mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-08-05 16:54:27 +00:00
13f35928a4
The struct zone is embedded in struct pglist_data which can be allocated
for each NUMA node early in the boot process. As it's not a slab object
nor a global lock, this was not symbolized.
Since the zone->lock is often contended, it'd be nice if we can
symbolize it. On NUMA systems, node_data array will have pointers for
struct pglist_data. By following the pointer, it can calculate the
address of each zone and its lock using BTF. On UMA, it can just use
contig_page_data and its zones.
The following example shows the zone lock contention at the end.
$ sudo ./perf lock con -abl -E 5 -- ./perf bench sched messaging
# Running 'sched/messaging' benchmark:
# 20 sender and receiver processes per group
# 10 groups == 400 processes run
Total time: 0.038 [sec]
contended total wait max wait avg wait address symbol
5167 18.17 ms 10.27 us 3.52 us ffff953340052d00 &kmem_cache_node (spinlock)
38 11.75 ms 465.49 us 309.13 us ffff95334060c480 &sock_inode_cache (spinlock)
3916 10.13 ms 10.43 us 2.59 us ffff953342aecb40 &kmem_cache_node (spinlock)
2963 10.02 ms 13.75 us 3.38 us ffff9533d2344098 &kmalloc-rnd-08-2k (spinlock)
216 5.05 ms 99.49 us 23.39 us ffff9542bf7d65d0 zone_lock (spinlock)
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <song@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: bpf@vger.kernel.org
Cc: linux-mm@kvack.org
Link: https://lore.kernel.org/r/20250401063055.7431-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
78 lines
1.6 KiB
C
78 lines
1.6 KiB
C
// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
|
|
/* Data structures shared between BPF and tools. */
|
|
#ifndef UTIL_BPF_SKEL_LOCK_DATA_H
|
|
#define UTIL_BPF_SKEL_LOCK_DATA_H
|
|
|
|
struct owner_tracing_data {
|
|
u32 pid; // Who has the lock.
|
|
u32 count; // How many waiters for this lock.
|
|
u64 timestamp; // The time while the owner acquires lock and contention is going on.
|
|
s32 stack_id; // Identifier for `owner_stat`, which stores as value in `owner_stacks`
|
|
};
|
|
|
|
struct tstamp_data {
|
|
u64 timestamp;
|
|
u64 lock;
|
|
u32 flags;
|
|
s32 stack_id;
|
|
};
|
|
|
|
struct contention_key {
|
|
s32 stack_id;
|
|
u32 pid;
|
|
u64 lock_addr_or_cgroup;
|
|
};
|
|
|
|
#define TASK_COMM_LEN 16
|
|
|
|
struct contention_task_data {
|
|
char comm[TASK_COMM_LEN];
|
|
};
|
|
|
|
/* default buffer size */
|
|
#define MAX_ENTRIES 16384
|
|
|
|
/*
|
|
* Upper bits of the flags in the contention_data are used to identify
|
|
* some well-known locks which do not have symbols (non-global locks).
|
|
*/
|
|
#define LCD_F_MMAP_LOCK (1U << 31)
|
|
#define LCD_F_SIGHAND_LOCK (1U << 30)
|
|
|
|
#define LCB_F_SLAB_ID_SHIFT 16
|
|
#define LCB_F_SLAB_ID_START (1U << 16)
|
|
#define LCB_F_SLAB_ID_END (1U << 26)
|
|
#define LCB_F_SLAB_ID_MASK 0x03FF0000U
|
|
|
|
#define LCB_F_TYPE_MAX (1U << 7)
|
|
#define LCB_F_TYPE_MASK 0x0000007FU
|
|
|
|
#define SLAB_NAME_MAX 28
|
|
|
|
struct contention_data {
|
|
u64 total_time;
|
|
u64 min_time;
|
|
u64 max_time;
|
|
u32 count;
|
|
u32 flags;
|
|
};
|
|
|
|
enum lock_aggr_mode {
|
|
LOCK_AGGR_ADDR = 0,
|
|
LOCK_AGGR_TASK,
|
|
LOCK_AGGR_CALLER,
|
|
LOCK_AGGR_CGROUP,
|
|
};
|
|
|
|
enum lock_class_sym {
|
|
LOCK_CLASS_NONE,
|
|
LOCK_CLASS_RQLOCK,
|
|
LOCK_CLASS_ZONE_LOCK,
|
|
};
|
|
|
|
struct slab_cache_data {
|
|
u32 id;
|
|
char name[SLAB_NAME_MAX];
|
|
};
|
|
|
|
#endif /* UTIL_BPF_SKEL_LOCK_DATA_H */
|