You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/buckifier/buckify_rocksdb.py

310 lines
11 KiB

# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals
try:
from builtins import str
except ImportError:
from __builtin__ import str
from targets_builder import TARGETSBuilder
import json
import os
import fnmatch
import sys
from util import ColorString
# This script generates TARGETS file for Buck.
# Buck is a build tool specifying dependencies among different build targets.
# User can pass extra dependencies as a JSON object via command line, and this
# script can include these dependencies in the generate TARGETS file.
# Usage:
# $python3 buckifier/buckify_rocksdb.py
# (This generates a TARGET file without user-specified dependency for unit
# tests.)
# $python3 buckifier/buckify_rocksdb.py \
# '{"fake": {
# "extra_deps": [":test_dep", "//fakes/module:mock1"],
# "extra_compiler_flags": ["-DROCKSDB_LITE", "-Os"]
# }
# }'
# (Generated TARGETS file has test_dep and mock1 as dependencies for RocksDB
# unit tests, and will use the extra_compiler_flags to compile the unit test
# source.)
# tests to export as libraries for inclusion in other projects
_EXPORTED_TEST_LIBS = ["env_basic_test"]
# Parse src.mk files as a Dictionary of
# VAR_NAME => list of files
def parse_src_mk(repo_path):
src_mk = repo_path + "/src.mk"
src_files = {}
for line in open(src_mk):
line = line.strip()
if len(line) == 0 or line[0] == '#':
continue
if '=' in line:
current_src = line.split('=')[0].strip()
src_files[current_src] = []
elif '.c' in line:
src_path = line.split('\\')[0].strip()
src_files[current_src].append(src_path)
return src_files
# get all .cc / .c files
def get_cc_files(repo_path):
cc_files = []
for root, dirnames, filenames in os.walk(repo_path): # noqa: B007 T25377293 Grandfathered in
root = root[(len(repo_path) + 1):]
if "java" in root:
# Skip java
continue
for filename in fnmatch.filter(filenames, '*.cc'):
cc_files.append(os.path.join(root, filename))
for filename in fnmatch.filter(filenames, '*.c'):
cc_files.append(os.path.join(root, filename))
return cc_files
# Get non_parallel tests from Makefile
def get_non_parallel_tests(repo_path):
Makefile = repo_path + "/Makefile"
s = set({})
found_non_parallel_tests = False
for line in open(Makefile):
line = line.strip()
if line.startswith("NON_PARALLEL_TEST ="):
found_non_parallel_tests = True
elif found_non_parallel_tests:
if line.endswith("\\"):
# remove the trailing \
line = line[:-1]
line = line.strip()
s.add(line)
else:
# we consumed all the non_parallel tests
break
return s
# Parse extra dependencies passed by user from command line
def get_dependencies():
deps_map = {
'': {
'extra_deps': [],
'extra_compiler_flags': []
}
}
if len(sys.argv) < 2:
return deps_map
def encode_dict(data):
rv = {}
for k, v in data.items():
if isinstance(v, dict):
v = encode_dict(v)
rv[k] = v
return rv
extra_deps = json.loads(sys.argv[1], object_hook=encode_dict)
for target_alias, deps in extra_deps.items():
deps_map[target_alias] = deps
return deps_map
# Prepare TARGETS file for buck
def generate_targets(repo_path, deps_map):
print(ColorString.info("Generating TARGETS"))
# parsed src.mk file
src_mk = parse_src_mk(repo_path)
# get all .cc files
cc_files = get_cc_files(repo_path)
# get non_parallel tests from Makefile
non_parallel_tests = get_non_parallel_tests(repo_path)
if src_mk is None or cc_files is None or non_parallel_tests is None:
return False
extra_argv = ""
if len(sys.argv) >= 2:
