Async get_events, handle_event, handle_readables, handle_writables

.vscode/settings.json

@@ -39,6 +39,7 @@
   "python.linting.pylintEnabled": true,
   "python.linting.pylintArgs": ["--generate-members"],
   "python.linting.flake8Enabled": true,
+  "python.linting.flake8Args": ["--config", ".flake8"],
   "python.linting.mypyEnabled": true,
   "python.formatting.provider": "autopep8",
   "autoDocstring.docstringFormat": "sphinx"

Makefile

@@ -27,9 +27,7 @@ endif
 .PHONY: container container-run container-release
 .PHONY: devtools dashboard dashboard-clean
 
-all:
-	echo $(IMAGE_TAG)
-	# lib-test
+all: lib-test
 
 https-certificates:
 	# Generate server key
@@ -94,7 +92,8 @@ lib-dep:
 		-r requirements.txt \
 		-r requirements-testing.txt \
 		-r requirements-release.txt \
-		-r requirements-tunnel.txt \
+		-r requirements-tunnel.txt && \
+	pip install "setuptools>=42"
 
 lib-lint:
 	python -m tox -e lint
@@ -128,6 +127,7 @@ lib-coverage:
 	$(OPEN) htmlcov/index.html
 
 lib-profile:
+	ulimit -n 65536 && \
 	sudo py-spy record \
 		-o profile.svg \
 		-t -F -s -- \
@@ -137,6 +137,9 @@ lib-profile:
 			--disable-http-proxy \
 			--enable-web-server \
 			--plugin proxy.plugin.WebServerPlugin \
+			--local-executor \
+			--backlog 65536 \
+			--open-file-limit 65536
 			--log-file /dev/null
 
 devtools:

README.md

@@ -109,6 +109,7 @@
     - [Setup Local Environment](#setup-local-environment)
     - [Setup Git Hooks](#setup-git-hooks)
     - [Sending a Pull Request](#sending-a-pull-request)
+- [Benchmarks](#benchmarks)
 - [Flags](#flags)
 - [Changelog](#changelog)
   - [v2.x](#v2x)
@@ -126,36 +127,56 @@
 
     ```console
     # On Macbook Pro 2019 / 2.4 GHz 8-Core Intel Core i9 / 32 GB RAM
-    ❯ hey -n 10000 -c 100 http://localhost:8899/http-route-example
-
-    Summary:
-      Total:	0.3248 secs
-      Slowest:	0.1007 secs
-      Fastest:	0.0002 secs
-      Average:	0.0028 secs
-      Requests/sec:	30784.7958
-
-      Total data:	190000 bytes
-      Size/request:	19 bytes
-
-    Response time histogram:
-      0.000 [1]	|
-      0.010 [9533]	|■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■
-      0.020 [384]	|■■
-
-    Latency distribution:
-      10% in 0.0004 secs
-      25% in 0.0007 secs
-      50% in 0.0013 secs
-      75% in 0.0029 secs
-      90% in 0.0057 secs
-      95% in 0.0097 secs
-      99% in 0.0185 secs
-
-    Status code distribution:
-      [200]	10000 responses
+    ❯ ./helper/benchmark.sh
+      CONCURRENCY: 100 workers, TOTAL REQUESTS: 100000 req, QPS: 5000 req/sec, TIMEOUT: 1 sec
+
+      Summary:
+        Total:	3.1560 secs
+        Slowest:	0.0375 secs
+        Fastest:	0.0006 secs
+        Average:	0.0031 secs
+        Requests/sec:	31685.9140
+
+        Total data:	1900000 bytes
+        Size/request:	19 bytes
+
+      Response time histogram:
+        0.001 [1]	|
+        0.004 [91680]	|■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■■
+        0.008 [7929]	|■■■
+        0.012 [263]	|
+        0.015 [29]	|
+        0.019 [8]	|
+        0.023 [23]	|
+        0.026 [15]	|
+        0.030 [27]	|
+        0.034 [16]	|
+        0.037 [9]	|
+
+
+      Latency distribution:
+        10% in 0.0022 secs
+        25% in 0.0025 secs
+        50% in 0.0029 secs
+        75% in 0.0034 secs
+        90% in 0.0041 secs
+        95% in 0.0048 secs
+        99% in 0.0066 secs
+
+      Details (average, fastest, slowest):
+        DNS+dialup:	0.0000 secs, 0.0006 secs, 0.0375 secs
+        DNS-lookup:	0.0000 secs, 0.0000 secs, 0.0000 secs
+        req write:	0.0000 secs, 0.0000 secs, 0.0046 secs
+        resp wait:	0.0030 secs, 0.0006 secs, 0.0320 secs
+        resp read:	0.0000 secs, 0.0000 secs, 0.0029 secs
+
+      Status code distribution:
+        [200]	100000 responses
     ```
 
+    PS: `proxy.py` and benchmark tools are running on the same machine during the above load test.
+    Checkout the repo and try it for yourself.  See [Benchmarks](#benchmarks) for more details.
+
 - Lightweight
   - Uses only `~5-20MB` RAM
   - No external dependency other than standard Python library
@@ -1977,13 +1998,21 @@ Every pull request is tested using GitHub actions.
 See [GitHub workflow](https://github.com/abhinavsingh/proxy.py/tree/develop/.github/workflows)
 for list of tests.
 
