| e53bf23f1c33076090b51184b82af4dd98d0c51c |
|
28-May-2014 |
Mark Hills <Mark.Hills@framestore.com> |
Optionally produce stats on syscall latency
Time spent in system time is not useful where a syscall depends on some
non-CPU resource, eg. typically open() or stat() to a network drive.
This patch adds a new flag (-w) to produce a summary of the time
difference between beginning and end of the system call (ie. latency)
This functionality has been useful to profile slow processes that
are not CPU-bound.
Signed-off-by: Mark Hills <mark.hills@framestore.com>
/external/strace/count.c
|
| ac5133d0cb5c18a39f6fa9b7ca2ebcba9277a904 |
|
29-May-2014 |
Dmitry V. Levin <ldv@altlinux.org> |
Constify count_syscall function
* count.c (count_syscall): Add const qualifier to timeval argument and
rename it. Store the wall clock time spent while in syscall in separate
timeval variable.
* defs.h (count_syscall): Update prototype.
* syscall.c (trace_syscall_exiting): Update count_syscall invocation.
/external/strace/count.c
|
| 8050cdc43c7d804cebe7657d6b5fe8bc37700f2c |
|
07-Mar-2013 |
Denys Vlasenko <vda.linux@googlemail.com> |
Tweaks for -c: fixed setitimer/getitimer hack; optimized call_summary_pers()
count_syscall() was calling setitimer/getitimer once in order to find
smallest "tick" OS uses in time accounting, in order to use it
for syscalls which apparently spent less than that time in syscall.
The code assumed that this "tick" is not zero... but it is zero
on linux-3.6.11. Which means that this hack doesn't work...
At least this change prevents this measurement from being done
_repeatedly_, by initializing one_tick to -1, not 0.
While at it, added comments in count_syscall() explaining what we are doing.
Optimized call_summary_pers() a bit, by eliminating redundant tv -> float
conversions, and prevented 0.0/0.0 which was resulting in "% time"
being shown as "-nan" if total CPU time spent was 0.000000
(try "strace -c /bin/true").
The code seems to seriously underestimate CPU usage:
"strace -c ls -lR /usr/share >/dev/null" shows total time spent
in syscalls to be only ~10..20% of what "time ls -lR /usr/share >/dev/null"
shows.
It might be useful to have a mode where we show wall clock time
spent in syscalls, not CPU time. It might also be more accurate.
text data bss dec hex filename
245019 676 5708 251403 3d60b strace_old
244923 684 5676 251283 3d593 strace
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
/external/strace/count.c
|
| 74ec14f968a418691b851cbbfeb0269174c64b08 |
|
21-Feb-2013 |
Denys Vlasenko <vda.linux@googlemail.com> |
Eliminate many SCNO_IS_VALID checks
By adding tcp->s_ent pointer tot syscall table entry,
we can replace sysent[tcp->scno] references by tcp->s_ent.
More importantly, we may ensure that tcp->s_ent is always valid,
regardless of tcp->scno value. This allows us to drop
SCNO_IS_VALID(tcp->scno) checks before we access syscall
table entry.
We can optimize (qual_flags[tcp->scno] & QUAL_foo) checks
with a similar technique.
Resulting code shrink:
text data bss dec hex filename
245975 700 19072 265747 40e13 strace.t3/strace
245703 700 19072 265475 40d03 strace.t4/strace
* count.c (count_syscall): Use cheaper SCNO_IN_RANGE() check.
* defs.h: Add "int qual_flg" and "const struct sysent *s_ent"
to struct tcb. Remove "int u_nargs" from it.
Add UNDEFINED_SCNO constant which will mark undefined scnos
in tcp->qual_flg.
* pathtrace.c (pathtrace_match): Drop SCNO_IS_VALID check.
Use tcp->s_ent instead of sysent[tcp->scno].
* process.c (sys_prctl): Use tcp->s_ent->nargs instead of tcp->u_nargs.
(sys_waitid): Likewise.
* strace.c (init): Add compile-time check that DEFAULT_QUAL_FLAGS
constant is consistent with init code.
* syscall.c (decode_socket_subcall): Use tcp->s_ent->nargs
instead of tcp->u_nargs. Set tcp->qual_flg and tcp->s_ent.
(decode_ipc_subcall): Likewise.
(printargs): Use tcp->s_ent->nargs instead of tcp->u_nargs.
(printargs_lu): Likewise.
(printargs_ld): Likewise.
(get_scno): [MIPS,ALPHA] Use cheaper SCNO_IN_RANGE() check.
If !SCNO_IS_VALID, set tcp->s_ent and tcp->qual_flg to default values.
