ACK: Cmnt: [PATCH v2 0/1][SRU][N/P] System hangs when running the memory stress test
Manuel Diewald
manuel.diewald at canonical.com
Tue Oct 7 09:50:51 UTC 2025
On Wed, Oct 01, 2025 at 09:41:41AM +0200, Alessio Faina wrote:
> On Tue, Sep 30, 2025 at 01:02:39PM +0800, AceLan Kao wrote:
> > From: "Chia-Lin Kao (AceLan)" <acelan.kao at canonical.com>
> >
> > BugLink: https://bugs.launchpad.net/bugs/2103680
> >
> > [Impact]
> > While running the memory stress test, the system becomes unresponsive.
> >
> > [Fix]
> > The commit from linux-next fixes the issue
> > 19c5fb83f2a4 mm: page_alloc: avoid kswapd thrashing due to NUMA restrictions
> >
> > [Test]
> > Run the following command on the machine
> > sudo stress-ng --aggressive --verify --timeout 300 --mmapmany 0
> > It should finish the test in 5mins.
> >
> > [Where problems could occur]
> > Given that the patch was reviewed and tested by multiple experienced
> > kernel developers, the likelihood of it causing a noticeable regression is
> > very low. It is far more likely to improve performance and stability on
> > NUMA systems under the conditions described in the commit message.
> >
> > Johannes Weiner (1):
> > mm: page_alloc: avoid kswapd thrashing due to NUMA restrictions
> >
> > mm/page_alloc.c | 24 ++++++++++++++++++++++++
> > 1 file changed, 24 insertions(+)
> >
> > --
> > 2.43.0
> >
> >
> > --
> > kernel-team mailing list
> > kernel-team at lists.ubuntu.com
> > https://lists.ubuntu.com/mailman/listinfo/kernel-team
>
> I've noticed you uploaded a patch for Q as well with the same content,
> it would be better if you could use the flat hierarchy including all the
> patches like the following one:
>
> [PATCH v2 0/1][SRU][N/P/Q] System hangs when running the memory stress test
> [PATCH v2 1/1][SRU][N/P] mm: page_alloc: avoid kswapd thrashing due to NUMA restrictions
> [PATCH v2 1/1][SRU][Q] mm: page_alloc: avoid kswapd thrashing due to NUMA restrictions
>
> --
> Alessio Faina
>
> --
> kernel-team mailing list
> kernel-team at lists.ubuntu.com
> https://lists.ubuntu.com/mailman/listinfo/kernel-team
Since Q is not a stable kernel yet and hence does not require reviews on
the mailing list, unlike N/P, I actually prefer it to be submitted
individually.
Acked-by: Manuel Diewald <manuel.diewald at canonical.com>
--
Manuel
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 833 bytes
Desc: not available
URL: <https://lists.ubuntu.com/archives/kernel-team/attachments/20251007/4ddd69e0/attachment.sig>
More information about the kernel-team
mailing list