mirror of
https://git.yoctoproject.org/poky
synced 2026-06-02 01:19:52 +00:00
bitbake: bitbake: Rework hash equivalence
Reworks the hash equivalence server to address performance issues that were encountered with the REST mechanism used previously, particularly during the heavy request load encountered during signature generation. Notable changes are: 1) The server protocol is no longer HTTP based. Instead, it uses a simpler JSON over a streaming protocol link. This protocol has much lower overhead than HTTP since it eliminates the HTTP headers. 2) The hash equivalence server can either bind to a TCP port, or a Unix domain socket. Unix domain sockets are more efficient for local communication, and so are preferred if the user enables hash equivalence only for the local build. The arguments to the 'bitbake-hashserve' command have been updated accordingly. 3) The value to which BB_HASHSERVE should be set to enable a local hash equivalence server is changed to "auto" instead of "localhost:0". The latter didn't make sense when the local server was using a Unix domain socket. 4) Clients are expected to keep a persistent connection to the server instead of creating a new connection each time a request is made for optimal performance. 5) Most of the client logic has been moved to the hashserve module in bitbake. This makes it easier to share the client code. 6) A new bitbake command has been added called 'bitbake-hashclient'. This command can be used to query a hash equivalence server, including fetching the statistics and running a performance stress test. 7) The table indexes in the SQLite database have been updated to optimize hash lookups. This change is backward compatible, as the database will delete the old indexes first if they exist. 8) The server has been reworked to use python async to maximize performance with persistently connected clients. This requires Python 3.5 or later. (Bitbake rev: 2124eec3a5830afe8e07ffb6f2a0df6a417ac973) Signed-off-by: Joshua Watt <JPEWhacker@gmail.com> Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>
This commit is contained in:
Joshua Watt
committed by
Richard Purdie
Richard Purdie
parent
34923e4f77
commit
20f032338f
@@ -3,203 +3,21 @@
|
||||
# SPDX-License-Identifier: GPL-2.0-only
|
||||
#
|
||||
|
||||
from http.server import BaseHTTPRequestHandler, HTTPServer
|
||||
import contextlib
|
||||
import urllib.parse
|
||||
from contextlib import closing
|
||||
import re
|
||||
import sqlite3
|
||||
import json
|
||||
import traceback
|
||||
import logging
|
||||
import socketserver
|
||||
import queue
|
||||
import threading
|
||||
import signal
|
||||
import socket
|
||||
import struct
|
||||
from datetime import datetime
|
||||
|
||||
logger = logging.getLogger('hashserv')
|
||||
UNIX_PREFIX = "unix://"
|
||||
|
||||
class HashEquivalenceServer(BaseHTTPRequestHandler):
|
||||
def log_message(self, f, *args):
|
||||
logger.debug(f, *args)
|
||||
ADDR_TYPE_UNIX = 0
|
||||
ADDR_TYPE_TCP = 1
|
||||
|
||||
def opendb(self):
|
||||
self.db = sqlite3.connect(self.dbname)
|
||||
self.db.row_factory = sqlite3.Row
|
||||
self.db.execute("PRAGMA synchronous = OFF;")
|
||||
self.db.execute("PRAGMA journal_mode = MEMORY;")
|
||||
|
||||
def do_GET(self):
|
||||
try:
|
||||
if not self.db:
|
||||
self.opendb()
|
||||
|
||||
p = urllib.parse.urlparse(self.path)
|
||||
|
||||
if p.path != self.prefix + '/v1/equivalent':
|
||||
self.send_error(404)
|
||||
return
|
||||
|
||||
query = urllib.parse.parse_qs(p.query, strict_parsing=True)
|
||||
method = query['method'][0]
|
||||
taskhash = query['taskhash'][0]
|
||||
|
||||
d = None
|
||||
with contextlib.closing(self.db.cursor()) as cursor:
|
||||
cursor.execute('SELECT taskhash, method, unihash FROM tasks_v2 WHERE method=:method AND taskhash=:taskhash ORDER BY created ASC LIMIT 1',
|
||||
{'method': method, 'taskhash': taskhash})
|
||||
|
||||
row = cursor.fetchone()
|
||||
|
||||
if row is not None:
|
||||
logger.debug('Found equivalent task %s', row['taskhash'])
|
||||
d = {k: row[k] for k in ('taskhash', 'method', 'unihash')}
|
||||
|
||||
self.send_response(200)
|
||||
self.send_header('Content-Type', 'application/json; charset=utf-8')
|
||||
self.end_headers()
|
||||
self.wfile.write(json.dumps(d).encode('utf-8'))
|
||||
except:
|
||||
logger.exception('Error in GET')
|
||||
self.send_error(400, explain=traceback.format_exc())
|
||||
return
|
||||
|
||||
def do_POST(self):
|
||||
try:
|
||||
if not self.db:
|
||||
self.opendb()
|
||||
|
||||
p = urllib.parse.urlparse(self.path)
|
||||
|
||||
if p.path != self.prefix + '/v1/equivalent':
|
||||
self.send_error(404)
|
||||
return
|
||||
|
||||
length = int(self.headers['content-length'])
|
||||
data = json.loads(self.rfile.read(length).decode('utf-8'))
|
||||
|
||||
with contextlib.closing(self.db.cursor()) as cursor:
|
||||
cursor.execute('''
|
||||
-- Find tasks with a matching outhash (that is, tasks that
|
||||
-- are equivalent)
|
||||
SELECT taskhash, method, unihash FROM tasks_v2 WHERE method=:method AND outhash=:outhash
|
||||
|
||||
-- If there is an exact match on the taskhash, return it.