+# Benchmarks
+
+Simply run the following command from repo root to start benchmark
+
+```console
+❯ ./helper/benchmark.sh
+```
+
 # Flags
 
 ```console
 ❯ proxy -h
 usage: -m [-h] [--enable-events] [--enable-conn-pool] [--threadless]
-          [--threaded] [--num-workers NUM_WORKERS] [--backlog BACKLOG]
-          [--hostname HOSTNAME] [--port PORT]
+          [--threaded] [--num-workers NUM_WORKERS] [--local-executor]
+          [--backlog BACKLOG] [--hostname HOSTNAME] [--port PORT]
           [--unix-socket-path UNIX_SOCKET_PATH]
           [--num-acceptors NUM_ACCEPTORS] [--version] [--log-level LOG_LEVEL]
           [--log-file LOG_FILE] [--log-format LOG_FORMAT]
@@ -2009,7 +2038,7 @@ usage: -m [-h] [--enable-events] [--enable-conn-pool] [--threadless]
           [--filtered-url-regex-config FILTERED_URL_REGEX_CONFIG]
           [--cloudflare-dns-mode CLOUDFLARE_DNS_MODE]
 
-proxy.py v2.3.2
+proxy.py v2.3.2.dev193+g87ff921.d20211121
 
 options:
   -h, --help            show this help message and exit
@@ -2026,6 +2055,13 @@ options:
                         handle each client connection.
   --num-workers NUM_WORKERS
                         Defaults to number of CPU cores.
+  --local-executor      Default: False. Disabled by default. When enabled
+                        acceptors will make use of local (same process)
+                        executor instead of distributing load across remote
+                        (other process) executors. Enable this option to
+                        achieve CPU affinity between acceptors and executors,
+                        instead of using underlying OS kernel scheduling
+                        algorithm.
   --backlog BACKLOG     Default: 100. Maximum number of pending connections to
                         proxy server
   --hostname HOSTNAME   Default: ::1. Server IP address.
@@ -2155,6 +2191,10 @@ https://github.com/abhinavsingh/proxy.py/issues/new
 
 # Changelog
 
+## v2.4.0
+
+- No longer support `Python 3.6` due to `asyncio.run` usage in the core.
+
 ## v2.x
 
 - No longer ~~a single file module~~.

check.py

@@ -53,16 +53,18 @@
                 sys.exit(1)
 
 # Update README.md flags section to match current library --help output
-# lib_help = subprocess.check_output(
-#     ['python', '-m', 'proxy', '-h']
-# )
-# with open('README.md', 'rb+') as f:
-#     c = f.read()
-#     pre_flags, post_flags = c.split(b'# Flags')
-#     help_text, post_changelog = post_flags.split(b'# Changelog')
-#     f.seek(0)
-#     f.write(pre_flags + b'# Flags\n\n```console\n\xe2\x9d\xaf proxy -h\n' + lib_help + b'```' +
-#             b'\n# Changelog' + post_changelog)
+lib_help = subprocess.check_output(
+    ['python', '-m', 'proxy', '-h'],
+)
+with open('README.md', 'rb+') as f:
+    c = f.read()
+    pre_flags, post_flags = c.split(b'# Flags')
+    help_text, post_changelog = post_flags.split(b'# Changelog')
+    f.seek(0)
+    f.write(
+        pre_flags + b'# Flags\n\n```console\n\xe2\x9d\xaf proxy -h\n' + lib_help + b'```' +
+        b'\n\n# Changelog' + post_changelog,
+    )
 
 # Version is also hardcoded in README.md flags section
 readme_version_cmd = 'cat README.md | grep "proxy.py v" | tail -2 | head -1 | cut -d " " -f 2 | cut -c2-'
@@ -72,7 +74,7 @@
 # Doesn't contain "v" prefix
 readme_version = readme_version_output.decode().strip()
 
-if readme_version != lib_version[1:].split('-')[0]:
+if readme_version != lib_version:
     print(
         'Version mismatch found. {0} (readme) vs {1} (lib).'.format(
             readme_version, lib_version,

docs/conf.py

@@ -241,11 +241,11 @@
 
 nitpicky = True
 _any_role = 'any'
+_py_obj_role = 'py:obj'
 _py_class_role = 'py:class'
 nitpick_ignore = [
     (_any_role, '<proxy.HttpProxyBasePlugin>'),
     (_any_role, '__init__'),
-    (_any_role, '--threadless'),
     (_any_role, 'Client'),
     (_any_role, 'event_queue'),
     (_any_role, 'fd_queue'),
@@ -256,8 +256,10 @@
     (_any_role, 'HttpParser.state'),
