From 4e6018e246df07db40861a980995c96e245ba6c9 Mon Sep 17 00:00:00 2001
From: yunwei37 <1067852565@qq.com>
Date: Sat, 18 Feb 2023 18:09:49 +0800
Subject: [PATCH] add README and install.sh

---
 README.md        | 30 ++++++++++++++++++++++++++++++
 doc/talk.md      | 13 +++++++++++++
 install.sh       |  4 ++++
 main.py          |  7 +------
 prompts/1.md     | 29 +++++++++++++++++++++++++++++
 requirements.txt |  1 +
 6 files changed, 78 insertions(+), 6 deletions(-)
 create mode 100644 doc/talk.md
 create mode 100755 install.sh
 create mode 100644 prompts/1.md

diff --git a/README.md b/README.md
index 659fbf2..91d2e80 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,32 @@
 # GPTtrace
 
+## Usage
+
+```console
+python main.py
+usage: GPTtrace [-h] [-e | -r TEXT] [-u UUID] [-t ACCESS_TOKEN]
+
+Use ChatGPT to write eBPF programs (bpftrace, etc.)
+
+optional arguments:
+  -h, --help            show this help message and exit
+  -e, --explain         Let ChatGPT explain what's eBPF
+  -r TEXT, --run TEXT   Generate commands using your input with ChatGPT, and run it
+  -u UUID, --uuid UUID  Conversion UUID to use, or passed through environment variable `GPTTRACE_CONV_UUID`
+  -t ACCESS_TOKEN, --access-token ACCESS_TOKEN
+                        ChatGPT access token, see `https://chat.openai.com/api/auth/session` or passed through
+                        `GPTTRACE_ACCESS_TOKEN`
+```
+
+## Examples
+
+- Files opened by process
+- Syscall count by program
+- Read bytes by process:
+- Read size distribution by process:
+- Show per-second syscall rates:
+- Trace disk size by process
+- Count page faults by process
+- Count LLC cache misses by process name and PID (uses PMCs):
+- Profile user-level stacks at 99 Hertz, for PID 189:
+- Files opened, for processes in the root cgroup-v2
diff --git a/doc/talk.md b/doc/talk.md
new file mode 100644
index 0000000..df4154e
--- /dev/null
+++ b/doc/talk.md
@@ -0,0 +1,13 @@
+# talk
+
+当我们开发软件时，经常需要进行调试和追踪，以发现程序中的问题。而 eBPF 技术已经成为了一个越来越受欢迎的工具，它可以帮助我们更加高效地进行追踪和分析。
+
+但是，eBPF 的开发需要一定的专业知识，对于一些不熟悉该技术的开发人员来说，可能会有一定的困难。这时，我们的 demo 工具 GPTtrace 就可以帮助你解决这个问题。
+
+使用 GPTtrace 工具，你只需要用最自然的语言描述你想要追踪的程序，它就会自动为你生成和运行 eBPF 程序，让你更加高效地进行追踪和分析。而且，如果你不了解 eBPF 技术，也不用担心，GPTtrace 会帮助你解释它是什么以及如何使用。
+
+除了自动追踪，GPTtrace 还有其他功能。通过 "-d bpftrace" 和 "-d eunomia" 参数，你可以深入了解 eBPF 的实现细节，并生成内核态代码，提高追踪的效率。而通过 "-o" 参数，你可以生成可执行文件，让你更加方便地运行你的追踪程序。
+
+当然，需要注意的是，GPTtrace 只是一个 demo 工具，不能应用于生产环境。但是，它展示了 ChatGPT 和 eBPF 技术结合的巨大潜力，相信这种结合将在未来的软件开发和调试中发挥重要作用。
+
+因此，如果你想更加高效地进行追踪和分析，GPTtrace 工具是一个值得尝试的工具。让我们期待 ChatGPT 在 eBPF 开发领域中的更多可能性！
\ No newline at end of file
diff --git a/install.sh b/install.sh
new file mode 100755
index 0000000..599b260
--- /dev/null
+++ b/install.sh
@@ -0,0 +1,4 @@
+#!/bin/bash
+
+sudo apt install bpftrace
+pip install -r requirements.txt
diff --git a/main.py b/main.py
index b050360..fd2c603 100755
--- a/main.py
+++ b/main.py
@@ -11,7 +11,6 @@ from marko.inline import RawText
 ENV_UUID = "GPTTRACE_CONV_UUID"
 ENV_ACCESS_TOKEN = "GPTTRACE_ACCESS_TOKEN"
 
-
 def main():
     parser = argparse.ArgumentParser(
         prog='GPTtrace',
@@ -50,9 +49,7 @@ def main():
         print(f"Command to run: {parsed[0]}")
         os.system(parsed[0])
 
-
-
-def generate_result(bot: Chatbot, text: str, session: str | None, print_out: bool = False) -> str:
+def generate_result(bot: Chatbot, text: str, session: str = None, print_out: bool = False) -> str:
     from io import StringIO
     prev_text = ""
     buf = StringIO()
@@ -69,7 +66,6 @@ def generate_result(bot: Chatbot, text: str, session: str | None, print_out: boo
         print()
     return buf.getvalue()
 
-
 def extract_code_blocks(text: str) -> List[str]:
     result = []
     parser = Parser()
@@ -80,6 +76,5 @@ def extract_code_blocks(text: str) -> List[str]:
             result.append(blk.children)
     return result
 
-
 if __name__ == "__main__":
     main()
diff --git a/prompts/1.md b/prompts/1.md
new file mode 100644
index 0000000..78774d2
--- /dev/null
+++ b/prompts/1.md
@@ -0,0 +1,29 @@
+# Files opened by process
+bpftrace -e 'tracepoint:syscalls:sys_enter_open { printf("%s %s\n", comm, str(args->filename)); }'
+
+# Syscall count by program
+bpftrace -e 'tracepoint:raw_syscalls:sys_enter { @[comm] = count(); }'
+
+# Read bytes by process:
+bpftrace -e 'tracepoint:syscalls:sys_exit_read /args->ret/ { @[comm] = sum(args->ret); }'
+
+# Read size distribution by process:
+bpftrace -e 'tracepoint:syscalls:sys_exit_read { @[comm] = hist(args->ret); }'
+
+# Show per-second syscall rates:
+bpftrace -e 'tracepoint:raw_syscalls:sys_enter { @ = count(); } interval:s:1 { print(@); clear(@); }'
+
+# Trace disk size by process
+bpftrace -e 'tracepoint:block:block_rq_issue { printf("%d %s %d\n", pid, comm, args->bytes); }'
+
+# Count page faults by process
+bpftrace -e 'software:faults:1 { @[comm] = count(); }'
+
+# Count LLC cache misses by process name and PID (uses PMCs):
+bpftrace -e 'hardware:cache-misses:1000000 { @[comm, pid] = count(); }'
+
+# Profile user-level stacks at 99 Hertz, for PID 189:
+bpftrace -e 'profile:hz:99 /pid == 189/ { @[ustack] = count(); }'
+
+# Files opened, for processes in the root cgroup-v2
+bpftrace -e 'tracepoint:syscalls:sys_enter_openat /cgroup == cgroupid("/sys/fs/cgroup/unified/mycg")/ { printf("%s\n", str(args->filename)); }'
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
index 9a37be4..911747d 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -35,3 +35,4 @@ tomlkit==0.11.6
 typing_extensions==4.5.0
 urllib3==1.26.14
 wrapt==1.14.1
+marko==1.3.0
\ No newline at end of file