(internal_fork): Use tcp->s_ent instead of sysent[tcp->scno].
(syscall_fixup_for_fork_exec): Remove SCNO_IS_VALID check.
Use tcp->s_ent instead of sysent[tcp->scno].
(get_syscall_args): Likewise.
(get_error): Drop SCNO_IS_VALID check where it is redundant.
(dumpio): Drop SCNO_IS_VALID check where it is redundant.
Use tcp->s_ent instead of sysent[tcp->scno].
(trace_syscall_entering): Use (tcp->qual_flg & UNDEFINED_SCNO) instead
of SCNO_IS_VALID check. Use tcp->s_ent instead of sysent[tcp->scno].
Drop SCNO_IS_VALID check where it is redundant.
Print undefined syscall name with undefined_scno_name(tcp).
(trace_syscall_exiting): Likewise.
* util.c (setbpt): Use tcp->s_ent instead of sysent[tcp->scno].
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
/external/strace/count.c
|
| 5721cdbcdba76eef854a30e7e56e328eae976e44 |
|
16-Feb-2013 |
Denys Vlasenko <vda.linux@googlemail.com> |
Mass rename of SCNO_IN_RANGE define to SCNO_IS_VALID
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
/external/strace/count.c
|
| c52826c267aaca5c976b10e13ee6debc0bdf3f43 |
|
15-May-2012 |
Denys Vlasenko <vda.linux@googlemail.com> |
Make sure current_wordsize and PERSONALITY0_WORDSIZE are ints in all arches
On 64bit systems with a single personality, they used to be sizeof(long),
which has type "long", not "int", which complicates printf formats.
* defs.h: Ensure that PERSONALITY0_WORDSIZE;s tyoe is int.
This in turn makes sure current_wordsize is also an int.
* count.c (call_summary): Revert the change which added cast to int.
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
/external/strace/count.c
|
| aa6d8504772e7754163a109fb6bcbfbe13c3212b |
|
28-Apr-2012 |
Mike Frysinger <vapier@gentoo.org> |
Cast current_wordsize to an int
On 64bit systems with a single personality, we see:
count.c: In function 'call_summary':
count.c:223:5: warning: format '%u' expects type 'unsigned int',
but argument 3 has type 'long unsigned int'
Since on multi-personality systems this is an array of ints, cast
the multiplication to an int and update the printf format.
* count.c (call_summary): Change %u to %d and cast first argument to int.
Signed-off-by: Mike Frysinger <vapier@gentoo.org>
/external/strace/count.c
|
| 9fd4f96d2a2527ac7ca90c156bfc11ce10118684 |
|
19-Mar-2012 |
Denys Vlasenko <vda.linux@googlemail.com> |
Optimize code if we have only one personality
On i386:
text data bss dec hex filename
238025 672 18980 257677 3ee8d strace.before
237389 704 18944 257037 3ec0d strace
* defs.h: Define PERSONALITY0_WORDSIZE as sizeof(long) if not defined.
Introduce new define, current_wordsize as
(personality_wordsize[current_personality]).
Make set_personality() no-op, current_personality constant zero,
current_wordsize as PERSONALITY0_WORDSIZE if we have only one personality.
* count.c (call_summary): Use current_wordsize instead of
personality_wordsize[current_personality].
* desc.c (printflock): Likewise.
* file.c (sys_utime): Likewise.
* io.c (tprint_iov): Likewise.
* process.c (printargv): Likewise.
* resource.c (decode_rlimit): Likewise.
* signal.c (sys_kill): Likewise.
(sys_rt_sigaction): Likewise.
* time.c (sprinttv): Likewise.
(sprint_timespec): Likewise.
(printitv_bitness): Likewise.
(tprint_timex): Likewise.
(printsigevent): Likewise.
* util.c (dumpiov): Likewise.
(umoven): Likewise.
(umovestr): Likewise.
* syscall.c: Initialize sysent to sysent0 etc.
Make current_personality, personality_wordsize[], set_personality()
conditional on SUPPORTED_PERSONALITIES > 1.
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
/external/strace/count.c
|
| a6d91ded3f2d5401e09a9c2fa442aabfbfe593a8 |
|
16-Mar-2012 |
Denys Vlasenko <vda.linux@googlemail.com> |
Tidy up includes and copyright notices, fix indentation
The files not mentioned in changelog below had only
copyright notices fixes and indentation fixes.
* defs.h: Include <stdint.h> and <inttypes.h>.
* file.c: Do not include <inttypes.h>.
Move struct kernel_dirent declaration below top include block.
* block.c: Do not include <stdint.h> and <inttypes.h>.
* quota.c: Likewise.
