jemalloc-5.3.0-150600.15.4.1<>,f%p9|#/ߺs*4x5l(veeAj&']듙YlHYwaVˆM{Rf1+nPT &Юmk@ )q::+mN$Jl$8NXQ  NOjw7~OVOCBgiK߄6!y2`v@ga[Y!聣Y6,WW?eѷtj>>X?Hd   Y!BO e    6 <Tr(8 98 :w F|G|H}I},X}4Y}<\}d]}|^}b~c~dJeOfRlTuhvwxyzDCjemalloc5.3.0150600.15.4.1General-purpose scalable concurrent malloc implementationjemalloc is a general-purpose scalable concurrent malloc(3) implementation. This package provides a shell wrapper script to run programs using jemalloc.f%h03-ch2bySUSE Linux Enterprise 15SUSE LLC BSD-2-Clausehttps://www.suse.com/Development/Libraries/C and C++http://jemalloc.net/linuxx86_64 }ȼˢZA큤ffffffc20e4f484e32436b361564076e0dcf6f1ce550bd0330971892159d92eddd88dffef38c471df273fcdbcce07751439ba093c2c1b42507659e568e7c193e2687392f1ae67667f35570c537ce66e72bf1f6db22fd8308f908951d14ae0a1ae3d7c1f5df0d122566d6a6fef0fc4e6fc613d25e0690150963b793670fbf8e24e2ee2be20738736c956111cd9d164e072fdf0388e3742d24e87a93b9e4df1e4e7ca83erootrootrootrootrootrootrootrootrootrootrootrootjemalloc-5.3.0-150600.15.4.1.src.rpmjemallocjemalloc(x86-64)@@    /bin/sh/usr/bin/envlibjemalloc2rpmlib(CompressedFileNames)rpmlib(FileDigests)rpmlib(PayloadFilesHavePrefix)rpmlib(PayloadIsXz)5.3.03.0.4-14.6.0-14.0-15.2-14.14.3fbu bUib_@__]Ik\O\\\@[G[i@[}P@Z4@Z~Y@Y@Y@X•@XD@X!@XWYZ@W5W)@Wo@V2Vl@V+rV7@meissner@suse.comjengelh@inai.demliska@suse.czguillaume.gardet@opensuse.orgmliska@suse.czmliska@suse.czguillaume.gardet@opensuse.orgmliska@suse.czmliska@suse.czjengelh@inai.demliska@suse.czmliska@suse.cznormand@linux.vnet.ibm.commmanu84@outlook.deguillaume.gardet@opensuse.orgmliska@suse.czguillaume@opensuse.orgmliska@suse.czmliska@suse.czmliska@suse.czidonmez@suse.comidonmez@suse.comidonmez@suse.comidonmez@suse.comidonmez@suse.comidonmez@suse.comidonmez@suse.comjslaby@suse.comidonmez@suse.comolaf@aepfle.deidonmez@suse.comidonmez@suse.com- reenable static flavor- Update to release 5.3.0 * Added the thread.idle mallctl which hints that the calling thread will be idle for a nontrivial period of time. * Allow small size classes to be the maximum size class to cache in the thread-specific cache, through the opt.[lg_]tcache_max option. * Make the behavior of realloc(ptr, 0) configurable with opt.zero_realloc. * Support C++17 over-aligned allocation. * Add the thread.peak mallctl for approximate per-thread peak memory tracking. * Add high resolution timestamp support for profiling. - Drop use-volatile-to-workaround-buffer-overflow-false-pos.patch (merged)- Add use-volatile-to-workaround-buffer-overflow-false-pos.patch upstream patch that supports -D_FORTIFY_SOURCE=3.- Set lg-page to 2^16 on aarch64 to be compatible with 64k page size kernel - https://github.com/jemalloc/jemalloc/pull/769- Enable LTO as it works (boo#1133136).- Simplify spec file.- Re-enable profiling on armv6/armv7 since boo#1105633 is fixed- Update to version 5.2.1: * Bug fixes: * Fix a severe virtual memory leak on Windows. This regression was first released in 5.0.0. * Fix size 0 handling in posix_memalign(). This regression was first released in 5.2.0. * Fix the prof_log unit test which may observe unexpected backtraces from compiler optimizations. The test was first added in 5.2.0. * Fix the declaration of the extent_avail tree. This regression was first released in 5.1.0. * Fix an incorrect reference in jeprof. This functionality was first released in 3.0.0. * Fix an assertion on the deallocation fast-path. This regression was first released in 5.2.0. * Fix the TLS_MODEL attribute in headers. This regression was first released in 5.0.0. * Optimizations and refactors: * Implement opt.retain on Windows and enable by default on 64-bit. * Optimize away a branch on the operator delete path. * Add format annotation to the format generator function. * Refactor and improve the size class header generation. * Remove best fit. * Avoid blocking on background thread locks for stats. - Remove disable-test_prof_log_many_traces-test.patch.