hard coded to 4), across the intire range of size classes. Small size classes already used this spacing, but in order to support this change, additional small size classes now fill [4 KiB .. 16 KiB). Large size classes range from [16 KiB .. 4 MiB). Huge size classes now support non-multiples of the chunk size in order to fill (4 MiB .. 16 MiB).
2014-10-06 08:54:10 +08:00
#define LARGE_MINCLASS (ZU(1) << LG_LARGE_MINCLASS)
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
/* Maximum number of regions in one slab. */
#define LG_SLAB_MAXREGS (LG_PAGE - LG_TINY_MIN)
#define SLAB_MAXREGS (1U << LG_SLAB_MAXREGS)
Avoid overflow in arena_run_regind(). Fix a regression due to: Remove an arena_bin_run_size_calc() constraint. 2a6f2af6e446a98a635caadd281a23ca09a491cb The removed constraint required that small run headers fit in one page, which indirectly limited runs such that they would not cause overflow in arena_run_regind(). Add an explicit constraint to arena_bin_run_size_calc() based on the largest number of regions that arena_run_regind() can handle (2^11 as currently configured).
2011-03-23 00:00:56 +08:00
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
/*
* The minimum ratio of active:dirty pages per arena is computed as:
*
Implement dynamic per arena control over dirty page purging. Add mallctls: - arenas.lg_dirty_mult is initialized via opt.lg_dirty_mult, and can be modified to change the initial lg_dirty_mult setting for newly created arenas. - arena.<i>.lg_dirty_mult controls an individual arena's dirty page purging threshold, and synchronously triggers any purging that may be necessary to maintain the constraint. - arena.<i>.chunk.purge allows the per arena dirty page purging function to be replaced. This resolves #93.
2015-03-19 09:55:33 +08:00
* (nactive >> lg_dirty_mult) >= ndirty
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
*
Implement dynamic per arena control over dirty page purging. Add mallctls: - arenas.lg_dirty_mult is initialized via opt.lg_dirty_mult, and can be modified to change the initial lg_dirty_mult setting for newly created arenas. - arena.<i>.lg_dirty_mult controls an individual arena's dirty page purging threshold, and synchronously triggers any purging that may be necessary to maintain the constraint. - arena.<i>.chunk.purge allows the per arena dirty page purging function to be replaced. This resolves #93.
2015-03-19 09:55:33 +08:00
* So, supposing that lg_dirty_mult is 3, there can be no less than 8 times as
* many active pages as dirty pages.
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
*/
Purge unused dirty pages in a fragmentation-reducing order. Purge unused dirty pages in an order that first performs clean/dirty run defragmentation, in order to mitigate available run fragmentation. Remove the limitation that prevented purging unless at least one chunk worth of dirty pages had accumulated in an arena. This limitation was intended to avoid excessive purging for small applications, but the threshold was arbitrary, and the effect of questionable utility. Relax opt_lg_dirty_mult from 5 to 3. This compensates for increased likelihood of allocating clean runs, given the same ratio of clean:dirty runs, and reduces the potential for repeated purging in pathological large malloc/free loops that push the active:dirty page ratio just over the purge threshold.
2012-10-31 06:42:37 +08:00
#define LG_DIRTY_MULT_DEFAULT 3
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
Implement decay-based unused dirty page purging. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. Add mallctls: - opt.purge - opt.decay_time - arena.<i>.decay - arena.<i>.decay_time - arenas.decay_time - stats.arenas.<i>.decay_time This resolves #325.
2016-02-20 12:09:31 +08:00
typedef enum {
purge_mode_ratio = 0,
purge_mode_decay = 1,
purge_mode_limit = 2
} purge_mode_t;
#define PURGE_DEFAULT purge_mode_ratio
/* Default decay time in seconds. */
#define DECAY_TIME_DEFAULT 10
/* Number of event ticks between time checks. */
#define DECAY_NTICKS_PER_UPDATE 1000
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
typedef struct arena_slab_data_s arena_slab_data_t;
Create arena_bin_info_t. Move read-only fields from arena_bin_t into arena_bin_info_t, primarily in order to avoid false cacheline sharing.
2011-03-16 04:59:15 +08:00
typedef struct arena_bin_info_s arena_bin_info_t;
Refactor arena->decay_* into arena->decay.* (arena_decay_t).
2016-10-11 11:32:19 +08:00
typedef struct arena_decay_s arena_decay_t;
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
typedef struct arena_bin_s arena_bin_t;
typedef struct arena_s arena_t;
Refactor arenas_cache tsd. Refactor arenas_cache tsd into arenas_tdata, which is a structure of type arena_tdata_t.
2016-02-20 11:37:10 +08:00
typedef struct arena_tdata_s arena_tdata_t;
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
#endif /* JEMALLOC_H_TYPES */
/******************************************************************************/
#ifdef JEMALLOC_H_STRUCTS
Integrate whole chunks into unused dirty page purging machinery. Extend per arena unused dirty page purging to manage unused dirty chunks in aaddtion to unused dirty runs. Rather than immediately unmapping deallocated chunks (or purging them in the --disable-munmap case), store them in a separate set of trees, chunks_[sz]ad_dirty. Preferrentially allocate dirty chunks. When excessive unused dirty pages accumulate, purge runs and chunks in ingegrated LRU order (and unmap chunks in the --enable-munmap case). Refactor extent_node_t to provide accessor functions.
2015-02-16 10:04:46 +08:00
#ifdef JEMALLOC_ARENA_STRUCTS_A
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
struct arena_slab_data_s {
/* Index of bin this slab is associated with. */
Rename index_t to szind_t to avoid an existing type on Solaris. This resolves #256.
2015-08-20 06:21:32 +08:00
szind_t binind;
Move small run metadata into the arena chunk header. Move small run metadata into the arena chunk header, with multiple expected benefits: - Lower run fragmentation due to reduced run sizes; runs are more likely to completely drain when there are fewer total regions. - Improved cache behavior. Prior to this change, run headers were always page-aligned, which put extra pressure on some CPU cache sets. The degree to which this was a problem was hardware dependent, but it likely hurt some even for the most advanced modern hardware. - Buffer overruns/underruns are less likely to corrupt allocator metadata. - Size classes between 4 KiB and 16 KiB become reasonable to support without any special handling, and the runs are small enough that dirty unused pages aren't a significant concern.
2014-09-29 16:31:39 +08:00
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
/* Number of free regions in slab. */
Move small run metadata into the arena chunk header. Move small run metadata into the arena chunk header, with multiple expected benefits: - Lower run fragmentation due to reduced run sizes; runs are more likely to completely drain when there are fewer total regions. - Improved cache behavior. Prior to this change, run headers were always page-aligned, which put extra pressure on some CPU cache sets. The degree to which this was a problem was hardware dependent, but it likely hurt some even for the most advanced modern hardware. - Buffer overruns/underruns are less likely to corrupt allocator metadata. - Size classes between 4 KiB and 16 KiB become reasonable to support without any special handling, and the runs are small enough that dirty unused pages aren't a significant concern.
2014-09-29 16:31:39 +08:00
unsigned nfree;
/* Per region allocated/deallocated bitmap. */
bitmap_t bitmap[BITMAP_GROUPS_MAX];
};
Integrate whole chunks into unused dirty page purging machinery. Extend per arena unused dirty page purging to manage unused dirty chunks in aaddtion to unused dirty runs. Rather than immediately unmapping deallocated chunks (or purging them in the --disable-munmap case), store them in a separate set of trees, chunks_[sz]ad_dirty. Preferrentially allocate dirty chunks. When excessive unused dirty pages accumulate, purge runs and chunks in ingegrated LRU order (and unmap chunks in the --enable-munmap case). Refactor extent_node_t to provide accessor functions.
2015-02-16 10:04:46 +08:00
#endif /* JEMALLOC_ARENA_STRUCTS_A */
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
Integrate whole chunks into unused dirty page purging machinery. Extend per arena unused dirty page purging to manage unused dirty chunks in aaddtion to unused dirty runs. Rather than immediately unmapping deallocated chunks (or purging them in the --disable-munmap case), store them in a separate set of trees, chunks_[sz]ad_dirty. Preferrentially allocate dirty chunks. When excessive unused dirty pages accumulate, purge runs and chunks in ingegrated LRU order (and unmap chunks in the --enable-munmap case). Refactor extent_node_t to provide accessor functions.
2015-02-16 10:04:46 +08:00
#ifdef JEMALLOC_ARENA_STRUCTS_B
Create arena_bin_info_t. Move read-only fields from arena_bin_t into arena_bin_info_t, primarily in order to avoid false cacheline sharing.
2011-03-16 04:59:15 +08:00
/*
Use bitmaps to track small regions. The previous free list implementation, which embedded singly linked lists in available regions, had the unfortunate side effect of causing many cache misses during thread cache fills. Fix this in two places: - arena_run_t: Use a new bitmap implementation to track which regions are available. Furthermore, revert to preferring the lowest available region (as jemalloc did with its old bitmap-based approach). - tcache_t: Move read-only tcache_bin_t metadata into tcache_bin_info_t, and add a contiguous array of pointers to tcache_t in order to track cached objects. This substantially increases the size of tcache_t, but results in much higher data locality for common tcache operations. As a side benefit, it is again possible to efficiently flush the least recently used cached objects, so this change changes flushing from MRU to LRU. The new bitmap implementation uses a multi-level summary approach to make finding the lowest available region very fast. In practice, bitmaps only have one or two levels, though the implementation is general enough to handle extremely large bitmaps, mainly so that large page sizes can still be entertained. Fix tcache_bin_flush_large() to always flush statistics, in the same way that tcache_bin_flush_small() was recently fixed. Use JEMALLOC_DEBUG rather than NDEBUG. Add dassert(), and use it for debug-only asserts.
2011-03-17 01:30:13 +08:00
* Read-only information associated with each element of arena_t's bins array
Create arena_bin_info_t. Move read-only fields from arena_bin_t into arena_bin_info_t, primarily in order to avoid false cacheline sharing.
2011-03-16 04:59:15 +08:00
* is stored separately, partly to reduce memory usage (only one copy, rather
* than one per arena), but mainly to avoid false cacheline sharing.
Implement Valgrind support, redzones, and quarantine. Implement Valgrind support, as well as the redzone and quarantine features, which help Valgrind detect memory errors. Redzones are only implemented for small objects because the changes necessary to support redzones around large and huge objects are complicated by in-place reallocation, to the point that it isn't clear that the maintenance burden is worth the incremental improvement to Valgrind support. Merge arena_salloc() and arena_salloc_demote(). Refactor i[v]salloc() to expose the 'demote' option.
2012-04-06 15:35:09 +08:00
*
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
* Each slab has the following layout:
Implement Valgrind support, redzones, and quarantine. Implement Valgrind support, as well as the redzone and quarantine features, which help Valgrind detect memory errors. Redzones are only implemented for small objects because the changes necessary to support redzones around large and huge objects are complicated by in-place reallocation, to the point that it isn't clear that the maintenance burden is worth the incremental improvement to Valgrind support. Merge arena_salloc() and arena_salloc_demote(). Refactor i[v]salloc() to expose the 'demote' option.
2012-04-06 15:35:09 +08:00
*
Remove redzone support. This resolves #369.
2016-04-06 09:18:15 +08:00
* /--------------------\
* | region 0 |
* |--------------------|
* | region 1 |
* |--------------------|
* | ... |
* | ... |
* | ... |
* |--------------------|
* | region nregs-1 |
* \--------------------/
Create arena_bin_info_t. Move read-only fields from arena_bin_t into arena_bin_info_t, primarily in order to avoid false cacheline sharing.
2011-03-16 04:59:15 +08:00
*/
struct arena_bin_info_s {
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
/* Size of regions in a slab for this bin's size class. */
Indentation style cleanup.
2016-02-23 02:44:58 +08:00
size_t reg_size;
Create arena_bin_info_t. Move read-only fields from arena_bin_t into arena_bin_info_t, primarily in order to avoid false cacheline sharing.
2011-03-16 04:59:15 +08:00
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
/* Total size of a slab for this bin's size class. */
size_t slab_size;
Create arena_bin_info_t. Move read-only fields from arena_bin_t into arena_bin_info_t, primarily in order to avoid false cacheline sharing.
2011-03-16 04:59:15 +08:00
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
/* Total number of regions in a slab for this bin's size class. */
Indentation style cleanup.
2016-02-23 02:44:58 +08:00
uint32_t nregs;
Create arena_bin_info_t. Move read-only fields from arena_bin_t into arena_bin_info_t, primarily in order to avoid false cacheline sharing.
