OOM on ZFS scrub

[vborja]

Every time zfs scrub executes exhaust memory hanging the server after several hours (This is almos 600T zpool). Issue as describe in: https://github.com/openzfs/zfs/issues/13546

-
Description: Ubuntu 22.04.1 LTS
Release: 22.04

-
zfsutils-linux:
  Installed: 2.1.4-0ubuntu0.1
  Candidate: 2.1.4-0ubuntu0.1
  Version table:
 *** 2.1.4-0ubuntu0.1 500
        500 http://be.archive.ubuntu.com/ubuntu jammy-updates/main amd64 Packages
        100 /var/lib/dpkg/status
     2.1.2-1ubuntu3 500
        500 http://be.archive.ubuntu.com/ubuntu jammy/main amd64 Packages

-
It is expected that zfs scrub finish within acceptable amount of time despite the size of the pool.

-
It crashes every time causing a kernel panic and rebooting.

ProblemType: Bug
DistroRelease: Ubuntu 22.04
Package: zfsutils-linux 2.1.4-0ubuntu0.1
ProcVersionSignature: Ubuntu 5.15.0-48.54-generic 5.15.53
Uname: Linux 5.15.0-48-generic x86_64
NonfreeKernelModules: zfs zunicode zavl icp zcommon znvpair
ApportVersion: 2.20.11-0ubuntu82.1
Architecture: amd64
CasperMD5CheckResult: unknown
Date: Mon Oct 10 14:38:38 2022
SourcePackage: zfs-linux
UpgradeStatus: Upgraded to jammy on 2022-07-01 (100 days ago)
modified.conffile..etc.default.zfs: [modified]
mtime.conffile..etc.default.zfs: 2022-07-18T13:53:36.058781

[BDV (bdv)]

One of our ZFS storage servers crashed several times in the past. I was running out of memory and ended with a kernel panic. The server did not have a load on these occasions, as it happened on Sundays. ZFS runs its scrubs on Sunday. (on our servers)

The pool size: 411TB

Release: Ubuntu 22.04.1 LTS
zfsutils-linux: 2.1.4-0ubuntu0.1