- Disable LTO (boo#1133136).- Drop static library package, nothing seems to use it. - Remove openSUSE 11.1 build support.- 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. * Add extents usage information to stats. * Log time information for sampled allocations. * Support 0 size in sdallocx. * Output rate for certain counters in malloc_stats. * Add mallctl interfaces: * opt.oversize_threshold * stats.arenas..extent_avail * stats.arenas..extents..n{dirty,muzzy,retained} * stats.arenas..extents..{dirty,muzzy,retained}_bytes * Optimizations and refactors: * Refactor the TSD module. * 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. * Improve error handling for THP state initialization. * Refactor and optimize the tcache fill / flush paths. * Optimize sync / lwsync on PowerPC. * Bypass extent_dalloc() when retain is enabled. * Lower the default number of background threads to 4 (when the feature is enabled). * Use arena index for arena-matching checks. * Avoid forced decay on thread termination when using background threads. * Disable muzzy decay by default. * Only initialize libgcc unwinder when profiling is enabled. * Bug fixes: * Fix background thread index issues with max_background_threads. * Fix stats output for opt.lg_extent_max_active_fit. * Properly trigger decay on tcache destroy. * Detect whether explicit extent zero out is necessary with huge pages or custom extent hooks, which may change the purge semantics. * 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. * Fix a missing unlock on extent register error handling. * Incompatible changes: * Remove --with-lg-page-sizes. - Change URL of the project.- Disable profiling on ppc until boo#1105633 get fixed- Disable profiling on armv6 until boo#1105633 get fixed- Disable profiling on armv7 until boo#1105633 get fixed- 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..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) * Set name mangling script in strict mode. (@nicolov) * Avoid MADV_HUGEPAGE on ARM. (@marxin) * Modify configure to determine return value of strerror_r. (@davidtgoldblatt, @cferris1000) * Make sure CXXFLAGS is tested with CPP compiler. (@nehaljwani) * Fix 32-bit build on MSVC. (@rustyx) * Fix external symbol on MSVC. (@maksqwe) * Avoid a printf format specifier warning. (@jasone) * Add configure option --disable-initial-exec-tls which can allow jemalloc to be dynamically loaded after program startup. (@davidtgoldblatt, @KenMacD) * AArch64: Add ILP32 support. (@cmuellner) * Add --with-lg-vaddr configure option to support cross compiling. (@cmuellner, @davidtgoldblatt) Optimizations and refactors: * Improve active extent fit with extent_max_active_fit. This considerably reduces fragmentation over time and improves virtual memory and metadata usage. (@davidtgoldblatt, @interwq) * Eagerly coalesce large extents to reduce fragmentation. (@interwq) * sdallocx: only read size info when page aligned (i.e. possibly sampled), which speeds up the sized deallocation path significantly. (@interwq) * Avoid attempting new mappings for in place expansion with retain, since it rarely succeeds in practice and causes high overhead. (@interwq) * Refactor OOM handling in newImpl. (@wqfish) * Add internal fine-grained logging functionality for debugging use. (@davidtgoldblatt) * Refactor arena / tcache