     (_any_role, 'HttpProtocolHandler'),
     (_any_role, 'multiprocessing.Manager'),
-    (_any_role, 'work_klass'),
     (_any_role, 'proxy.core.base.tcp_upstream.TcpUpstreamConnectionHandler'),
+    (_any_role, 'work_klass'),
+    (_py_class_role, '_asyncio.Task'),
+    (_py_class_role, 'asyncio.events.AbstractEventLoop'),
     (_py_class_role, 'CacheStore'),
     (_py_class_role, 'HttpParser'),
     (_py_class_role, 'HttpProtocolHandlerPlugin'),
@@ -268,11 +270,17 @@
     (_py_class_role, 'paramiko.channel.Channel'),
     (_py_class_role, 'proxy.http.parser.parser.T'),
     (_py_class_role, 'proxy.plugin.cache.store.base.CacheStore'),
+    (_py_class_role, 'proxy.core.pool.AcceptorPool'),
+    (_py_class_role, 'proxy.core.executors.ThreadlessPool'),
+    (_py_class_role, 'proxy.core.acceptor.threadless.T'),
+    (_py_class_role, 'queue.Queue[Any]'),
     (_py_class_role, 'TcpClientConnection'),
     (_py_class_role, 'TcpServerConnection'),
     (_py_class_role, 'unittest.case.TestCase'),
     (_py_class_role, 'unittest.result.TestResult'),
     (_py_class_role, 'UUID'),
-    (_py_class_role, 'WebsocketFrame'),
     (_py_class_role, 'Url'),
+    (_py_class_role, 'WebsocketFrame'),
+    (_py_class_role, 'Work'),
+    (_py_obj_role, 'proxy.core.acceptor.threadless.T'),
 ]

examples/web_scraper.py

@@ -9,7 +9,6 @@
     :license: BSD, see LICENSE for more details.
 """
 import time
-import socket
 
 from typing import Dict
 
@@ -40,11 +39,11 @@ class WebScraper(Work):
     only PUBSUB protocol.
     """
 
-    def get_events(self) -> Dict[socket.socket, int]:
+    async def get_events(self) -> Dict[int, int]:
         """Return sockets and events (read or write) that we are interested in."""
         return {}
 
-    def handle_events(
+    async def handle_events(
             self,
             readables: Readables,
             writables: Writables,

helper/benchmark.sh

@@ -0,0 +1,77 @@
+#!/bin/bash
+#
+# proxy.py
+# ~~~~~~~~
+# ⚡⚡⚡ Fast, Lightweight, Programmable, TLS interception capable
+#     proxy server for Application debugging, testing and development.
+#
+# :copyright: (c) 2013-present by Abhinav Singh and contributors.
+# :license: BSD, see LICENSE for more details.
+#
+usage() {
+  echo "Usage: ./helper/benchmark.sh"
+  echo "You must run this script from proxy.py repo root."
+}
+
+DIRNAME=$(dirname "$0")
+if [ "$DIRNAME" != "./helper" ]; then
+  usage
+  exit 1
+fi
+
+BASENAME=$(basename "$0")
+if [ "$BASENAME" != "benchmark.sh" ]; then
+  usage
+  exit 1
+fi
+
+PWD=$(pwd)
+if [ $(basename $PWD) != "proxy.py" ]; then
+  usage
+  exit 1
+fi
+
+TIMEOUT=1
+QPS=20000
+CONCURRENCY=100
+TOTAL_REQUESTS=100000
+OPEN_FILE_LIMIT=65536
+BACKLOG=OPEN_FILE_LIMIT
+PID_FILE=/tmp/proxy.pid
+
+ulimit -n $OPEN_FILE_LIMIT
+
+# time python -m \
+#     proxy \
+#     --enable-web-server \
+#     --plugin proxy.plugin.WebServerPlugin \
+#     --backlog $BACKLOG \
+#     --open-file-limit $OPEN_FILE_LIMIT \
+#     --pid-file $PID_FILE \
+#     --log-file /dev/null
+
+PID=$(cat $PID_FILE)
+if [[ -z "$PID" ]]; then
+  echo "Either pid file doesn't exist or no pid found in the pid file"
+  exit 1
+fi
+ADDR=$(lsof -Pan -p $PID -i | grep -v COMMAND | awk '{ print $9 }')
+
+PRE_RUN_OPEN_FILES=$(./helper/monitor_open_files.sh)
+
+echo "CONCURRENCY: $CONCURRENCY workers, TOTAL REQUESTS: $TOTAL_REQUESTS req, QPS: $QPS req/sec, TIMEOUT: $TIMEOUT sec"
+hey \
+    -n $TOTAL_REQUESTS \
+    -c $CONCURRENCY \
+    -q $QPS \
+    -t $TIMEOUT \
+    http://$ADDR/http-route-example
+
+POST_RUN_OPEN_FILES=$(./helper/monitor_open_files.sh)
+
+echo $output
+
+echo "Open files diff:"
+diff <( echo "$PRE_RUN_OPEN_FILES" ) <( echo "$POST_RUN_OPEN_FILES" )
+
+# while true; do netstat -ant | grep .8899 | awk '{print $6}' | sort | uniq -c | sort -n; sleep 1; done

helper/monitor_open_files.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-
+#
 # proxy.py
 # ~~~~~~~~
 # ⚡⚡⚡ Fast, Lightweight, Programmable, TLS interception capable