* desc.c: Likewise.
* signal.c: Likewise.
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
/external/strace/count.c
|
| 4c65c44478f1591d96cda425d78451334fe1d401 |
|
08-Mar-2012 |
Denys Vlasenko <vda.linux@googlemail.com> |
Trivial tweaks to error messages
* strace.c (test_ptrace_setoptions_followfork): Use kill_save_errno
instead of kill.
(trace): Use perror_msg instead of perror.
* count.c (set_sortby): Use error_msg_and_die instead of fprintf.
* syscall.c (qualify): Likewise.
* util.c (ptrace_restart): Expand error message.
(umoven): Likewise.
(umovestr): Likewise.
(upeek): Use perror_msg instead of sprintf + perror.
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
/external/strace/count.c
|
| ed720fda5d515f1359fcd3242223e553d1216789 |
|
25-Feb-2012 |
Denys Vlasenko <vda.linux@googlemail.com> |
Automated removal of non-Linux code
This change is generated by running every source through the following command:
unifdef -DLINUX -Dlinux -USUNOS4 -USVR4 -UUNIXWARE -UFREEBSD
-USUNOS4_KERNEL_ARCH_KLUDGE -UHAVE_MP_PROCFS
-UHAVE_POLLABLE_PROCFS -UHAVE_PR_SYSCALL -UUSE_PROCFS file.c
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
/external/strace/count.c
|
| 0b315b65432cda20c7e5608c5124289036522fa7 |
|
03-Feb-2012 |
H.J. Lu <hongjiu.lu@intel.com> |
Cast to long for %l in printf
Cast a value to long for %l in printf to avoid compiler warning
on systems where it may be long long.
* count.c (call_summary_pers): Cast to long.
* ipc.c (sys_mq_open, printmqattr): Likewise.
* quota.c (decode_cmd_data): Likewise.
* resource.c (sys_sysinfo): Likewise.
* time.c (tprint_timex): Likewise.
/external/strace/count.c
|
| 1d46ba57a8ab16b353b531f2bbefe2ad7f354ca9 |
|
31-Aug-2011 |
Denys Vlasenko <dvlasenk@redhat.com> |
Make out-of-memory handling more uniform
This fixes one real bug in dumpstr().
* defs.h: Declare die_out_of_memory().
* strace.c (die_out_of_memory): New function.
(strace_popen): If allocation fails, call die_out_of_memory().
(main): Likewise.
(expand_tcbtab): Likewise.
(rebuild_pollv): Likewise.
* count.c (count_syscall): Likewise.
(call_summary_pers): Likewise.
* desc.c (decode_select): Likewise.
* file.c (sys_getdents): Likewise.
(sys_getdents64): Likewise.
(sys_getdirentries): Likewise.
* pathtrace.c (pathtrace_match): Likewise.
* syscall.c (qualify): Likewise.
* util.c (printstr): Likewise.
(dumpiov): Likewise.
(dumpstr): Likewise.
(fixvfork): Likewise.
* mem.c (sys_mincore): Don't check free() parameter for NULL.
Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
/external/strace/count.c
|
| cb6f056004a10d5c3ed0341366e3ddeb53cac5e6 |
|
25-Aug-2011 |
Denys Vlasenko <dvlasenk@redhat.com> |
Opotimize "scno >= 0 && scno < nsyscalls" check
gcc can't figure out on its own that this check can be done with
single compare, and does two compares. We can help it by casting
scno to unsigned long: ((unsigned long)(scno) < nsyscalls)
* defs.h: New macro SCNO_IN_RANGE(long_var).
* count.c (count_syscall): Use SCNO_IN_RANGE() instead of open-coded check.
* syscall.c (getrval2): Use SCNO_IN_RANGE() instead of open-coded check.
This fixes a bug: missing check for scno < 0 and scno > nsyscalls
instead of scno >= nsyscalls.
(get_scno): Use SCNO_IN_RANGE() instead of open-coded check.
This fixes a bug: scno > nsyscalls instead of scno >= nsyscalls.
(known_scno): Use SCNO_IN_RANGE() instead of open-coded check.
(internal_syscall): Likewise.
(syscall_enter): Likewise.
(trace_syscall_entering): Likewise.
(get_error): Likewise.
(trace_syscall_exiting): Likewise.
Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
/external/strace/count.c
|
| c95a88f124895042345473fad58daa30da9e1565 |
|
21-Aug-2011 |
Denys Vlasenko <dvlasenk@redhat.com> |
count_syscall() always returns 0, optimize it
* defs.h (count_syscall): Change return type from int to void.
* count.c (count_syscall): Change return type from int to void.
