From 91e467bc568f15da2eac688e131010601e889184 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Sun, 10 Sep 2017 19:23:14 -0700 Subject: perf machine: Use hashtable for machine threads To process any events, it needs to find the thread in the machine first. The machine maintains a rb tree to store all threads. The rb tree is protected by a rw lock. It is not a problem for current perf which serially processing events. However, it will have scalability performance issue to process events in parallel, especially on a heavy load system which have many threads. Introduce a hashtable to divide the big rb tree into many samll rb tree for threads. The index is thread id % hashtable size. It can reduce the lock contention. Committer notes: Renamed some variables and function names to reduce semantic confusion: 'struct threads' pointers: thread -> threads threads hastable index: tid -> hash_bucket struct threads *machine__thread() -> machine__threads() Cast tid to (unsigned int) to handle -1 in machine__threads() (Kan Liang) Signed-off-by: Kan Liang Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Andi Kleen Cc: Jiri Olsa Cc: Lukasz Odzioba Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1505096603-215017-2-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/machine.h | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) (limited to 'tools/perf/util/machine.h') diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index 3cdb1340f917..fe2f05848050 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -23,6 +23,17 @@ extern const char *ref_reloc_sym_names[]; struct vdso_info; +#define THREADS__TABLE_BITS 8 +#define THREADS__TABLE_SIZE (1 << THREADS__TABLE_BITS) + +struct threads { + struct rb_root entries; + pthread_rwlock_t lock; + unsigned int nr; + struct list_head dead; + struct thread *last_match; +}; + struct machine { struct rb_node rb_node; pid_t pid; @@ -30,11 +41,7 @@ struct machine { bool comm_exec; bool kptr_restrict_warned; char *root_dir; - struct rb_root threads; - pthread_rwlock_t threads_lock; - unsigned int nr_threads; - struct list_head dead_threads; - struct thread *last_match; + struct threads threads[THREADS__TABLE_SIZE]; struct vdso_info *vdso_info; struct perf_env *env; struct dsos dsos; @@ -48,6 +55,12 @@ struct machine { }; }; +static inline struct threads *machine__threads(struct machine *machine, pid_t tid) +{ + /* Cast it to handle tid == -1 */ + return &machine->threads[(unsigned int)tid % THREADS__TABLE_SIZE]; +} + static inline struct map *__machine__kernel_map(struct machine *machine, enum map_type type) { -- cgit v1.2.3