lbrycrd/test/functional/test_runner.py

525 lines
20 KiB
Python
Raw Normal View History

2016-03-19 20:58:06 +01:00
#!/usr/bin/env python3
# Copyright (c) 2014-2016 The Bitcoin Core developers
# Distributed under the MIT software license, see the accompanying
# file COPYING or http://www.opensource.org/licenses/mit-license.php.
"""Run regression test suite.
This module calls down into individual test cases via subprocess. It will
forward all unrecognized arguments onto the individual test scripts.
Functional tests are disabled on Windows by default. Use --force to run them anyway.
For a description of arguments recognized by test scripts, see
`test/functional/test_framework/test_framework.py:BitcoinTestFramework.main`.
"""
import argparse
import configparser
2017-05-18 23:33:33 +02:00
import datetime
import os
import time
import shutil
import signal
import sys
import subprocess
import tempfile
import re
import logging
# Formatting. Default colors to empty strings.
BOLD, BLUE, RED, GREY = ("", ""), ("", ""), ("", ""), ("", "")
2017-04-17 19:46:20 +02:00
try:
# Make sure python thinks it can write unicode to its stdout
"\u2713".encode("utf_8").decode(sys.stdout.encoding)
TICK = ""
CROSS = ""
CIRCLE = ""
except UnicodeDecodeError:
TICK = "P "
CROSS = "x "
CIRCLE = "o "
if os.name == 'posix':
# primitive formatting on supported
# terminal via ANSI escape sequences:
BOLD = ('\033[0m', '\033[1m')
BLUE = ('\033[0m', '\033[0;34m')
RED = ('\033[0m', '\033[0;31m')
GREY = ('\033[0m', '\033[1;30m')
TEST_EXIT_PASSED = 0
TEST_EXIT_SKIPPED = 77
BASE_SCRIPTS= [
# Scripts that are run by the travis build process.
# Longest test should go first, to favor running tests in parallel
2016-12-03 21:46:33 +01:00
'wallet-hd.py',
'walletbackup.py',
2016-12-03 21:46:33 +01:00
# vv Tests less than 5m vv
'p2p-fullblocktest.py',
'fundrawtransaction.py',
'p2p-compactblocks.py',
'segwit.py',
# vv Tests less than 2m vv
'wallet.py',
2016-08-04 04:28:39 +02:00
'wallet-accounts.py',
2016-12-03 21:46:33 +01:00
'p2p-segwit.py',
'wallet-dump.py',
'listtransactions.py',
2016-12-03 21:46:33 +01:00
# vv Tests less than 60s vv
'sendheaders.py',
'zapwallettxes.py',
'importmulti.py',
'mempool_limit.py',
'merkle_blocks.py',
2015-11-14 21:44:35 +01:00
'receivedby.py',
2016-12-03 21:46:33 +01:00
'abandonconflict.py',
'bip68-112-113-p2p.py',
'rawtransactions.py',
'reindex.py',
# vv Tests less than 30s vv
2017-06-07 22:14:20 +02:00
'zmq_test.py',
'mempool_resurrect_test.py',
'txn_doublespend.py --mineblock',
'txn_clone.py',
'getchaintips.py',
'rest.py',
'mempool_spendcoinbase.py',
'mempool_reorg.py',
'mempool_persist.py',
'httpbasics.py',
'multi_rpc.py',
'proxy_test.py',
'signrawtransactions.py',
'disconnect_ban.py',
'decodescript.py',
'blockchain.py',
'disablewallet.py',
2017-03-25 15:29:56 +01:00
'net.py',
'keypool.py',
'p2p-mempool.py',
2015-11-19 02:55:52 +01:00
'prioritise_transaction.py',
'invalidblockrequest.py',
'invalidtxrequest.py',
2016-03-15 17:09:16 +01:00
'p2p-versionbits-warning.py',
'preciousblock.py',
2016-02-19 01:31:12 +01:00
'importprunedfunds.py',
'signmessages.py',
2016-08-31 13:38:23 +02:00
'nulldummy.py',
'import-rescan.py',
'bumpfee.py',
'rpcnamedargs.py',
'listsinceblock.py',
'p2p-leaktests.py',
'wallet-encryption.py',
'uptime.py',
]
