project-base/server-skynet-source-3rd-jemalloc
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Implement per-CPU arena.

Browse Source 
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.
This commit is contained in:
Qi Wang
2017-02-02 17:02:05 -08:00
committed by Qi Wang
parent 8721e19c04
commit ec532e2c5c
16 changed files with 415 additions and 119 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/jemalloc/internal/arena_externs.h
View File

@@ -13,6 +13,10 @@ extern ssize_t opt_decay_time;
extern const arena_bin_info_t arena_bin_info[NBINS];
extern percpu_arena_mode_t percpu_arena_mode;
extern const char *opt_percpu_arena;
extern const char *percpu_arena_mode_names[];
void arena_stats_large_nrequests_add(tsdn_t *tsdn, arena_stats_t *arena_stats,
szind_t szind, uint64_t nrequests);
void arena_stats_mapped_add(tsdn_t *tsdn, arena_stats_t *arena_stats,