linux/tools/perf/util/machine.h

242 lines
8.0 KiB
C
Raw Normal View History

#ifndef __PERF_MACHINE_H
#define __PERF_MACHINE_H
#include <sys/types.h>
#include <linux/rbtree.h>
#include "map.h"
#include "dso.h"
#include "event.h"
perf report/top: Add option to collapse undesired parts of call graph For example, in an application with an expensive function implemented with deeply nested recursive calls, the default call-graph presentation is dominated by the different callchains within that function. By ignoring these callees, we can collect the callchains leading into the function and compactly identify what to blame for expensive calls. For example, in this report the callers of garbage_collect() are scattered across the tree: $ perf report -d ruby 2>- | grep -m10 ^[^#]*[a-z] 22.03% ruby [.] gc_mark --- gc_mark |--59.40%-- mark_keyvalue | st_foreach | gc_mark_children | |--99.75%-- rb_gc_mark | | rb_vm_mark | | gc_mark_children | | gc_marks | | |--99.00%-- garbage_collect If we ignore the callees of garbage_collect(), its callers are coalesced: $ perf report --ignore-callees garbage_collect -d ruby 2>- | grep -m10 ^[^#]*[a-z] 72.92% ruby [.] garbage_collect --- garbage_collect vm_xmalloc |--47.08%-- ruby_xmalloc | st_insert2 | rb_hash_aset | |--98.45%-- features_index_add | | rb_provide_feature | | rb_require_safe | | vm_call_method Signed-off-by: Greg Price <price@mit.edu> Tested-by: Jiri Olsa <jolsa@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130623031720.GW22203@biohazard-cafe.mit.edu Link: http://lkml.kernel.org/r/20130708115746.GO22203@biohazard-cafe.mit.edu Cc: Fengguang Wu <fengguang.wu@intel.com> [ remove spaces at beginning of line, reported by Fengguang Wu ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-12-07 05:48:05 +00:00
struct addr_location;
struct branch_stack;
struct perf_evsel;
struct perf_sample;
struct symbol;
struct thread;
union perf_event;
/* Native host kernel uses -1 as pid index in machine */
#define HOST_KERNEL_ID (-1)
#define DEFAULT_GUEST_KERNEL_ID (0)
extern const char *ref_reloc_sym_names[];
struct vdso_info;
struct machine {
struct rb_node rb_node;
pid_t pid;
u16 id_hdr_size;
bool comm_exec;
char *root_dir;
struct rb_root threads;
perf machine: Protect the machine->threads with a rwlock In addition to using refcounts for the struct thread lifetime management, we need to protect access to machine->threads from concurrent access. That happens in 'perf top', where a thread processes events, inserting and deleting entries from that rb_tree while another thread decays hist_entries, that end up dropping references and ultimately deleting threads from the rb_tree and releasing its resources when no further hist_entry (or other data structures, like in 'perf sched') references it. So the rule is the same for refcounts + protected trees in the kernel, get the tree lock, find object, bump the refcount, drop the tree lock, return, use object, drop the refcount if no more use of it is needed, keep it if storing it in some other data structure, drop when releasing that data structure. I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and "perf_event__preprocess_sample(&al)" with "addr_location__put(&al)". The addr_location__put() one is because as we return references to several data structures, we may end up adding more reference counting for the other data structures and then we'll drop it at addr_location__put() time. Acked-by: David Ahern <dsahern@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 23:43:22 +00:00
pthread_rwlock_t threads_lock;
struct list_head dead_threads;
struct thread *last_match;
struct vdso_info *vdso_info;
struct dsos dsos;
struct map_groups kmaps;
struct map *vmlinux_maps[MAP__NR_TYPES];
u64 kernel_start;
symbol_filter_t symbol_filter;
pid_t *current_tid;
union { /* Tool specific area */
void *priv;
u64 db_id;
};
};
static inline
struct map *machine__kernel_map(struct machine *machine, enum map_type type)
{
return machine->vmlinux_maps[type];
}
int machine__get_kernel_start(struct machine *machine);
static inline u64 machine__kernel_start(struct machine *machine)
{
if (!machine->kernel_start)
machine__get_kernel_start(machine);
return machine->kernel_start;
}
static inline bool machine__kernel_ip(struct machine *machine, u64 ip)
{
u64 kernel_start = machine__kernel_start(machine);
return ip >= kernel_start;
}
struct thread *machine__find_thread(struct machine *machine, pid_t pid,
pid_t tid);