EXTENDED_SCRIPTS = [
# These tests are not run by the travis build process.
# Longest test should go first, to favor running tests in parallel
2016-12-03 21:46:33 +01:00
'pruning.py',
# vv Tests less than 20m vv
'smartfees.py',
# vv Tests less than 5m vv
'maxuploadtarget.py',
'mempool_packages.py',
'dbcrash.py',
2016-12-03 21:46:33 +01:00
# vv Tests less than 2m vv
'bip68-sequence.py',
'getblocktemplate_longpoll.py',
2017-02-07 23:43:36 +01:00
'p2p-timeouts.py',
2016-12-03 21:46:33 +01:00
# vv Tests less than 60s vv
'bip9-softforks.py',
2016-12-03 21:46:33 +01:00
'p2p-feefilter.py',
'rpcbind_test.py',
# vv Tests less than 30s vv
'assumevalid.py',
'bip65-cltv.py',
'bip65-cltv-p2p.py',
'bipdersig-p2p.py',
'bipdersig.py',
2017-06-15 21:29:53 +02:00
'example_test.py',
'getblocktemplate_proposals.py',
'txn_doublespend.py',
'txn_clone.py --mineblock',
'forknotify.py',
'invalidateblock.py',
'p2p-acceptblock.py',
2015-10-30 19:55:32 +01:00
'replace-by-fee.py',
]
# Place EXTENDED_SCRIPTS first since it has the 3 longest running tests
ALL_SCRIPTS = EXTENDED_SCRIPTS + BASE_SCRIPTS
NON_SCRIPTS = [
# These are python files that live in the functional tests directory, but are not test scripts.
"combine_logs.py",
"create_cache.py",
"test_runner.py",
]
def main():
# Parse arguments and pass through unrecognised args
parser = argparse.ArgumentParser(add_help=False,
usage='%(prog)s [test_runner.py options] [script options] [scripts]',
description=__doc__,
epilog='''
Help text and arguments for individual test script:''',
formatter_class=argparse.RawTextHelpFormatter)
parser.add_argument('--coverage', action='store_true', help='generate a basic coverage report for the RPC interface')
parser.add_argument('--exclude', '-x', help='specify a comma-seperated-list of scripts to exclude.')
parser.add_argument('--extended', action='store_true', help='run the extended test suite in addition to the basic tests')
parser.add_argument('--force', '-f', action='store_true', help='run tests even on platforms where they are disabled by default (e.g. windows).')
parser.add_argument('--help', '-h', '-?', action='store_true', help='print help text and exit')
parser.add_argument('--jobs', '-j', type=int, default=4, help='how many test scripts to run in parallel. Default=4.')
parser.add_argument('--keepcache', '-k', action='store_true', help='the default behavior is to flush the cache directory on startup. --keepcache retains the cache from the previous testrun.')
parser.add_argument('--quiet', '-q', action='store_true', help='only print results summary and failure logs')
2017-05-18 23:33:33 +02:00
parser.add_argument('--tmpdirprefix', '-t', default=tempfile.gettempdir(), help="Root directory for datadirs")
args, unknown_args = parser.parse_known_args()
# args to be passed on always start with two dashes; tests are the remaining unknown args
tests = [arg for arg in unknown_args if arg[:2] != "--"]
passon_args = [arg for arg in unknown_args if arg[:2] == "--"]
# Read config generated by configure.
config = configparser.ConfigParser()
configfile = os.path.abspath(os.path.dirname(__file__)) + "/../config.ini"
config.read_file(open(configfile))
passon_args.append("--configfile=%s" % configfile)
# Set up logging
logging_level = logging.INFO if args.quiet else logging.DEBUG
logging.basicConfig(format='%(message)s', level=logging_level)
2017-05-18 23:33:33 +02:00
# Create base test directory
tmpdir = "%s/bitcoin_test_runner_%s" % (args.tmpdirprefix, datetime.datetime.now().strftime("%Y%m%d_%H%M%S"))
os.makedirs(tmpdir)
logging.debug("Temporary test directory at %s" % tmpdir)
enable_wallet = config["components"].getboolean("ENABLE_WALLET")
enable_utils = config["components"].getboolean("ENABLE_UTILS")
enable_bitcoind = config["components"].getboolean("ENABLE_BITCOIND")
if config["environment"]["EXEEXT"] == ".exe" and not args.force:
# https://github.com/bitcoin/bitcoin/commit/d52802551752140cf41f0d9a225a43e84404d3e9
# https://github.com/bitcoin/bitcoin/pull/5677#issuecomment-136646964
print("Tests currently disabled on Windows by default. Use --force option to enable")
sys.exit(0)
if not (enable_wallet and enable_utils and enable_bitcoind):
print("No functional tests to run. Wallet, utils, and bitcoind must all be enabled")
print("Rerun `configure` with -enable-wallet, -with-utils and -with-daemon and rerun make")
sys.exit(0)
# Build list of tests
if tests:
