Cargo.toml

@@ -18,10 +18,10 @@ serde = { version = "1", features = ["derive"] }
 byteorder = "1.4.3"
 futures-util = { version = "0.3.17", default-features = false, features = ["std"] }
 lazy_static = "1.4.0"
-pretty_env_logger = "0.5.0"
+pretty_env_logger = "0.4.0"
 uuid = { version = "1", features = ["v4"] }
-derive_builder = "0.20.0"
+derive_builder = "0.11.2"
-config = { version = "0.14", features = ["toml"] }
+config = { version = "0.11", features = ["toml"] }
 derive_more = "0.99.17"
 url = { version = "2.2.2", features = ["serde"]}
 async-trait = "0.1.36"
@@ -29,22 +29,22 @@ clap = { version = "4.1.11", features = ["derive", "env"] }
 tokio = { version = "1.0", default-features = false, features = ["sync", "macros", "rt-multi-thread", "time"] }
 tracing-subscriber = { version = "0.3.0", features = ["env-filter"] }
 actix = "0.13.0"
-tonic = { version = "0.11.0", features = ["transport", "channel"] }
+tonic = { version = "0.10.2", features = ["transport", "channel"] }
 prost = "0.12.3"
 tokio-stream = "0.1.14"
 async-stream = "0.3.5"
 actix-rt = "2.9.0"
 futures = "0.3.30"
 tower-service = "0.3.2"
-dashmap = { version = "6.0.0", features = ["serde"] }
+dashmap = { version = "5.5.3", features = ["serde"] }
 
 
 [build-dependencies]
 serde_json = "1"
-tonic-build = "0.11.0"
+tonic-build = "0.10.2"
 
 [dev-dependencies]
-base64 = "0.22.0"
+base64 = "0.13.0"
 anyhow = "1.0.63"
 maplit = "1.0.2"
 

bench/requirements.txt

@@ -1,27 +1,27 @@
-blinker==1.8.2
+blinker==1.7.0
 Brotli==1.1.0
-certifi==2024.8.30
+certifi==2023.11.17
 charset-normalizer==3.3.2
 click==8.1.7
 ConfigArgParse==1.7
-Flask==3.0.3
+Flask==3.0.0
 Flask-BasicAuth==0.2.0
-Flask-Cors==5.0.0
+Flask-Cors==4.0.0
-gevent==24.2.1
+gevent==23.9.1
-geventhttpclient==2.3.1
+geventhttpclient==2.0.11
-greenlet==3.1.1
+greenlet==3.0.2
-idna==3.10
+idna==3.6
-itsdangerous==2.2.0
+itsdangerous==2.1.2
-Jinja2==3.1.4
+Jinja2==3.1.2
-locust==2.31.6
+locust==2.20.0
-MarkupSafe==2.1.5
+MarkupSafe==2.1.3
-msgpack==1.1.0
+msgpack==1.0.7
-psutil==6.0.0
+psutil==5.9.7
-pyzmq==26.2.0
+pyzmq==25.1.2
-requests==2.32.3
+requests==2.31.0
 roundrobin==0.0.4
 six==1.16.0
-urllib3==2.2.3
+urllib3==2.1.0
-Werkzeug==3.0.4
+Werkzeug==3.0.1
 zope.event==5.0
-zope.interface==7.0.3
+zope.interface==6.1