|
||||
-- Otherwise return the oldest matching outhash of any
|
||||
-- taskhash
|
||||
ORDER BY CASE WHEN taskhash=:taskhash THEN 1 ELSE 2 END,
|
||||
created ASC
|
||||
|
||||
-- Only return one row
|
||||
LIMIT 1
|
||||
''', {k: data[k] for k in ('method', 'outhash', 'taskhash')})
|
||||
|
||||
row = cursor.fetchone()
|
||||
|
||||
# If no matching outhash was found, or one *was* found but it
|
||||
# wasn't an exact match on the taskhash, a new entry for this
|
||||
# taskhash should be added
|
||||
if row is None or row['taskhash'] != data['taskhash']:
|
||||
# If a row matching the outhash was found, the unihash for
|
||||
# the new taskhash should be the same as that one.
|
||||
# Otherwise the caller provided unihash is used.
|
||||
unihash = data['unihash']
|
||||
if row is not None:
|
||||
unihash = row['unihash']
|
||||
|
||||
insert_data = {
|
||||
'method': data['method'],
|
||||
'outhash': data['outhash'],
|
||||
'taskhash': data['taskhash'],
|
||||
'unihash': unihash,
|
||||
'created': datetime.now()
|
||||
}
|
||||
|
||||
for k in ('owner', 'PN', 'PV', 'PR', 'task', 'outhash_siginfo'):
|
||||
if k in data:
|
||||
insert_data[k] = data[k]
|
||||
|
||||
cursor.execute('''INSERT INTO tasks_v2 (%s) VALUES (%s)''' % (
|
||||
', '.join(sorted(insert_data.keys())),
|
||||
', '.join(':' + k for k in sorted(insert_data.keys()))),
|
||||
insert_data)
|
||||
|
||||
logger.info('Adding taskhash %s with unihash %s', data['taskhash'], unihash)
|
||||
|
||||
self.db.commit()
|
||||
d = {'taskhash': data['taskhash'], 'method': data['method'], 'unihash': unihash}
|
||||
else:
|
||||
d = {k: row[k] for k in ('taskhash', 'method', 'unihash')}
|
||||
|
||||
self.send_response(200)
|
||||
self.send_header('Content-Type', 'application/json; charset=utf-8')
|
||||
self.end_headers()
|
||||
self.wfile.write(json.dumps(d).encode('utf-8'))
|
||||
except:
|
||||
logger.exception('Error in POST')
|
||||
self.send_error(400, explain=traceback.format_exc())
|
||||
return
|
||||
|
||||
class ThreadedHTTPServer(HTTPServer):
|
||||
quit = False
|
||||
|
||||
def serve_forever(self):
|
||||
self.requestqueue = queue.Queue()
|
||||
self.handlerthread = threading.Thread(target=self.process_request_thread)
|
||||
self.handlerthread.daemon = False
|
||||
|
||||
self.handlerthread.start()
|
||||
|
||||
signal.signal(signal.SIGTERM, self.sigterm_exception)
|
||||
super().serve_forever()
|
||||
os._exit(0)
|
||||
|
||||
def sigterm_exception(self, signum, stackframe):
|
||||
self.server_close()
|
||||
os._exit(0)
|
||||
|
||||
def server_bind(self):
|
||||
HTTPServer.server_bind(self)
|
||||
self.socket.setsockopt(socket.SOL_SOCKET, socket.SO_LINGER, struct.pack('ii', 1, 0))
|
||||
|
||||
def process_request_thread(self):
|
||||
while not self.quit:
|
||||
try:
|
||||
(request, client_address) = self.requestqueue.get(True)
|
||||
except queue.Empty:
|
||||
continue
|
||||
if request is None:
|
||||
continue
|
||||
try:
|
||||
self.finish_request(request, client_address)
|
||||
except Exception:
|
||||
self.handle_error(request, client_address)