interactions. (@davidtgoldblatt) * Refactor extent management with dumpable flag. (@davidtgoldblatt) * Add runtime detection of lazy purging. (@interwq) * Use pairing heap instead of red-black tree for extents_avail. (@djwatson) * Use sysctl on startup in FreeBSD. (@trasz) * Use thread local prng state instead of atomic. (@djwatson) * Make decay to always purge one more extent than before, because in practice large extents are usually the ones that cross the decay threshold. Purging the additional extent helps save memory as well as reduce VM fragmentation. (@interwq) * Fast division by dynamic values. (@davidtgoldblatt) * Improve the fit for aligned allocation. (@interwq, @edwinsmith) * Refactor extent_t bitpacking. (@rkmisra) * Optimize the generated assembly for ticker operations. (@davidtgoldblatt) * Convert stats printing to use a structured text emitter. (@davidtgoldblatt) * Remove preserve_lru feature for extents management. (@djwatson) * Consolidate two memory loads into one on the fast deallocation path. (@davidtgoldblatt, @interwq) Bug fixes (most of the issues are only relevant to jemalloc 5.0): * Fix deadlock with multithreaded fork in OS X. (@davidtgoldblatt) * Validate returned file descriptor before use. (@zonyitoo) * Fix a few background thread initialization and shutdown issues. (@interwq) * Fix an extent coalesce + decay race by taking both coalescing extents off the LRU list. (@interwq) * Fix potentially unbound increase during decay, caused by one thread keep stashing memory to purge while other threads generating new pages. The number of pages to purge is checked to prevent this. (@interwq) * Fix a FreeBSD bootstrap assertion. (@strejda, @interwq) * Handle 32 bit mutex counters. (@rkmisra) * Fix a indexing bug when creating background threads. (@davidtgoldblatt, @binliu19) * Fix arguments passed to extent_init. (@yuleniwo, @interwq) * Fix addresses used for ordering mutexes. (@rkmisra) * Fix abort_conf processing during bootstrap. (@interwq) * Fix include path order for out-of-tree builds. (@cmuellner) Incompatible changes: * Remove --disable-thp. (@interwq) * Remove mallctl interfaces: * config.thp (@interwq) Documentation: * Add TUNING.md. (@interwq, @davidtgoldblatt, @djwatson)- Disable THP for ARM (32 bits). This fix build by passing all tests successfully- Add 0001-ARM-Don-t-extend-bit-LG_VADDR-to-compute-high-addres.patch: fixes #979.- Add 0001-remove-CPU_SPINWAIT.patch: 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..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..initialized + arena..destroy + arena..{dirty,muzzy}_decay_ms + arena..extent_hooks + arenas.{dirty,muzzy}_decay_ms + arenas.bin..slab_size + arenas.nlextents + arenas.lextent..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..{dirty,muzzy}_decay_ms + stats.arenas..uptime + stats.arenas..{pmuzzy,base,internal,resident} + stats.arenas..{dirty,muzzy}_{npurge,nmadvise,purged} + stats.arenas..bins..{nslabs,reslabs,curslabs} + stats.arenas..bins..mutex.{num_ops,num_spin_acq,num_wait ,max_wait_time,total_wait_time,max_num_thds,num_owner_switch} + stats.arenas..lextents..{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..lg_dirty_mult + arena..decay_time + arena..chunk_hooks + arenas.initialized + arenas.lg_dirty_mult + arenas.decay_time + arenas.bin..run_size + arenas.nlruns + arenas.lrun..size + arenas.nhchunks + arenas.hchunk..size + arenas.extend + stats.cactive + stats.arenas..lg_dirty_mult + stats.arenas..decay_time + stats.arenas..metadata.{mapped,allocated} + stats.arenas..{npurge,nmadvise,purged} + stats.arenas..huge.{allocated,nmalloc,ndalloc,nrequests} + stats.arenas..bins..