Revisions of jemalloc
Jan Engelhardt (jengelh)
committed
(revision 68)
trim changelog that's irrelevant to the user because it affects other platforms, build procedure, or deep internals
Jan Engelhardt (jengelh)
committed
(revision 67)
- Drop static library package, nothing seems to use it. - Remove openSUSE 11.1 build support.
Martin Liška (marxin)
accepted
request 691467
from
Martin Liška (marxin)
(revision 66)
- Add disable-test_prof_log_many_traces-test.patch in order to workaround https://github.com/jemalloc/jemalloc/issues/1477. - Update to version 5.2.0: New features: * Implement oversize_threshold, which uses a dedicated arena for allocations crossing the specified threshold to reduce fragmentation. (@interwq) * Add extents usage information to stats. (@tyleretzel) * Log time information for sampled allocations. (@tyleretzel) * Support 0 size in sdallocx. (@djwatson) * Output rate for certain counters in malloc_stats. (@zinoale) * Add configure option --enable-readlinkat, which allows the use of readlinkat over readlink. (@davidtgoldblatt) * Add configure options --{enable,disable}-{static,shared} to allow not building unwanted libraries. (@Ericson2314) * Add configure option --disable-libdl to enable fully static builds. (@interwq) * Add mallctl interfaces: * opt.oversize_threshold (@interwq) * stats.arenas.<i>.extent_avail (@tyleretzel) * stats.arenas.<i>.extents.<j>.n{dirty,muzzy,retained} (@tyleretzel) * stats.arenas.<i>.extents.<j>.{dirty,muzzy,retained}_bytes (@tyleretzel) Portability improvements: * Update MSVC builds. (@maksqwe, @rustyx) * Workaround a compiler optimizer bug on s390x. (@rkmisra) * Make use of pthread_set_name_np(3) on FreeBSD. (@trasz) * Implement malloc_getcpu() to enable percpu_arena for windows. (@santagada) * Link against -pthread instead of -lpthread. (@paravoid) * Make background_thread not dependent on libdl. (@interwq) * Add stringify to fix a linker directive issue on MSVC. (@daverigby) * Detect and fall back when 8-bit atomics are unavailable. (@interwq) * Fall back to the default pthread_create(3) if dlsym(3) fails. (@interwq) Optimizations and refactors: * Refactor the TSD module. (@davidtgoldblatt) * Avoid taking extents_muzzy mutex when muzzy is disabled. (@interwq) * Avoid taking large_mtx for auto arenas on the tcache flush path. (@interwq) * Optimize ixalloc by avoiding a size lookup. (@interwq) * Implement opt.oversize_threshold which uses a dedicated arena for requests crossing the threshold, also eagerly purges the oversize extents. Default the threshold to 8 MiB. (@interwq) * Clean compilation with -Wextra. (@gnzlbg, @jasone) * Refactor the size class module. (@davidtgoldblatt) * Refactor the stats emitter. (@tyleretzel) * Optimize pow2_ceil. (@rkmisra) * Avoid runtime detection of lazy purging on FreeBSD. (@trasz) * Optimize mmap(2) alignment handling on FreeBSD. (@trasz) * Improve error handling for THP state initialization. (@jsteemann) * Rework the malloc() fast path. (@djwatson) * Rework the free() fast path. (@djwatson) * Refactor and optimize the tcache fill / flush paths. (@djwatson) * Optimize sync / lwsync on PowerPC. (@chmeeedalf) * Bypass extent_dalloc() when retain is enabled. (@interwq) * Optimize the locking on large deallocation. (@interwq) * Reduce the number of pages committed from sanity checking in debug build. (@trasz, @interwq) * Deprecate OSSpinLock. (@interwq) * Lower the default number of background threads to 4 (when the feature is enabled). (@interwq) * Optimize the trylock spin wait. (@djwatson) * Use arena index for arena-matching checks. (@interwq) * Avoid forced decay on thread termination when using background threads. (@interwq) * Disable muzzy decay by default. (@djwatson, @interwq) * Only initialize libgcc unwinder when profiling is enabled. (@paravoid, @interwq) Bug fixes (all only relevant to jemalloc 5.x): * Fix background thread index issues with max_background_threads. (@djwatson, @interwq) * Fix stats output for opt.lg_extent_max_active_fit. (@interwq) * Fix opt.prof_prefix initialization. (@davidtgoldblatt) * Properly trigger decay on tcache destroy. (@interwq, @amosbird) * Fix tcache.flush. (@interwq) * Detect whether explicit extent zero out is necessary with huge pages or custom extent hooks, which may change the purge semantics. (@interwq) * Fix a side effect caused by extent_max_active_fit combined with decay-based purging, where freed extents can accumulate and not be reused for an extended period of time. (@interwq, @mpghf) * Fix a missing unlock on extent register error handling. (@zoulasc) Testing: * Simplify the Travis script output. (@gnzlbg) * Update the test scripts for FreeBSD. (@devnexen) * Add unit tests for the producer-consumer pattern. (@interwq) * Add Cirrus-CI config for FreeBSD builds. (@jasone) * Add size-matching sanity checks on tcache flush. (@davidtgoldblatt, @interwq) Incompatible changes: * Remove --with-lg-page-sizes. (@davidtgoldblatt) Documentation: * Attempt to build docs by default, however skip doc building when xsltproc is missing. (@interwq, @cmuellner) - Change URL of the project.