2011-03-16 04:59:15 +08:00
Use bitmaps to track small regions. The previous free list implementation, which embedded singly linked lists in available regions, had the unfortunate side effect of causing many cache misses during thread cache fills. Fix this in two places: - arena_run_t: Use a new bitmap implementation to track which regions are available. Furthermore, revert to preferring the lowest available region (as jemalloc did with its old bitmap-based approach). - tcache_t: Move read-only tcache_bin_t metadata into tcache_bin_info_t, and add a contiguous array of pointers to tcache_t in order to track cached objects. This substantially increases the size of tcache_t, but results in much higher data locality for common tcache operations. As a side benefit, it is again possible to efficiently flush the least recently used cached objects, so this change changes flushing from MRU to LRU. The new bitmap implementation uses a multi-level summary approach to make finding the lowest available region very fast. In practice, bitmaps only have one or two levels, though the implementation is general enough to handle extremely large bitmaps, mainly so that large page sizes can still be entertained. Fix tcache_bin_flush_large() to always flush statistics, in the same way that tcache_bin_flush_small() was recently fixed. Use JEMALLOC_DEBUG rather than NDEBUG. Add dassert(), and use it for debug-only asserts.
2011-03-17 01:30:13 +08:00
/*
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
* Metadata used to manipulate bitmaps for slabs associated with this
Use bitmaps to track small regions. The previous free list implementation, which embedded singly linked lists in available regions, had the unfortunate side effect of causing many cache misses during thread cache fills. Fix this in two places: - arena_run_t: Use a new bitmap implementation to track which regions are available. Furthermore, revert to preferring the lowest available region (as jemalloc did with its old bitmap-based approach). - tcache_t: Move read-only tcache_bin_t metadata into tcache_bin_info_t, and add a contiguous array of pointers to tcache_t in order to track cached objects. This substantially increases the size of tcache_t, but results in much higher data locality for common tcache operations. As a side benefit, it is again possible to efficiently flush the least recently used cached objects, so this change changes flushing from MRU to LRU. The new bitmap implementation uses a multi-level summary approach to make finding the lowest available region very fast. In practice, bitmaps only have one or two levels, though the implementation is general enough to handle extremely large bitmaps, mainly so that large page sizes can still be entertained. Fix tcache_bin_flush_large() to always flush statistics, in the same way that tcache_bin_flush_small() was recently fixed. Use JEMALLOC_DEBUG rather than NDEBUG. Add dassert(), and use it for debug-only asserts.
2011-03-17 01:30:13 +08:00
* bin.
*/
Indentation style cleanup.
2016-02-23 02:44:58 +08:00
bitmap_info_t bitmap_info;
Create arena_bin_info_t. Move read-only fields from arena_bin_t into arena_bin_info_t, primarily in order to avoid false cacheline sharing.
2011-03-16 04:59:15 +08:00
};
Refactor arena->decay_* into arena->decay.* (arena_decay_t).
2016-10-11 11:32:19 +08:00
struct arena_decay_s {
/*
* Approximate time in seconds from the creation of a set of unused
* dirty pages until an equivalent set of unused dirty pages is purged
* and/or reused.
*/
ssize_t time;
Fix and simplify decay-based purging. Simplify decay-based purging attempts to only be triggered when the epoch is advanced, rather than every time purgeable memory increases. In a correctly functioning system (not previously the case; see below), this only causes a behavior difference if during subsequent purge attempts the least recently used (LRU) purgeable memory extent is initially too large to be purged, but that memory is reused between attempts and one or more of the next LRU purgeable memory extents are small enough to be purged. In practice this is an arbitrary behavior change that is within the set of acceptable behaviors. As for the purging fix, assure that arena->decay.ndirty is recorded *after* the epoch advance and associated purging occurs. Prior to this fix, it was possible for purging during epoch advance to cause a substantially underrepresentative (arena->ndirty - arena->decay.ndirty), i.e. the number of dirty pages attributed to the current epoch was too low, and a series of unintended purges could result. This fix is also relevant in the context of the simplification described above, but the bug's impact would be limited to over-purging at epoch advances.
2016-10-12 06:30:01 +08:00
/* time / SMOOTHSTEP_NSTEPS. */
Refactor arena->decay_* into arena->decay.* (arena_decay_t).
2016-10-11 11:32:19 +08:00
nstime_t interval;
/*
* Time at which the current decay interval logically started. We do
* not actually advance to a new epoch until sometime after it starts
* because of scheduling and computation delays, and it is even possible
* to completely skip epochs. In all cases, during epoch advancement we
* merge all relevant activity into the most recently recorded epoch.
*/
nstime_t epoch;
Fix and simplify decay-based purging. Simplify decay-based purging attempts to only be triggered when the epoch is advanced, rather than every time purgeable memory increases. In a correctly functioning system (not previously the case; see below), this only causes a behavior difference if during subsequent purge attempts the least recently used (LRU) purgeable memory extent is initially too large to be purged, but that memory is reused between attempts and one or more of the next LRU purgeable memory extents are small enough to be purged. In practice this is an arbitrary behavior change that is within the set of acceptable behaviors. As for the purging fix, assure that arena->decay.ndirty is recorded *after* the epoch advance and associated purging occurs. Prior to this fix, it was possible for purging during epoch advance to cause a substantially underrepresentative (arena->ndirty - arena->decay.ndirty), i.e. the number of dirty pages attributed to the current epoch was too low, and a series of unintended purges could result. This fix is also relevant in the context of the simplification described above, but the bug's impact would be limited to over-purging at epoch advances.
2016-10-12 06:30:01 +08:00
/* Deadline randomness generator. */
Refactor arena->decay_* into arena->decay.* (arena_decay_t).
2016-10-11 11:32:19 +08:00
uint64_t jitter_state;
/*
Fix and simplify decay-based purging. Simplify decay-based purging attempts to only be triggered when the epoch is advanced, rather than every time purgeable memory increases. In a correctly functioning system (not previously the case; see below), this only causes a behavior difference if during subsequent purge attempts the least recently used (LRU) purgeable memory extent is initially too large to be purged, but that memory is reused between attempts and one or more of the next LRU purgeable memory extents are small enough to be purged. In practice this is an arbitrary behavior change that is within the set of acceptable behaviors. As for the purging fix, assure that arena->decay.ndirty is recorded *after* the epoch advance and associated purging occurs. Prior to this fix, it was possible for purging during epoch advance to cause a substantially underrepresentative (arena->ndirty - arena->decay.ndirty), i.e. the number of dirty pages attributed to the current epoch was too low, and a series of unintended purges could result. This fix is also relevant in the context of the simplification described above, but the bug's impact would be limited to over-purging at epoch advances.
2016-10-12 06:30:01 +08:00
* Deadline for current epoch. This is the sum of interval and per
* epoch jitter which is a uniform random variable in [0..interval).
* Epochs always advance by precise multiples of interval, but we
* randomize the deadline to reduce the likelihood of arenas purging in
* lockstep.
Refactor arena->decay_* into arena->decay.* (arena_decay_t).
2016-10-11 11:32:19 +08:00
*/
nstime_t deadline;
/*
* Number of dirty pages at beginning of current epoch. During epoch
Fix and simplify decay-based purging. Simplify decay-based purging attempts to only be triggered when the epoch is advanced, rather than every time purgeable memory increases. In a correctly functioning system (not previously the case; see below), this only causes a behavior difference if during subsequent purge attempts the least recently used (LRU) purgeable memory extent is initially too large to be purged, but that memory is reused between attempts and one or more of the next LRU purgeable memory extents are small enough to be purged. In practice this is an arbitrary behavior change that is within the set of acceptable behaviors. As for the purging fix, assure that arena->decay.ndirty is recorded *after* the epoch advance and associated purging occurs. Prior to this fix, it was possible for purging during epoch advance to cause a substantially underrepresentative (arena->ndirty - arena->decay.ndirty), i.e. the number of dirty pages attributed to the current epoch was too low, and a series of unintended purges could result. This fix is also relevant in the context of the simplification described above, but the bug's impact would be limited to over-purging at epoch advances.
2016-10-12 06:30:01 +08:00
* advancement we use the delta between arena->decay.ndirty and
* arena->ndirty to determine how many dirty pages, if any, were
* generated.
Refactor arena->decay_* into arena->decay.* (arena_decay_t).
2016-10-11 11:32:19 +08:00
*/
size_t ndirty;
/*
* Trailing log of how many unused dirty pages were generated during
* each of the past SMOOTHSTEP_NSTEPS decay epochs, where the last
* element is the most recent epoch. Corresponding epoch times are
Fix and simplify decay-based purging. Simplify decay-based purging attempts to only be triggered when the epoch is advanced, rather than every time purgeable memory increases. In a correctly functioning system (not previously the case; see below), this only causes a behavior difference if during subsequent purge attempts the least recently used (LRU) purgeable memory extent is initially too large to be purged, but that memory is reused between attempts and one or more of the next LRU purgeable memory extents are small enough to be purged. In practice this is an arbitrary behavior change that is within the set of acceptable behaviors. As for the purging fix, assure that arena->decay.ndirty is recorded *after* the epoch advance and associated purging occurs. Prior to this fix, it was possible for purging during epoch advance to cause a substantially underrepresentative (arena->ndirty - arena->decay.ndirty), i.e. the number of dirty pages attributed to the current epoch was too low, and a series of unintended purges could result. This fix is also relevant in the context of the simplification described above, but the bug's impact would be limited to over-purging at epoch advances.
2016-10-12 06:30:01 +08:00
* relative to epoch.
Refactor arena->decay_* into arena->decay.* (arena_decay_t).
2016-10-11 11:32:19 +08:00
*/
size_t backlog[SMOOTHSTEP_NSTEPS];
};
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
struct arena_bin_s {
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
/* All operations on arena_bin_t fields require lock ownership. */
Indentation style cleanup.
2016-02-23 02:44:58 +08:00
malloc_mutex_t lock;
Push locks into arena bins. For bin-related allocation, protect data structures with bin locks rather than arena locks. Arena locks remain for run allocation/deallocation and other miscellaneous operations. Restructure statistics counters to maintain per bin allocated/nmalloc/ndalloc, but continue to provide arena-wide statistics via aggregation in the ctl code.
2010-03-14 12:32:56 +08:00
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
/*
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
* Current slab being used to service allocations of this bin's size
* class. slabcur is independent of slabs_{nonfull,full}; whenever
* slabcur is reassigned, the previous slab must be deallocated or
* inserted into slabs_{nonfull,full}.
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
*/
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
extent_t *slabcur;
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
/*
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
* Heap of non-full slabs. This heap is used to assure that new
* allocations come from the non-full slab that is lowest in memory.
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
*/
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
extent_heap_t slabs_nonfull;
/* Ring sentinel used to track full slabs. */
extent_t slabs_full;
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
/* Bin statistics. */
Indentation style cleanup.
2016-02-23 02:44:58 +08:00
malloc_bin_stats_t stats;
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
};
struct arena_s {
Implement allocation profiling and leack checking. Add the --enable-prof and --enable-prof-libunwind configure options. Add the B/b, F/f, I/i, L/l, and U/u JEMALLOC_OPTIONS. Interval-based profile dump triggering is not yet implemented. Add supporting generic code: * Add memory barriers. * Add prn (LCG PRNG). * Add hash (Murmur hash function). * Add ckh (cuckoo hash tables).
2010-02-11 02:37:56 +08:00
/* This arena's index within the arenas array. */
unsigned ind;
Push locks into arena bins. For bin-related allocation, protect data structures with bin locks rather than arena locks. Arena locks remain for run allocation/deallocation and other miscellaneous operations. Restructure statistics counters to maintain per bin allocated/nmalloc/ndalloc, but continue to provide arena-wide statistics via aggregation in the ctl code.
2010-03-14 12:32:56 +08:00
/*
Do not allocate metadata via non-auto arenas, nor tcaches. This assures that all internally allocated metadata come from the first opt_narenas arenas, i.e. the automatically multiplexed arenas.
2016-04-23 05:34:14 +08:00
* Number of threads currently assigned to this arena, synchronized via
* atomic operations. Each thread has two distinct assignments, one for
* application-serving allocation, and the other for internal metadata
* allocation. Internal metadata must not be allocated from arenas
* created via the arenas.extend mallctl, because the arena.<i>.reset
* mallctl indiscriminately discards all allocations for the affected
* arena.
*
* 0: Application allocation.
* 1: Internal metadata allocation.
Improve thread-->arena assignment. Rather than blindly assigning threads to arenas in round-robin fashion, choose the lowest-numbered arena that currently has the smallest number of threads assigned to it. Add the "stats.arenas.<i>.nthreads" mallctl.
2011-03-19 04:41:33 +08:00
*/
Do not allocate metadata via non-auto arenas, nor tcaches. This assures that all internally allocated metadata come from the first opt_narenas arenas, i.e. the automatically multiplexed arenas.
