Files
rocm-systems/cmake/Templates/omnitrace-install.py.in
T
Jonathan R. Madsen 9de3a6b0b4 Linux Perf Support + Causal Profiling Updates (#276)
* causal backtrace updates

- fix initial causal sampling period value

* causal delay updates

- tweak handling of sleep_for_overhead

* Fix experiment global scaling for prog pts

- results in drastically improved predictions

* pthread_mutex_gotcha updates

- disable all wrappers during causal profiling

* validate-causal-json.py updates

- support decimal stddev
- fix setting stddev from command-line

* causal perform_experiment_impl update

- handle start failing because finalizing

* deprecate causal::component::sample_rate

- appears to not help at all

* Rework sample info

* Increase causal unwind_depth

- use OMNITRACE_MAX_UNWIND_DEPTH

* validate-causal-json updates

- min experiments
  - exclude reporting predictions with less than X experiments at a given speedup
- percent samples
  - only print samples within X% of the peak (default: 95%)

* Update timemory submodule

- extensions to sampling for signals delivered via non-timer method
  - e.g. via HW counter overflow

* dwarf_entry::operator< updates

- sort via file

* causal profiling docs updates

- info about backends
- info about installing/enabling perf

* config updates: causal backend

- CausalBackend enum
- OMNITRACE_CAUSAL_BACKEND: perf, timer, auto
- omnitrace-causal option: --backend

* debug update

- use spin_mutex instead of std::mutex

* address_range::contains update

- range from 0-100 contains range from 10-100 but was returning false because high was == 100 not < 100

* symbol::operator< update

- handle load address differences

* sampling updates (non-causal)

- update get_timer to get_trigger + dynamic_cast

* container::static_vector updates

- support construction from container::c_array
- update_size private member func for handling atomic m_size

* Move perf files

- moved library/causal/perf.{hpp,cpp} to library/perf.{hpp,cpp}

* causal example update

- created impl.hpp (forward decls)
- renamed {cpu,rng}_func_impl to {cpu,rng}_impl_func
- only create two threads which run N iterations instead of two threads each iteration

* Update timemory submodule

- updates to unwind::processed_entry
- updates to procfs::maps

* Updated causal documentation

- fixed line numbers changed by modifications to causal example

* omnitrace-causal exe updates

- set OMNITRACE_THREAD_POOL_SIZE to zero by default

* core/containers updates

- static_vector: provide data() member function
- c_array pop_front() and pop_back() member functions

* core: config and argparse updates + perf

- core/perf.{hpp,cpp}
  - forward decl of enums
  - config-related capabilities
- argparse: --sample-overflow
- renamed some config functions
  - e.g. get_sampling_cpu_freq -> get_sampling_cputime_freq
- added config settings related to overflow sampling via perf
- added timer_sampling and overflow_sampling categories

* Update timemory submodule

- sampling allocator flushing

* binary updates

- lookup_ipaddr_entry
- use bfd_find_nearest_line instead of bfd_find_nearest_line_discriminator
  - discriminators are not used
- explicit instantiations of inlined_symbol::serialize

* Bump VERSION to 1.10.0

* sampling and perf updates

- support overflow sampling via Linux Perf
- update perf namespace
- update perf::perf_event
  - update record ctor: pointer instead of const ref
  - update open member func: return optional string
  - add m_batch_size member variable
- sampling updates
  - support overflow sampling
  - flush allocators
  - increase buffer size from 1024 to 2048
  - restructure post-processing in light of perf overflow supports
  - improve offload memory usage only load buffers for thread
  - load_offload_buffer(tid) uses thread-specific filepos
- component updates
  - backtrace_metrics::operator-=
  - backtrace_metrics::operator-
  - backtrace::sample does not record for overflow signal
  - callchain: perf overflow sample

* core updates

- component::sampling_percent does not report self + uses_percent_units

* causal updates

- tweak get_line_info
- overloads for set_current_selection (uint64_t, c_array, std::array)
- delay
  - use sampling::pause/sampling::resume
- experiment
  - experiment::sample derives from unwind::processed_entry
  - experiment::samples is vector instead of set
  - fixed samples
  - overloads for is_selected (uint64_t, c_array, std::array)
  - scaling factor defaults to 100 instead of 50
  - serialize updates follow change to experiment::sample
  - modify algorithm for increasing/decreasing experiment length
- sample_data
  - use map<uintptr, uint64_t> instead of set<sample_data>
  - get_samples returns vector<sample_data> instead of set<sample_data>
- sampling
  - support overflow via Linux Perf
  - update causal_offload_buffer
  - flush sampling allocator
- backtrace
  - overflow component

* libomnitrace-dl updates

- handle dl::InstrumentMode::PythonProfile

* testing updates (causal)