# Individual tests have been specified. Run specified tests that exist
# in the ALL_SCRIPTS list. Accept the name with or without .py extension.
tests = [re.sub("\.py$", "", t) + ".py" for t in tests]
test_list = []
for t in tests:
if t in ALL_SCRIPTS:
test_list.append(t)
else:
print("{}WARNING!{} Test '{}' not found in full test list.".format(BOLD[1], BOLD[0], t))
else:
# No individual tests have been specified.
# Run all base tests, and optionally run extended tests.
test_list = BASE_SCRIPTS
if args.extended:
# place the EXTENDED_SCRIPTS first since the three longest ones
# are there and the list is shorter
test_list = EXTENDED_SCRIPTS + test_list
2017-02-15 15:59:19 +01:00
# Remove the test cases that the user has explicitly asked to exclude.
if args.exclude:
tests_excl = [re.sub("\.py$", "", t) + ".py" for t in args.exclude.split(',')]
for exclude_test in tests_excl:
if exclude_test in test_list:
test_list.remove(exclude_test)
else:
print("{}WARNING!{} Test '{}' not found in current test list.".format(BOLD[1], BOLD[0], exclude_test))
2017-02-15 15:59:19 +01:00
if not test_list:
print("No valid test scripts specified. Check that your test is in one "
"of the test lists in test_runner.py, or run test_runner.py with no arguments to run all tests")
2017-02-15 15:59:19 +01:00
sys.exit(0)
if args.help:
2017-03-23 18:54:18 +01:00
# Print help for test_runner.py, then print help of the first script (with args removed) and exit.
parser.print_help()
2017-03-23 18:54:18 +01:00
subprocess.check_call([(config["environment"]["SRCDIR"] + '/test/functional/' + test_list[0].split()[0])] + ['-h'])
sys.exit(0)
check_script_list(config["environment"]["SRCDIR"])
if not args.keepcache:
shutil.rmtree("%s/test/cache" % config["environment"]["BUILDDIR"], ignore_errors=True)
2017-05-18 23:33:33 +02:00
run_tests(test_list, config["environment"]["SRCDIR"], config["environment"]["BUILDDIR"], config["environment"]["EXEEXT"], tmpdir, args.jobs, args.coverage, passon_args)
2017-05-18 23:33:33 +02:00
def run_tests(test_list, src_dir, build_dir, exeext, tmpdir, jobs=1, enable_coverage=False, args=[]):
2017-04-12 16:41:13 +02:00
# Warn if bitcoind is already running (unix only)
try:
if subprocess.check_output(["pidof", "bitcoind"]) is not None:
print("%sWARNING!%s There is already a bitcoind process running on this system. Tests may fail unexpectedly due to resource contention!" % (BOLD[1], BOLD[0]))
except (OSError, subprocess.SubprocessError):
pass
# Warn if there is a cache directory
cache_dir = "%s/test/cache" % build_dir
if os.path.isdir(cache_dir):
print("%sWARNING!%s There is a cache directory here: %s. If tests fail unexpectedly, try deleting the cache directory." % (BOLD[1], BOLD[0], cache_dir))
#Set env vars
if "BITCOIND" not in os.environ:
os.environ["BITCOIND"] = build_dir + '/src/bitcoind' + exeext
tests_dir = src_dir + '/test/functional/'
flags = ["--srcdir={}/src".format(build_dir)] + args
2017-04-12 16:41:13 +02:00
flags.append("--cachedir=%s" % cache_dir)
if enable_coverage:
coverage = RPCCoverage()
flags.append(coverage.flag)
logging.debug("Initializing coverage directory at %s" % coverage.dir)
else:
coverage = None
if len(test_list) > 1 and jobs > 1:
# Populate cache
2017-05-18 23:33:33 +02:00
subprocess.check_output([tests_dir + 'create_cache.py'] + flags + ["--tmpdir=%s/cache" % tmpdir])
#Run Tests
2017-05-18 23:33:33 +02:00
job_queue = TestHandler(jobs, tests_dir, tmpdir, test_list, flags)