struct comm *machine__thread_exec_comm(struct machine *machine,
struct thread *thread);
int machine__process_comm_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
int machine__process_exit_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
int machine__process_fork_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
int machine__process_lost_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
perf tools: handle PERF_RECORD_LOST_SAMPLES This patch modifies the perf tool to handle the new RECORD type, PERF_RECORD_LOST_SAMPLES. The number of lost-sample events is stored in .nr_events[PERF_RECORD_LOST_SAMPLES]. The exact number of samples which the kernel dropped is stored in total_lost_samples. When the percentage of dropped samples is greater than 5%, a warning is printed. Here are some examples: Eg 1, Recording different frequently-occurring events is safe with the patch. Only a very low drop rate is associated with such actions. $ perf record -e '{cycles:p,instructions:p}' -c 20003 --no-time ~/tchain ~/tchain $ perf report -D | tail SAMPLE events: 120243 MMAP2 events: 5 LOST_SAMPLES events: 24 FINISHED_ROUND events: 15 cycles:p stats: TOTAL events: 59348 SAMPLE events: 59348 instructions:p stats: TOTAL events: 60895 SAMPLE events: 60895 $ perf report --stdio --group # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 24 # # Samples: 120K of event 'anon group { cycles:p, instructions:p }' # Event count (approx.): 24048600000 # # Overhead Command Shared Object Symbol # ................ ........... ................ .................................. # 99.74% 99.86% tchain_edit tchain_edit [.] f3 0.09% 0.02% tchain_edit tchain_edit [.] f2 0.04% 0.00% tchain_edit [kernel.vmlinux] [k] ixgbe_read_reg Eg 2, Recording the same thing multiple times can lead to high drop rate, but it is not a useful configuration. $ perf record -e '{cycles:p,cycles:p}' -c 20003 --no-time ~/tchain Warning: Processed 600592 samples and lost 99.73% samples! [perf record: Woken up 148 times to write data] [perf record: Captured and wrote 36.922 MB perf.data (1206322 samples)] [perf record: Woken up 1 times to write data] [perf record: Captured and wrote 0.121 MB perf.data (1629 samples)] Signed-off-by: Kan Liang <kan.liang@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: eranian@google.com Link: http://lkml.kernel.org/r/1431285195-14269-9-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-10 19:13:15 +00:00
int machine__process_lost_samples_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
int machine__process_aux_event(struct machine *machine,
union perf_event *event);
int machine__process_itrace_start_event(struct machine *machine,
union perf_event *event);
int machine__process_mmap_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
int machine__process_event(struct machine *machine, union perf_event *event,
struct perf_sample *sample);
typedef void (*machine__process_t)(struct machine *machine, void *data);
struct machines {
struct machine host;
struct rb_root guests;
symbol_filter_t symbol_filter;
};
void machines__init(struct machines *machines);
void machines__exit(struct machines *machines);
void machines__process_guests(struct machines *machines,
machine__process_t process, void *data);
struct machine *machines__add(struct machines *machines, pid_t pid,
const char *root_dir);
struct machine *machines__find_host(struct machines *machines);
struct machine *machines__find(struct machines *machines, pid_t pid);
struct machine *machines__findnew(struct machines *machines, pid_t pid);
void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size);
char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
void machines__set_symbol_filter(struct machines *machines,
symbol_filter_t symbol_filter);
void machines__set_comm_exec(struct machines *machines, bool comm_exec);
struct machine *machine__new_host(void);
int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
void machine__exit(struct machine *machine);
void machine__delete_threads(struct machine *machine);
void machine__delete(struct machine *machine);
void machine__remove_thread(struct machine *machine, struct thread *th);
struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
struct addr_location *al);
struct mem_info *sample__resolve_mem(struct perf_sample *sample,
struct addr_location *al);
int thread__resolve_callchain(struct thread *thread,
struct perf_evsel *evsel,
struct perf_sample *sample,
struct symbol **parent,
