linux/tools/perf/util/sort.h

118 lines
3.1 KiB
C
Raw Normal View History

#ifndef __PERF_SORT_H
#define __PERF_SORT_H
#include "../builtin.h"
#include "util.h"
#include "color.h"
#include <linux/list.h>
#include "cache.h"
#include <linux/rbtree.h>
#include "symbol.h"
#include "string.h"
#include "callchain.h"
#include "strlist.h"
#include "values.h"
#include "../perf.h"
#include "debug.h"
#include "header.h"
#include "parse-options.h"
#include "parse-events.h"
#include "thread.h"
#include "sort.h"
extern regex_t parent_regex;
extern char *sort_order;
extern char default_parent_pattern[];
extern char *parent_pattern;
extern char default_sort_order[];
extern int sort__need_collapse;
extern int sort__has_parent;
extern char *field_sep;
extern struct sort_entry sort_comm;
extern struct sort_entry sort_dso;
extern struct sort_entry sort_sym;
extern struct sort_entry sort_parent;
extern unsigned int dsos__col_width;
extern unsigned int comms__col_width;
extern unsigned int threads__col_width;
perf tools: Bind callchains to the first sort dimension column Currently, the callchains are displayed using a constant left margin. So depending on the current sort dimension configuration, callchains may appear to be well attached to the first sort dimension column field which is mostly the case, except when the first dimension of sorting is done by comm, because these are right aligned. This patch binds the callchain to the first letter in the first column, whatever type of column it is (dso, comm, symbol). Before: 0.80% perf [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify | | __fsnotify_parent After: 0.80% perf [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify | | __fsnotify_parent Also, for clarity, we don't put anymore the callchain as is but: - If we have a top level ancestor in the callchain, start it with a first ascii hook. Before: 0.80% perf [kernel] [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify [..] [..] After: 0.80% perf [kernel] [k] __lock_acquire | --- __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify [..] [..] - Otherwise, if we have several top level ancestors, then display these like we did before: 1.69% Xorg | |--21.21%-- vread_hpet | 0x7fffd85b46fc | 0x7fffd85b494d | 0x7f4fafb4e54d | |--15.15%-- exaOffscreenAlloc | |--9.09%-- I830WaitLpRing Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> LKML-Reference: <1256246604-17156-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-22 21:23:23 +00:00
extern enum sort_type sort__first_dimension;
struct hist_entry {
struct rb_node rb_node;
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 06:29:58 +00:00
u64 count;
u64 count_sys;
u64 count_us;
u64 count_guest_sys;
u64 count_guest_us;
/*
* XXX WARNING!
* thread _has_ to come after ms, see
* hist_browser__selected_thread in util/newt.c
*/
struct map_symbol ms;
struct thread *thread;
u64 ip;
char level;
u8 filtered;
struct symbol *parent;
perf diff: Introduce tool to show performance difference I guess it is enough to show some examples: [root@doppio linux-2.6-tip]# rm -f perf.data* [root@doppio linux-2.6-tip]# ls -la perf.data* ls: cannot access perf.data*: No such file or directory [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74440 2009-12-14 20:03 perf.data [root@doppio linux-2.6-tip]# perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2692 samples) ] [root@doppio linux-2.6-tip]# ls -la perf.data* -rw------- 1 root root 74280 2009-12-14 20:03 perf.data -rw------- 1 root root 74440 2009-12-14 20:03 perf.data.old [root@doppio linux-2.6-tip]# perf diff | head -5 1 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 -15307806 [kernel.kallsyms] __kmalloc 3 +1 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -p | head -5 1 +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 [kernel.kallsyms] __kmalloc 3 +1 /lib64/libc-2.10.1.so __GI_memmove 4 +4 /lib64/libc-2.10.1.so _int_malloc 5 +7 -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -v | head -5 1 361449551 326454971 -34994580 /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 151009241 135701435 -15307806 [kernel.kallsyms] __kmalloc 3 +1 101805328 105471269 +3665941 /lib64/libc-2.10.1.so __GI_memmove 4 +4 78041440 101550435 +23508995 /lib64/libc-2.10.1.so _int_malloc 5 +7 59536172 98074985 +38538813 [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# perf diff -vp | head -5 1 9.00% 8.00% +1.00% /lib64/libc-2.10.1.so _IO_vfprintf_internal 2 3.00% 3.00% [kernel.kallsyms] __kmalloc 3 +1 2.00% 2.00% /lib64/libc-2.10.1.so __GI_memmove 4 +4 2.00% 2.00% /lib64/libc-2.10.1.so _int_malloc 5 +7 1.00% 2.00% -1.00% [kernel.kallsyms] __d_lookup [root@doppio linux-2.6-tip]# This should be enough for diffs where the system is non volatile, i.e. when one doesn't updates binaries. For volatile environments, stay tuned for the next perf tool feature: a buildid cache populated by 'perf record', managed by 'perf buildid-cache' a-la ccache, and used by all the report tools. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Stephen Hemminger <shemminger@vyatta.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> LKML-Reference: <1260828571-3613-3-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-14 22:09:31 +00:00