|
||||
finally:
|
||||
self.shutdown_request(request)
|
||||
os._exit(0)
|
||||
|
||||
def process_request(self, request, client_address):
|
||||
self.requestqueue.put((request, client_address))
|
||||
|
||||
def server_close(self):
|
||||
super().server_close()
|
||||
self.quit = True
|
||||
self.requestqueue.put((None, None))
|
||||
self.handlerthread.join()
|
||||
|
||||
def create_server(addr, dbname, prefix=''):
|
||||
class Handler(HashEquivalenceServer):
|
||||
pass
|
||||
|
||||
db = sqlite3.connect(dbname)
|
||||
def setup_database(database, sync=True):
|
||||
db = sqlite3.connect(database)
|
||||
db.row_factory = sqlite3.Row
|
||||
|
||||
Handler.prefix = prefix
|
||||
Handler.db = None
|
||||
Handler.dbname = dbname
|
||||
|
||||
with contextlib.closing(db.cursor()) as cursor:
|
||||
with closing(db.cursor()) as cursor:
|
||||
cursor.execute('''
|
||||
CREATE TABLE IF NOT EXISTS tasks_v2 (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
@@ -220,11 +38,56 @@ def create_server(addr, dbname, prefix=''):
|
||||
UNIQUE(method, outhash, taskhash)
|
||||
)
|
||||
''')
|
||||
cursor.execute('CREATE INDEX IF NOT EXISTS taskhash_lookup ON tasks_v2 (method, taskhash)')
|
||||
cursor.execute('CREATE INDEX IF NOT EXISTS outhash_lookup ON tasks_v2 (method, outhash)')
|
||||
cursor.execute('PRAGMA journal_mode = WAL')
|
||||
cursor.execute('PRAGMA synchronous = %s' % ('NORMAL' if sync else 'OFF'))
|
||||
|
||||
ret = ThreadedHTTPServer(addr, Handler)
|
||||
# Drop old indexes
|
||||
cursor.execute('DROP INDEX IF EXISTS taskhash_lookup')
|
||||
cursor.execute('DROP INDEX IF EXISTS outhash_lookup')
|
||||
|
||||
logger.info('Starting server on %s\n', ret.server_port)
|
||||
# Create new indexes
|
||||
cursor.execute('CREATE INDEX IF NOT EXISTS taskhash_lookup_v2 ON tasks_v2 (method, taskhash, created)')
|
||||
cursor.execute('CREATE INDEX IF NOT EXISTS outhash_lookup_v2 ON tasks_v2 (method, outhash)')
|
||||
|
||||
return ret
|
||||
return db
|
||||
|
||||
|
||||
def parse_address(addr):
|
||||
if addr.startswith(UNIX_PREFIX):
|
||||
return (ADDR_TYPE_UNIX, (addr[len(UNIX_PREFIX):],))
|
||||
else:
|
||||
m = re.match(r'\[(?P<host>[^\]]*)\]:(?P<port>\d+)$', addr)
|
||||
if m is not None:
|
||||
host = m.group('host')
|
||||
port = m.group('port')
|
||||
else:
|
||||
host, port = addr.split(':')
|
||||
|
||||
return (ADDR_TYPE_TCP, (host, int(port)))
|
||||
|
||||
|
||||
def create_server(addr, dbname, *, sync=True):
|
||||
from . import server
|
||||
db = setup_database(dbname, sync=sync)
|
||||
s = server.Server(db)
|
||||
|
||||
(typ, a) = parse_address(addr)
|
||||
if typ == ADDR_TYPE_UNIX:
|
||||
s.start_unix_server(*a)
|
||||
else:
|
||||
s.start_tcp_server(*a)
|
||||
|
||||
return s
|
||||
|
||||
|
||||
def create_client(addr):
|
||||
from . import client
|
||||
c = client.Client()
|
||||
|
||||
(typ, a) = parse_address(addr)
|
||||
if typ == ADDR_TYPE_UNIX:
|
||||
c.connect_unix(*a)
|
||||
else:
|
||||
c.connect_tcp(*a)
|
||||
|
||||
return c
|
||||
|
||||
Reference in New Issue
Block a user