Re: [RFC PATCH v5 3/4] mm/vmscan: avoid pointless large folio splits without swap
Barry Song <[email protected]>
| Newsgroups | org.kernel.vger.cgroups,org.kernel.vger.linux-kernel,org.kvack.linux-mm |
|---|---|
| Message-ID | <CAGsJ_4ykCQWuYyAxOWk5thUOZpCAcGb+W_uCq4KVAFffo2Cn4Q@mail.gmail.com> |
On Thu, Aug 6, 2026 at 9:58 PM David Hildenbrand (Arm) <[email protected]> wrote: > > On 7/30/26 14:23, Xueyuan Chen wrote: > > From: "Barry Song (Xiaomi)" <[email protected]> > > > > When swap is disabled, exhausted, or unavailable due to memcg swap > > limits, splitting a large anonymous folio cannot make swapout progress. > > The fallback only destroys the large folio and inflates split statistics. > > > > Use -E2BIG from folio_alloc_swap() as the explicit signal that splitting > > the folio might allow swapout of smaller pieces. For other allocation > > failures, keep the existing activation path and avoid the split. > > > > This preserves the split fallback for fragmented or partially available > > swap, while avoiding it when there is no backing space for any part of the > > folio. > > > > Reported-by: Nanzhe Zhao <[email protected]> > > Do you have a link to the report? No. Nanzhe mentioned that to me verbally. > > I assume this is not Fixes-worthy. > [...] > > Acked-by: David Hildenbrand (Arm) <[email protected]> > > -- > Cheers, > > David