- causal line 155 -> causal line 100
- causal line 165 -> causal line 110

* formatting

* exit_gotcha updates

- exit_info for abort()
- message about non-zero exit code

* testing updates

- fail regex for causal tests
- validate-causal-json: >= min_experiments instead of > min_experiments
- handle OMNITRACE_DEBUG_SETTINGS in omnitrace_write_test_config

* causal sampling updates

- add new lines where appropriate

* causal data updates

- reorder diagnostic info when experiment fails to start

* binary updates

- symbol address range from address to address + symsize + 1
  - add 1 based on debug info

* causal data updates

- sample_selection wait_ns defaults to 1,000 instead of 10,000
- sample_selection wait scaled by iteration number
- save_line_info_impl verbosity
- print latest_eligible_pc when experiment does not start

* causal sampling + component updates

- perf backend disables component::backtrace
- ensure get_sampling_(realtime|cputime|overflow)_signal do not malloc

* causal: remove period stats

* validate-causal-json update

- fix --help

* causal data updates

- improve eligible pc history reporting when experiment fails to start

* causal data updates

- fix compute_eligible_lines_impl
  - eligible address ranges returning too many ranges
  - occasionally, overwrite all *true* eligible address ranges

* causal data updates

- reduce scoped ranges to symbol ranges
- is_eligible_address() returns true contains (not just coarse)
- revert some sample_selection behavior

* binary address_multirange updates

- make coarse_range private
- fix operator+=(pair<coarse, uintptr_t>)

* causal example update

- fix nsync to default to once per iteration

* binary analysis updates

- tweak header file includes

* causal updates

- remove factoring in sleep_for_overhead
- invoke delay::process() even if experiment is not active

* causal data updates

- update latest_eligible_pc structure

* update omnitrace-install.py.in

- fix support for fedora
  - /etc/os-release does not have ID_LIKE
  - fallback to RHEL 8.7 if version not specified

* update omnitrace-install.py.in

- fix support for debian
  - /etc/os-release does not have ID_LIKE
  - version mapping

* Update documentation

- update docs on installation

* causal data and experiment updates

- data: reset_sample_selection

* causal set_current_selection debugging

- debug messages for failed e2e runs

* causal data and backtrace component updates

- data: set_current_selection returns the number of eligible addresses added
- backtrace: if cputime signal has selected zero IPs > 5x, then realtime signal starts contributing call-stacks

* core library updates

- move config::parse_numeric_range to utility namespace
- add core/utility.cpp
- support range:increment, e.g. 5-25:10 expands to '5 15 25' instead of '5 10 15 20 25'

* omnitrace-causal update

- end-to-end expands all speedups
- support range:increment in speedups

* causal backtrace updates

- remove select_ival (realtime signal always contributes when select_count == 0)

* containers: static_vector update

- explicit c_array constructor
- explicit std::array constructor

* causal data updates

- remove set_current_selection(uint64_t)
- remove set_current_selection(std::array)
- sample_selection increase default wait time
- report eligible PC candidates
- move reset_sample_selection to perform_experiment_impl
- decrease latest_eligible_pc array size
- set_current_selection does not guard for experiment::active

* core debug updates

- OMNITRACE_PRINT_COLOR macros

* causal data updates

- tweak to experiment never started message

* causal gotcha updates

- remove unused code

* critical trace updates

- remove unused code

* omnitrace-causal

- OMNITRACE_LAUNCHER

* causal data updates

- don't fail on end-to-end + omnitrace-causal

* causal backtrace updates

- reintroduce select_ival behavior

* causal data updates

- tweak verbose messages about number of PC candidates

* core mproc updates

- utilities for waiting on child PID and diagnosing status
  - omnitrace::mproc::wait_pid
  - omnitrace::mproc::diagnose_status

* omnitrace-run updates

- support --fork argument for executing via fork in current process + execvpe on child instead of execvpe in current process

* omnitrace-causal updates

- wait_pid and diagnose_status just call equivalent functions in omnitrace::mproc

* ubuntu-focal workflow update

- attempt to launch ubuntu-focal-codecov job with CAP_SYS_ADMIN and use perf backend

* tests reorg and updates

- remove binary-rewrite-sampling and runtime-instrument-sampling tests
- rename *-preload tests (which use omnitrace-sample exe) to *-sampling
- split tests/CMakeLists.txt into several tests/omnitrace-<category>-tests.cmake files
- tweak to causal-both-omni-func test
  - add args: -n 2 -b timer

* update validate-causal-json.py

- better reasoning info for adjusting tolerance
- always apply tolerance adjustments in CI mode

* causal e2e tests update

- add label "causal-e2e" label
- tweak params
  - old: 80 12 432525 500000000
  - new: 80 50 432525 100000000
- disable processor affinity for slow-func/line-100 tests
  - artificially inflates some speedups with perf

* unblocking_gotcha updates

- overload operator() according to gotcha function index

* blocking_gotcha updates

- overload operator() according to gotcha function index
- fix bug where potentially post block functors (e.g. pthread_mutex_trylock) throw error if lock is not acquired.