2016-04-23 05:34:14 +08:00
unsigned nthreads[2];
Improve thread-->arena assignment. Rather than blindly assigning threads to arenas in round-robin fashion, choose the lowest-numbered arena that currently has the smallest number of threads assigned to it. Add the "stats.arenas.<i>.nthreads" mallctl.
2011-03-19 04:41:33 +08:00
/*
* There are three classes of arena operations from a locking
* perspective:
Refactor arenas array (fixes deadlock). Refactor the arenas array, which contains pointers to all extant arenas, such that it starts out as a sparse array of maximum size, and use double-checked atomics-based reads as the basis for fast and simple arena_get(). Additionally, reduce arenas_lock's role such that it only protects against arena initalization races. These changes remove the possibility for arena lookups to trigger locking, which resolves at least one known (fork-related) deadlock. This resolves #315.
2016-02-25 15:58:10 +08:00
* 1) Thread assignment (modifies nthreads) is synchronized via atomics.
Improve thread-->arena assignment. Rather than blindly assigning threads to arenas in round-robin fashion, choose the lowest-numbered arena that currently has the smallest number of threads assigned to it. Add the "stats.arenas.<i>.nthreads" mallctl.
2011-03-19 04:41:33 +08:00
* 2) Bin-related operations are protected by bin locks.
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
* 3) Chunk-related operations are protected by this mutex.
Push locks into arena bins. For bin-related allocation, protect data structures with bin locks rather than arena locks. Arena locks remain for run allocation/deallocation and other miscellaneous operations. Restructure statistics counters to maintain per bin allocated/nmalloc/ndalloc, but continue to provide arena-wide statistics via aggregation in the ctl code.
2010-03-14 12:32:56 +08:00
*/
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
malloc_mutex_t lock;
arena_stats_t stats;
/*
* List of tcaches for extant threads associated with this arena.
Implement explicit tcache support. Add the MALLOCX_TCACHE() and MALLOCX_TCACHE_NONE macros, which can be used in conjunction with the *allocx() API. Add the tcache.create, tcache.flush, and tcache.destroy mallctls. This resolves #145.
2015-01-30 07:30:47 +08:00
* Stats from these are merged incrementally, and at exit if
* opt_stats_print is enabled.
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
*/
ql_head(tcache_t) tcache_ql;
Implement interval-based heap profile dumping. Add mallctl interfaces for profiling parameters. Fix a file descriptor leak in heap profile dumping.
2010-02-12 05:19:21 +08:00
uint64_t prof_accumbytes;
Implement cache index randomization for large allocations. Extract szad size quantization into {extent,run}_quantize(), and . quantize szad run sizes to the union of valid small region run sizes and large run sizes. Refactor iteration in arena_run_first_fit() to use run_quantize{,_first,_next(), and add support for padded large runs. For large allocations that have no specified alignment constraints, compute a pseudo-random offset from the beginning of the first backing page that is a multiple of the cache line size. Under typical configurations with 4-KiB pages and 64-byte cache lines this results in a uniform distribution among 64 page boundary offsets. Add the --disable-cache-oblivious option, primarily intended for performance testing. This resolves #13.
2015-05-05 00:58:36 +08:00
/*
* PRNG state for cache index randomization of large allocation base
* pointers.
*/
uint64_t offset_state;
Add arena-specific and selective dss allocation. Add the "arenas.extend" mallctl, so that it is possible to create new arenas that are outside the set that jemalloc automatically multiplexes threads onto. Add the ALLOCM_ARENA() flag for {,r,d}allocm(), so that it is possible to explicitly allocate from a particular arena. Add the "opt.dss" mallctl, which controls the default precedence of dss allocation relative to mmap allocation. Add the "arena.<i>.dss" mallctl, which makes it possible to set the default dss precedence on a per arena or global basis. Add the "arena.<i>.purge" mallctl, which obsoletes "arenas.purge". Add the "stats.arenas.<i>.dss" mallctl.
2012-10-12 04:53:15 +08:00
dss_prec_t dss_prec;
Implement dynamic per arena control over dirty page purging. Add mallctls: - arenas.lg_dirty_mult is initialized via opt.lg_dirty_mult, and can be modified to change the initial lg_dirty_mult setting for newly created arenas. - arena.<i>.lg_dirty_mult controls an individual arena's dirty page purging threshold, and synchronously triggers any purging that may be necessary to maintain the constraint. - arena.<i>.chunk.purge allows the per arena dirty page purging function to be replaced. This resolves #93.
2015-03-19 09:55:33 +08:00
/* Minimum ratio (log base 2) of nactive:ndirty. */
ssize_t lg_dirty_mult;
Implement decay-based unused dirty page purging. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. Add mallctls: - opt.purge - opt.decay_time - arena.<i>.decay - arena.<i>.decay_time - arenas.decay_time - stats.arenas.<i>.decay_time This resolves #325.
2016-02-20 12:09:31 +08:00
/* True if a thread is currently executing arena_purge_to_limit(). */
Convert arena_maybe_purge() recursion to iteration. This resolves #235.
2015-06-23 09:50:32 +08:00
bool purging;
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
/* Number of pages in active extents. */
Various minor cleanups. Clean up whitespace. Lock access of swap_avail when printing stats. Use inttypes.h for portable printf() format specifiers, specifically for uint64_t (PRIu64). Change highchunks and curchunks stats from (unsigned long) to (size_t).
2010-01-25 08:41:01 +08:00
size_t nactive;
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
/*
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
* Current count of pages within unused extents that are potentially
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
* dirty, and for which madvise(... MADV_DONTNEED) has not been called.
* By tracking this, we can institute a limit on how much dirty unused
* memory is mapped for each arena.
*/
size_t ndirty;
Refactor arena->decay_* into arena->decay.* (arena_decay_t).
2016-10-11 11:32:19 +08:00
/* Decay-based purging state. */
arena_decay_t decay;
Implement decay-based unused dirty page purging. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. Add mallctls: - opt.purge - opt.decay_time - arena.<i>.decay - arena.<i>.decay_time - arenas.decay_time - stats.arenas.<i>.decay_time This resolves #325.
2016-02-20 12:09:31 +08:00
Rename huge to large.
2016-06-01 05:50:21 +08:00
/* Extant large allocations. */
ql_head(extent_t) large;
/* Synchronizes all large allocation/update/deallocation. */
malloc_mutex_t large_mtx;
Move centralized chunk management into arenas. Migrate all centralized data structures related to huge allocations and recyclable chunks into arena_t, so that each arena can manage huge allocations and recyclable virtual memory completely independently of other arenas. Add chunk node caching to arenas, in order to avoid contention on the base allocator. Use chunks_rtree to look up huge allocations rather than a red-black tree. Maintain a per arena unsorted list of huge allocations (which will be needed to enumerate huge allocations during arena reset). Remove the --enable-ivsalloc option, make ivsalloc() always available, and use it for size queries if --enable-debug is enabled. The only practical implications to this removal are that 1) ivsalloc() is now always available during live debugging (and the underlying radix tree is available during core-based debugging), and 2) size query validation can no longer be enabled independent of --enable-debug. Remove the stats.chunks.{current,total,high} mallctls, and replace their underlying statistics with simpler atomically updated counters used exclusively for gdump triggering. These statistics are no longer very useful because each arena manages chunks independently, and per arena statistics provide similar information. Simplify chunk synchronization code, now that base chunk allocation cannot cause recursive lock acquisition.
2015-02-12 04:24:27 +08:00
/*
Rename chunks_{cached,retained,mtx} to extents_{cached,retained,mtx}.
2016-06-02 02:35:30 +08:00
* Heaps of extents that were previously allocated. These are used when
* allocating extents, in an attempt to re-use address space.
Move centralized chunk management into arenas. Migrate all centralized data structures related to huge allocations and recyclable chunks into arena_t, so that each arena can manage huge allocations and recyclable virtual memory completely independently of other arenas. Add chunk node caching to arenas, in order to avoid contention on the base allocator. Use chunks_rtree to look up huge allocations rather than a red-black tree. Maintain a per arena unsorted list of huge allocations (which will be needed to enumerate huge allocations during arena reset). Remove the --enable-ivsalloc option, make ivsalloc() always available, and use it for size queries if --enable-debug is enabled. The only practical implications to this removal are that 1) ivsalloc() is now always available during live debugging (and the underlying radix tree is available during core-based debugging), and 2) size query validation can no longer be enabled independent of --enable-debug. Remove the stats.chunks.{current,total,high} mallctls, and replace their underlying statistics with simpler atomically updated counters used exclusively for gdump triggering. These statistics are no longer very useful because each arena manages chunks independently, and per arena statistics provide similar information. Simplify chunk synchronization code, now that base chunk allocation cannot cause recursive lock acquisition.
2015-02-12 04:24:27 +08:00
*/
Rename chunks_{cached,retained,mtx} to extents_{cached,retained,mtx}.
2016-06-02 02:35:30 +08:00
extent_heap_t extents_cached[NPSIZES];
extent_heap_t extents_retained[NPSIZES];
Protect extents_dirty access with extents_mtx. This fixes race conditions during purging.
2016-09-23 02:57:28 +08:00
/*
* Ring sentinel used to track unused dirty memory. Dirty memory is
* managed as an LRU of cached extents.
*/
extent_t extents_dirty;
/* Protects extents_{cached,retained,dirty}. */
Rename chunks_{cached,retained,mtx} to extents_{cached,retained,mtx}.
2016-06-02 02:35:30 +08:00
malloc_mutex_t extents_mtx;
Generalize chunk management hooks. Add the "arena.<i>.chunk_hooks" mallctl, which replaces and expands on the "arena.<i>.chunk.{alloc,dalloc,purge}" mallctls. The chunk hooks allow control over chunk allocation/deallocation, decommit/commit, purging, and splitting/merging, such that the application can rely on jemalloc's internal chunk caching and retaining functionality, yet implement a variety of chunk management mechanisms and policies. Merge the chunks_[sz]ad_{mmap,dss} red-black trees into chunks_[sz]ad_retained. This slightly reduces how hard jemalloc tries to honor the dss precedence setting; prior to this change the precedence setting was also consulted when recycling chunks. Fix chunk purging. Don't purge chunks in arena_purge_stashed(); instead deallocate them in arena_unstash_purged(), so that the dirty memory linkage remains valid until after the last time it is used. This resolves #176 and #201.
2015-07-28 23:28:19 +08:00
Modify extent hook functions to take an (extent_t *) argument. This facilitates the application accessing its own extent allocator metadata during hook invocations. This resolves #259.
2016-06-04 03:05:53 +08:00
/* User-configurable extent hook functions. */
union {
extent_hooks_t *extent_hooks;
void *extent_hooks_pun;
};
Rename extent_node_t to extent_t.
2016-03-24 12:09:28 +08:00
/* Cache of extent structures that were allocated via base_alloc(). */
ql_head(extent_t) extent_cache;
malloc_mutex_t extent_cache_mtx;
Move centralized chunk management into arenas. Migrate all centralized data structures related to huge allocations and recyclable chunks into arena_t, so that each arena can manage huge allocations and recyclable virtual memory completely independently of other arenas. Add chunk node caching to arenas, in order to avoid contention on the base allocator. Use chunks_rtree to look up huge allocations rather than a red-black tree. Maintain a per arena unsorted list of huge allocations (which will be needed to enumerate huge allocations during arena reset). Remove the --enable-ivsalloc option, make ivsalloc() always available, and use it for size queries if --enable-debug is enabled. The only practical implications to this removal are that 1) ivsalloc() is now always available during live debugging (and the underlying radix tree is available during core-based debugging), and 2) size query validation can no longer be enabled independent of --enable-debug. Remove the stats.chunks.{current,total,high} mallctls, and replace their underlying statistics with simpler atomically updated counters used exclusively for gdump triggering. These statistics are no longer very useful because each arena manages chunks independently, and per arena statistics provide similar information. Simplify chunk synchronization code, now that base chunk allocation cannot cause recursive lock acquisition.
2015-02-12 04:24:27 +08:00
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
/* bins is used to store heaps of free regions. */
Simplify small size class infrastructure. Program-generate small size class tables for all valid combinations of LG_TINY_MIN, LG_QUANTUM, and PAGE_SHIFT. Use the appropriate table to generate all relevant data structures, and remove the distinction between tiny/quantum/cacheline/subpage bins. Remove --enable-dynamic-page-shift. This option didn't prove useful in practice, and it prevented optimizations. Add Tilera architecture support.
2012-02-29 08:50:47 +08:00
arena_bin_t bins[NBINS];
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
};
Refactor arenas_cache tsd. Refactor arenas_cache tsd into arenas_tdata, which is a structure of type arena_tdata_t.