* syscall.c (trace_syscall_exiting): Change code around call
to count_syscall accordingly.
Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
/external/strace/count.c
|
| 7b609d5ba0852e6c56ba311350ebd4412361777b |
|
22-Jun-2011 |
Denys Vlasenko <dvlasenk@redhat.com> |
Whitespace cleanups. No code changes.
* count.c: Place opening curly brace after if (),
not on the next line. Almost all strace code alredy
uses this style.
* desc.c: Likewise.
* file.c: Likewise.
* net.c: Likewise.
* pathtrace.c: Likewise.
* process.c: Likewise.
* quota.c: Likewise.
* signal.c: Likewise.
* strace.c: Likewise.
* syscall.c: Likewise.
* time.c: Likewise.
Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
/external/strace/count.c
|
| 30145dda9d7ff70df1d5ad750a183572c73e8963 |
|
07-Sep-2010 |
Dmitry V. Levin <ldv@altlinux.org> |
Fix const-correctness issues uncovered by gcc -Wwrite-strings
* defs.h (struct xlat): Add const qualifier to the field of
type "char *".
(set_sortby, qualify, printnum, printnum_int): Add const qualifier to
arguments of type "char *".
* count.c (set_sortby): Add const qualifier to the argument and
automatic variable of type "char *".
* desc.c (decode_select): Add const qualifier to automatic variables of
type "char *".
* ioctlsort.c (struct ioctlent): Add const qualifier to fields of
type "char *".
(main): Add const qualifier to argv.
* process.c (printargv): Add const qualifier to the argument and
automatic variable of type "char *".
(printargc) Add const qualifier to argument of type "char *".
* signal.c (sprintsigmask, parse_sigset_t): Add const qualifier to
arguments of type "char *".
* strace.c (progname): Add const qualifier.
(detach): Add const qualifier to automatic variable of type "char *".
* stream.c (struct strbuf): Add const qualifier to the field of
type "char *".
* syscall.c (struct qual_options): Add const qualifier to fields of
type "char *".
(qual_syscall, qual_fault, qual_desc, lookup_class): Add const qualifier
to arguments of type "char *".
(qual_signal): Add const qualifier to the argument of type "char *",
avoid modification of constant argument.
(qualify): Likewise.
* util.c (printflags): Add const qualifier to automatic variable of
type "char *".
(printnum, printnum_int): Add const qualifier to arguments of
type "char *".
/external/strace/count.c
|
| e3a7ef5a2a3ac31bfa0d3f9ce65981e51700073e |
|
28-Mar-2010 |
Dmitry V. Levin <ldv@altlinux.org> |
Implement -C option to combine regular and -c output
* defs.h (cflag_t): New enum.
* strace.1: Document -C option.
* strace.c (cflag): Update type.
(main): Handle -C option.
(trace): Update use of cflag.
* count.c (count_syscall): Move clearing of TCB_INSYSCALL to ...
* syscall.c (trace_syscall): ... here. Update use of cflag.
Based on patch by Adrien Kunysz.
/external/strace/count.c
|
| a97f03b781904bbb1af35d9610cec88930359096 |
|
19-Apr-2008 |
Dmitry V. Levin <ldv@altlinux.org> |
2008-04-19 Dmitry V. Levin <ldv@altlinux.org>
* count.c (call_summary_pers): Check calloc() return value.
Signed-off-by: "Yang Zhiguo" <yzgcsu@cn.fujitsu.com>
/external/strace/count.c
|
| 14e3174d1c0d583aaa1b5938530541cf6a103874 |
|
11-Jul-2007 |
Roland McGrath <roland@redhat.com> |
2007-07-11 Roland McGrath <roland@redhat.com>
* count.c (call_summary_pers): Use tv_float conversion for output of
cumulative time, in case it is negative from bogus -O value.
From Lai JiangShan <laijs@cn.fujitsu.com>.
/external/strace/count.c
|
| 7d61ff1dbf7226ed35a35c12b8b642bd5fc9a0a9 |
|
21-Dec-2006 |
Dmitry V. Levin <ldv@altlinux.org> |
2006-12-21 Dmitry V. Levin <ldv@altlinux.org>
Move counts code to separate file.
* count.c: New file.
* Makefile.am (strace_SOURCES): Add count.c.
* syscall.c (call_counts, countv, counts, shortest, time_cmp,
syscall_cmp, count_cmp, sortfun, overhead, set_sortby,
set_overhead, call_summary_pers, call_summary): Move to count.c
* count.c (count_syscall): New function.
* defs.h (count_syscall): Declare it.
* syscall.c (trace_syscall): Use it.
/external/strace/count.c
|