* parse_numeric_range update

- support unordered_set

* config update

- OMNITRACE_DEBUG_{TIDS,PIDS} use parse_numeric_range
2023-04-13 02:14:35 -05:00

294 lines
9.8 KiB
Python
Executable File

#!/usr/bin/env python3
import os
import re
import sys
import stat
import argparse
import tempfile
import subprocess as sp
from urllib import request
from urllib.error import HTTPError
omnitrace_version = "@OMNITRACE_VERSION@"
_rocm_path = os.environ.get("ROCM_PATH", "/opt/rocm")
_rocm_version = None
def get_rocm_version(rocm_hint):
global _rocm_path
global _rocm_version
if rocm_hint is not None and rocm_hint is not True:
if rocm_hint.replace(".", "0").isnumeric():
_rocm_version = rocm_hint
else:
_rocm_path = rocm_hint
def _parse_version(_v):
return re.split(r"[\\.-]", _v) if _v is not None else None
_version = _parse_version(_rocm_version)
for fname in [
"version",
"version-dev",
"version-hip-libraries",
"version-hiprt",
"version-hiprt-devel",
"version-hip-sdk",
"version-libs",
"version-utils",
]:
if _version is not None and len(_version) > 0:
break
_fname = os.path.join(_rocm_path, ".info", fname)
if os.path.exists(_fname):
with open(_fname, "r") as f:
_version = _parse_version(f.readlines()[0].strip("\n"))
if _version is not None and len(_version) > 0:
_major = int(_version[0])
_minor = int(_version[1]) if len(_version) >= 2 else 0
_rocm_version = f"{_major}.{_minor}"
return "-ROCm-{}".format((10000 * _major) + (100 * _minor))
return None
def get_os_info(os_distrib, os_version):
_os_info = {}
with open("/etc/os-release", "r") as f:
for line in [_v.strip() for _v in f.readlines()]:
if "=" not in line:
continue
_key, _data = line.split("=", 1)
_os_info[_key] = _data.strip('"')
def _parse_version(_v):
_version = re.split(r"[\\.-]", _v)
return (
"{}.{}".format(_version[0], _version[1])
if len(_version) > 1
else "{}".format(_version[0])
)
if os_distrib is None or os_distrib == "auto":
if "ubuntu" in _os_info["ID"]:
os_distrib = "ubuntu"
elif "opensuse" in _os_info["ID"]:
os_distrib = "opensuse"
elif "rhel" in _os_info["ID"]:
os_distrib = "rhel"
elif "centos" in _os_info["ID"]:
os_distrib = "rhel"
elif "rockylinux" in _os_info["ID"]:
os_distrib = "rhel"
elif "debian" in _os_info["ID"]:
os_distrib = "ubuntu"
if "debian" in _os_info["ID"] and os_version is None:
_debian_version = float(_parse_version(_os_info["VERSION_ID"]))
if _debian_version >= 11.0:
os_version = "20.04"
else:
os_version = "18.04"
elif "fedora" in _os_info["ID"]:
os_distrib = "rhel"
# fedora has different versioning system so fallback to 8.7
if os_version is None:
os_version = "8.7"
else:
# if we don't have an exact match, check ID_LIKE
if "ID_LIKE" not in _os_info.keys():
_os_info["ID_LIKE"] = _os_info["ID"]
if "debian" in _os_info["ID_LIKE"]:
os_distrib = "ubuntu"
if os_version is None:
# fallback on 18.04 if ID is not ubuntu but debian-like
os_version = "18.04"
elif "suse" in _os_info["ID_LIKE"]:
os_distrib = "opensuse"
# fallback on 15.3 if ID is not opensuse but suse-like
if os_version is None:
os_version = "15.3"
elif "rhel" in _os_info["ID_LIKE"] or "centos" in _os_info["ID_LIKE"]:
os_distrib = "rhel"
if os_version is None:
os_version = "8.7"
else:
raise RuntimeError(
"Unknown ID_LIKE value in /etc/os-release: {}".format(
_os_info["ID_LIKE"]
)
)
elif os_distrib == "centos":
os_distrib = "rhel"
# uses same versioning system
elif os_distrib == "fedora":
os_distrib = "rhel"
if os_version is None:
# fedora has different versioning system so fallback to 8.7
os_version = "8.7"
if os_version is None:
os_version = _parse_version(_os_info["VERSION_ID"])
return (os_distrib, os_version)
def print_log(*args, **kwargs):
sys.stdout.flush()
sys.stderr.flush()
sys.stderr.write("### ")
sys.stderr.write(*args, **kwargs)
sys.stderr.write("\n")
sys.stderr.flush()
def run(*args, **kwargs):
print_log("Executing: {}\n".format(" ".join(*args)))
sp.run(*args, **kwargs, check=True)
sys.stderr.write("\n")
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument(
"--version",
help="Print omnitrace version which will be installed",