2016-02-20 11:37:10 +08:00
/* Used in conjunction with tsd for fast arena-related context lookup. */
struct arena_tdata_s {
Implement decay-based unused dirty page purging. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. Add mallctls: - opt.purge - opt.decay_time - arena.<i>.decay - arena.<i>.decay_time - arenas.decay_time - stats.arenas.<i>.decay_time This resolves #325.
2016-02-20 12:09:31 +08:00
ticker_t decay_ticker;
Refactor arenas_cache tsd. Refactor arenas_cache tsd into arenas_tdata, which is a structure of type arena_tdata_t.
2016-02-20 11:37:10 +08:00
};
Integrate whole chunks into unused dirty page purging machinery. Extend per arena unused dirty page purging to manage unused dirty chunks in aaddtion to unused dirty runs. Rather than immediately unmapping deallocated chunks (or purging them in the --disable-munmap case), store them in a separate set of trees, chunks_[sz]ad_dirty. Preferrentially allocate dirty chunks. When excessive unused dirty pages accumulate, purge runs and chunks in ingegrated LRU order (and unmap chunks in the --enable-munmap case). Refactor extent_node_t to provide accessor functions.
2015-02-16 10:04:46 +08:00
#endif /* JEMALLOC_ARENA_STRUCTS_B */
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
#endif /* JEMALLOC_H_STRUCTS */
/******************************************************************************/
#ifdef JEMALLOC_H_EXTERNS
Implement cache index randomization for large allocations. Extract szad size quantization into {extent,run}_quantize(), and . quantize szad run sizes to the union of valid small region run sizes and large run sizes. Refactor iteration in arena_run_first_fit() to use run_quantize{,_first,_next(), and add support for padded large runs. For large allocations that have no specified alignment constraints, compute a pseudo-random offset from the beginning of the first backing page that is a multiple of the cache line size. Under typical configurations with 4-KiB pages and 64-byte cache lines this results in a uniform distribution among 64 page boundary offsets. Add the --disable-cache-oblivious option, primarily intended for performance testing. This resolves #13.
2015-05-05 00:58:36 +08:00
static const size_t large_pad =
#ifdef JEMALLOC_CACHE_OBLIVIOUS
PAGE
#else
0
#endif
;
Implement decay-based unused dirty page purging. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. Add mallctls: - opt.purge - opt.decay_time - arena.<i>.decay - arena.<i>.decay_time - arenas.decay_time - stats.arenas.<i>.decay_time This resolves #325.
2016-02-20 12:09:31 +08:00
extern purge_mode_t opt_purge;
extern const char *purge_mode_names[];
Implement cache index randomization for large allocations. Extract szad size quantization into {extent,run}_quantize(), and . quantize szad run sizes to the union of valid small region run sizes and large run sizes. Refactor iteration in arena_run_first_fit() to use run_quantize{,_first,_next(), and add support for padded large runs. For large allocations that have no specified alignment constraints, compute a pseudo-random offset from the beginning of the first backing page that is a multiple of the cache line size. Under typical configurations with 4-KiB pages and 64-byte cache lines this results in a uniform distribution among 64 page boundary offsets. Add the --disable-cache-oblivious option, primarily intended for performance testing. This resolves #13.
2015-05-05 00:58:36 +08:00
extern ssize_t opt_lg_dirty_mult;
Implement decay-based unused dirty page purging. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. Add mallctls: - opt.purge - opt.decay_time - arena.<i>.decay - arena.<i>.decay_time - arenas.decay_time - stats.arenas.<i>.decay_time This resolves #325.
2016-02-20 12:09:31 +08:00
extern ssize_t opt_decay_time;
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
Initialize arena_bin_info at compile time rather than at boot time. This resolves #370.
2016-04-07 20:04:12 +08:00
extern const arena_bin_info_t arena_bin_info[NBINS];
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
Rename most remaining *chunk* APIs to *extent*.
2016-06-02 03:59:02 +08:00
extent_t *arena_extent_cache_alloc(tsdn_t *tsdn, arena_t *arena,
Modify extent hook functions to take an (extent_t *) argument. This facilitates the application accessing its own extent allocator metadata during hook invocations. This resolves #259.
2016-06-04 03:05:53 +08:00
extent_hooks_t **r_extent_hooks, void *new_addr, size_t size,
size_t alignment, bool *zero);
Rename most remaining *chunk* APIs to *extent*.
2016-06-02 03:59:02 +08:00
void arena_extent_cache_dalloc(tsdn_t *tsdn, arena_t *arena,
Modify extent hook functions to take an (extent_t *) argument. This facilitates the application accessing its own extent allocator metadata during hook invocations. This resolves #259.
2016-06-04 03:05:53 +08:00
extent_hooks_t **r_extent_hooks, extent_t *extent);
Protect extents_dirty access with extents_mtx. This fixes race conditions during purging.
2016-09-23 02:57:28 +08:00
void arena_extent_cache_maybe_insert(tsdn_t *tsdn, arena_t *arena,
extent_t *extent, bool cache);
void arena_extent_cache_maybe_remove(tsdn_t *tsdn, arena_t *arena,
extent_t *extent, bool cache);
Rename most remaining *chunk* APIs to *extent*.
2016-06-02 03:59:02 +08:00
extent_t *arena_extent_alloc_large(tsdn_t *tsdn, arena_t *arena,
Add/use chunk_split_wrapper(). Remove redundant ptr/oldsize args from huge_*(). Refactor huge/chunk/arena code boundaries.
2016-05-19 12:02:46 +08:00
size_t usize, size_t alignment, bool *zero);
Rename most remaining *chunk* APIs to *extent*.
2016-06-02 03:59:02 +08:00
void arena_extent_dalloc_large(tsdn_t *tsdn, arena_t *arena,
extent_t *extent, bool locked);
void arena_extent_ralloc_large_shrink(tsdn_t *tsdn, arena_t *arena,
Add/use chunk_split_wrapper(). Remove redundant ptr/oldsize args from huge_*(). Refactor huge/chunk/arena code boundaries.
2016-05-19 12:02:46 +08:00
extent_t *extent, size_t oldsize);
Rename most remaining *chunk* APIs to *extent*.
2016-06-02 03:59:02 +08:00
void arena_extent_ralloc_large_expand(tsdn_t *tsdn, arena_t *arena,
Add/use chunk_split_wrapper(). Remove redundant ptr/oldsize args from huge_*(). Refactor huge/chunk/arena code boundaries.
2016-05-19 12:02:46 +08:00
extent_t *extent, size_t oldsize);
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
ssize_t arena_lg_dirty_mult_get(tsdn_t *tsdn, arena_t *arena);
bool arena_lg_dirty_mult_set(tsdn_t *tsdn, arena_t *arena,
Add witness, a simple online locking validator. This resolves #358.
2016-04-14 14:36:15 +08:00
ssize_t lg_dirty_mult);
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
ssize_t arena_decay_time_get(tsdn_t *tsdn, arena_t *arena);
bool arena_decay_time_set(tsdn_t *tsdn, arena_t *arena, ssize_t decay_time);
void arena_purge(tsdn_t *tsdn, arena_t *arena, bool all);
void arena_maybe_purge(tsdn_t *tsdn, arena_t *arena);
Implement the arena.<i>.reset mallctl. This makes it possible to discard all of an arena's allocations in a single operation. This resolves #146.
2016-04-23 05:37:17 +08:00
void arena_reset(tsd_t *tsd, arena_t *arena);
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
void arena_tcache_fill_small(tsdn_t *tsdn, arena_t *arena,
tcache_bin_t *tbin, szind_t binind, uint64_t prof_accumbytes);
Initialize arena_bin_info at compile time rather than at boot time. This resolves #370.
2016-04-07 20:04:12 +08:00
void arena_alloc_junk_small(void *ptr, const arena_bin_info_t *bin_info,
Implement Valgrind support, redzones, and quarantine. Implement Valgrind support, as well as the redzone and quarantine features, which help Valgrind detect memory errors. Redzones are only implemented for small objects because the changes necessary to support redzones around large and huge objects are complicated by in-place reallocation, to the point that it isn't clear that the maintenance burden is worth the incremental improvement to Valgrind support. Merge arena_salloc() and arena_salloc_demote(). Refactor i[v]salloc() to expose the 'demote' option.
2012-04-06 15:35:09 +08:00
bool zero);
Add quarantine unit tests. Verify that freed regions are quarantined, and that redzone corruption is detected. Introduce a testing idiom for intercepting/replacing internal functions. In this case the replaced function is ordinarily a static function, but the idiom should work similarly for library-private functions.
2013-12-18 07:14:36 +08:00
#ifdef JEMALLOC_JET
Initialize arena_bin_info at compile time rather than at boot time. This resolves #370.
2016-04-07 20:04:12 +08:00
typedef void (arena_dalloc_junk_small_t)(void *, const arena_bin_info_t *);
Add junk/zero filling unit tests, and fix discovered bugs. Fix growing large reallocation to junk fill new space. Fix huge deallocation to junk fill when munmap is disabled.
2014-01-08 08:47:56 +08:00
extern arena_dalloc_junk_small_t *arena_dalloc_junk_small;
#else
Initialize arena_bin_info at compile time rather than at boot time. This resolves #370.
2016-04-07 20:04:12 +08:00
void arena_dalloc_junk_small(void *ptr, const arena_bin_info_t *bin_info);
Add junk/zero filling unit tests, and fix discovered bugs. Fix growing large reallocation to junk fill new space. Fix huge deallocation to junk fill when munmap is disabled.
2014-01-08 08:47:56 +08:00
#endif
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
void *arena_malloc_hard(tsdn_t *tsdn, arena_t *arena, size_t size,
szind_t ind, bool zero);
void *arena_palloc(tsdn_t *tsdn, arena_t *arena, size_t usize,
Refactor huge_*() calls into arena internals. Make redirects to the huge_*() API the arena code's responsibility, since arenas now take responsibility for all allocation sizes.
2015-02-13 06:06:37 +08:00
size_t alignment, bool zero, tcache_t *tcache);
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
void arena_prof_promote(tsdn_t *tsdn, extent_t *extent, const void *ptr,
size_t usize);
void arena_dalloc_promoted(tsdn_t *tsdn, extent_t *extent, void *ptr,
tcache_t *tcache, bool slow_path);
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
void arena_dalloc_bin_junked_locked(tsdn_t *tsdn, arena_t *arena,
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
extent_t *extent, void *ptr);
void arena_dalloc_small(tsdn_t *tsdn, arena_t *arena, extent_t *extent,
void *ptr);
Use rtree-based chunk lookups rather than pointer bit twiddling. Look up chunk metadata via the radix tree, rather than using CHUNK_ADDR2BASE(). Propagate pointer's containing extent. Minimize extent lookups by doing a single lookup (e.g. in free()) and propagating the pointer's extent into nearly all the functions that may need it.
2016-03-24 11:29:33 +08:00
bool arena_ralloc_no_move(tsdn_t *tsdn, extent_t *extent, void *ptr,
size_t oldsize, size_t size, size_t extra, bool zero);
void *arena_ralloc(tsdn_t *tsdn, arena_t *arena, extent_t *extent, void *ptr,
size_t oldsize, size_t size, size_t alignment, bool zero, tcache_t *tcache);
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
dss_prec_t arena_dss_prec_get(tsdn_t *tsdn, arena_t *arena);
bool arena_dss_prec_set(tsdn_t *tsdn, arena_t *arena, dss_prec_t dss_prec);
Implement dynamic per arena control over dirty page purging. Add mallctls: - arenas.lg_dirty_mult is initialized via opt.lg_dirty_mult, and can be modified to change the initial lg_dirty_mult setting for newly created arenas. - arena.<i>.lg_dirty_mult controls an individual arena's dirty page purging threshold, and synchronously triggers any purging that may be necessary to maintain the constraint. - arena.<i>.chunk.purge allows the per arena dirty page purging function to be replaced. This resolves #93.
2015-03-19 09:55:33 +08:00
ssize_t arena_lg_dirty_mult_default_get(void);
bool arena_lg_dirty_mult_default_set(ssize_t lg_dirty_mult);
Implement decay-based unused dirty page purging. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. Add mallctls: - opt.purge - opt.decay_time - arena.<i>.decay - arena.<i>.decay_time - arenas.decay_time - stats.arenas.<i>.decay_time This resolves #325.
2016-02-20 12:09:31 +08:00
ssize_t arena_decay_time_default_get(void);
bool arena_decay_time_default_set(ssize_t decay_time);
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
void arena_basic_stats_merge(tsdn_t *tsdn, arena_t *arena,
unsigned *nthreads, const char **dss, ssize_t *lg_dirty_mult,
ssize_t *decay_time, size_t *nactive, size_t *ndirty);
void arena_stats_merge(tsdn_t *tsdn, arena_t *arena, unsigned *nthreads,
Add witness, a simple online locking validator. This resolves #358.
