server-skynet-source-3rd-je.../include/jemalloc
Qi Wang ec532e2c5c Implement per-CPU arena.
The new feature, opt.percpu_arena, determines thread-arena association
dynamically based CPU id. Three modes are supported: "percpu", "phycpu"
and disabled.

"percpu" uses the current core id (with help from sched_getcpu())
directly as the arena index, while "phycpu" will assign threads on the
same physical CPU to the same arena. In other words, "percpu" means # of
arenas == # of CPUs, while "phycpu" has # of arenas == 1/2 * (# of
CPUs). Note that no runtime check on whether hyper threading is enabled
is added yet.

When enabled, threads will be migrated between arenas when a CPU change
is detected. In the current design, to reduce overhead from reading CPU
id, each arena tracks the thread accessed most recently. When a new
thread comes in, we will read CPU id and update arena if necessary.
2017-03-08 23:19:01 -08:00
..
internal Implement per-CPU arena. 2017-03-08 23:19:01 -08:00
jemalloc_defs.h.in Detect LG_SIZEOF_PTR depending on MSVC platform target 2016-02-20 10:50:24 -08:00
jemalloc_macros.h.in Replace tabs following #define with spaces. 2017-01-20 21:45:53 -08:00
jemalloc_mangle.sh Fix name mangling for stress tests. 2014-01-16 17:38:01 -08:00
jemalloc_protos.h.in Add JEMALLOC_CXX_THROW to the memalign() function prototype. 2015-08-26 13:47:20 -07:00
jemalloc_rename.sh Fix name mangling for stress tests. 2014-01-16 17:38:01 -08:00
jemalloc_typedefs.h.in Refactor purging and splitting/merging. 2016-12-26 18:08:16 -08:00
jemalloc.sh Replace tabs following #define with spaces. 2017-01-20 21:45:53 -08:00