{nruns,reruns,curruns} + stats.arenas..lruns..{nmalloc,ndalloc,nrequests,curruns} + stats.arenas..hchunks..{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)- 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.- 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.- Update to version 4.3.1 * Fix a severe virtual memory leak. This regression was first released in 4.3.0.- Update to version 4.3.0 New features: * Add "J" (JSON) support to malloc_stats_print(). * Add Cray compiler support. Optimizations: * Add/use adaptive spinning for bootstrapping and radix tree node initialization. Bugfixes: * Fix large allocation to search starting in the optimal size class heap, which can substantially reduce virtual memory churn and fragmentation. This regression was first released in 4.0.0. * Fix stats.arenas..nthreads accounting. * Fix and simplify decay-based purging. * Make DSS (sbrk(2)-related) operations lockless, which resolves potential deadlocks during thread exit. * Fix over-sized allocation of radix tree leaf nodes. * Fix over-sized allocation of arena_t (plus associated stats) data structures. * Fix EXTRA_CFLAGS to not affect configuration. * Fix a Valgrind integration bug. * Disallow 0x5a junk filling when running in Valgrind. * Fix a file descriptor leak on Linux. This regression was first released in 4.2.0. * Fix static linking of jemalloc with glibc. * Use syscall(2) rather than {open,read,close}(2) during boot on Linux. This works around other libraries' system call wrappers performing reentrant allocation. * Fix OS X default zone replacement to work with OS X 10.12. * Fix cached memory management to avoid needless commit/decommit operations during purging, which resolves permanent virtual memory map fragmentation issues on Windows. * Fix TSD fetches to avoid (recursive) allocation. This is relevant to non-TLS and Windows configurations. * Fix malloc_conf overriding to work on Windows. * Forcibly disable lazy-lock on Windows (was forcibly *enabled*).- Update to version 4.2.1 * Fix bootstrapping issues for configurations that require allocation during tsd initialization (e.g. --disable-tls). * Fix gettimeofday() version of nstime_update(). * Fix Valgrind regressions in calloc() and chunk_alloc_wrapper(). * Fix potential VM map fragmentation regression. * Fix opt_zero-triggered in-place huge reallocation zeroing. * Fix heap profiling context leaks in reallocation edge cases.- Update to version 4.2.0 * Add the arena..reset mallctl, which makes it possible to discard all of an arena's allocations in a single operation. * Add the stats.retained and stats.arenas..retained statistics. * Add the --with-version configure option. * Support --with-lg-page values larger than actual page size. * Use pairing heaps rather than red-black trees for various hot data structures. * Streamline fast paths of rtree operations. * Optimize the fast paths of calloc() and [m,d,sd]allocx(). * Decommit unused virtual memory if the OS does not overcommit. * Specify MAP_NORESERVE on Linux if [heuristic] overcommit is active, in order to avoid unfortunate interactions during fork(2). * Fix chunk accounting related to triggering gdump profiles. * Link against librt for clock_gettime(2) if glibc < 2.17. * Scale leak report summary according to sampling probability.