2016-04-14 14:36:15 +08:00
const char **dss, ssize_t *lg_dirty_mult, ssize_t *decay_time,
size_t *nactive, size_t *ndirty, arena_stats_t *astats,
Rename huge to large.
2016-06-01 05:50:21 +08:00
malloc_bin_stats_t *bstats, malloc_large_stats_t *lstats);
Do not allocate metadata via non-auto arenas, nor tcaches. This assures that all internally allocated metadata come from the first opt_narenas arenas, i.e. the automatically multiplexed arenas.
2016-04-23 05:34:14 +08:00
unsigned arena_nthreads_get(arena_t *arena, bool internal);
void arena_nthreads_inc(arena_t *arena, bool internal);
void arena_nthreads_dec(arena_t *arena, bool internal);
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
arena_t *arena_new(tsdn_t *tsdn, unsigned ind);
Simplify run quantization.
2016-04-09 05:16:19 +08:00
void arena_boot(void);
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
void arena_prefork0(tsdn_t *tsdn, arena_t *arena);
void arena_prefork1(tsdn_t *tsdn, arena_t *arena);
void arena_prefork2(tsdn_t *tsdn, arena_t *arena);
void arena_prefork3(tsdn_t *tsdn, arena_t *arena);
void arena_postfork_parent(tsdn_t *tsdn, arena_t *arena);
void arena_postfork_child(tsdn_t *tsdn, arena_t *arena);
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
#endif /* JEMALLOC_H_EXTERNS */
/******************************************************************************/
#ifdef JEMALLOC_H_INLINES
#ifndef JEMALLOC_ENABLE_INLINE
Remove obsolete stats.arenas.<i>.metadata.mapped mallctl. Rename stats.arenas.<i>.metadata.allocated mallctl to stats.arenas.<i>.metadata .
2016-06-02 04:40:48 +08:00
void arena_metadata_add(arena_t *arena, size_t size);
void arena_metadata_sub(arena_t *arena, size_t size);
size_t arena_metadata_get(arena_t *arena);
Fix a prof-related locking order bug. Fix a locking order bug that could cause deadlock during fork if heap profiling were enabled.
2013-02-07 03:59:30 +08:00
bool arena_prof_accum_impl(arena_t *arena, uint64_t accumbytes);
bool arena_prof_accum_locked(arena_t *arena, uint64_t accumbytes);
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
bool arena_prof_accum(tsdn_t *tsdn, arena_t *arena, uint64_t accumbytes);
Rename index_t to szind_t to avoid an existing type on Solaris. This resolves #256.
2015-08-20 06:21:32 +08:00
szind_t arena_bin_index(arena_t *arena, arena_bin_t *bin);
Use rtree-based chunk lookups rather than pointer bit twiddling. Look up chunk metadata via the radix tree, rather than using CHUNK_ADDR2BASE(). Propagate pointer's containing extent. Minimize extent lookups by doing a single lookup (e.g. in free()) and propagating the pointer's extent into nearly all the functions that may need it.
2016-03-24 11:29:33 +08:00
prof_tctx_t *arena_prof_tctx_get(tsdn_t *tsdn, const extent_t *extent,
const void *ptr);
void arena_prof_tctx_set(tsdn_t *tsdn, extent_t *extent, const void *ptr,
size_t usize, prof_tctx_t *tctx);
void arena_prof_tctx_reset(tsdn_t *tsdn, extent_t *extent, const void *ptr,
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
prof_tctx_t *tctx);
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
void arena_decay_ticks(tsdn_t *tsdn, arena_t *arena, unsigned nticks);
void arena_decay_tick(tsdn_t *tsdn, arena_t *arena);
void *arena_malloc(tsdn_t *tsdn, arena_t *arena, size_t size, szind_t ind,
Fast-path improvement: reduce # of branches and unnecessary operations. - Combine multiple runtime branches into a single malloc_slow check. - Avoid calling arena_choose / size2index / index2size on fast path. - A few micro optimizations.
2015-10-28 06:12:10 +08:00
bool zero, tcache_t *tcache, bool slow_path);
Refactor rtree to always use base_alloc() for node allocation.
2016-04-16 15:36:11 +08:00
arena_t *arena_aalloc(tsdn_t *tsdn, const void *ptr);
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
size_t arena_salloc(tsdn_t *tsdn, const extent_t *extent, const void *ptr);
Use rtree-based chunk lookups rather than pointer bit twiddling. Look up chunk metadata via the radix tree, rather than using CHUNK_ADDR2BASE(). Propagate pointer's containing extent. Minimize extent lookups by doing a single lookup (e.g. in free()) and propagating the pointer's extent into nearly all the functions that may need it.
2016-03-24 11:29:33 +08:00
void arena_dalloc(tsdn_t *tsdn, extent_t *extent, void *ptr,
tcache_t *tcache, bool slow_path);
void arena_sdalloc(tsdn_t *tsdn, extent_t *extent, void *ptr, size_t size,
tcache_t *tcache, bool slow_path);
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
#endif
#if (defined(JEMALLOC_ENABLE_INLINE) || defined(JEMALLOC_ARENA_C_))
Optimize malloc() and free() fast paths. Embed the bin index for small page runs into the chunk page map, in order to omit [...] in the following dependent load sequence: ptr-->mapelm-->[run-->bin-->]bin_info Move various non-critcal code out of the inlined function chain into helper functions (tcache_event_hard(), arena_dalloc_small(), and locking).
2012-05-02 15:30:36 +08:00
# ifdef JEMALLOC_ARENA_INLINE_A
Implement metadata statistics. There are three categories of metadata: - Base allocations are used for bootstrap-sensitive internal allocator data structures. - Arena chunk headers comprise pages which track the states of the non-metadata pages. - Internal allocations differ from application-originated allocations in that they are for internal use, and that they are omitted from heap profiles. The metadata statistics comprise the metadata categories as follows: - stats.metadata: All metadata -- base + arena chunk headers + internal allocations. - stats.arenas.<i>.metadata.mapped: Arena chunk headers. - stats.arenas.<i>.metadata.allocated: Internal allocations. This is reported separately from the other metadata statistics because it overlaps with the allocated and active statistics, whereas the other metadata statistics do not. Base allocations are not reported separately, though their magnitude can be computed by subtracting the arena-specific metadata. This resolves #163.
2014-11-28 03:22:36 +08:00
JEMALLOC_INLINE void
Remove obsolete stats.arenas.<i>.metadata.mapped mallctl. Rename stats.arenas.<i>.metadata.allocated mallctl to stats.arenas.<i>.metadata .
2016-06-02 04:40:48 +08:00
arena_metadata_add(arena_t *arena, size_t size)
Implement metadata statistics. There are three categories of metadata: - Base allocations are used for bootstrap-sensitive internal allocator data structures. - Arena chunk headers comprise pages which track the states of the non-metadata pages. - Internal allocations differ from application-originated allocations in that they are for internal use, and that they are omitted from heap profiles. The metadata statistics comprise the metadata categories as follows: - stats.metadata: All metadata -- base + arena chunk headers + internal allocations. - stats.arenas.<i>.metadata.mapped: Arena chunk headers. - stats.arenas.<i>.metadata.allocated: Internal allocations. This is reported separately from the other metadata statistics because it overlaps with the allocated and active statistics, whereas the other metadata statistics do not. Base allocations are not reported separately, though their magnitude can be computed by subtracting the arena-specific metadata. This resolves #163.
2014-11-28 03:22:36 +08:00
{
Remove obsolete stats.arenas.<i>.metadata.mapped mallctl. Rename stats.arenas.<i>.metadata.allocated mallctl to stats.arenas.<i>.metadata .
2016-06-02 04:40:48 +08:00
atomic_add_z(&arena->stats.metadata, size);
Implement metadata statistics. There are three categories of metadata: - Base allocations are used for bootstrap-sensitive internal allocator data structures. - Arena chunk headers comprise pages which track the states of the non-metadata pages. - Internal allocations differ from application-originated allocations in that they are for internal use, and that they are omitted from heap profiles. The metadata statistics comprise the metadata categories as follows: - stats.metadata: All metadata -- base + arena chunk headers + internal allocations. - stats.arenas.<i>.metadata.mapped: Arena chunk headers. - stats.arenas.<i>.metadata.allocated: Internal allocations. This is reported separately from the other metadata statistics because it overlaps with the allocated and active statistics, whereas the other metadata statistics do not. Base allocations are not reported separately, though their magnitude can be computed by subtracting the arena-specific metadata. This resolves #163.
2014-11-28 03:22:36 +08:00
}
JEMALLOC_INLINE void
Remove obsolete stats.arenas.<i>.metadata.mapped mallctl. Rename stats.arenas.<i>.metadata.allocated mallctl to stats.arenas.<i>.metadata .
2016-06-02 04:40:48 +08:00
arena_metadata_sub(arena_t *arena, size_t size)
Implement metadata statistics. There are three categories of metadata: - Base allocations are used for bootstrap-sensitive internal allocator data structures. - Arena chunk headers comprise pages which track the states of the non-metadata pages. - Internal allocations differ from application-originated allocations in that they are for internal use, and that they are omitted from heap profiles. The metadata statistics comprise the metadata categories as follows: - stats.metadata: All metadata -- base + arena chunk headers + internal allocations. - stats.arenas.<i>.metadata.mapped: Arena chunk headers. - stats.arenas.<i>.metadata.allocated: Internal allocations. This is reported separately from the other metadata statistics because it overlaps with the allocated and active statistics, whereas the other metadata statistics do not. Base allocations are not reported separately, though their magnitude can be computed by subtracting the arena-specific metadata. This resolves #163.
2014-11-28 03:22:36 +08:00
{
Remove obsolete stats.arenas.<i>.metadata.mapped mallctl. Rename stats.arenas.<i>.metadata.allocated mallctl to stats.arenas.<i>.metadata .
2016-06-02 04:40:48 +08:00
atomic_sub_z(&arena->stats.metadata, size);
Implement metadata statistics. There are three categories of metadata: - Base allocations are used for bootstrap-sensitive internal allocator data structures. - Arena chunk headers comprise pages which track the states of the non-metadata pages. - Internal allocations differ from application-originated allocations in that they are for internal use, and that they are omitted from heap profiles. The metadata statistics comprise the metadata categories as follows: - stats.metadata: All metadata -- base + arena chunk headers + internal allocations. - stats.arenas.<i>.metadata.mapped: Arena chunk headers. - stats.arenas.<i>.metadata.allocated: Internal allocations. This is reported separately from the other metadata statistics because it overlaps with the allocated and active statistics, whereas the other metadata statistics do not. Base allocations are not reported separately, though their magnitude can be computed by subtracting the arena-specific metadata. This resolves #163.
2014-11-28 03:22:36 +08:00
}
JEMALLOC_INLINE size_t
Remove obsolete stats.arenas.<i>.metadata.mapped mallctl. Rename stats.arenas.<i>.metadata.allocated mallctl to stats.arenas.<i>.metadata .
2016-06-02 04:40:48 +08:00
arena_metadata_get(arena_t *arena)
Implement metadata statistics. There are three categories of metadata: - Base allocations are used for bootstrap-sensitive internal allocator data structures. - Arena chunk headers comprise pages which track the states of the non-metadata pages. - Internal allocations differ from application-originated allocations in that they are for internal use, and that they are omitted from heap profiles. The metadata statistics comprise the metadata categories as follows: - stats.metadata: All metadata -- base + arena chunk headers + internal allocations. - stats.arenas.<i>.metadata.mapped: Arena chunk headers. - stats.arenas.<i>.metadata.allocated: Internal allocations. This is reported separately from the other metadata statistics because it overlaps with the allocated and active statistics, whereas the other metadata statistics do not. Base allocations are not reported separately, though their magnitude can be computed by subtracting the arena-specific metadata. This resolves #163.
2014-11-28 03:22:36 +08:00
{
Remove obsolete stats.arenas.<i>.metadata.mapped mallctl. Rename stats.arenas.<i>.metadata.allocated mallctl to stats.arenas.<i>.metadata .
