writeback_throttling_sane(9)

💖 writeback_throttling_sane(9) — Kernel API Manual 💖

okay so real talk bestie, this is a page from the Kernel API Manual and it's all about one tiny little function that's basically asking "hey… is the normal dirty throttling thing actually working rn or nah?" 🫶

---

✨ NAME ✨

writeback_throttling_sane — literally just answers the question: is the usual dirty throttling mechanism available? 💅

---

🌸 SYNOPSIS 🌸

bool writeback_throttling_sane (struct scan_control *sc );

no cap, that's the whole signature. copy it exactly, don't get cute with the spacing 🎀

---

🦋 ARGUMENTS 🦋

• sc — the scan_control in question. that's the one we're side-eyeing 👀

---

⭐ DESCRIPTION ⭐

okay so here's the tea ☕ — the normal page dirty throttling mechanism in balance_dirty_pages is completely broken with the legacy memcg. like, not "a little wonky", not "needs a lil patch", completely broken. 😭 and instead, direct stalling in shrink_folio_list gets used for throttling instead.

and the way that fallback is giving… nothing. it lacks all the niceties:

• fairness
• adaptive pausing
• bandwidth proportional allocation
• configurability

all of it. gone. not invited to the party 🙈

so what this function does is it tests whether the vmscan currently in progress can assume that the normal dirty throttling mechanism is operational. that's it. that's the whole vibe check ✅

---

💜 SEE ALSO 💜

Kernel file ./mm/vmscan.c, plus these absolute icons:

• lruvec_lru_size(9)
• remove_mapping(9)
• folio_putback_lru(9)
• folio_isolate_lru(9)
• check_move_unevictable_folios(9)

go read them, iykyk 📚✨

---

and that's the page!! 🎀 this lil cutie lives in ./mm, it's dated October 2026, and it's filed under writeback_throttling_sane(9) — slay, periodt, go touch some folios bestie 💖🦋🌸