- Update to version 4.1.1 * Fix hashing functions to avoid unaligned memory accesses (and resulting crashes). This is relevant at least to some ARM-based platforms. * Fix fork()-related lock rank ordering reversals. These reversals were unlikely to cause deadlocks in practice except when heap profiling was enabled and active. * Fix various chunk leaks in OOM code paths. * Fix malloc_stats_print() to print opt.narenas correctly. * Fix a variety of test failures that were due to test fragility rather than core bugs. - Remove disable_oom_test.patch, fixed upstream. - Run testsuite in parallel where possible- add disable_oom_test.patch- Update to version 4.1.0 New features: * Implement decay-based unused dirty page purging, a major optimization with mallctl API impact. This is an alternative to the existing ratio-based unused dirty page purging, and is intended to eventually become the sole purging mechanism. New mallctls: + opt.purge + opt.decay_time + arena..decay + arena..decay_time + arenas.decay_time + stats.arenas..decay_time * Add --with-malloc-conf, which makes it possible to embed a default options string during configuration. This was motivated by the desire to specify - -with-malloc-conf=purge:decay , since the default must remain purge:ratio until the 5.0.0 release. * Make *allocx() size class overflow behavior defined. The maximum size class is now less thanPTRDIFF_MAX to protect applications against numerical overflow, and all allocation functions are guaranteed to indicate errors rather than potentially crashing if the request size exceeds the maximum size class. * jeprof: + Add raw heap profile support. + Add --retain and --exclude for backtrace symbol filtering. Optimizations: * Optimize the fast path to combine various bootstrapping and configuration checks and execute more streamlined code in the common case. * Use linear scan for small bitmaps (used for small object tracking). In addition to speeding up bitmap operations on 64-bit systems, this reduces allocator metadata overhead by approximately 0.2%. * Separate arena_avail trees, which substantially speeds up run tree operations. * Use memoization (boot-time-computed table) for run quantization. Separate arena_avail trees reduced the importance of this optimization. * Attempt mmap-based in-place huge reallocation. This can dramatically speed up incremental huge reallocation. Incompatible changes: * Make opt.narenas unsigned rather than size_t. Bug fixes: * Fix stats.cactive accounting regression. * Handle unaligned keys in hash(). This caused problems for some ARM systems. * Refactor arenas array. In addition to fixing a fork-related deadlock, this makes arena lookups faster and simpler. * Move retained memory allocation out of the default chunk allocation function, to a location that gets executed even if the application installs a custom chunk allocation function. This resolves a virtual memory leak. * Fix a potential tsd cleanup leak. * Fix run quantization. In practice this bug had no impact unless applications requested memory with alignment exceeding one page. * Fix LinuxThreads-specific bootstrapping deadlock. (Cosmin Paraschiv) * jeprof: + Don't discard curl options if timeout is not defined. (@djwatson) + Detect failed profile fetches. (@djwatson) * Fix stats.arenas..{dss,lg_dirty_mult,decay_time,pactive,pdirty} for --disable-stats case.- Fix build/test in SLE_11 by using gcc48- Update to version 4.0.4 * Fix xallocx(..., MALLOCX_ZERO to zero the last full trailing page of large allocations that have been randomly assigned an offset of 0 when --enable-cache-oblivious configure option is enabled.