Commit Graph

6111 Commits

Author SHA1 Message Date
Bartosz Taudul
a1acea0c50
Support hw sample times on server. 2021-06-04 13:38:45 +02:00
Bartosz Taudul
2765be92fb
Sample time for hardware samples. 2021-06-04 12:50:55 +02:00
Bartosz Taudul
1616411257
Use AVX2 to search in strings with 32-byte blocks. 2021-06-03 13:49:38 +02:00
Bartosz Taudul
348582d6e4
Search for string matches with 8-byte blocks. 2021-06-03 13:10:26 +02:00
Bartosz Taudul
f8bb24ed36
Search for a character in string in 8-byte blocks. 2021-06-03 12:47:00 +02:00
Bartosz Taudul
483d31c1f4
Ringbuffer tail is not updated by kernel. 2021-06-03 01:14:44 +02:00
Bartosz Taudul
eb38640114
Fix uninitialized pointer. 2021-06-03 00:53:49 +02:00
Bartosz Taudul
b79014f3ee
Optimize parsing numbers.
Don't read byte-by-byte, process data in 8-byte packets.
2021-06-03 00:27:01 +02:00
Bartosz Taudul
b7c5939bb8
Merge remote-tracking branch 'origin/master' into hw 2021-06-02 01:12:28 +02:00
Bartosz Taudul
f4d80a4f5f
Fix rpmalloc init for TRACY_MANUAL_LIFETIME path. 2021-05-31 22:55:30 +02:00
Bartosz Taudul
1badc53e71
Update NEWS. 2021-05-31 22:40:57 +02:00
Bartosz Taudul
3da84d1579
Hide rpmalloc init behind thread local boolean. 2021-05-31 22:38:22 +02:00
Bartosz Taudul
b0fc0d5dcc
Check if rpmalloc has to be initialized before each operation.
The C++11 spec states in [basic.stc.thread] thread storage duration:

2. A variable with thread storage duration shall be initialized before its
   first odr-use (3.2) and, if constructed, shall be destroyed on thread exit.

Previously Tracy relied on the TLS data being initialized:
- During thread creation (MSVC).
- Or during first use in a thread, but the initialization was performed for
  the whole TLS block.