bench/results/README.md

@@ -1,212 +0,0 @@
-# Benchmark Report
-
-Benchmarks were run at various stages of development to keep track of
-performance. Tech stacks were changed and the implementation optimized
-to increase throughput. This report summarizes the findings of the
-benchmarks
-
-Ultimately, we were able to identify a bottleneck that was previously
-hidden in mCaptcha (hidden because a different bottleneck like DB access
-eclipsed it :p) [and were able to increase performance of the critical
-path by ~147 times](https://git.batsense.net/mCaptcha/dcache/pulls/3)
-through a trivial optimization.
-
-## Environment
-
-These benchmarks were run on a noisy development laptop and should be
-used for guidance only. 
-
-- CPU: AMD Ryzen 5 5600U with Radeon Graphics (12) @ 4.289GHz
-- Memory: 22849MiB
-- OS:  Arch Linux x86_64
-- Kernel: 6.6.7-arch1-1
-- rustc: 1.73.0 (cc66ad468 2023-10-03)
-
-## Baseline: Tech stack version 1
-
-Actix Web based networking with JSON for message format. Was chosen for
-prototyping, and was later used to set a baseline.
-
-## Without connection pooling in server-to-server communications
-
-### Single requests (no batching)
-
-
-<details>
-
-
-<summary>Peak throughput observed was 1117 request/second (please click
-to see charts)</summary>
-
-
-#### Total number of requests vs time
-
-![number of requests](./v1/nopooling/nopipelining/total_requests_per_second_1703969194.png)
-
-#### Response times(ms) vs time
-
-![repsonse times(ms)](<./v1/nopooling/nopipelining/response_times_(ms)_1703969194.png>)
-
-#### Number of concurrent users vs time
-
-![number of concurrent
-users](./v1/nopooling/nopipelining/number_of_users_1703969194.png)
-
-
-</details>
-
-### Batched requests
-
-<details>
-<summary>
-Each network request contained 1,000 application requests, so peak throughput observed was 1,800 request/second.
-Please click to see charts</summary>
-
-
-#### Total number of requests vs time
-
-![number of requests](./v1/pooling/pipelining/total_requests_per_second_1703968582.png)
-
-#### Response times(ms) vs time
-
-![repsonse times(ms)](<./v1/pooling/pipelining/response_times_(ms)_1703968582.png>))
-
-#### Number of concurrent users vs time
-
-![number of concurrent
-users](./v1/pooling/pipelining/number_of_users_1703968582.png)
-
-
-</details>
-
-## With connection pooling in server-to-server communications
-
-
-### Single requests (no batching)
-
-<details>
-<summary>
-Peak throughput observed was 3904 request/second. Please click to see
-charts</summary>
-
-
-#### Total number of requests vs time
-
-![number of requests](./v1/pooling/nopipelining/total_requests_per_second_1703968214.png)
-
-#### Response times(ms) vs time
-
-![repsonse times(ms)](<./v1/pooling/nopipelining/response_times_(ms)_1703968215.png>)
-
-#### Number of concurrent users vs time
-
-![number of concurrent
-users](./v1/pooling/nopipelining/number_of_users_1703968215.png)
-
-
-</details>
-
-### Batched requests
-
-
-<details>
-<summary>
-Each network request contained 1,000 application requests, so peak throughput observed was 15,800 request/second.
-Please click to see charts.
-</summary>
-
-
-#### Total number of requests vs time
-
-![number of requests](./v1/pooling/pipelining/total_requests_per_second_1703968582.png)
-
-#### Response times(ms) vs time
-
-![repsonse times(ms)](<./v1/pooling/pipelining/response_times_(ms)_1703968582.png>))
-
-#### Number of concurrent users vs time
-
-![number of concurrent
-users](./v1/pooling/pipelining/number_of_users_1703968582.png)
-
-</details>
-
-
-## Tech stack version 2
-
-Tonic for the network stack and GRPC for wire format. We ran over a
-dozen benchmarks with this tech stack. The trend was similar to the ones
-observed above: throughput was higher when connection pool was used and
-even higher when requests were batched. _But_ the throughput of all of these benchmarks were lower than the
-baseline benchmarks!
-
-The CPU was busier. We put it through
-[flamgragh](https://github.com/flamegraph-rs/flamegraph) and hit it with
-the same test suite to identify compute-heavy areas. The result was
-unexpected:
-
-![flamegraph indicating libmcaptcha being
-slow](./v2/libmcaptcha-bottleneck/problem/flamegraph.svg)
-
-libmCaptcha's [AddVisitor
-handler](https://github.com/mCaptcha/libmcaptcha/blob/e3f456f35b2c9e55e0475b01b3e05d48b21fd51f/src/master/embedded/counter.rs#L124)
-was taking up 59% of CPU time of the entire test run. This is a very
-critical part of the variable difficulty factor PoW algorithm that
-mCaptcha uses. We never ran into this bottleneck before because in other
-cache implementations, it was always preceded with a database request.
-It surfaced here as we are using in-memory data sources in dcache.
-
-libmCaptcha uses an actor-based approach with message passing for clean
-concurrent state management. Message passing is generally faster in most
-cases, but in our case, sharing memory using CPU's concurrent primitives
-turned out to be significantly faster:
-
-![flamegraph indicating libmcaptcha being
-slow](./v2/libmcaptcha-bottleneck/solution/flamegraph.svg)
-
-CPU time was reduced from 59% to 0.4%, roughly by one 147 times!
-
-With this fix in place:
-
-
-### Connection pooled server-to-server communications, single requests (no batching)
-
-Peak throughput observed was 4816 request/second, ~1000 requests/second
-more than baseline.
-
-
-#### Total number of requests vs time
-
-![number of requests](./v2/grpc-conn-pool-post-bottleneck/single/total_requests_per_second_1703970940.png)
-
-#### Response times(ms) vs time
-
-![repsonse times(ms)](./v2/grpc-conn-pool-post-bottleneck/single/response_times_(ms)_1703970940.png)
-
-#### Number of concurrent users vs time
-
-![number of concurrent
-users](./v2/grpc-conn-pool-post-bottleneck/single/number_of_users_1703970940.png)
-
-
-### Connection pooled server-to-server communications, batched requests
-
-
-Each network request contained 1,000 application requests, so peak throughput observed was 95,700 request/second. This six times higher than baseline.
-Please click to see charts.
-
-
-#### Total number of requests vs time
-
-![number of requests](./v2/grpc-conn-pool-post-bottleneck/pipeline/total_requests_per_second_1703971082.png)
-
-#### Response times(ms) vs time
-
-![repsonse times(ms)](./v2/grpc-conn-pool-post-bottleneck/pipeline/response_times_(ms)_1703971082.png)
-
-#### Number of concurrent users vs time
-
-![number of concurrent
-users](./v2/grpc-conn-pool-post-bottleneck/pipeline/number_of_users_1703971082.png)
-
-</details>