buildservice-autocommit
accepted
request 645590
from
Martin Liška (marxin)
(revision 65)
baserev update by copy to link target
Martin Liška (marxin)
accepted
request 645563
from
michel_mno
(revision 64)
- Disable profiling on ppc until boo#1105633 get fixed because same jemalloc hung when build for ppc https://build.opensuse.org/package/live_build_log/openSUSE:Factory:PowerPC/jemalloc/standard/ppc
buildservice-autocommit
accepted
request 639125
from
Jan Engelhardt (jengelh)
(revision 63)
baserev update by copy to link target
Jan Engelhardt (jengelh)
accepted
request 639121
from
Manu Maier (mmanu84)
(revision 62)
- Disable profiling on armv6 until boo#1105633 get fixed
buildservice-autocommit
accepted
request 630930
from
Jan Engelhardt (jengelh)
(revision 61)
baserev update by copy to link target
Jan Engelhardt (jengelh)
accepted
request 630928
from
Guillaume GARDET (Guillaume_G)
(revision 60)
- Disable profiling on armv7 until boo#1105633 get fixed
buildservice-autocommit
accepted
request 606134
from
Martin Liška (marxin)
(revision 59)
baserev update by copy to link target
Martin Liška (marxin)
committed
(revision 58)
- Update to version 5.1.0: * remove patches: 0001-ARM-Don-t-extend-bit-LG_VADDR-to-compute-high-addres.patch and 0001-remove-CPU_SPINWAIT.patch. New features: * Implement transparent huge page support for internal metadata. (@interwq) * Add opt.thp to allow enabling / disabling transparent huge pages for all mappings. (@interwq) * Add maximum background thread count option. (@djwatson) * Allow prof_active to control opt.lg_prof_interval and prof.gdump. (@interwq) * Allow arena index lookup based on allocation addresses via mallctl. (@lionkov) * Allow disabling initial-exec TLS model. (@davidtgoldblatt, @KenMacD) * Add opt.lg_extent_max_active_fit to set the max ratio between the size of the active extent selected (to split off from) and the size of the requested allocation. (@interwq, @davidtgoldblatt) * Add retain_grow_limit to set the max size when growing virtual address space. (@interwq) * Add mallctl interfaces: * arena.<i>.retain_grow_limit (@interwq) * arenas.lookup (@lionkov) * max_background_threads (@djwatson) * opt.lg_extent_max_active_fit (@interwq) * opt.max_background_threads (@djwatson) * opt.metadata_thp (@interwq) * opt.thp (@interwq) * stats.metadata_thp (@interwq) Portability improvements: * Support GNU/kFreeBSD configuration. (@paravoid) * Support m68k, nios2 and SH3 architectures. (@paravoid) * Fall back to FD_CLOEXEC when O_CLOEXEC is unavailable. (@zonyitoo) * Fix symbol listing for cross-compiling. (@tamird) * Fix high bits computation on ARM. (@davidtgoldblatt, @paravoid) * Disable the CPU_SPINWAIT macro for Power. (@davidtgoldblatt, @marxin) * Fix MSVC 2015 & 2017 builds. (@rustyx) * Improve RISC-V support. (@EdSchouten)
buildservice-autocommit
accepted
request 575200
from
Jan Engelhardt (jengelh)
(revision 57)
baserev update by copy to link target
Jan Engelhardt (jengelh)
accepted
request 574948
from
Guillaume GARDET (Guillaume_G)
(revision 56)
- Disable THP for ARM (32 bits). This fix build by passing all tests successfully
buildservice-autocommit
accepted
request 531585
from
Martin Liška (marxin)
(revision 55)
baserev update by copy to link target
Martin Liška (marxin)
committed
(revision 54)
- Add 0001-remove-CPU_SPINWAIT.patch: revert 701daa5298b3befe2aff05ce590533165abb9ba4 in order to fix #761.
