Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 03 Oct 2024 14:21:12 +0000
From:      bugzilla-noreply@freebsd.org
To:        geom@FreeBSD.org
Subject:   [Bug 242747] geli: AMD Epyc+GELI not using Hardware AES
Message-ID:  <bug-242747-14739-fOp3MYCHqk@https.bugs.freebsd.org/bugzilla/>
In-Reply-To: <bug-242747-14739@https.bugs.freebsd.org/bugzilla/>
References:  <bug-242747-14739@https.bugs.freebsd.org/bugzilla/>

next in thread | previous in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D242747

--- Comment #34 from Eirik Oeverby <ltning-freebsd@anduin.net> ---
(In reply to John Baldwin from comment #33)
I can confirm that the performance problems here are absolutely crippling. I
honestly assumed this was cleared up by now, but I haven't installed new
machines with any significant core counts for a while, so I have not been
bitten by it.

Can we just Get This Done? The defaults *will* make any new-ish (last 5 yea=
rs,
at least) AMD machine grind to a halt if it has more than a couple of disks=
 and
uses GELI.

I'd think we would rather want to have have suboptimal (but not
machine-hanging) performance on Intel over an absolute train crash on AMD as
the out-of-the-box experience.

/Eirik

--=20
You are receiving this mail because:
You are the assignee for the bug.=



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-242747-14739-fOp3MYCHqk>