Date: Wed, 10 Nov 2021 23:43:46 -0500 From: Chris Ross <cross+freebsd@distal.com> To: freebsd-fs <freebsd-fs@freebsd.org> Cc: freebsd-stable@freebsd.org Subject: Re: swap_pager: cannot allocate bio Message-ID: <09989390-FED9-45A6-A866-4605D3766DFE@distal.com> In-Reply-To: <9FE99EEF-37C5-43D1-AC9D-17F3EDA19606@distal.com> References: <9FE99EEF-37C5-43D1-AC9D-17F3EDA19606@distal.com>
next in thread | previous in thread | raw e-mail | index | archive | help
> On Nov 10, 2021, at 23:35, Chris Ross <cross+freebsd@distal.com> =
wrote:
>=20
> Hey all. I have a system that I=E2=80=99m trying to do some intensive =
CPU and I/O on. FreeBSD 13.0-RELEASE, amd64, 128GB RAM, hardware RAID1 =
OS volume, and a large (40TB) zpool where most of the I/O is happening.
>=20
> Initially, it was failing for me because it was running out of swap =
space. It had only the normal small (4-8G) swap partition, so I resized =
the filesystems on the root disk and now have 400+GB swap. The system =
had frozen up and I wasn=E2=80=99t able to log in. When I go to the =
console, I find a long list of:
>=20
> swap_pager: cannot allocate bio
>=20
> lines. I was able to log into the console as root and pstat -s shows =
the swap minimally used (7.5GB used). Attempting a =E2=80=9Czpool =
status=E2=80=9D at that point locked up. I don=E2=80=99t know if the =
problem is the memory subsystem, or zfs.
>=20
> But, based on the error, is there perhaps some kernel parameter I can =
tune that might prevent the swap pager from encountering that error?
Moving to freebsd-fs. More information makes it looks more like a ZFS =
problem than anything else.
I am able to log into another root virtual console, and I can run ps =
(shows many things, including dozens of "cron: running job (cron)=E2=80=9D=
jobs, in D state), and I=E2=80=99m able to wander around the root disk =
(3T ufs filesystem) without trouble. But, as mentioned above the =
=E2=80=9Czpool status=E2=80=9D is hung, and I suspect if I tried to =
access anything in that filesystem it would hang to. Those cron jobs, =
which aren=E2=80=99t anything I added, I assume are just system =E2=80=9Cc=
heck around the system=E2=80=9D cron jobs that are getting stuck there.
So, if anyone has any suggestions. I can leave this system stuck like =
this for a little while, but I=E2=80=99ll probably want to bring it back =
before the end of the day tomorrow. (I=E2=80=99m US EST, so it=E2=80=99s =
almost midnight here. I=E2=80=99ll check in on email for suggestions or =
ideas in the morning.)
Thanks all.
- Chris=
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?09989390-FED9-45A6-A866-4605D3766DFE>