2016-06-02 04:40:48 +08:00
return (atomic_read_z(&arena->stats.metadata));
Implement metadata statistics. There are three categories of metadata: - Base allocations are used for bootstrap-sensitive internal allocator data structures. - Arena chunk headers comprise pages which track the states of the non-metadata pages. - Internal allocations differ from application-originated allocations in that they are for internal use, and that they are omitted from heap profiles. The metadata statistics comprise the metadata categories as follows: - stats.metadata: All metadata -- base + arena chunk headers + internal allocations. - stats.arenas.<i>.metadata.mapped: Arena chunk headers. - stats.arenas.<i>.metadata.allocated: Internal allocations. This is reported separately from the other metadata statistics because it overlaps with the allocated and active statistics, whereas the other metadata statistics do not. Base allocations are not reported separately, though their magnitude can be computed by subtracting the arena-specific metadata. This resolves #163.
2014-11-28 03:22:36 +08:00
}
Fix a prof-related locking order bug. Fix a locking order bug that could cause deadlock during fork if heap profiling were enabled.
2013-02-07 03:59:30 +08:00
JEMALLOC_INLINE bool
Avoid arena_prof_accum()-related locking when possible. Refactor arena_prof_accum() and its callers to avoid arena locking when prof_interval is 0 (as when profiling is disabled). Reported by Ben Maurer.
2012-11-14 04:56:27 +08:00
arena_prof_accum_impl(arena_t *arena, uint64_t accumbytes)
{
cassert(config_prof);
assert(prof_interval != 0);
arena->prof_accumbytes += accumbytes;
if (arena->prof_accumbytes >= prof_interval) {
Improve interval-based profile dump triggering. When an allocation is large enough to trigger multiple dumps, use modular math rather than subtraction to reset the interval counter. Prior to this change, it was possible for a single allocation to cause many subsequent allocations to all trigger profile dumps. When updating usable size for a sampled object, try to cancel out the difference between LARGE_MINCLASS and usable size from the interval counter.
2016-05-29 08:29:03 +08:00
arena->prof_accumbytes %= prof_interval;
Fix a prof-related locking order bug. Fix a locking order bug that could cause deadlock during fork if heap profiling were enabled.
2013-02-07 03:59:30 +08:00
return (true);
Avoid arena_prof_accum()-related locking when possible. Refactor arena_prof_accum() and its callers to avoid arena locking when prof_interval is 0 (as when profiling is disabled). Reported by Ben Maurer.
2012-11-14 04:56:27 +08:00
}
Fix a prof-related locking order bug. Fix a locking order bug that could cause deadlock during fork if heap profiling were enabled.
2013-02-07 03:59:30 +08:00
return (false);
Avoid arena_prof_accum()-related locking when possible. Refactor arena_prof_accum() and its callers to avoid arena locking when prof_interval is 0 (as when profiling is disabled). Reported by Ben Maurer.
2012-11-14 04:56:27 +08:00
}
Fix a prof-related locking order bug. Fix a locking order bug that could cause deadlock during fork if heap profiling were enabled.
2013-02-07 03:59:30 +08:00
JEMALLOC_INLINE bool
Avoid arena_prof_accum()-related locking when possible. Refactor arena_prof_accum() and its callers to avoid arena locking when prof_interval is 0 (as when profiling is disabled). Reported by Ben Maurer.
2012-11-14 04:56:27 +08:00
arena_prof_accum_locked(arena_t *arena, uint64_t accumbytes)
{
cassert(config_prof);
Apply likely()/unlikely() to allocation/deallocation fast paths.
2014-09-12 07:20:44 +08:00
if (likely(prof_interval == 0))
Fix a prof-related locking order bug. Fix a locking order bug that could cause deadlock during fork if heap profiling were enabled.
2013-02-07 03:59:30 +08:00
return (false);
return (arena_prof_accum_impl(arena, accumbytes));
Avoid arena_prof_accum()-related locking when possible. Refactor arena_prof_accum() and its callers to avoid arena locking when prof_interval is 0 (as when profiling is disabled). Reported by Ben Maurer.
2012-11-14 04:56:27 +08:00
}
Fix a prof-related locking order bug. Fix a locking order bug that could cause deadlock during fork if heap profiling were enabled.
2013-02-07 03:59:30 +08:00
JEMALLOC_INLINE bool
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
arena_prof_accum(tsdn_t *tsdn, arena_t *arena, uint64_t accumbytes)
Avoid arena_prof_accum()-related locking when possible. Refactor arena_prof_accum() and its callers to avoid arena locking when prof_interval is 0 (as when profiling is disabled). Reported by Ben Maurer.
2012-11-14 04:56:27 +08:00
{
cassert(config_prof);
Apply likely()/unlikely() to allocation/deallocation fast paths.
2014-09-12 07:20:44 +08:00
if (likely(prof_interval == 0))
Fix a prof-related locking order bug. Fix a locking order bug that could cause deadlock during fork if heap profiling were enabled.
2013-02-07 03:59:30 +08:00
return (false);
{
bool ret;
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
malloc_mutex_lock(tsdn, &arena->lock);
Fix a prof-related locking order bug. Fix a locking order bug that could cause deadlock during fork if heap profiling were enabled.
2013-02-07 03:59:30 +08:00
ret = arena_prof_accum_impl(arena, accumbytes);
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
malloc_mutex_unlock(tsdn, &arena->lock);
Fix a prof-related locking order bug. Fix a locking order bug that could cause deadlock during fork if heap profiling were enabled.
2013-02-07 03:59:30 +08:00
return (ret);
}
Avoid arena_prof_accum()-related locking when possible. Refactor arena_prof_accum() and its callers to avoid arena locking when prof_interval is 0 (as when profiling is disabled). Reported by Ben Maurer.
2012-11-14 04:56:27 +08:00
}
Use rtree-based chunk lookups rather than pointer bit twiddling. Look up chunk metadata via the radix tree, rather than using CHUNK_ADDR2BASE(). Propagate pointer's containing extent. Minimize extent lookups by doing a single lookup (e.g. in free()) and propagating the pointer's extent into nearly all the functions that may need it.
2016-03-24 11:29:33 +08:00
# endif /* JEMALLOC_ARENA_INLINE_A */
Avoid arena_prof_accum()-related locking when possible. Refactor arena_prof_accum() and its callers to avoid arena locking when prof_interval is 0 (as when profiling is disabled). Reported by Ben Maurer.
2012-11-14 04:56:27 +08:00
Use rtree-based chunk lookups rather than pointer bit twiddling. Look up chunk metadata via the radix tree, rather than using CHUNK_ADDR2BASE(). Propagate pointer's containing extent. Minimize extent lookups by doing a single lookup (e.g. in free()) and propagating the pointer's extent into nearly all the functions that may need it.
2016-03-24 11:29:33 +08:00
# ifdef JEMALLOC_ARENA_INLINE_B
Rename index_t to szind_t to avoid an existing type on Solaris. This resolves #256.
2015-08-20 06:21:32 +08:00
JEMALLOC_INLINE szind_t
Create arena_bin_info_t. Move read-only fields from arena_bin_t into arena_bin_info_t, primarily in order to avoid false cacheline sharing.
2011-03-16 04:59:15 +08:00
arena_bin_index(arena_t *arena, arena_bin_t *bin)
{
Silence miscellaneous 64-to-32-bit data loss warnings.
2016-02-25 04:42:23 +08:00
szind_t binind = (szind_t)(bin - arena->bins);
Simplify small size class infrastructure. Program-generate small size class tables for all valid combinations of LG_TINY_MIN, LG_QUANTUM, and PAGE_SHIFT. Use the appropriate table to generate all relevant data structures, and remove the distinction between tiny/quantum/cacheline/subpage bins. Remove --enable-dynamic-page-shift. This option didn't prove useful in practice, and it prevented optimizations. Add Tilera architecture support.
2012-02-29 08:50:47 +08:00
assert(binind < NBINS);
Create arena_bin_info_t. Move read-only fields from arena_bin_t into arena_bin_info_t, primarily in order to avoid false cacheline sharing.
2011-03-16 04:59:15 +08:00
return (binind);
}
Implement per thread heap profiling. Rename data structures (prof_thr_cnt_t-->prof_tctx_t, prof_ctx_t-->prof_gctx_t), and convert to storing a prof_tctx_t for sampled objects. Convert PROF_ALLOC_PREP() to prof_alloc_prep(), since precise backtrace depth within jemalloc functions is no longer an issue (pprof prunes irrelevant frames). Implement mallctl's: - prof.reset implements full sample data reset, and optional change of sample interval. - prof.lg_sample reads the current sample interval (opt.lg_prof_sample was the permanent source of truth prior to prof.reset). - thread.prof.name provides naming capability for threads within heap profile dumps. - thread.prof.active makes it possible to activate/deactivate heap profiling for individual threads. Modify the heap dump files to contain per thread heap profile data. This change is incompatible with the existing pprof, which will require enhancements to read and process the enriched data.
2014-08-19 07:22:13 +08:00
JEMALLOC_INLINE prof_tctx_t *
Use rtree-based chunk lookups rather than pointer bit twiddling. Look up chunk metadata via the radix tree, rather than using CHUNK_ADDR2BASE(). Propagate pointer's containing extent. Minimize extent lookups by doing a single lookup (e.g. in free()) and propagating the pointer's extent into nearly all the functions that may need it.
2016-03-24 11:29:33 +08:00
arena_prof_tctx_get(tsdn_t *tsdn, const extent_t *extent, const void *ptr)
Fix a heap profiling regression. Call prof_ctx_set() in all paths through prof_{m,re}alloc(). Inline arena_prof_ctx_get().
2010-10-21 11:52:00 +08:00
{
Reduce cpp conditional logic complexity. Convert configuration-related cpp conditional logic to use static constant variables, e.g.: #ifdef JEMALLOC_DEBUG [...] #endif becomes: if (config_debug) { [...] } The advantage is clearer, more concise code. The main disadvantage is that data structures no longer have conditionally defined fields, so they pay the cost of all fields regardless of whether they are used. In practice, this is only a minor concern; config_stats will go away in an upcoming change, and config_prof is the only other major feature that depends on more than a few special-purpose fields.
2012-02-11 12:22:09 +08:00
cassert(config_prof);
Fix a heap profiling regression. Call prof_ctx_set() in all paths through prof_{m,re}alloc(). Inline arena_prof_ctx_get().
2010-10-21 11:52:00 +08:00
assert(ptr != NULL);
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
if (unlikely(!extent_slab_get(extent)))
Rename huge to large.
2016-06-01 05:50:21 +08:00
return (large_prof_tctx_get(tsdn, extent));
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
return ((prof_tctx_t *)(uintptr_t)1U);
Fix a heap profiling regression. Call prof_ctx_set() in all paths through prof_{m,re}alloc(). Inline arena_prof_ctx_get().
2010-10-21 11:52:00 +08:00
}
Fix heap profiling bugs. Fix a regression due to the recent heap profiling accuracy improvements: prof_{m,re}alloc() must set the object's profiling context regardless of whether it is sampled. Fix management of the CHUNK_MAP_CLASS chunk map bits, such that all large object (re-)allocation paths correctly initialize the bits. Prior to this fix, in-place realloc() cleared the bits, resulting in incorrect reported object size from arena_salloc_demote(). After this fix the non-demoted bit pattern is all zeros (instead of all ones), which makes it easier to assure that the bits are properly set.
2010-10-23 01:45:59 +08:00
JEMALLOC_INLINE void
Use rtree-based chunk lookups rather than pointer bit twiddling. Look up chunk metadata via the radix tree, rather than using CHUNK_ADDR2BASE(). Propagate pointer's containing extent. Minimize extent lookups by doing a single lookup (e.g. in free()) and propagating the pointer's extent into nearly all the functions that may need it.
2016-03-24 11:29:33 +08:00
arena_prof_tctx_set(tsdn_t *tsdn, extent_t *extent, const void *ptr,
size_t usize, prof_tctx_t *tctx)
Fix heap profiling bugs. Fix a regression due to the recent heap profiling accuracy improvements: prof_{m,re}alloc() must set the object's profiling context regardless of whether it is sampled. Fix management of the CHUNK_MAP_CLASS chunk map bits, such that all large object (re-)allocation paths correctly initialize the bits. Prior to this fix, in-place realloc() cleared the bits, resulting in incorrect reported object size from arena_salloc_demote(). After this fix the non-demoted bit pattern is all zeros (instead of all ones), which makes it easier to assure that the bits are properly set.
2010-10-23 01:45:59 +08:00
{
Reduce cpp conditional logic complexity. Convert configuration-related cpp conditional logic to use static constant variables, e.g.: #ifdef JEMALLOC_DEBUG [...] #endif becomes: if (config_debug) { [...] } The advantage is clearer, more concise code. The main disadvantage is that data structures no longer have conditionally defined fields, so they pay the cost of all fields regardless of whether they are used. In practice, this is only a minor concern; config_stats will go away in an upcoming change, and config_prof is the only other major feature that depends on more than a few special-purpose fields.