It seems that new compilers are more granular with how they perform the
initialization, hence rpmalloc init has to be checked before each allocation,
as it cannot be "folded" into, for example, initialization of the profiler
itself.
2021-05-31 02:31:42 +02:00
Bartosz Taudul
92fb197aac
Use weak compare, yield thread. 2021-05-31 02:22:13 +02:00
Bartosz Taudul
94ec6a0d9d
Move TracyYield.hpp to common. 2021-05-31 02:19:35 +02:00
Bartosz Taudul
c41473b445
Cosmetics. 2021-05-31 02:12:16 +02:00
Bartosz Taudul
3feb2473a2
Fix rpmalloc on ios.
https://github.com/mjansson/rpmalloc/issues/146
2021-05-30 13:38:29 +02:00
Timo Suoranta
f6eb909152
Documentation for CMake FetchContent support 2021-05-30 12:51:04 +02:00
Timo Suoranta
629b6d88bb
Provide CMake TracyClient header only library 2021-05-30 12:45:16 +02:00
Bartosz Taudul
e606c75695
Don't require GL headers if tracing is disabled. 2021-05-29 12:01:03 +02:00
Bartosz Taudul
688a9722c7
Update ImGui to 1.83 + docking. 2021-05-25 22:21:54 +02:00
Bartosz Taudul
4fc02f5680
Ignore intrinsic wrappers during code location resolution. 2021-05-24 00:02:44 +02:00
Bartosz Taudul
f8ccd8c40d
Move TracyStackFrames to common. 2021-05-23 23:51:56 +02:00
Bartosz Taudul
a6011cd1ad
Ignore intrinsic wrappers in callstack frames.
With gcc/clang the wrapper functions for intrinsics are annoyingly inserted at
top level of stack traces, making it hard to see the call site. Filter out all
known instrinsic headers.
2021-05-23 23:22:45 +02:00
Bartosz Taudul
c13611cf0c
Make unreliable hw stats darker. 2021-05-23 21:32:48 +02:00
Bartosz Taudul
cfb6d0d2ae
Timestamp conversion might be temporarily unavailable. 2021-05-23 20:32:09 +02:00
Bartosz Taudul
233a0bb6d6
Set precise_ip to 0 for cache on Intel.
Fuck knows how this is supposed to work. perf_event_open() opens the
descriptor successfully, but it produces no samples, if precise_ip is not 0.
There are no such problems on ARM (where precise_ip is 3, but maybe it is not
supported at all on that architecture, again, fuck knows if), and on AMD
perf_event_open() does not succeed when precise_ip > 0.
2021-05-23 19:45:13 +02:00
Bartosz Taudul
b2d5fe8e1f
Reduce sampling frequency. 2021-05-23 19:03:11 +02:00
Bartosz Taudul
b1e4d16537
PIDs are no longer needed in samples. 2021-05-23 19:00:45 +02:00
Bartosz Taudul
bbd1c4505c
Restrict perf to return events only for the current PID. 2021-05-23 18:53:09 +02:00
Bartosz Taudul
4ad6f682c8
Exclude VM-related stuff. 2021-05-23 18:44:16 +02:00
Bartosz Taudul
fece23a32b
Set frequency, not period.
This enables sampling on ARM dev board.
2021-05-23 18:02:06 +02:00
Bartosz Taudul
7d3119cbac
Remove irrelevant flag. 2021-05-23 18:01:18 +02:00
Bartosz Taudul
d869b9a8bc
Update manual. 2021-05-23 16:25:18 +02:00
Bartosz Taudul
19c41b94c0
Add glow to hotness indicators on lines. 2021-05-23 13:52:38 +02:00
Bartosz Taudul
a6f85bd061
Color hardware samples stats. 2021-05-23 13:13:38 +02:00
Bartosz Taudul
48ab346835
Add goodness color table accessor. 2021-05-23 12:49:40 +02:00
Bartosz Taudul
2544b891de
Add goodness color generator. 2021-05-23 12:49:20 +02:00
Bartosz Taudul
1b589855e8
Adjust hotness color scaling. 2021-05-23 12:29:48 +02:00
Bartosz Taudul
815cf7d00a
Display hardware counter statistics in asm line columns. 2021-05-23 02:39:31 +02:00
Bartosz Taudul
77c33327f4
Merge remote-tracking branch 'origin/master' into hw 2021-05-23 01:01:21 +02:00
Bartosz Taudul
5f7225ce32
Merge pull request #224 from keur/external_trace_use_file_and_line
Use file:line when comparing traces
2021-05-22 12:36:05 +02:00
Bartosz Taudul
1fc0e1ead5
Merge pull request #225 from stgatilov/patch-1
Tiny fix in manual
2021-05-22 12:13:26 +02:00
Kevin Kuehler
871d41be1f Implement FindMatchingZone(..)
Sets m_compare to the matched index. It supports multiple flags. It can
be run by comparing function name, source file, line number, and any
combination thereof. When searching for a match, we do 3 runs, quitting
out if any of them succeed.

  1. Look for zone with same function same, source file, line number.
  2. Look for zone with same function same, source file.
  3. Look for zone with same function same.
2021-05-22 01:33:06 -07:00
stgatilov
e01ba2d7d4
Tiny fix in manual
Without parentheses, bitwise-and takes precedence over bitwise-or.
2021-05-22 14:20:36 +07:00
Bartosz Taudul
34ca6d865e
Sample branches and cache more frequently. 2021-05-22 02:28:32 +02:00
Bartosz Taudul
c7026cbc1f
Reduce hw sample period. 2021-05-22 02:27:34 +02:00
Bartosz Taudul
089eda0be9
Precise_ip should be shared in each pair of counters. 2021-05-22 02:16:49 +02:00
Bartosz Taudul
fef507dfa2
Merge remote-tracking branch 'origin/master' into hw 2021-05-22 02:05:47 +02:00
Bartosz Taudul
68948712b4
Don't sleep if queues are empty, but there's queries to handle. 2021-05-22 01:12:42 +02:00