[Bug 277389] Reproduceable low memory freeze on 14.0-RELEASE-p5

From: <bugzilla-noreply_at_freebsd.org>
Date: Mon, 18 Mar 2024 02:54:46 UTC
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=277389

--- Comment #27 from Mark Millard <marklmi26-fbsd@yahoo.com> ---
(In reply to pascal.guitierrez from comment #26)

I'll note that I never used mount_nullfs explicitly at
any point but I still got the huge difference in VNODE
results in "vmstat -z" when doing your test iozone
runs, all based just on the:

nullfs_load="YES"
vfs.nullfs.cache_vnodes=0

vs. not distinction. There may be implicit/automatic
use involved? ( zfs_load="YES" both ways. )

Because of your hangup status, doing a "vmstat -z" and
saving the output before doing the read iozone test
would be good. Both with and without the 3 lines for
comparison/contrast: the vmstat -z output differences
should indicate if internally any difference is being
made.

I made the suggestion because I've no way to tell if
what I've been reporting contributes to your context
or not: I've never seen the OOM activity or hangups.
But the huge Wired figures that even survive the ARC
shrinking suggest potential contribution to an OOM
status.

-- 
You are receiving this mail because:
You are the assignee for the bug.