Martin Liška (marxin)
accepted
request 531565
from
Martin Liška (marxin)
(revision 53)
- Add 0001-ARM-Don-t-extend-bit-LG_VADDR-to-compute-high-addres.patch: fixes #979. - Revert 701daa5298b3befe2aff05ce590533165abb9ba4 in order to fix #761. - Update to version 5.0.1 Bug fixes: * Update decay->nunpurged before purging, in order to avoid potential update races and subsequent incorrect purging volume. ([37]@interwq) * Only abort on dlsym(3) error if the failure impacts an enabled feature (lazy locking and/or background threads). This mitigates an initialization failure bug for which we still do not have a clear reproduction test case. ([38]@interwq) * Modify tsd management so that it neither crashes nor leaks if a thread's only allocation activity is to call free() after TLS destructors have been executed. This behavior was observed when operating with GNU libc, and is unlikely to be an issue with other libc implementations. ([39]@interwq) * Mask signals during background thread creation. This prevents signals from being inadvertently delivered to background threads. ([40]@jasone, [41]@davidtgoldblatt, [42]@interwq) * Avoid inactivity checks within background threads, in order to prevent recursive mutex acquisition. ([43]@interwq) * Fix extent_grow_retained() to use the specified hooks when the arena.<i>.extent_hooks mallctl is used to override the default hooks. ([44]@interwq) * Add missing reentrancy support for custom extent hooks which allocate. ([45]@interwq) * Post-fork(2), re-initialize the list of tcaches associated with each arena to contain no tcaches except the forking thread's. ([46]@interwq) * Add missing post-fork(2) mutex reinitialization for extent_grow_mtx. This fixes potential deadlocks after fork(2). ([47]@interwq) * Enforce minimum autoconf version (currently 2.68), since 2.63 is known to generate corrupt configure scripts. ([48]@jasone) * Ensure that the configured page size (--with-lg-page) is no larger than the configured huge page size (--with-lg-hugepage). ([49]@jasone) New features: * Implement optional per-CPU arena support; threads choose which arena to use based on current CPU rather than on fixed thread-->arena associations. ([59]@interwq) * Implement two-phase decay of unused dirty pages. Pages transition from dirty-->muzzy-->clean, where the first phase transition relies on madvise(... MADV_FREE) semantics, and the second phase transition discards pages such that they are replaced with demand-zeroed pages on next access. ([60]@jasone) * Increase decay time resolution from seconds to milliseconds. ([61]@jasone) * Implement opt-in per CPU background threads, and use them for asynchronous decay-driven unused dirty page purging. ([62]@interwq) * Add mutex profiling, which collects a variety of statistics useful for diagnosing overhead/contention issues. ([63]@interwq) * Add C++ new/delete operator bindings. ([64]@djwatson) * Support manually created arena destruction, such that all data and metadata are discarded. Add MALLCTL_ARENAS_DESTROYED for accessing merged stats associated with destroyed arenas. ([65]@jasone) * Add MALLCTL_ARENAS_ALL as a fixed index for use in accessing merged/destroyed arena statistics via mallctl. ([66]@jasone) * Add opt.abort_conf to optionally abort if invalid configuration options are detected during initialization. ([67]@interwq) * Add opt.stats_print_opts, so that e.g. JSON output can be selected for the stats dumped during exit if opt.stats_print is true. ([68]@jasone) * Add --with-version=VERSION for use when embedding jemalloc into another project's git repository. ([69]@jasone) * Add --disable-thp to support cross compiling. ([70]@jasone) * Add --with-lg-hugepage to support cross compiling. ([71]@jasone) * Add mallctl interfaces (various authors): + background_thread + opt.abort_conf + opt.retain + opt.percpu_arena + opt.background_thread + opt.{dirty,muzzy}_decay_ms + opt.stats_print_opts + arena.<i>.initialized + arena.<i>.destroy + arena.<i>.{dirty,muzzy}_decay_ms + arena.<i>.extent_hooks + arenas.{dirty,muzzy}_decay_ms + arenas.bin.<i>.slab_size + arenas.nlextents + arenas.lextent.