# Heuristically quote and canonicalize whitespace for inclusion
# in how the file was generated.
extra_argv = " '{0}'".format(" ".join(sys.argv[1].split()))
TARGETS = TARGETSBuilder("%s/TARGETS" % repo_path, extra_argv)
# rocksdb_lib
TARGETS.add_library(
"rocksdb_lib",
src_mk["LIB_SOURCES"] +
# always add range_tree, it's only excluded on ppc64, which we don't use internally
src_mk["RANGE_TREE_SOURCES"] +
Meta-internal folly integration with F14FastMap (#9546) Summary: Especially after updating to C++17, I don't see a compelling case for *requiring* any folly components in RocksDB. I was able to purge the existing hard dependencies, and it can be quite difficult to strip out non-trivial components from folly for use in RocksDB. (The prospect of doing that on F14 has changed my mind on the best approach here.) But this change creates an optional integration where we can plug in components from folly at compile time, starting here with F14FastMap to replace std::unordered_map when possible (probably no public APIs for example). I have replaced the biggest CPU users of std::unordered_map with compile-time pluggable UnorderedMap which will use F14FastMap when USE_FOLLY is set. USE_FOLLY is always set in the Meta-internal buck build, and a simulation of that is in the Makefile for public CI testing. A full folly build is not needed, but checking out the full folly repo is much simpler for getting the dependency, and anything else we might want to optionally integrate in the future. Some picky details: * I don't think the distributed mutex stuff is actually used, so it was easy to remove. * I implemented an alternative to `folly::constexpr_log2` (which is much easier in C++17 than C++11) so that I could pull out the hard dependencies on `ConstexprMath.h` * I had to add noexcept move constructors/operators to some types to make F14's complainUnlessNothrowMoveAndDestroy check happy, and I added a macro to make that easier in some common cases. * Updated Meta-internal buck build to use folly F14Map (always) No updates to HISTORY.md nor INSTALL.md as this is not (yet?) considered a production integration for open source users. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9546 Test Plan: CircleCI tests updated so that a couple of them use folly. Most internal unit & stress/crash tests updated to use Meta-internal latest folly. (Note: they should probably use buck but they currently use Makefile.) Example performance improvement: when filter partitions are pinned in cache, they are tracked by PartitionedFilterBlockReader::filter_map_ and we can build a test that exercises that heavily. Build DB with ``` TEST_TMPDIR=/dev/shm/rocksdb ./db_bench -benchmarks=fillrandom -num=10000000 -disable_wal=1 -write_buffer_size=30000000 -bloom_bits=16 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0 -partition_index_and_filters ``` and test with (simultaneous runs with & without folly, ~20 times each to see convergence) ``` TEST_TMPDIR=/dev/shm/rocksdb ./db_bench_folly -readonly -use_existing_db -benchmarks=readrandom -num=10000000 -bloom_bits=16 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0 -partition_index_and_filters -duration=40 -pin_l0_filter_and_index_blocks_in_cache ``` Average ops/s no folly: 26229.2 Average ops/s with folly: 26853.3 (+2.4%) Reviewed By: ajkr Differential Revision: D34181736 Pulled By: pdillinger fbshipit-source-id: ffa6ad5104c2880321d8a1aa7187e00ab0d02e94
3 years ago
src_mk["TOOL_LIB_SOURCES"],
deps=["//folly/container:f14_hash"])
# rocksdb_whole_archive_lib
TARGETS.add_library(
"rocksdb_whole_archive_lib",
src_mk["LIB_SOURCES"] +
# always add range_tree, it's only excluded on ppc64, which we don't use internally
src_mk["RANGE_TREE_SOURCES"] +
src_mk["TOOL_LIB_SOURCES"],