union {
unsigned long position;
struct hist_entry *pair;
struct rb_root sorted_chain;
};
struct callchain_node callchain[0];
};
perf tools: Bind callchains to the first sort dimension column Currently, the callchains are displayed using a constant left margin. So depending on the current sort dimension configuration, callchains may appear to be well attached to the first sort dimension column field which is mostly the case, except when the first dimension of sorting is done by comm, because these are right aligned. This patch binds the callchain to the first letter in the first column, whatever type of column it is (dso, comm, symbol). Before: 0.80% perf [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify | | __fsnotify_parent After: 0.80% perf [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify | | __fsnotify_parent Also, for clarity, we don't put anymore the callchain as is but: - If we have a top level ancestor in the callchain, start it with a first ascii hook. Before: 0.80% perf [kernel] [k] __lock_acquire __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify [..] [..] After: 0.80% perf [kernel] [k] __lock_acquire | --- __lock_acquire lock_acquire | |--58.33%-- _spin_lock | | | |--28.57%-- inotify_should_send_event | | fsnotify [..] [..] - Otherwise, if we have several top level ancestors, then display these like we did before: 1.69% Xorg | |--21.21%-- vread_hpet | 0x7fffd85b46fc | 0x7fffd85b494d | 0x7f4fafb4e54d | |--15.15%-- exaOffscreenAlloc | |--9.09%-- I830WaitLpRing Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> LKML-Reference: <1256246604-17156-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-22 21:23:23 +00:00
enum sort_type {
SORT_PID,
SORT_COMM,
SORT_DSO,
SORT_SYM,
SORT_PARENT
};
/*
* configurable sorting bits
*/
struct sort_entry {
struct list_head list;
const char *se_header;
int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *);
int64_t (*se_collapse)(struct hist_entry *, struct hist_entry *);
int (*se_snprintf)(struct hist_entry *self, char *bf, size_t size,
unsigned int width);
unsigned int *se_width;
bool elide;
};
extern struct sort_entry sort_thread;
extern struct list_head hist_entry__sort_list;
void setup_sorting(const char * const usagestr[], const struct option *opts);
extern size_t sort__thread_print(FILE *, struct hist_entry *, unsigned int);
extern size_t sort__comm_print(FILE *, struct hist_entry *, unsigned int);
extern size_t sort__dso_print(FILE *, struct hist_entry *, unsigned int);
extern size_t sort__sym_print(FILE *, struct hist_entry *, unsigned int __used);
extern int64_t cmp_null(void *, void *);
extern int64_t sort__thread_cmp(struct hist_entry *, struct hist_entry *);
extern int64_t sort__comm_cmp(struct hist_entry *, struct hist_entry *);
extern int64_t sort__comm_collapse(struct hist_entry *, struct hist_entry *);
extern int64_t sort__dso_cmp(struct hist_entry *, struct hist_entry *);
extern int64_t sort__sym_cmp(struct hist_entry *, struct hist_entry *);
extern int64_t sort__parent_cmp(struct hist_entry *, struct hist_entry *);
extern size_t sort__parent_print(FILE *, struct hist_entry *, unsigned int);
extern int sort_dimension__add(const char *);
perf diff: Use perf_session__fprintf_hists just like 'perf record' That means that almost everything you can do with 'perf report' can be done with 'perf diff', for instance: $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2699 samples) ] $ perf record -f find / > /dev/null [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.062 MB perf.data (~2687 samples) ] perf diff | head -8 9.02% +1.00% find libc-2.10.1.so [.] _IO_vfprintf_internal 2.91% -1.00% find [kernel] [k] __kmalloc 2.85% -1.00% find [kernel] [k] ext4_htree_store_dirent 1.99% -1.00% find [kernel] [k] _atomic_dec_and_lock 2.44% find [kernel] [k] half_md4_transform $ So if you want to zoom into libc: $ perf diff --dsos libc-2.10.1.so | head -8 37.34% find [.] _IO_vfprintf_internal 10.34% find [.] __GI_memmove 8.25% +2.00% find [.] _int_malloc 5.07% -1.00% find [.] __GI_mempcpy 7.62% +2.00% find [.] _int_free $ And if there were multiple commands using libc, it is also possible to aggregate them all by using --sort symbol: $ perf diff --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% [.] __GI_mempcpy 7.62% +2.00% [.] _int_free $ The displacement column now is off by default, to use it: perf diff -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34% [.] _IO_vfprintf_internal 10.34% [.] __GI_memmove 8.25% +2.00% [.] _int_malloc 5.07% -1.00% +2 [.] __GI_mempcpy 7.62% +2.00% -1 [.] _int_free $ Using -t/--field-separator can be used for scripting: $ perf diff -t, -m --dsos libc-2.10.1.so --sort symbol | head -8 37.34, , ,[.] _IO_vfprintf_internal 10.34, , ,[.] __GI_memmove 8.25,+2.00%, ,[.] _int_malloc 5.07,-1.00%, +2,[.] __GI_mempcpy 7.62,+2.00%, -1,[.] _int_free 6.99,+1.00%, -1,[.] _IO_new_file_xsputn 1.89,-2.00%, +4,[.] __readdir64 $ Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1260978567-550-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-12-16 15:49:27 +00:00
void sort_entry__setup_elide(struct sort_entry *self, struct strlist *list,
const char *list_name, FILE *fp);
#endif /* __PERF_SORT_H */