bench/results/v2/grpc-no-conn-pool-single/out.html

@@ -10,7 +10,7 @@
     <script src="https://cdn.jsdelivr.net/npm/britecharts@3/dist/bundled/britecharts.min.js"></script>
 
     <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/britecharts@3/dist/css/britecharts.min.css" type="text/css" /></head>
-    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/bulma/1.0.3/css/bulma.min.css" />
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/bulma/0.7.1/css/bulma.min.css" />
 
   </head>
 

renovate.json

@@ -1,21 +0,0 @@
-{
-  "$schema": "https://docs.renovatebot.com/renovate-schema.json",
-  "extends": [
-    "config:recommended",
-    ":dependencyDashboard"
-  ],
-  "labels": [
-    "renovate-bot"
-  ],
-  "prHourlyLimit": 0,
-  "timezone": "Asia/kolkata",
-  "prCreation": "immediate",
-  "vulnerabilityAlerts": {
-    "enabled": true,
-    "labels": [
-      "renovate-bot",
-      "renovate-security",
-      "security"
-    ]
-  }
-}

requirements.txt

@@ -1,32 +1,32 @@
 asyncio==3.4.3
-blinker==1.8.2
+blinker==1.7.0
 Brotli==1.1.0
-certifi==2024.8.30
+certifi==2023.11.17
 charset-normalizer==3.3.2
 click==8.1.7
 ConfigArgParse==1.7
-Flask==3.0.3
+Flask==3.0.0
 Flask-BasicAuth==0.2.0
-Flask-Cors==5.0.0
+Flask-Cors==4.0.0
-gevent==24.2.1
+gevent==23.9.1
-geventhttpclient==2.3.1
+geventhttpclient==2.0.11
-greenlet==3.1.1
+greenlet==3.0.2
 grpc-interceptor==0.15.4
-grpcio==1.66.1
+grpcio==1.60.0
 grpcio-tools==1.60.0
-idna==3.10
+idna==3.6
-itsdangerous==2.2.0
+itsdangerous==2.1.2
-Jinja2==3.1.4
+Jinja2==3.1.2
-locust==2.31.6
+locust==2.20.0
-MarkupSafe==2.1.5
+MarkupSafe==2.1.3
-msgpack==1.1.0
+msgpack==1.0.7
-protobuf==4.25.5
+protobuf==4.25.1
-psutil==6.0.0
+psutil==5.9.7
-pyzmq==26.2.0
+pyzmq==25.1.2
-requests==2.32.3
+requests==2.31.0
 roundrobin==0.0.4
 six==1.16.0
-urllib3==2.2.3
+urllib3==2.1.0
-Werkzeug==3.0.4
+Werkzeug==3.0.1
 zope.event==5.0
-zope.interface==7.0.3
+zope.interface==6.1