Meta-internal folly integration with F14FastMap (#9546) Summary: Especially after updating to C++17, I don't see a compelling case for *requiring* any folly components in RocksDB. I was able to purge the existing hard dependencies, and it can be quite difficult to strip out non-trivial components from folly for use in RocksDB. (The prospect of doing that on F14 has changed my mind on the best approach here.) But this change creates an optional integration where we can plug in components from folly at compile time, starting here with F14FastMap to replace std::unordered_map when possible (probably no public APIs for example). I have replaced the biggest CPU users of std::unordered_map with compile-time pluggable UnorderedMap which will use F14FastMap when USE_FOLLY is set. USE_FOLLY is always set in the Meta-internal buck build, and a simulation of that is in the Makefile for public CI testing. A full folly build is not needed, but checking out the full folly repo is much simpler for getting the dependency, and anything else we might want to optionally integrate in the future. Some picky details: * I don't think the distributed mutex stuff is actually used, so it was easy to remove. * I implemented an alternative to `folly::constexpr_log2` (which is much easier in C++17 than C++11) so that I could pull out the hard dependencies on `ConstexprMath.h` * I had to add noexcept move constructors/operators to some types to make F14's complainUnlessNothrowMoveAndDestroy check happy, and I added a macro to make that easier in some common cases. * Updated Meta-internal buck build to use folly F14Map (always) No updates to HISTORY.md nor INSTALL.md as this is not (yet?) considered a production integration for open source users. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9546 Test Plan: CircleCI tests updated so that a couple of them use folly. Most internal unit & stress/crash tests updated to use Meta-internal latest folly. (Note: they should probably use buck but they currently use Makefile.) Example performance improvement: when filter partitions are pinned in cache, they are tracked by PartitionedFilterBlockReader::filter_map_ and we can build a test that exercises that heavily. Build DB with ``` TEST_TMPDIR=/dev/shm/rocksdb ./db_bench -benchmarks=fillrandom -num=10000000 -disable_wal=1 -write_buffer_size=30000000 -bloom_bits=16 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0 -partition_index_and_filters ``` and test with (simultaneous runs with & without folly, ~20 times each to see convergence) ``` TEST_TMPDIR=/dev/shm/rocksdb ./db_bench_folly -readonly -use_existing_db -benchmarks=readrandom -num=10000000 -bloom_bits=16 -compaction_style=2 -fifo_compaction_max_table_files_size_mb=10000 -fifo_compaction_allow_compaction=0 -partition_index_and_filters -duration=40 -pin_l0_filter_and_index_blocks_in_cache ``` Average ops/s no folly: 26229.2 Average ops/s with folly: 26853.3 (+2.4%) Reviewed By: ajkr Differential Revision: D34181736 Pulled By: pdillinger fbshipit-source-id: ffa6ad5104c2880321d8a1aa7187e00ab0d02e94
3 years ago
deps=["//folly/container:f14_hash"],
headers=None,
extra_external_deps="",
link_whole=True)
# rocksdb_test_lib
TARGETS.add_library(
"rocksdb_test_lib",
src_mk.get("MOCK_LIB_SOURCES", []) +
src_mk.get("TEST_LIB_SOURCES", []) +
src_mk.get("EXP_LIB_SOURCES", []) +
src_mk.get("ANALYZER_LIB_SOURCES", []),
[":rocksdb_lib"],
extra_test_libs=True
)
# rocksdb_tools_lib
TARGETS.add_library(
"rocksdb_tools_lib",
src_mk.get("BENCH_LIB_SOURCES", []) +
src_mk.get("ANALYZER_LIB_SOURCES", []) +
["test_util/testutil.cc"],
[":rocksdb_lib"])
# rocksdb_cache_bench_tools_lib
TARGETS.add_library(
"rocksdb_cache_bench_tools_lib",
src_mk.get("CACHE_BENCH_LIB_SOURCES", []),
[":rocksdb_lib"])
# rocksdb_stress_lib
TARGETS.add_rocksdb_library(
"rocksdb_stress_lib",
src_mk.get("ANALYZER_LIB_SOURCES", [])
+ src_mk.get('STRESS_LIB_SOURCES', [])
+ ["test_util/testutil.cc"])
# db_stress binary
TARGETS.add_binary("db_stress",
["db_stress_tool/db_stress.cc"],
[":rocksdb_stress_lib"])
# bench binaries
for src in src_mk.get("MICROBENCH_SOURCES", []):
name = src.rsplit('/',1)[1].split('.')[0] if '/' in src else src.split('.')[0]
TARGETS.add_binary(
name,
[src],
[],
extra_bench_libs=True
)
print("Extra dependencies:\n{0}".format(json.dumps(deps_map)))
