resctrl_l3_m...esource_init(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

πŸ’… resctrl_l3_mon_resource_init β€” bestie's guide to boot-time monitor setup ✨

okay so real talk, this one's from the Kernel API Manual (yes, the manpage name got truncated to resctrl_l3_m...esource_init(9) and honestly? it's giving "username cut off at 16 characters" energy πŸ’€ but we move).


🌸 NAME 🌸

resctrl_l3_mon_resource_init β€” literally the function that initialises the global monitoring structures. that's it, that's the vibe check πŸ’–


πŸŽ€ SYNOPSIS πŸŽ€

int resctrl_l3_mon_resource_init (void );

πŸ¦‹ ARGUMENTS πŸ¦‹

  • void β€” no arguments. nothing. zero. not a single crumb of input needed, she's self-sufficient πŸ‘‘

⭐ DESCRIPTION ⭐

okay so picture this: it's boot time, everything's coming online, and someone has to set up the global monitor resources that don't belong to any specific domain. that someone is her. 🫢

specifically she allocates and initialises those global monitor resources β€” i.e. the closid_num_dirty_rmid[] that's used to find the CLOSID with the cleanest set of RMIDs. like a little ✨cleanliness ranking✨ for your control groups.

she's called exactly once during boot, after the struct rdt_resource's have been configured but before the filesystem is mounted. noted. main character energy but with a very specific schedule. 😀

⚠️ also important: Resctrl's cpuhp callbacks may be called before this point to bring a domain online. so like... she's not necessarily first to the party, she's just the one who brings the snacks πŸ”₯

πŸ’œ RETURN πŸ’œ

  • 0 β€” success, slay, she ate πŸ’…βœ¨
  • -ENOMEM β€” no memory. not enough RAM for her. tragic. 😭

🌈 SEE ALSO 🌈

the whole squad, fr fr πŸ§šπŸ’–


mwah πŸ’‹ that's the page. sourced from ./fs/resctrl, dated October 2026, function resctrl_l3_mon_resource_init(9) β€” go forth and initialise your global monitor resources, bestie, iykyk 🌸⭐

πŸ“¦ where this page comes from