2012-02-11 12:22:09 +08:00
cassert(config_prof);
Fix heap profiling bugs. Fix a regression due to the recent heap profiling accuracy improvements: prof_{m,re}alloc() must set the object's profiling context regardless of whether it is sampled. Fix management of the CHUNK_MAP_CLASS chunk map bits, such that all large object (re-)allocation paths correctly initialize the bits. Prior to this fix, in-place realloc() cleared the bits, resulting in incorrect reported object size from arena_salloc_demote(). After this fix the non-demoted bit pattern is all zeros (instead of all ones), which makes it easier to assure that the bits are properly set.
2010-10-23 01:45:59 +08:00
assert(ptr != NULL);
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
if (unlikely(!extent_slab_get(extent)))
Rename huge to large.
2016-06-01 05:50:21 +08:00
large_prof_tctx_set(tsdn, extent, tctx);
Fix heap profiling bugs. Fix a regression due to the recent heap profiling accuracy improvements: prof_{m,re}alloc() must set the object's profiling context regardless of whether it is sampled. Fix management of the CHUNK_MAP_CLASS chunk map bits, such that all large object (re-)allocation paths correctly initialize the bits. Prior to this fix, in-place realloc() cleared the bits, resulting in incorrect reported object size from arena_salloc_demote(). After this fix the non-demoted bit pattern is all zeros (instead of all ones), which makes it easier to assure that the bits are properly set.
2010-10-23 01:45:59 +08:00
}
Fix a heap profiling regression. Call prof_ctx_set() in all paths through prof_{m,re}alloc(). Inline arena_prof_ctx_get().
2010-10-21 11:52:00 +08:00
Resolve an unsupported special case in arena_prof_tctx_set(). Add arena_prof_tctx_reset() and use it instead of arena_prof_tctx_set() when resetting the tctx pointer during reallocation, which happens whenever an originally sampled reallocated object is not sampled during reallocation. This regression was introduced by 594c759f37c301d0245dc2accf4d4aaf9d202819 (Optimize arena_prof_tctx_set().)
2015-09-15 14:48:11 +08:00
JEMALLOC_INLINE void
Use rtree-based chunk lookups rather than pointer bit twiddling. Look up chunk metadata via the radix tree, rather than using CHUNK_ADDR2BASE(). Propagate pointer's containing extent. Minimize extent lookups by doing a single lookup (e.g. in free()) and propagating the pointer's extent into nearly all the functions that may need it.
2016-03-24 11:29:33 +08:00
arena_prof_tctx_reset(tsdn_t *tsdn, extent_t *extent, const void *ptr,
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
prof_tctx_t *tctx)
Resolve an unsupported special case in arena_prof_tctx_set(). Add arena_prof_tctx_reset() and use it instead of arena_prof_tctx_set() when resetting the tctx pointer during reallocation, which happens whenever an originally sampled reallocated object is not sampled during reallocation. This regression was introduced by 594c759f37c301d0245dc2accf4d4aaf9d202819 (Optimize arena_prof_tctx_set().)
2015-09-15 14:48:11 +08:00
{
cassert(config_prof);
assert(ptr != NULL);
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
assert(!extent_slab_get(extent));
Resolve an unsupported special case in arena_prof_tctx_set(). Add arena_prof_tctx_reset() and use it instead of arena_prof_tctx_set() when resetting the tctx pointer during reallocation, which happens whenever an originally sampled reallocated object is not sampled during reallocation. This regression was introduced by 594c759f37c301d0245dc2accf4d4aaf9d202819 (Optimize arena_prof_tctx_set().)
2015-09-15 14:48:11 +08:00
Rename huge to large.
2016-06-01 05:50:21 +08:00
large_prof_tctx_reset(tsdn, extent);
Resolve an unsupported special case in arena_prof_tctx_set(). Add arena_prof_tctx_reset() and use it instead of arena_prof_tctx_set() when resetting the tctx pointer during reallocation, which happens whenever an originally sampled reallocated object is not sampled during reallocation. This regression was introduced by 594c759f37c301d0245dc2accf4d4aaf9d202819 (Optimize arena_prof_tctx_set().)
2015-09-15 14:48:11 +08:00
}
Implement decay-based unused dirty page purging. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. Add mallctls: - opt.purge - opt.decay_time - arena.<i>.decay - arena.<i>.decay_time - arenas.decay_time - stats.arenas.<i>.decay_time This resolves #325.
2016-02-20 12:09:31 +08:00
JEMALLOC_ALWAYS_INLINE void
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
arena_decay_ticks(tsdn_t *tsdn, arena_t *arena, unsigned nticks)
Implement decay-based unused dirty page purging. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. Add mallctls: - opt.purge - opt.decay_time - arena.<i>.decay - arena.<i>.decay_time - arenas.decay_time - stats.arenas.<i>.decay_time This resolves #325.
2016-02-20 12:09:31 +08:00
{
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
tsd_t *tsd;
Implement decay-based unused dirty page purging. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. Add mallctls: - opt.purge - opt.decay_time - arena.<i>.decay - arena.<i>.decay_time - arenas.decay_time - stats.arenas.<i>.decay_time This resolves #325.
2016-02-20 12:09:31 +08:00
ticker_t *decay_ticker;
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
if (unlikely(tsdn_null(tsdn)))
Implement decay-based unused dirty page purging. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. Add mallctls: - opt.purge - opt.decay_time - arena.<i>.decay - arena.<i>.decay_time - arenas.decay_time - stats.arenas.<i>.decay_time This resolves #325.
2016-02-20 12:09:31 +08:00
return;
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
tsd = tsdn_tsd(tsdn);
Implement decay-based unused dirty page purging. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. Add mallctls: - opt.purge - opt.decay_time - arena.<i>.decay - arena.<i>.decay_time - arenas.decay_time - stats.arenas.<i>.decay_time This resolves #325.
2016-02-20 12:09:31 +08:00
decay_ticker = decay_ticker_get(tsd, arena->ind);
if (unlikely(decay_ticker == NULL))
return;
if (unlikely(ticker_ticks(decay_ticker, nticks)))
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
arena_purge(tsdn, arena, false);
Implement decay-based unused dirty page purging. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. Add mallctls: - opt.purge - opt.decay_time - arena.<i>.decay - arena.<i>.decay_time - arenas.decay_time - stats.arenas.<i>.decay_time This resolves #325.
2016-02-20 12:09:31 +08:00
}
JEMALLOC_ALWAYS_INLINE void
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
arena_decay_tick(tsdn_t *tsdn, arena_t *arena)
Implement decay-based unused dirty page purging. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. Add mallctls: - opt.purge - opt.decay_time - arena.<i>.decay - arena.<i>.decay_time - arenas.decay_time - stats.arenas.<i>.decay_time This resolves #325.
2016-02-20 12:09:31 +08:00
{
Add various mutex ownership assertions.
2016-09-24 03:18:36 +08:00
malloc_mutex_assert_not_owner(tsdn, &arena->lock);
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
arena_decay_ticks(tsdn, arena, 1);
Implement decay-based unused dirty page purging. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. Add mallctls: - opt.purge - opt.decay_time - arena.<i>.decay - arena.<i>.decay_time - arenas.decay_time - stats.arenas.<i>.decay_time This resolves #325.
2016-02-20 12:09:31 +08:00
}
Add and use JEMALLOC_ALWAYS_INLINE. Add JEMALLOC_ALWAYS_INLINE and use it to guarantee that the entire fast paths of the primary allocation/deallocation functions are inlined.
2013-01-23 00:45:43 +08:00
JEMALLOC_ALWAYS_INLINE void *
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
arena_malloc(tsdn_t *tsdn, arena_t *arena, size_t size, szind_t ind, bool zero,
Refactor arena_malloc_hard() out of arena_malloc().
2016-02-20 10:40:03 +08:00
tcache_t *tcache, bool slow_path)
Streamline tcache-related malloc/free fast paths. tcache_get() is inlined, so do the config_tcache check inside tcache_get() and simplify its callers. Make arena_malloc() an inline function, since it is part of the malloc() fast path. Remove conditional logic that cause build issues if --disable-tcache was specified.
2012-02-14 04:29:49 +08:00
{
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
assert(!tsdn_null(tsdn) || tcache == NULL);
Streamline tcache-related malloc/free fast paths. tcache_get() is inlined, so do the config_tcache check inside tcache_get() and simplify its callers. Make arena_malloc() an inline function, since it is part of the malloc() fast path. Remove conditional logic that cause build issues if --disable-tcache was specified.
2012-02-14 04:29:49 +08:00
assert(size != 0);
Fast-path improvement: reduce # of branches and unnecessary operations. - Combine multiple runtime branches into a single malloc_slow check. - Avoid calling arena_choose / size2index / index2size on fast path. - A few micro optimizations.
2015-10-28 06:12:10 +08:00
if (likely(tcache != NULL)) {
if (likely(size <= SMALL_MAXCLASS)) {
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
return (tcache_alloc_small(tsdn_tsd(tsdn), arena,
tcache, size, ind, zero, slow_path));
Fast-path improvement: reduce # of branches and unnecessary operations. - Combine multiple runtime branches into a single malloc_slow check. - Avoid calling arena_choose / size2index / index2size on fast path. - A few micro optimizations.
2015-10-28 06:12:10 +08:00
}
if (likely(size <= tcache_maxclass)) {
Rename huge to large.
2016-06-01 05:50:21 +08:00
return (tcache_alloc_large(tsdn_tsd(tsdn), arena,
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
tcache, size, ind, zero, slow_path));
Fast-path improvement: reduce # of branches and unnecessary operations. - Combine multiple runtime branches into a single malloc_slow check. - Avoid calling arena_choose / size2index / index2size on fast path. - A few micro optimizations.
2015-10-28 06:12:10 +08:00
}
/* (size > tcache_maxclass) case falls through. */
assert(size > tcache_maxclass);
}
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
return (arena_malloc_hard(tsdn, arena, size, ind, zero));
Streamline tcache-related malloc/free fast paths. tcache_get() is inlined, so do the config_tcache check inside tcache_get() and simplify its callers. Make arena_malloc() an inline function, since it is part of the malloc() fast path. Remove conditional logic that cause build issues if --disable-tcache was specified.
2012-02-14 04:29:49 +08:00
}
Implement metadata statistics. There are three categories of metadata: - Base allocations are used for bootstrap-sensitive internal allocator data structures. - Arena chunk headers comprise pages which track the states of the non-metadata pages. - Internal allocations differ from application-originated allocations in that they are for internal use, and that they are omitted from heap profiles. The metadata statistics comprise the metadata categories as follows: - stats.metadata: All metadata -- base + arena chunk headers + internal allocations. - stats.arenas.<i>.metadata.mapped: Arena chunk headers. - stats.arenas.<i>.metadata.allocated: Internal allocations. This is reported separately from the other metadata statistics because it overlaps with the allocated and active statistics, whereas the other metadata statistics do not. Base allocations are not reported separately, though their magnitude can be computed by subtracting the arena-specific metadata. This resolves #163.
2014-11-28 03:22:36 +08:00
JEMALLOC_ALWAYS_INLINE arena_t *
Refactor rtree to always use base_alloc() for node allocation.
2016-04-16 15:36:11 +08:00
arena_aalloc(tsdn_t *tsdn, const void *ptr)
Implement metadata statistics. There are three categories of metadata: - Base allocations are used for bootstrap-sensitive internal allocator data structures. - Arena chunk headers comprise pages which track the states of the non-metadata pages. - Internal allocations differ from application-originated allocations in that they are for internal use, and that they are omitted from heap profiles. The metadata statistics comprise the metadata categories as follows: - stats.metadata: All metadata -- base + arena chunk headers + internal allocations. - stats.arenas.<i>.metadata.mapped: Arena chunk headers. - stats.arenas.<i>.metadata.allocated: Internal allocations. This is reported separately from the other metadata statistics because it overlaps with the allocated and active statistics, whereas the other metadata statistics do not. Base allocations are not reported separately, though their magnitude can be computed by subtracting the arena-specific metadata. This resolves #163.
2014-11-28 03:22:36 +08:00
{
Refactor rtree to always use base_alloc() for node allocation.
2016-04-16 15:36:11 +08:00
return (extent_arena_get(iealloc(tsdn, ptr)));
Implement metadata statistics. There are three categories of metadata: - Base allocations are used for bootstrap-sensitive internal allocator data structures. - Arena chunk headers comprise pages which track the states of the non-metadata pages. - Internal allocations differ from application-originated allocations in that they are for internal use, and that they are omitted from heap profiles. The metadata statistics comprise the metadata categories as follows: - stats.metadata: All metadata -- base + arena chunk headers + internal allocations. - stats.arenas.<i>.metadata.mapped: Arena chunk headers. - stats.arenas.<i>.metadata.allocated: Internal allocations. This is reported separately from the other metadata statistics because it overlaps with the allocated and active statistics, whereas the other metadata statistics do not. Base allocations are not reported separately, though their magnitude can be computed by subtracting the arena-specific metadata. This resolves #163.