action="store_true",
)
parser.add_argument(
"-p", "--prefix", help="Installation prefix", type=str, default="/opt/omnitrace"
)
parser.add_argument(
"-i",
"--interactive",
help="Prompt to accept the license and include/exclude subdirectory",
action="store_true",
)
parser.add_argument(
"-D",
"--download-path",
help="Download directory (default: temporary directory)",
type=str,
default=None,
)
parser.add_argument(
"-d",
"--os-distrib",
help="Target OS distribution",
type=str,
default=None,
choices=("auto", "ubuntu", "opensuse", "rhel", "centos", "fedora"),
)
parser.add_argument(
"-v", "--os-version", help="Target OS version", type=str, default=None
)
parser.add_argument(
"-k",
"--keep-download",
help="Do not delete downloaded file as installation",
action="store_true",
)
parser.add_argument(
"--rocm",
help="Install omnitrace with ROCm support. Accepts either a ROCm version (e.g. '5.4') or the root path to the ROCm install containing .info/version* file(s) (e.g. /opt/rocm if /opt/rocm/.info/version exists). If no argument is provided, the ROCm version will attempted to be deduced from $ENV{ROCM_PATH}/.info/version",
nargs="?",
default=None,
const=True,
metavar="VERSION or ROCM_PATH with .info/version file(s)",
)
# right now, only valid set of extensions are: papi + ompt + python3
# in the future, this might change, e.g. MPI variants
parser.add_argument(
"-e",
"--extensions",
help="Omnitrace extensions, e.g. PAPI, OMPT, and Python3",
nargs="*",
default=("papi", "ompt", "python3"),
choices=("papi", "ompt", "python3"),
)
args = parser.parse_args()
if args.version:
print(f"omnitrace {omnitrace_version}")
sys.exit(0)
os_distrib, os_version = get_os_info(args.os_distrib, args.os_version)
rocm_version = get_rocm_version(args.rocm) if args.rocm is not None else ""
extensions = ""
if "papi" in args.extensions:
extensions += "-PAPI"
if "ompt" in args.extensions:
extensions += "-OMPT"
if "python3" in args.extensions:
extensions += "-Python3"
if rocm_version is None:
raise RuntimeError(
f"Error! ROCm version could not be determined from {_rocm_path}/.info/version*. Please provide a ROCm version or the root path to the ROCm install containing the .info directory, e.g. '--rocm 5.4' or '--rocm /path/to/rocm/install'"
)
script = f"omnitrace-{omnitrace_version}-{os_distrib}-{os_version}{rocm_version}{extensions}.sh"
url = f"https://github.com/AMDResearch/omnitrace/releases/download/v{omnitrace_version}/{script}"
download_dir = (
tempfile.mkdtemp(prefix="omnitrace-install-")
if args.download_path is None
else args.download_path
)
install_script = os.path.join(download_dir, script)
try:
if not os.path.exists(download_dir):
print_log(f"Creating download directory: {download_dir} ...")
os.makedirs(download_dir)
print_log(f"Downloading {url} ...")
try:
response = request.urlretrieve(url, install_script)
except HTTPError as e:
print_log(f"")
print_log(f"Error: {e}")
print_log(f"")
print_log(f"Error: Installer script download from {url} failed!")
if args.rocm is not None:
print_log(
f"There may not be a pre-built installer for ROCm version {_rocm_version}"
)
sys.exit(-1)
if os.path.exists(install_script):
print_log(f"Download completed: {install_script}")
else:
raise RuntimeError(f"Download completed but {install_script} does not exist")
os.chmod(install_script, stat.S_IRWXU)
if not os.path.exists(args.prefix):
print_log(f"Creating directory: {args.prefix} ...")
os.makedirs(args.prefix)
install_args = (
["--exclude-subdir", "--skip-license"] if not args.interactive else []
)
print_log(f"Installing omnitrace to {args.prefix} ...")
run([install_script, f"--prefix={args.prefix}"] + install_args)
print_log(
f"omnitrace v{omnitrace_version} installation to {args.prefix} succeeded!"
)
finally:
if not args.keep_download:
print_log(f"Removing install script {install_script} ...")
os.remove(install_script)
# remove the directory if it is a temporary directory
if args.download_path is None:
print_log(f"Removing temporary directory {download_dir} ...")
os.rmdir(download_dir)