- Update to version 4.0.3 * See included ChangeLog for complete changes.h03-ch2b 17261343095.3.0-150600.15.4.15.3.0-150600.15.4.1jemalloc-configjemalloc.shjeprofjemallocjemalloc.htmljemalloc.3.gz/usr/bin//usr/share/doc/packages//usr/share/doc/packages/jemalloc//usr/share/man/man3/-fmessage-length=0 -grecord-gcc-switches -O2 -Wall -D_FORTIFY_SOURCE=2 -fstack-protector-strong -funwind-tables -fasynchronous-unwind-tables -fstack-clash-protection -gobs://build.suse.de/SUSE:Maintenance:35607/SUSE_SLE-15-SP6_Update/aff25b9cd13e6816e486d395c97cebba-jemalloc.SUSE_SLE-15-SP6_Updatedrpmxz5x86_64-suse-linuxPOSIX shell script, ASCII text executable, with very long linesPOSIX shell script, ASCII text executablePerl script text executabledirectoryXML 1.0 document, UTF-8 Unicode text, with very long linesC source, ASCII text, with very long lines (gzip compressed data, max compression, from Unix)RRR%l&D_9utf-82c69625f4d84f3f83ee3eec446745a14828c8074a340676fe4b34648bcd41a85? 7zXZ !t/࿓~]"k%Y|~Μ hNܙӜXh&_Uh5e%D}3avq@r{H Ȳ@ډAk;&{ӜɮuZ)QV >Jr/BP8">!bɱNԋ0 |H}.>.'MY+pL dɔE_v@foG-xH`٫wP1XyO518C7cF쭟A[j_4%ߨ&]iP;042QE-Qeq6Y U)9Jt|E\H cwwI{uPT]499S@\Խܛ` Ƌ&QI]ylvY-&Xݽmtw6G 玻|[!._ߜtvIy4 0ĨppHpYDu̕1-Y$QǑ8U*qB nM5^NaֺzrnBnFYӆ=b,,]v6=K= 9ۼ她^ћE6cpPr<>rXS+N҉6o,p(L`J7&0E8 n J]l]]{Q0dzk*Yh Eal#-yfԊ%@>37z#\[wb̝9Rdeo|.eP"F%L^V\6:k?[КZ?<;]E,z (v}W !F r6Oc-y řjzɌ_sZN }C)Pbmު%n? V"%S>8L˿RSNGI9R=ɉ|EZ=Si/#/02gbawJ% Od"x<SfZӢBT x a;+t:cCXw\s;iDA2A=dAʕ9y7U+AO{Cpu6دJ sI@vWUTl%nko;4XX~ޠ|[pF5MnH0X_ٻ &*pDI0L:! ؞Vv19VSJ)FCr-+pz|{%z \ѡ!׮F9nK$ܩ:8wV|_ɟʵE`ӝҫL:OKa07N*Ddf*Lm#(ط CQ#Cmj4*j>4>VvzSlE&ʰq9XFxTy4Ff`WM,ղfsMOs( ߍ27_Sh:<5 }5sq݀ծ%y03H'=`OqeNZCmPcfVKfD5mr Hpmřѫh@ q:w[v|-j"ܽNpVDm<3u,R kەJmRgwSݔE[ۑ8/w,6ݵ[5͢%M[zߕ}RL8vF^ͅ˱  q1AڗLSũ{:KR`AsDz`Raк1U/H] m6*0Qksw6hD4sfA G#>h[ʾuv^oB.)J\. ]*q`c(n !u4L4ϢJV輸&yٻBOLƯ*[3ɢZxxFÈUޟ_B(㠴Uy{N?pO2r,$QYq fKDWL6t,:dC'͎O#; -|`MX<υ*E\>ˑ}JK R3!W=iGc,Łq0kEps뿋ǵ|@I1qDr*.hb}rf&7aGA`xG>iyo,}}e!60izI!L 'SN&PsX"A)t1jT9A[iZLB;kY㑱EځPNe B!XY}JablZal:e/_Vh-qτr.o$UZ8y!yEqɃY|TYP2. %P->,z8+6D{d=N#A|MJu2Nٺp񱐻 %ڇy^Zw%̓Kaj{nG#5+uU)-\eBs}]Y AHx=}Fyvە.[c*| e V ˊ> - H4M ,T[gXuOH8-AMH17y_;QJ8n15sNˑ|t||5g89o|R c欦?ra42K "N< ݪ' r$J''BCUg!rh稤J#KD#HܮD)KٝbBmc#w? Nz2tC.MY?,jGQ\="a_|fEs z2W_&8ڏ%בjK], Ff0@;D]?ES6VwiTv h3|hVw7סїdh:K!Y̤>=KWE$0dVn_R׈9{ayd0=acJyUdy: [YE i,RVUQzE=/:k,ѿcr* z/pjc~ ]fPڶ; 1=fˈCSF\2BO!עK(bRS~pSׁ_ 7tqLທQ] \": Pp`NXC]jfL<ᅻ3 v9n6/ D؟+`o^"X]Vɓ#c (RX+\0F $Y3w Sػw/TST[pާF\_,%-ݠsC-œr})G5>˺JN@k1ghmrV˧Jb|2=w3$yyوŇPfqlVv|UqR~xwAS33(>giopT|+.3{_0>;,ꩃ2Kr4o18uY3Ew̛,sb6PO (I#׋:s+96܍l!S0>&&𪉒ajP󹚮IzRd)NsCc10J,Y^%'޾K԰ g2|{KϏ,b ׃IB" p~=SVO7(/D Dj|G@c7D0"=eI@)benSǎ= RM3CR<گ3ndQBncU|c’ IXqix$kE+7 :BI{SXSݏ~;<4FA,^iEl1U;@xpkE-Ѻ/^Ʉ %0?[âƧ>Ф8eؕ炟tG&aC^Wșe9%,u`"ntpPotY1qHPGȽL!a9̭0Jﻇ[uVN֫  H`V¤bl:' eS"Q:ۺfw5ǠV(s 54+ F.T h3#AeC(VR-Hfocunx7 *<@^JBr 6H ^1zU0hI1[!:o*ޚgi ْ4#*Wt3Hk3v9Rkp͠7ssZQ~e|@젍D>Gt(ӄ(C9?|")- [wnżF]:EOn@t+4,+%C/h:^Sl ,L_A(ɽOr]tAXbk^6 ۿ?Ue?3SOroga"S9[GQ;0Ff#%n1߃ۢ. MZ)g%"mhكЪD^yaW:SG vǭ9L9rBAɡB.}O`ll(BW?YuLT'c)lrw[/nݢ`-wk,Z 7PxTU Q4vjPqԧ˗^U~=B#]:ck1<|_&oh#%ĔxO)+xRtxᷔ2ZO`Lxue(/Pz_r0'r@ZLu4P= |m+Inˣ%V2 G Lmu䮲(b~i1Nݣy\Z©7T+COCy$j^mS ХF¿+{CXElacB<ߊj|;Qm{x"1ɴl9IxhPbZ&ӑV,8| yKY4Roj'4ڃc+M&'@$%(ksNvOdREe(4qٹ~ *0QmQ -jwR[wDI4:qXj픆8&[W8Z'./Ru=*Lwzf4TzVxƃS:qz4%H!MGscFo`bPaXA݊JEoUQ5Qhck '7E^KsX{3{:z'7iOWX , ?ip4sk\ X*n? -4|C#Rō s<E_KJjq57Gm]97J5{_b"'8]cXB3iUEİTiJx !O('# 2Y(*a癶.uLr? wN”1Q~mxhKPgP`33V8f qA:WnUN/1#7*9t} h$ՄX5|ΉȗHۻ\`FB|JX :Ȱty;Jf)k;lrq^%xoD} Vx@+|6S~zE2Í%;;W0 <$'#{Yv/ َ /zjdT5P\GǷ+ܳ-#Q mkU|\:. :<*2tqQ튿1ʤ6e9W-'c6 ˌIv/&ᜈ$3yC.;tׄ /۷_.87"q.h m$߀suUF#X!f7^gȯ SZS>8>{ny<P:X3jj:@ Mg::**Kf[["s&V.f}9).2OYEbLBi>_dzfn%XT !qaOtŮ:t|!6ap2] ^/skv3zŀ(ŠVc}czUAqc zv@@Y gǯ a6&\zpmd-]f@q`pfYr)WrjަS7H^W,zfoZ@qkuz  G?Jx_Y  rQE31s?WE VP]ԡ: 5i96Δψ0 ^.p74n4tH#v y%>0C  㞈=KC(S"7XN W1Ii:?_4cSXAML&la=PAN8K@+tF[ٯ*-B 'f H*嘷R:3 rq4hڥ$c;\PnAq/oqZmb8emA~ڈ67'AH*6἞5{j}#j9d|Atb蓼GlN-X.ĭ.qNV2:XգRrr'X~% #T":õ# .2|yR[OzO A`鄖O%B*3NZ>fnMjbQ֧\+Ndc1őqHoKl4pi_&yx[O\Bbu;(3FdGDAP,^AQ |6A`qۣr4>y׵jBeйv]fKBmlͣ'70߭I0"y]*xX03M('զ9^1PՈCQpCɱ;h 9R`ZqӌtxQ+A1Grz0ˢ7H ZY2Tku_Y,+t٪^*fsخ^QA,̛|yy)y 9 d6$C#Ğhpx:Ů9p&GZ9^Ame|5N,M>a7CjA^ HP^*ˌ=^ j@qV!'