2014-11-28 03:22:36 +08:00
}
Make arena_salloc() an inline function.
2012-04-20 09:28:03 +08:00
/* Return the size of the allocation pointed to by ptr. */
Add and use JEMALLOC_ALWAYS_INLINE. Add JEMALLOC_ALWAYS_INLINE and use it to guarantee that the entire fast paths of the primary allocation/deallocation functions are inlined.
2013-01-23 00:45:43 +08:00
JEMALLOC_ALWAYS_INLINE size_t
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
arena_salloc(tsdn_t *tsdn, const extent_t *extent, const void *ptr)
Make arena_salloc() an inline function.
2012-04-20 09:28:03 +08:00
{
size_t ret;
assert(ptr != NULL);
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
if (likely(extent_slab_get(extent)))
ret = index2size(extent_slab_data_get_const(extent)->binind);
else
Rename huge to large.
2016-06-01 05:50:21 +08:00
ret = large_salloc(tsdn, extent);
Make arena_salloc() an inline function.
2012-04-20 09:28:03 +08:00
return (ret);
}
Add and use JEMALLOC_ALWAYS_INLINE. Add JEMALLOC_ALWAYS_INLINE and use it to guarantee that the entire fast paths of the primary allocation/deallocation functions are inlined.
2013-01-23 00:45:43 +08:00
JEMALLOC_ALWAYS_INLINE void
Use rtree-based chunk lookups rather than pointer bit twiddling. Look up chunk metadata via the radix tree, rather than using CHUNK_ADDR2BASE(). Propagate pointer's containing extent. Minimize extent lookups by doing a single lookup (e.g. in free()) and propagating the pointer's extent into nearly all the functions that may need it.
2016-03-24 11:29:33 +08:00
arena_dalloc(tsdn_t *tsdn, extent_t *extent, void *ptr, tcache_t *tcache,
bool slow_path)
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
{
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
assert(!tsdn_null(tsdn) || tcache == NULL);
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
assert(ptr != NULL);
Move centralized chunk management into arenas. Migrate all centralized data structures related to huge allocations and recyclable chunks into arena_t, so that each arena can manage huge allocations and recyclable virtual memory completely independently of other arenas. Add chunk node caching to arenas, in order to avoid contention on the base allocator. Use chunks_rtree to look up huge allocations rather than a red-black tree. Maintain a per arena unsorted list of huge allocations (which will be needed to enumerate huge allocations during arena reset). Remove the --enable-ivsalloc option, make ivsalloc() always available, and use it for size queries if --enable-debug is enabled. The only practical implications to this removal are that 1) ivsalloc() is now always available during live debugging (and the underlying radix tree is available during core-based debugging), and 2) size query validation can no longer be enabled independent of --enable-debug. Remove the stats.chunks.{current,total,high} mallctls, and replace their underlying statistics with simpler atomically updated counters used exclusively for gdump triggering. These statistics are no longer very useful because each arena manages chunks independently, and per arena statistics provide similar information. Simplify chunk synchronization code, now that base chunk allocation cannot cause recursive lock acquisition.
2015-02-12 04:24:27 +08:00
Replace extent_achunk_[gs]et() with extent_slab_[gs]et().
2016-04-07 22:24:14 +08:00
if (likely(extent_slab_get(extent))) {
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
/* Small allocation. */
if (likely(tcache != NULL)) {
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
szind_t binind = extent_slab_data_get(extent)->binind;
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
tcache_dalloc_small(tsdn_tsd(tsdn), tcache, ptr, binind,
slow_path);
Move centralized chunk management into arenas. Migrate all centralized data structures related to huge allocations and recyclable chunks into arena_t, so that each arena can manage huge allocations and recyclable virtual memory completely independently of other arenas. Add chunk node caching to arenas, in order to avoid contention on the base allocator. Use chunks_rtree to look up huge allocations rather than a red-black tree. Maintain a per arena unsorted list of huge allocations (which will be needed to enumerate huge allocations during arena reset). Remove the --enable-ivsalloc option, make ivsalloc() always available, and use it for size queries if --enable-debug is enabled. The only practical implications to this removal are that 1) ivsalloc() is now always available during live debugging (and the underlying radix tree is available during core-based debugging), and 2) size query validation can no longer be enabled independent of --enable-debug. Remove the stats.chunks.{current,total,high} mallctls, and replace their underlying statistics with simpler atomically updated counters used exclusively for gdump triggering. These statistics are no longer very useful because each arena manages chunks independently, and per arena statistics provide similar information. Simplify chunk synchronization code, now that base chunk allocation cannot cause recursive lock acquisition.
2015-02-12 04:24:27 +08:00
} else {
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
arena_dalloc_small(tsdn, extent_arena_get(extent),
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
extent, ptr);
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
}
} else {
size_t usize = extent_usize_get(extent);
Streamline tcache-related malloc/free fast paths. tcache_get() is inlined, so do the config_tcache check inside tcache_get() and simplify its callers. Make arena_malloc() an inline function, since it is part of the malloc() fast path. Remove conditional logic that cause build issues if --disable-tcache was specified.
2012-02-14 04:29:49 +08:00
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
if (likely(tcache != NULL) && usize <= tcache_maxclass) {
if (config_prof && unlikely(usize <= SMALL_MAXCLASS)) {
arena_dalloc_promoted(tsdn, extent, ptr,
tcache, slow_path);
Implement cache index randomization for large allocations. Extract szad size quantization into {extent,run}_quantize(), and . quantize szad run sizes to the union of valid small region run sizes and large run sizes. Refactor iteration in arena_run_first_fit() to use run_quantize{,_first,_next(), and add support for padded large runs. For large allocations that have no specified alignment constraints, compute a pseudo-random offset from the beginning of the first backing page that is a multiple of the cache line size. Under typical configurations with 4-KiB pages and 64-byte cache lines this results in a uniform distribution among 64 page boundary offsets. Add the --disable-cache-oblivious option, primarily intended for performance testing. This resolves #13.
2015-05-05 00:58:36 +08:00
} else {
Rename huge to large.
2016-06-01 05:50:21 +08:00
tcache_dalloc_large(tsdn_tsd(tsdn), tcache,
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
ptr, usize, slow_path);
Refactor huge_*() calls into arena internals. Make redirects to the huge_*() API the arena code's responsibility, since arenas now take responsibility for all allocation sizes.
2015-02-13 06:06:37 +08:00
}
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
} else
Rename huge to large.
2016-06-01 05:50:21 +08:00
large_dalloc(tsdn, extent);
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
}
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
}
Add support for sized deallocation. This adds a new `sdallocx` function to the external API, allowing the size to be passed by the caller. It avoids some extra reads in the thread cache fast path. In the case where stats are enabled, this avoids the work of calculating the size from the pointer. An assertion validates the size that's passed in, so enabling debugging will allow users of the API to debug cases where an incorrect size is passed in. The performance win for a contrived microbenchmark doing an allocation and immediately freeing it is ~10%. It may have a different impact on a real workload. Closes #28
2014-08-29 03:41:48 +08:00
JEMALLOC_ALWAYS_INLINE void
Use rtree-based chunk lookups rather than pointer bit twiddling. Look up chunk metadata via the radix tree, rather than using CHUNK_ADDR2BASE(). Propagate pointer's containing extent. Minimize extent lookups by doing a single lookup (e.g. in free()) and propagating the pointer's extent into nearly all the functions that may need it.
2016-03-24 11:29:33 +08:00
arena_sdalloc(tsdn_t *tsdn, extent_t *extent, void *ptr, size_t size,
tcache_t *tcache, bool slow_path)
Add support for sized deallocation. This adds a new `sdallocx` function to the external API, allowing the size to be passed by the caller. It avoids some extra reads in the thread cache fast path. In the case where stats are enabled, this avoids the work of calculating the size from the pointer. An assertion validates the size that's passed in, so enabling debugging will allow users of the API to debug cases where an incorrect size is passed in. The performance win for a contrived microbenchmark doing an allocation and immediately freeing it is ~10%. It may have a different impact on a real workload. Closes #28
2014-08-29 03:41:48 +08:00
{
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
assert(!tsdn_null(tsdn) || tcache == NULL);
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
assert(ptr != NULL);
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
Replace extent_achunk_[gs]et() with extent_slab_[gs]et().
2016-04-07 22:24:14 +08:00
if (likely(extent_slab_get(extent))) {
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
/* Small allocation. */
if (likely(tcache != NULL)) {
szind_t binind = size2index(size);
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
assert(binind == extent_slab_data_get(extent)->binind);
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
tcache_dalloc_small(tsdn_tsd(tsdn), tcache, ptr, binind,
slow_path);
} else {
arena_dalloc_small(tsdn, extent_arena_get(extent),
Move slabs out of chunks.
2016-05-30 09:34:50 +08:00
extent, ptr);
Add support for sized deallocation. This adds a new `sdallocx` function to the external API, allowing the size to be passed by the caller. It avoids some extra reads in the thread cache fast path. In the case where stats are enabled, this avoids the work of calculating the size from the pointer. An assertion validates the size that's passed in, so enabling debugging will allow users of the API to debug cases where an incorrect size is passed in. The performance win for a contrived microbenchmark doing an allocation and immediately freeing it is ~10%. It may have a different impact on a real workload. Closes #28
2014-08-29 03:41:48 +08:00
}
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
} else {
if (likely(tcache != NULL) && size <= tcache_maxclass) {
if (config_prof && unlikely(size <= SMALL_MAXCLASS)) {
arena_dalloc_promoted(tsdn, extent, ptr,
tcache, slow_path);
Refactor huge_*() calls into arena internals. Make redirects to the huge_*() API the arena code's responsibility, since arenas now take responsibility for all allocation sizes.
2015-02-13 06:06:37 +08:00
} else {
Rename huge to large.
2016-06-01 05:50:21 +08:00
tcache_dalloc_large(tsdn_tsd(tsdn), tcache, ptr,
Resolve bootstrapping issues when embedded in FreeBSD libc. b2c0d6322d2307458ae2b28545f8a5c9903d7ef5 (Add witness, a simple online locking validator.) caused a broad propagation of tsd throughout the internal API, but tsd_fetch() was designed to fail prior to tsd bootstrapping. Fix this by splitting tsd_t into non-nullable tsd_t and nullable tsdn_t, and modifying all internal APIs that do not critically rely on tsd to take nullable pointers. Furthermore, add the tsd_booted_get() function so that tsdn_fetch() can probe whether tsd bootstrapping is complete and return NULL if not. All dangerous conversions of nullable pointers are tsdn_tsd() calls that assert-fail on invalid conversion.
2016-05-11 13:21:10 +08:00
size, slow_path);
Refactor huge_*() calls into arena internals. Make redirects to the huge_*() API the arena code's responsibility, since arenas now take responsibility for all allocation sizes.
2015-02-13 06:06:37 +08:00
}
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
} else
Rename huge to large.
2016-06-01 05:50:21 +08:00
large_dalloc(tsdn, extent);
Use huge size class infrastructure for large size classes.
2016-05-28 15:17:28 +08:00
}
Add support for sized deallocation. This adds a new `sdallocx` function to the external API, allowing the size to be passed by the caller. It avoids some extra reads in the thread cache fast path. In the case where stats are enabled, this avoids the work of calculating the size from the pointer. An assertion validates the size that's passed in, so enabling debugging will allow users of the API to debug cases where an incorrect size is passed in. The performance win for a contrived microbenchmark doing an allocation and immediately freeing it is ~10%. It may have a different impact on a real workload. Closes #28
2014-08-29 03:41:48 +08:00
}
Normalize size classes. Normalize size classes to use the same number of size classes per size doubling (currently hard coded to 4), across the intire range of size classes. Small size classes already used this spacing, but in order to support this change, additional small size classes now fill [4 KiB .. 16 KiB). Large size classes range from [16 KiB .. 4 MiB). Huge size classes now support non-multiples of the chunk size in order to fill (4 MiB .. 16 MiB).
2014-10-06 08:54:10 +08:00
# endif /* JEMALLOC_ARENA_INLINE_B */
Refactor jemalloc.c into multiple source files. Fix a stats bug in large object curruns accounting. Replace tcache_bin_fill() with arena_tcache_fill(), and fix a bug in an OOM error path. Fix API name mangling to coexist with __attribute__((malloc)).
2010-01-17 01:53:50 +08:00
#endif
#endif /* JEMALLOC_H_INLINES */
/******************************************************************************/
Reference in New Issue Copy Permalink