Date: Tue, 21 Mar 2023 14:37:30 -0700 From: Mark Millard <marklmi@yahoo.com> To: ken@freebsd.org, FreeBSD Hackers <freebsd-hackers@freebsd.org> Subject: RE: Getting v_wire_count from a kernel core dump? Message-ID: <5AFA0CE6-48EF-4F41-ABE5-2B417A6BA271@yahoo.com> References: <5AFA0CE6-48EF-4F41-ABE5-2B417A6BA271.ref@yahoo.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Ken Merry <ken_at_freebsd.org> wrote on
Date: Tue, 21 Mar 2023 15:11:30 UTC :
> I have kernel core dumps from several machines out in the field =
(customer sites) that were out of memory panics, and I=E2=80=99m trying =
to figure out, from the kernel core dumps, whether we=E2=80=99re dealing =
with a potential page leak.
>=20
> For context, these machines are running stable/13 from April 2021, but =
they do have the fix for this bug:
Originally I was going to ask which message(s) were produced.
But then I noticed the mismatched time frame ("April 2021")
for the general vintage of the kernel involved vs. the modern
mnessaging.
QUOTE
author Mark Johnston <markj@FreeBSD.org> 2022-01-14 20:03:53 +0000
committer Mark Johnston <markj@FreeBSD.org> 2022-02-28 14:06:58 +0000
commit 13ba1d2836762d09f338158372806b90ce3d63ba (patch)
tree 5547db830727964bc7cb6c68a60fb062f85a5010 /sys/vm/vm_pageout.c
parent 19624b4c6b67881812e2bec0808a9d831cc61bb5 (diff)
download src-13ba1d2836762d09f338158372806b90ce3d63ba.tar.gz
src-13ba1d2836762d09f338158372806b90ce3d63ba.zip
vm_pageout: Print a more accurate message to the console before an OOM =
kill
Previously we'd always print "out of swap space." This can be =
misleading, as there are other reasons an OOM kill can be triggered. In =
particular, it's entirely possible to trigger an OOM kill on a system =
with plenty of free swap space. =20
END QUOTE
The change leads to messages that look like:
pid . . .(?), jid . . ., uid . . ., was killed: failed to reclaim memory
pid . . .(?), jid . . ., uid . . ., was killed: a thread waited too long =
to allocate a page
pid . . .(?), jid . . ., uid . . ., was killed: out of swap space
Each of the 3 have rather different implications.
The last is actually a misnomer in that it really is one or
both of:
swap blk zone exhausted
swap pctrie zone exhausted
Those are kernel data structures, not directly swap space on
media.
You may want to pick up the messaging change.
=3D=3D=3D
Mark Millard
marklmi at yahoo.com
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?5AFA0CE6-48EF-4F41-ABE5-2B417A6BA271>