<i>.size + arenas.create + stats.background_thread.{num_threads,num_runs,run_interval} + stats.mutexes.{ctl,background_thread,prof,reset}.{num_ops,num_ spin_acq,num_wait,max_wait_time,total_wait_time,max_num_thds,n um_owner_switch} + stats.arenas.<i>.{dirty,muzzy}_decay_ms + stats.arenas.<i>.uptime + stats.arenas.<i>.{pmuzzy,base,internal,resident} + stats.arenas.<i>.{dirty,muzzy}_{npurge,nmadvise,purged} + stats.arenas.<i>.bins.<j>.{nslabs,reslabs,curslabs} + stats.arenas.<i>.bins.<j>.mutex.{num_ops,num_spin_acq,num_wait ,max_wait_time,total_wait_time,max_num_thds,num_owner_switch} + stats.arenas.<i>.lextents.<j>.{nmalloc,ndalloc,nrequests,curle xtents} + stats.arenas.i.mutexes.{large,extent_avail,extents_dirty,exten ts_muzzy,extents_retained,decay_dirty,decay_muzzy,base,tcache_ list}.{num_ops,num_spin_acq,num_wait,max_wait_time,total_wait_ time,max_num_thds,num_owner_switch} Portability improvements: * Improve reentrant allocation support, such that deadlock is less likely if e.g. a system library call in turn allocates memory. ([72]@davidtgoldblatt, [73]@interwq) * Support static linking of jemalloc with glibc. ([74]@djwatson) Optimizations and refactors: * Organize virtual memory as "extents" of virtual memory pages, rather than as naturally aligned "chunks", and store all metadata in arbitrarily distant locations. This reduces virtual memory external fragmentation, and will interact better with huge pages (not yet explicitly supported). ([75]@jasone) * Fold large and huge size classes together; only small and large size classes remain. ([76]@jasone) * Unify the allocation paths, and merge most fast-path branching decisions. ([77]@davidtgoldblatt, [78]@interwq) * Embed per thread automatic tcache into thread-specific data, which reduces conditional branches and dereferences. Also reorganize tcache to increase fast-path data locality. ([79]@interwq) * Rewrite atomics to closely model the C11 API, convert various synchronization from mutex-based to atomic, and use the explicit memory ordering control to resolve various hypothetical races without increasing synchronization overhead. ([80]@davidtgoldblatt) * Extensively optimize rtree via various methods: + Add multiple layers of rtree lookup caching, since rtree lookups are now part of fast-path deallocation. ([81]@interwq) + Determine rtree layout at compile time. ([82]@jasone) + Make the tree shallower for common configurations. ([83]@jasone) + Embed the root node in the top-level rtree data structure, thus avoiding one level of indirection. ([84]@jasone) + Further specialize leaf elements as compared to internal node elements, and directly embed extent metadata needed for fast-path deallocation. ([85]@jasone) + Ignore leading always-zero address bits (architecture-specific). ([86]@jasone) * Reorganize headers (ongoing work) to make them hermetic, and disentangle various module dependencies. ([87]@davidtgoldblatt) * Convert various internal data structures such as size class metadata from boot-time-initialized to compile-time-initialized. Propagate resulting data structure simplifications, such as making arena metadata fixed-size. ([88]@jasone) * Simplify size class lookups when constrained to size classes that are multiples of the page size. This speeds lookups, but the primary benefit is complexity reduction in code that was the source of numerous regressions. ([89]@jasone) * Lock individual extents when possible for localized extent operations, rather than relying on a top-level arena lock. ([90]@davidtgoldblatt, [91]@jasone) * Use first fit layout policy instead of best fit, in order to improve packing. ([92]@jasone) * If munmap(2) is not in use, use an exponential series to grow each arena's virtual memory, so that the number of disjoint virtual memory mappings remains low. ([93]@jasone) * Implement per arena base allocators, so that arenas never share any virtual memory pages. ([94]@jasone) * Automatically generate private symbol name mangling macros. ([95]@jasone) Incompatible changes: * Replace chunk hooks with an expanded/normalized set of extent hooks. ([96]@jasone) * Remove