Jump to content
Main menu
Main menu
move to sidebar
hide
Navigation
Main page
Recent changes
Random page
freem
Search
Search
Appearance
Create account
Log in
Personal tools
Create account
Log in
Pages for logged out editors
learn more
Contributions
Talk
Editing
Openai/693db64c-02e8-8010-a9f4-b71edd48bb4d
(section)
Add languages
Page
Discussion
English
Read
Edit
Edit source
View history
Tools
Tools
move to sidebar
hide
Actions
Read
Edit
Edit source
View history
General
What links here
Related changes
Special pages
Page information
Appearance
move to sidebar
hide
Warning:
You are not logged in. Your IP address will be publicly visible if you make any edits. If you
log in
or
create an account
, your edits will be attributed to your username, along with other benefits.
Anti-spam check. Do
not
fill this in!
=== Assistant: Good. === Good. Now we actually have something solid, and it confirms a suspicion I was already forming but wanted proof for. First, forget systemctl entirely. PID 1 here is supervisord, not systemd. That means everything you care about is user-space, supervised processes, not services in the traditional Linux sense. You were trying to interrogate a ghost. Now look at ps aux. The center of gravity is clear: this environment is essentially three layers deep. At the bottom, supervisord starts a few shell scripts. Those scripts start two real actors: a Jupyter server stack and a terminal server stack. The important thing is that almost all the interesting Python traffic is coming from PID 232 and PID 208, which are Jupyter kernel / server processes, not background daemons. Then ss -tanp ties the knot neatly. All those mysterious ports you saw earlier? They belong to PID 232, which is an ipykernel_launcher.py. That means the kernel itself is opening multiple loopback listeners and making local TCP connections, which is exactly how Jupyter brokers communication between the frontend, kernel, and internal services. Port 33001 being a “hub” now makes perfect sense: it’s kernel-internal RPC, not some rogue server. Crucially, nothing external is binding these ports, nothing is stuck in SYN-SENT, and nothing is being blocked. The network is healthy. The OS is boring. The supervisor is boring. Which leaves you with the uncomfortable but useful conclusion: your issue is not infrastructure, not services, and not sockets. It’s either application logic, request flow, or a deadlock / wait higher up in your Python or gRPC stack. Here’s the sharp question you should answer next, and don’t dodge it: what behavior are you seeing that made you suspect system services in the first place? A hang? A timeout? A silent failure? Because now we know where not to look, which is real progress. If you want, next we can trace one specific port end-to-end, or attach logs to a specific PID and stop guessing entirely.
Summary:
Please note that all contributions to freem are considered to be released under the Creative Commons Attribution-ShareAlike 4.0 (see
Freem:Copyrights
for details). If you do not want your writing to be edited mercilessly and redistributed at will, then do not submit it here.
You are also promising us that you wrote this yourself, or copied it from a public domain or similar free resource.
Do not submit copyrighted work without permission!
Cancel
Editing help
(opens in new window)