>gϞo;Eҭe \N [;pC/~!u)l} ʏv?^vA)W/ݷd)Tq몣qӣ3DjTĥG Ft Шw$`>WA5s$+`' dH[SnBW6_"oJqyc*zq|rF( cJΣg Qh+T@Qx Vh/}Ь&QLձ;'sM~ QxRTbe".c UЊ=P>#!-w2͵/ȇk~L2閪oB>ܹ]iC]I>Tn!CU&i}Z)zHCAh,4ƐY_X#JLnDve ԥ,L(UGiL7Se -Y&zt.8)P)p*uzRnrI%?PdA@<^2AJZ <}iz*EM5Z~<2͌'ux33M`UP 4}~obM^ oR:fe*G^? ]𤖦L&=|ݶk8h\~cd?;1h{[nc0 =J-hJ!on8}~F2n83ELÊ!6O,b)6KM*6*TQzR-D 0y/6O,J #QDKF)^STNָ0s#WJs,} V$tr ~9qcvUcZ1#W1CJ}[%fі"̊vx+}Nk8jE\EvxGmpF ~4cf$UzPQ,Nm{@Q3T*ĭ(5$<[2{:fn$;m7A++aF71E73¥BJ[3wODL IL1# (5U$6aT; <~hcJbu^)+Edy\vZ.)Y%#UrBq9MK/Eg3't߲:uUކfoDFDHfUhN}8N ],)Z'}8F|kPdQv4/ɲ69ۥ>XVs(V$D 8 W*d&hI}lR^ON2@/w L u.ئ-;gbY2wMbAGX~>lXhiʈ?SF*e5BMdžaviwlG6(g%.9uxDQS>Vv`)thzDGNa60ৎttEU9˰™"I9DQ vs@t(@nYpX~gȌ/O8nuu$n}?jm瀧S= F"AYբ :M4=3F.;3BK #}؃w\$'/?I6Kreϓ1\tfnJ}v_JtߜAYm-0-Rfϰ_AS)s_F:]م7g4zƍ;bf-K!9;W-{7yФWm:Iwi5s/f&Lz:p\oRijPG<@Ru6vȉ r6 { S\iƫȳ%cay3G1axID 8m䮟'<:åɞdRۼHiS塺;is l.;o} q)$l,7_"IS|Oq6T|6-eHXǸwxhA@64E f$ѳkQ.R(#FVa9#<#+A>UpJ#tfjB\YK/!`El#Q3V*;UgH0Ь++bAQ{hxE -*sz6(SP3U#|r`iJ3!8 ' \)8Oݙp+W)H;q&K!`g1<v(@ed M`о\=2٨pB6'UR%> 籹G90-׏Թ[ Wd & 'kB\ࡂ ߑ[bjd~'~6&.ү'0Ljauk7{zpQ"u$o)ǐ5r>\f@hlT~;`,j$)&|WOA*J԰)W -v:QB+Տ* Z2BS+IN}a=1!c\hBIL5\VAo,!g4EKw2Tx^ q(odSD$w\Gw@T[z&!t8CТe̵!q*ZLV0 :BJ=H9İ, 1<6JmzN[G{Pp{1餭.~tY߶FŲ"drbb<Ut.FI'dSG|&+ H?BՇS}iHT h>3_|qH(喙qy)Z/lh!)߻oS]+BkVh̞'w^Lʔ1t  (2, /T=ti>-cp . ѕ&[lLzuڝB|#J .\P,*ƯBJ< ~rlpCEӽ>&SgHľRI|1d*k ;3ؠ+2 oFVS Qv0C\? N$`ɝ8ȮYib䩃eM>k7җre k^\6ùf9Մ;BOﳕk:І̞պz7FqDm;m] QhY!=w8$} /LEhY?}+ j|a\CG-_kX_Ґ: oTWH7R-V)g)&YL*m ghϸ7^'WaOUt zCKׁ,#z** Ca4V+T-=ƔTAmY1_My&=Ng66;դ6 h7_;'PIJRy%Ĥ5١wPaqTTt/SNKJw_k(eyj2 '+"$B@P"r=F.w&C+wS屙`} d.G@h.Ay0`Um ?LhS0]slRꗚc%XSk#G*9u;jM#&5l¯+s2:4̦bq{ xș6~⨛Kdc>Ag>IV-FToRz)_[h_y:1{=(V+q?kqR N]:jv5)}yl ?{}cF7G\Snv&fD a(k(L!zu%,׌?m#6#{݈ =Ylsr|IbQJ>]%[[WʧEeZ }I$/*}XfrPH^vXnKn6$B bǃ*see]aEAˀʡXf³/߰ޟ^QyFb^np0SzJ*Vs257~ڲ9P&fm#dMhm)hho`(e f*Mzz-ƛ#dm10vVRǀq qAdvf1HύOB?ek~IMLݍ3gKR>|cXq:N|zhtTMaEn$6Lߕm`PU}o)AM׾= <>N f;v_͸pa`zzb+5oSBtQȽ׫RΗ8$ȃək* 1ܬX/*VĜ[ʓ $&[`h]cհj'E^7Dvnqe ނbޱxD0_9ndDkv4z/.RZ%kW>LP4fa!I5#1Z:-_Nl;sh7݌|gn{vhTbS1ۤd.y"T`߳*[~< w\UN%;ErO`q8I6 E+5h%c s܅1%S?Cf̰K"3:sB>h̨_{A @L" zďy>LFC(($S턨[¦L?G10jĹIP.t"QIlqm3=1ޥړ)A*)Mu *% 4Jx)8 )9.h.gs{!];Wh=X k8x VUcg#:>63w_d<̏Iگx'wm*ƺ2#K0;n@%J畢e-pjg~.'xo뻛$v=a[1[&9SiJ;Ezx> xz޴H:V;M OKEtopҖ$N8x{sb ~psz*ha0zI OxCw°zaYJ݉[HGU;'ty'uq[U3$+7fCH3L!B(3b&^$\cKȃڟx,SmP xLNvX0J{PNڞ4%[Co;6d@"*yxv_\@ s'.Ն%"ZQgsr* 6la 'ک:2X66EB,ܶ P;k= Ri9GLJ: $j1p\_Xr]5DWT)Sѿ# H܈zalۑ r  6;ULw..d+7Q9 aLƬ7#PMd2'z48g gjNvE #3*ϥV螮+BJ \O5҈#d$Y6YvCը|v4''gy͢QvUXTQA7 |7ѣ>UFyְx' kG;#>-0TnB#=7+l 1i!MXi{SZ)3,jR/+RYԢn@|l\>{']_u@+n͹~Whs4Zs79"]##aԄrtsӍ=` v)820-v[듫H# h+Bo`imr BHVܒh PӴE+32u:G7H/hFUruR}@#ak*GwL}0}xEq&7\>:pY9>vF7 tt$6!\SPp8g{yN/焷BPȕιp4Ϊy+tǙ,^tYjo$bp"v3ݏǑax7?0yw㛸oe9"1 :JW hD$,12' I[J m_Vm.OaW`YվVhqUٖ:x;1Qg5Yif\C7a^cS.3J'̝øQ1זohʅ\a;_#Yo=8$sM\g#*lzsfѡ@-Ԉ{$pe?A :<My}i]eb֟2WZTUtwa:ڐmIf{KK[p#=3K{J*)KܔrbhH(6]|Tkl1d]#L=!n\n OUgkWA(qL$B@WfViZ{vX1H''":b2xO{I_Tdhnbd(8yWa-ߔ/ٮ iNR._!$xqG!z&/5l=zl|wR2_-@.%#%Vnm!U96>Bq>vBjZK?“Ά 5o<gR}5vv^''-B&[˓ Л?p}3OW*w4 7V:,L4#,xY"kKף+eVV_np_|Ol\V[3?O7Ub$#ks H۳b)nuMxmv3]O d}=kY . =^m+( t?zC9btkd}AwmH(C&&>'ab係؋;YB#TV }H*iu*[\Zqa7޲$Ir6I4{,2OFIl[o_'8, Ȼu ÎF\eӬvO0HĻb^ФX2YM7тVރ,o I}v~M!A| q *E AY̓st%6xI#ɱ8euam' V& TMO{2OY,u ȬtCb`ƚDB !Qgr ~Q.wQ#r( ?eX[MEKBTo®sС'l暕XsbEwQ7 (K]w0ρ;E{.\K&Kj猂Y1j-'sл<+K|p+h 2 `+tׂ]ɍ2EOǀr=F*BL^b}CJnӥ6Z)Q2M\Rf& ]͘w O{R@ZWTfȪ)&We}5p^wXb `*ii`2^oFgDo={xqcfpnX2DPO"-Pd~?Z5(puAX9ӭ}5'VqE~}{E8)T.jwQj7 ):Ч)Hu)ɽ'r|f006j]բ_#hb.WR"i/(G] 7"@8ܒF?("_m!?+'p@,m33:6^˭$)=,F,B=r_9kO«oy*et56-_dtV>#LV5'06~!Z+aOC8_WʵHVQo g<7P-2Nu*<~ٍiJ@ 6(ΤDjij%e+s}/ح} xoF*^1?Yikc-31 冖 iHm]K %̜"|L%iL2o$_i@!wI6w4dk-a>#uͳ:[35Ă \HI1:/GSc3 eb4%^\/.y2* ̀Ieѡ6" QmTUV4#3>x.g-|*$8Ȩ·RNckXf}146wIU/M1h4z#݋CH58EgԵ<3Q1}]Y%--%J 1^r:htl^(,Rϐ :VT 6Z!