ratio-based purging. ([97]@jasone) * Remove --disable-tcache. ([98]@jasone) * Remove --disable-tls. ([99]@jasone) * Remove --enable-ivsalloc. ([100]@jasone) * Remove --with-lg-size-class-group. ([101]@jasone) * Remove --with-lg-tiny-min. ([102]@jasone) * Remove --disable-cc-silence. ([103]@jasone) * Remove --enable-code-coverage. ([104]@jasone) * Remove --disable-munmap (replaced by opt.retain). ([105]@jasone) * Remove Valgrind support. ([106]@jasone) * Remove quarantine support. ([107]@jasone) * Remove redzone support. ([108]@jasone) * Remove mallctl interfaces (various authors): + config.munmap + config.tcache + config.tls + config.valgrind + opt.lg_chunk + opt.purge + opt.lg_dirty_mult + opt.decay_time + opt.quarantine + opt.redzone + opt.thp + arena.<i>.lg_dirty_mult + arena.<i>.decay_time + arena.<i>.chunk_hooks + arenas.initialized + arenas.lg_dirty_mult + arenas.decay_time + arenas.bin.<i>.run_size + arenas.nlruns + arenas.lrun.<i>.size + arenas.nhchunks + arenas.hchunk.<i>.size + arenas.extend + stats.cactive + stats.arenas.<i>.lg_dirty_mult + stats.arenas.<i>.decay_time + stats.arenas.<i>.metadata.{mapped,allocated} + stats.arenas.<i>.{npurge,nmadvise,purged} + stats.arenas.<i>.huge.{allocated,nmalloc,ndalloc,nrequests} + stats.arenas.<i>.bins.<j>.{nruns,reruns,curruns} + stats.arenas.<i>.lruns.<j>.{nmalloc,ndalloc,nrequests,curruns} + stats.arenas.<i>.hchunks.<j>.{nmalloc,ndalloc,nrequests,curhch unks} Bug fixes: * Improve interval-based profile dump triggering to dump only one profile when a single allocation's size exceeds the interval. ([109]@jasone) * Use prefixed function names (as controlled by --with-jemalloc-prefix) when pruning backtrace frames in jeprof. ([110]@jasone)
buildservice-autocommit
accepted
request 478563
from
Ismail Dönmez (namtrac)
(revision 52)
baserev update by copy to link target
Ismail Dönmez (namtrac)
committed
(revision 51)
- Update to version 4.5.0 New features: * Add --disable-thp and the opt.thp mallctl to provide opt-out mechanisms for transparent huge page integration. * Restructure *CFLAGS configuration, so that CFLAGS behaves typically, and EXTRA_CFLAGS provides a way to specify e.g. -Werror during building, but not during configuration. Bug fixes: * Fix DSS (sbrk(2)-based) allocation. This regression was first released in 4.3.0. * Handle race in per size class utilization computation. This functionality was first released in 4.0.0. * Fix lock order reversal during gdump. * Fix/refactor tcache synchronization. This regression was first released in 4.0.0. * Fix various JSON-formatted malloc_stats_print() bugs. This functionality was first released in 4.3.0. * Fix huge-aligned allocation. This regression was first released in 4.4.0. * When transparent huge page integration is enabled, detect what state pages start in according to the kernel's current operating mode, and only convert arena chunks to non-huge during purging if that is not their initial state. This functionality was first released in 4.4.0. * Fix lg_chunk clamping for the --enable-cache-oblivious --disable-fill case. This regression was first released in 4.0.0.
buildservice-autocommit
accepted
request 443696
from
Ismail Dönmez (namtrac)
(revision 50)
baserev update by copy to link target
Ismail Dönmez (namtrac)
committed
(revision 49)
- Update to version 4.4.0 Optimizations: * Add extent serial numbers and use them where appropriate as a sort key that is higher priority than address, so that the allocation policy prefers older extents. This tends to improve locality (decrease fragmentation) when memory grows downward. * Refactor madvise(2) configuration so that MADV_FREE is detected and utilized on Linux 4.5 and newer. * Mark partially purged arena chunks as non-huge-page. This improves interaction with Linux's transparent huge page functionality. Bug fixes: * Fix size class computations for edge conditions involving extremely large allocations. This regression was first released in 4.0.0. * Remove overly restrictive assertions related to the cactive statistic. This regression was first released in 4.1.0.
Displaying revisions 21 - 40 of 88