time0 = time.time()
test_results = []
max_len_name = len(max(test_list, key=len))
for _ in range(len(test_list)):
test_result, stdout, stderr = job_queue.get_next()
test_results.append(test_result)
if test_result.status == "Passed":
logging.debug("\n%s%s%s passed, Duration: %s s" % (BOLD[1], test_result.name, BOLD[0], test_result.time))
elif test_result.status == "Skipped":
logging.debug("\n%s%s%s skipped" % (BOLD[1], test_result.name, BOLD[0]))
else:
print("\n%s%s%s failed, Duration: %s s\n" % (BOLD[1], test_result.name, BOLD[0], test_result.time))
print(BOLD[1] + 'stdout:\n' + BOLD[0] + stdout + '\n')
print(BOLD[1] + 'stderr:\n' + BOLD[0] + stderr + '\n')
print_results(test_results, max_len_name, (int(time.time() - time0)))
if coverage:
coverage.report_rpc_coverage()
logging.debug("Cleaning up coverage data")
coverage.cleanup()
2017-05-18 23:33:33 +02:00
# Clear up the temp directory if all subdirectories are gone
if not os.listdir(tmpdir):
os.rmdir(tmpdir)
all_passed = all(map(lambda test_result: test_result.was_successful, test_results))
sys.exit(not all_passed)
def print_results(test_results, max_len_name, runtime):
results = "\n" + BOLD[1] + "%s | %s | %s\n\n" % ("TEST".ljust(max_len_name), "STATUS ", "DURATION") + BOLD[0]
test_results.sort(key=lambda result: result.name.lower())
all_passed = True
time_sum = 0
for test_result in test_results:
all_passed = all_passed and test_result.was_successful
time_sum += test_result.time
test_result.padding = max_len_name
results += str(test_result)
status = TICK + "Passed" if all_passed else CROSS + "Failed"
results += BOLD[1] + "\n%s | %s | %s s (accumulated) \n" % ("ALL".ljust(max_len_name), status.ljust(9), time_sum) + BOLD[0]
results += "Runtime: %s s\n" % (runtime)
print(results)
class TestHandler:
"""
Trigger the testscrips passed in via the list.
"""
2017-05-18 23:33:33 +02:00
def __init__(self, num_tests_parallel, tests_dir, tmpdir, test_list=None, flags=None):
assert(num_tests_parallel >= 1)
self.num_jobs = num_tests_parallel
self.tests_dir = tests_dir
2017-05-18 23:33:33 +02:00
self.tmpdir = tmpdir
self.test_list = test_list
self.flags = flags
self.num_running = 0
# In case there is a graveyard of zombie bitcoinds, we can apply a
# pseudorandom offset to hopefully jump over them.
# (625 is PORT_RANGE/MAX_NODES)
self.portseed_offset = int(time.time() * 1000) % 625
self.jobs = []
def get_next(self):
while self.num_running < self.num_jobs and self.test_list:
# Add tests
self.num_running += 1
t = self.test_list.pop(0)
2017-05-18 23:33:33 +02:00
portseed = len(self.test_list) + self.portseed_offset
portseed_arg = ["--portseed={}".format(portseed)]
log_stdout = tempfile.SpooledTemporaryFile(max_size=2**16)
log_stderr = tempfile.SpooledTemporaryFile(max_size=2**16)
2017-03-23 18:54:18 +01:00
test_argv = t.split()
2017-05-18 23:33:33 +02:00
tmpdir = ["--tmpdir=%s/%s_%s" % (self.tmpdir, re.sub(".py$", "", test_argv[0]), portseed)]
self.jobs.append((t,
time.time(),
2017-05-18 23:33:33 +02:00
subprocess.Popen([self.tests_dir + test_argv[0]] + test_argv[1:] + self.flags + portseed_arg + tmpdir,
universal_newlines=True,
stdout=log_stdout,
stderr=log_stderr),
log_stdout,
log_stderr))
if not self.jobs:
raise IndexError('pop from empty list')
while True:
# Return first proc that finishes
time.sleep(.5)
for j in self.jobs:
(name, time0, proc, log_out, log_err) = j
if os.getenv('TRAVIS') == 'true' and int(time.time() - time0) > 20 * 60:
# In travis, timeout individual tests after 20 minutes (to stop tests hanging and not
# providing useful output.
proc.send_signal(signal.SIGINT)
if proc.poll() is not None:
log_out.seek(0), log_err.seek(0)
[stdout, stderr] = [l.read().decode('utf-8') for l in (log_out, log_err)]
log_out.close(), log_err.close()
if proc.returncode == TEST_EXIT_PASSED and stderr == "":
status = "Passed"
elif proc.returncode == TEST_EXIT_SKIPPED:
status = "Skipped"
else:
status = "Failed"
self.num_running -= 1
self.jobs.remove(j)
return TestResult(name, status, int(time.time() - time0)), stdout, stderr
print('.', end='', flush=True)
class TestResult():
def __init__(self, name, status, time):
self.name = name
self.status = status
self.time = time
self.padding = 0
def __repr__(self):
if self.status == "Passed":
color = BLUE
glyph = TICK
elif self.status == "Failed":
color = RED
glyph = CROSS
elif self.status == "Skipped":
color = GREY
glyph = CIRCLE
return color[1] + "%s | %s%s | %s s\n" % (self.name.ljust(self.padding), glyph, self.status.ljust(7), self.time) + color[0]
@property
def was_successful(self):
return self.status != "Failed"
def check_script_list(src_dir):
"""Check scripts directory.
Check that there are no scripts in the functional tests directory which are
not being run by pull-tester.py."""
script_dir = src_dir + '/test/functional/'
python_files = set([t for t in os.listdir(script_dir) if t[-3:] == ".py"])
missed_tests = list(python_files - set(map(lambda x: x.split()[0], ALL_SCRIPTS + NON_SCRIPTS)))
if len(missed_tests) != 0:
2017-04-12 16:41:13 +02:00
print("%sWARNING!%s The following scripts are not being run: %s. Check the test lists in test_runner.py." % (BOLD[1], BOLD[0], str(missed_tests)))
if os.getenv('TRAVIS') == 'true':
# On travis this warning is an error to prevent merging incomplete commits into master
sys.exit(1)
class RPCCoverage(object):
"""
Coverage reporting utilities for test_runner.
Coverage calculation works by having each test script subprocess write
coverage files into a particular directory. These files contain the RPC
commands invoked during testing, as well as a complete listing of RPC
commands per `bitcoin-cli help` (`rpc_interface.txt`).
After all tests complete, the commands run are combined and diff'd against
the complete list to calculate uncovered RPC commands.
See also: test/functional/test_framework/coverage.py
"""
def __init__(self):
self.dir = tempfile.mkdtemp(prefix="coverage")
self.flag = '--coveragedir=%s' % self.dir
def report_rpc_coverage(self):
"""
Print out RPC commands that were unexercised by tests.
"""
uncovered = self._get_uncovered_rpc_commands()
if uncovered:
print("Uncovered RPC commands:")
print("".join((" - %s\n" % i) for i in sorted(uncovered)))
else:
print("All RPC commands covered.")
def cleanup(self):
return shutil.rmtree(self.dir)
def _get_uncovered_rpc_commands(self):
"""
Return a set of currently untested RPC commands.
"""
# This is shared from `test/functional/test-framework/coverage.py`
reference_filename = 'rpc_interface.txt'
coverage_file_prefix = 'coverage.'
coverage_ref_filename = os.path.join(self.dir, reference_filename)
coverage_filenames = set()
all_cmds = set()
covered_cmds = set()
if not os.path.isfile(coverage_ref_filename):
raise RuntimeError("No coverage reference found")
with open(coverage_ref_filename, 'r') as f:
all_cmds.update([i.strip() for i in f.readlines()])
for root, dirs, files in os.walk(self.dir):
for filename in files:
if filename.startswith(coverage_file_prefix):
coverage_filenames.add(os.path.join(root, filename))
for filename in coverage_filenames:
with open(filename, 'r') as f:
covered_cmds.update([i.strip() for i in f.readlines()])
return all_cmds - covered_cmds
if __name__ == '__main__':
main()