ώ!̨R>1Nt_|ǶܚuN8$=G>TxռDJ,~-^Y5TnƸ#:dꉖOVP.e[9Uaec]纑ٓ 4'#76Yb򘎎gGڜ5so%NgZд>d,W9)i^:6W sV ."}s1=N,H"+(1ixC durSeT gNAΥĺcKwjFQ/wNAfE[I著 !_;ڑ ӥ.kN=?knZ즓*`d͔3j{?̺%¨uدo)O' >M`_fCF8~UAއl 2}J.a1Hx ^&f`DUq\- ۋ8$b;PMdvE$|psVX{UKzGuD:w을g&&uUP{sDȱViFh6AЁ^]8V` ~ĩ|9C`ٕ<%tx~[:~dbn -ZKb"@*d(\D˭i,:ri7Cq7kerTVc"yPM8ǫJ*yg]F2pC [%X2Kh6~|/h[j4o۾ -=̝II!320J|L((8A<dJ:W ŚNX_H?3ol=I昔i{ߚaƽ0eojק־= '*u1*.n}2=}mo~1U~ԱM+ƟyoAiv`iF~ɧ!ՕluKJWE~D6xT`:P{y&Tdm׻Gܽ ݽ%I<.:⨎41Y$ypo% b^U_a`ݧ7yԶ}փ*0h~?+97hʾ0Mþg:Vµe(SU LॎX1Rz[MHn9Fט'8Sw9$5&Jm{yh_ :X67խ?<^o5cB]lIEov=!s!E7 }zeE4e 0qPT n ΒFɘZ:W[j{(z̙V bIZW,S $j\:HXaw`4"jWؤSQt;HfNCm!'1aCaIb+?xۧmTK)YpKsB #Ew@,WRN2NBs4Ro0DȦ崼5ڹvkЃcί$iSW,BJvb̪7јʉ!nu>''$ݏz~[ 1+^ض_TЯHOS"V'2;;厾 yI736C`Ocqi*P %!%} W p!Ky !^dF[V)E oRWk=M*HH'´0,ʝ']=nV?Kb~5}]#vp(ma :S} :-=^e}4AoY~k,iU+rܷ1rqދ6q*Bu a`h:$%@+3}p-OF5g_(yqwŁK#zAm%9gY +95yV.Sщ#-9O<؅Muj[^9]v0C!#r/ݒTbw4> LOS}:!ڶ(6F=B_"3R=<]_qΕoy'1n!Cݼ Z1DJ;U xL))hPYN0[U뜥O`_8T s+@&eYp+ JYH9$sˉHeVe EQìMVߺX3@oHߠWL*j?|kc,l7~_WE'!DɖT',ԥ1??H|&61u K*68{//qO,lꈱvc ͒7hM`E' hեE6f<܉E6zEYetn!Ѽn X7Fƪ @] V9{%1~v@po!,Nj˿[>jS`fnmKu:ǎh˕/(,ez<GyeUuvo1$UmAQQ >7g_ Ŝ< 﫽-ǐK e&_VHbB;9{QXZ/I$g|^ުyqRo4wu;^)ꭑ9( ׿DlEj0 `>7EzTߧ ~HwP94,#gjM_N*7ɍtXaHue*e%f?( ,Wvو .P)^n*BA)$B"M rXS?3-"Aպ 5 ha[N/;!q-=GD<2zyg%C 2;s?7hJ_,Y-vD\zh dr%s"qAۊ&6 x 1oV 1]*-%5bfl 5K5)*Ih&?bN|vy.ƼABLڪ,v_U{8KЇ]@GpRjӰ]_@;QV.ջͬH-TowdR@mi̺Q"fĪYHhQ( XSVy!T`ϛ0np} {"KNsq]ߙT=({*>qCV1v,yU|0VL 7n} N)Z.)b s4,~-4b˒`wuMUY2rhPmT[iIO^ -kt)4 X 񁇧f4STL25 _yڎ?[4R'hlvp.01aG+JY+ qG:Ҋh1W;9Wzs2N+oXDkxIsоy|g4j8hI`Qu:D >_P"Oe0YlSK֡fܼ-@>3걥[Qꋣ4J~q[(5sS'o `OԜVylBB|+%ӒQ_po $V Y,wCwy\0s|VrNyc'i} pAD<`Mव15$|(?%8G >߾K^pl[V t;׳\r3Ь TXjSU`wo})#kڛKq>"ugv淽&+X98@ |׿<Bۼ%iּI XbZ<(h8{F:P]TA: &gsO-:7c8_JwcT61ƬJkb&m-qS60Dy-c}>WXHڐdj?>&-5%E_c͖j'}]""Wpn7l?Bˌ7v'k^H䥇D 7ɨEsxٙY ~S'azLͿ`D~զ`A-)EեkJh 춾~"촽{ _VPڒhJ={ +{-341:D9G2 q 7IiF`˥Rbۅ%DJ8c=< G|1ݒ5A.eì%ܛeqJygJ# O(ΎSQ7q#s{^:znl tԪRXqrkvmbr.@=@>%kCI 8FS>8<%@p@s\]%Qv=Q.M'v6qdhX#dŭN@`)!{8abYօ3eH5PkR] QHhSTciG*.nhT|:NӴ1bNJ.Z41ऺZQ_c1]2N:Ċ.D-'QOo{oc9)>=ʛ0)0qf.q|3\(mڲ| 衪kRzцAy"x SƧ 5䠓6Q߮ MbcT&C9XV UF t*'{ZvΎWQ6~"]K,ęr.@~^qpW(YGjycNrJeJ&`O/%aJ~Ҧbk&ƟvZUkJhdibj4!l+!s]l!_? nEG|Ì/w|XKjtЬ- )hN)i5PRmi%H9@[Ux/aU ><'DN{܀q{# Imdlw6QE ޔbl|],256w)$/v4V0qƶL([À=vL:Q![/AYHSpܙn O2*"3Ղb7tĆ[_ qR[/gHFJ=IkHct \Tr!x9 $嵰úRA!p-cP]s*1 lc| %t+46z[z#$a{#Ji''קsh hVZǾBf*0U%sZsڇsw"B' y:^mDHxe{-ex_|ק U^?.]Gd-'} mwd0>2^ӯ꡷ ??OgdP6KdDji6[A E`S: wMr@?&M%$hVN#:_Y<{6-48m$Nmbߞ\2k/DLm2NG3PzḶ} Q[ʋ^ z1HN+YVBj$x"eޫ{*j42; *TȈq8herM,(ƫzpgJ1IMYG9: 3&{uB$$/ {^HT_BGŒLj[ 'LGMAv2,B-Fkhd z-r6>磬a(XtWW~[L엘LlqRGmX+jz[u$3P͢lc.oZB$m7 V&j#E&#OPu^8mBBA u})( ^LVt 5qtL0("=ޫg"/cF$W_1۽$*4ɬ/YZdcϐ&ˠZ\§q3F@^YTSH6Äl]^ó:m6c v:mMb=< X7RaԺQXmS,7ҋN|n^dz+jcGs@H~p$-` e6G_VF ֺԵb@m,٢% ^iULt5ԜGrIWriGqXg';R̈́y uM'xwtca|O}C!0r=Tʼ(}I\b?Kȶj+)kuH^[=6qmN+Js8ہdv3[M9} KgW ̖:UС&K2~e zmhCB =һƈg/v N;n;)MnUwle:y2L7qa3~| Cpna?L/d1X0ؕ3F~>\6_;^`_ C4?Hj8oTӨ(g"OI,Sx=~w :% Xwx2i\Ư:a&`DvPX+|ޏl5YށqzEz<5w[1SyNOȱҎ2B[VCkc &;3)P1úGߗs)\:0AA!@v.վ,B963v_E^Gqrr0?vUqdF a/'qFi2&"s'Ŧ&Ll~6}YdwVsXpVoJ-;[204mp -hB hk|1H.;#̅5 S]]<+R珯N%6U;dFg`̊8bQVûIɬԗ%35._/ Mn%nȯxp!Bf #$~M eRPW{0%QN]E +12eg 44,harMWgr$֫2oSw9@lrx\nVlo%~kIIG C#7B yUB0Np`jURě_І:1QqMh'#ys aqHh#z_S:#(#6 f_vh'HaBw%x~y` F;]IuO M!iMh댠lB:U!=IРz5b³+?O{PPGq~%gPIvِf19Vc9d'ʻͥ6gx%:`a.K|c3SPeh=GaJ+OI`#ՔEzd+^E} kL )9H>d͎(glKv zI~0^0P<2ʍKach)_)EXxl4W>;1&Mb?kઍ ޓVhȽǷa ߾۞ kZf^k*NIxSm0rh읣@*÷/#IDi*} XcHxfZǛ+aŮvg ЬzZ j)\hoQa'#^2`/!iHn>u0ZfVeP@+Btʪ/HȱB2\\oCP[22ǐ BMHʨHNXlUk:}YIwfqЭ3cY?oQ`=OIwZqL$o[gs;|‹@v]?MFE9u4Zp?^7IÚɤ3^RUQ/f2Y "_AI;,%E(Ɨ#yAH'1{XЈԺtXl.OCU<5 ԢfOZ/Wb;/+:91LN&nƓp"ɢ^)yb[H 聣}N?.pY*6Cs>_nnOIщA0WH=Xh\9eܺ({7 C&mFFŇo;RhZפ.56@oc<;Ib,Hgatڏ3ͯ=nSM6-b=_TGg> ܊XX^v3d3z҅Tٔ7%,{BYdkTq CK[nɈ\Lhپ= ^Q444̤/P;˂e{xgTGRw  \i㠢¾PyU;C>/%{q8ˆ2DQ_Qoa\lQ>C.CZ*Èǰ[KzO YZ