struct addr_location *root_al,
int max_stack);
/*
* Default guest kernel is defined by parameter --guestkallsyms
* and --guestmodules
*/
static inline bool machine__is_default_guest(struct machine *machine)
{
return machine ? machine->pid == DEFAULT_GUEST_KERNEL_ID : false;
}
static inline bool machine__is_host(struct machine *machine)
{
return machine ? machine->pid == HOST_KERNEL_ID : false;
}
perf machine: Protect the machine->threads with a rwlock In addition to using refcounts for the struct thread lifetime management, we need to protect access to machine->threads from concurrent access. That happens in 'perf top', where a thread processes events, inserting and deleting entries from that rb_tree while another thread decays hist_entries, that end up dropping references and ultimately deleting threads from the rb_tree and releasing its resources when no further hist_entry (or other data structures, like in 'perf sched') references it. So the rule is the same for refcounts + protected trees in the kernel, get the tree lock, find object, bump the refcount, drop the tree lock, return, use object, drop the refcount if no more use of it is needed, keep it if storing it in some other data structure, drop when releasing that data structure. I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and "perf_event__preprocess_sample(&al)" with "addr_location__put(&al)". The addr_location__put() one is because as we return references to several data structures, we may end up adding more reference counting for the other data structures and then we'll drop it at addr_location__put() time. Acked-by: David Ahern <dsahern@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 23:43:22 +00:00
struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
struct dso *machine__findnew_dso(struct machine *machine, const char *filename);
size_t machine__fprintf(struct machine *machine, FILE *fp);
static inline
struct symbol *machine__find_kernel_symbol(struct machine *machine,
enum map_type type, u64 addr,
struct map **mapp,
symbol_filter_t filter)
{
return map_groups__find_symbol(&machine->kmaps, type, addr,
mapp, filter);
}
static inline
struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr,
struct map **mapp,
symbol_filter_t filter)
{
return machine__find_kernel_symbol(machine, MAP__FUNCTION, addr,
mapp, filter);
}
static inline
struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
const char *name,
struct map **mapp,
symbol_filter_t filter)
{
return map_groups__find_function_by_name(&machine->kmaps, name, mapp,
filter);
}
struct map *machine__findnew_module_map(struct machine *machine, u64 start,
const char *filename);
int machine__load_kallsyms(struct machine *machine, const char *filename,
enum map_type type, symbol_filter_t filter);
int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
symbol_filter_t filter);
size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
bool (skip)(struct dso *dso, int parm), int parm);
size_t machines__fprintf_dsos(struct machines *machines, FILE *fp);
size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
bool (skip)(struct dso *dso, int parm), int parm);
void machine__destroy_kernel_maps(struct machine *machine);
int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel);
int machine__create_kernel_maps(struct machine *machine);
int machines__create_kernel_maps(struct machines *machines, pid_t pid);
int machines__create_guest_kernel_maps(struct machines *machines);
void machines__destroy_kernel_maps(struct machines *machines);
size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
int machine__for_each_thread(struct machine *machine,
int (*fn)(struct thread *thread, void *p),
void *priv);
int machines__for_each_thread(struct machines *machines,
int (*fn)(struct thread *thread, void *p),
void *priv);
int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
struct target *target, struct thread_map *threads,
perf_event__handler_t process, bool data_mmap,
unsigned int proc_map_timeout);
static inline
int machine__synthesize_threads(struct machine *machine, struct target *target,
struct thread_map *threads, bool data_mmap,
unsigned int proc_map_timeout)
{
return __machine__synthesize_threads(machine, NULL, target, threads,
perf_event__process, data_mmap,
proc_map_timeout);
}
pid_t machine__get_current_tid(struct machine *machine, int cpu);
int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
pid_t tid);
#endif /* __PERF_MACHINE_H */