# Dictionary test executable name -> relative source file path
test_source_map = {}
# c_test.c is added through TARGETS.add_c_test(). If there
# are more than one .c test file, we need to extend
# TARGETS.add_c_test() to include other C tests too.
for test_src in src_mk.get("TEST_MAIN_SOURCES_C", []):
if test_src != 'db/c_test.c':
print("Don't know how to deal with " + test_src)
return False
TARGETS.add_c_test()
try:
with open(f"{repo_path}/buckifier/bench.json") as json_file:
fast_fancy_bench_config_list = json.load(json_file)
for config_dict in fast_fancy_bench_config_list:
clean_benchmarks = {}
benchmarks = config_dict['benchmarks']
for binary, benchmark_dict in benchmarks.items():
clean_benchmarks[binary] = {}
for benchmark, overloaded_metric_list in benchmark_dict.items():
clean_benchmarks[binary][benchmark] = []
for metric in overloaded_metric_list:
if not isinstance(metric, dict):
clean_benchmarks[binary][benchmark].append(metric)
TARGETS.add_fancy_bench_config(config_dict['name'], clean_benchmarks, False, config_dict['expected_runtime_one_iter'], config_dict['sl_iterations'], config_dict['regression_threshold'])
with open(f"{repo_path}/buckifier/bench-slow.json") as json_file:
slow_fancy_bench_config_list = json.load(json_file)
for config_dict in slow_fancy_bench_config_list:
clean_benchmarks = {}
benchmarks = config_dict['benchmarks']
for binary, benchmark_dict in benchmarks.items():
clean_benchmarks[binary] = {}
for benchmark, overloaded_metric_list in benchmark_dict.items():
clean_benchmarks[binary][benchmark] = []
for metric in overloaded_metric_list:
if not isinstance(metric, dict):
clean_benchmarks[binary][benchmark].append(metric)
for config_dict in slow_fancy_bench_config_list:
TARGETS.add_fancy_bench_config(config_dict['name']+"_slow", clean_benchmarks, True, config_dict['expected_runtime_one_iter'], config_dict['sl_iterations'], config_dict['regression_threshold'])
# it is better servicelab experiments break
# than rocksdb github ci
except Exception:
pass
TARGETS.add_test_header()
for test_src in src_mk.get("TEST_MAIN_SOURCES", []):
test = test_src.split('.c')[0].strip().split('/')[-1].strip()
test_source_map[test] = test_src
print("" + test + " " + test_src)
for target_alias, deps in deps_map.items():
for test, test_src in sorted(test_source_map.items()):
if len(test) == 0:
print(ColorString.warning("Failed to get test name for %s" % test_src))
continue
test_target_name = \
test if not target_alias else test + "_" + target_alias
if test in _EXPORTED_TEST_LIBS:
test_library = "%s_lib" % test_target_name
TARGETS.add_library(test_library, [test_src], deps=[":rocksdb_test_lib"], extra_test_libs=True)
TARGETS.register_test(
test_target_name,
test_src,
deps = json.dumps(deps['extra_deps'] + [':'+test_library]),
extra_compiler_flags = json.dumps(deps['extra_compiler_flags']))
else:
TARGETS.register_test(
test_target_name,
test_src,
deps = json.dumps(deps['extra_deps'] + [":rocksdb_test_lib"] ),
extra_compiler_flags = json.dumps(deps['extra_compiler_flags']))
print(ColorString.info("Generated TARGETS Summary:"))
print(ColorString.info("- %d libs" % TARGETS.total_lib))
print(ColorString.info("- %d binarys" % TARGETS.total_bin))
print(ColorString.info("- %d tests" % TARGETS.total_test))
return True
def get_rocksdb_path():
# rocksdb = {script_dir}/..
script_dir = os.path.dirname(sys.argv[0])
script_dir = os.path.abspath(script_dir)
rocksdb_path = os.path.abspath(
os.path.join(script_dir, "../"))
return rocksdb_path
def exit_with_error(msg):
print(ColorString.error(msg))
sys.exit(1)
def main():
deps_map = get_dependencies()
# Generate TARGETS file for buck
ok = generate_targets(get_rocksdb_path(), deps_map)
if not ok:
exit_with_error("Failed to generate TARGETS files")
if __name__ == "__main__":
main()