From nobody Tue Oct 17 23:54:02 2023
X-Original-To: freebsd-fs@mlmmj.nyi.freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1])
	by mlmmj.nyi.freebsd.org (Postfix) with ESMTP id 4S99my0CJpz4xCff
	for <freebsd-fs@mlmmj.nyi.freebsd.org>; Tue, 17 Oct 2023 23:54:10 +0000 (UTC)
	(envelope-from brooks@spindle.one-eyed-alien.net)
Received: from spindle.one-eyed-alien.net (spindle.one-eyed-alien.net [199.48.129.229])
	(using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)
	 key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256)
	(Client did not present a certificate)
	by mx1.freebsd.org (Postfix) with ESMTPS id 4S99mx1WR0z4L7J
	for <freebsd-fs@freebsd.org>; Tue, 17 Oct 2023 23:54:09 +0000 (UTC)
	(envelope-from brooks@spindle.one-eyed-alien.net)
Authentication-Results: mx1.freebsd.org;
	dkim=none;
	spf=none (mx1.freebsd.org: domain of brooks@spindle.one-eyed-alien.net has no SPF policy when checking 199.48.129.229) smtp.mailfrom=brooks@spindle.one-eyed-alien.net;
	dmarc=none
Received: by spindle.one-eyed-alien.net (Postfix, from userid 3001)
	id D9FF73C019A; Tue, 17 Oct 2023 23:54:02 +0000 (UTC)
Date: Tue, 17 Oct 2023 23:54:02 +0000
From: Brooks Davis <brooks@freebsd.org>
To: freebsd-fs@freebsd.org
Subject: Re: performance impact of various compression schemes on a zvol
Message-ID: <ZS8emljfSTml5uaL@spindle.one-eyed-alien.net>
References: <ZS8Lt5wGKc6vIRrf@int21h>
List-Id: Filesystems <freebsd-fs.freebsd.org>
List-Archive: https://lists.freebsd.org/archives/freebsd-fs
List-Help: <mailto:freebsd-fs+help@freebsd.org>
List-Post: <mailto:freebsd-fs@freebsd.org>
List-Subscribe: <mailto:freebsd-fs+subscribe@freebsd.org>
List-Unsubscribe: <mailto:freebsd-fs+unsubscribe@freebsd.org>
Sender: owner-freebsd-fs@freebsd.org
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <ZS8Lt5wGKc6vIRrf@int21h>
X-Spamd-Bar: /
X-Spamd-Result: default: False [-0.34 / 15.00];
	NEURAL_HAM_LONG(-1.00)[-1.000];
	AUTH_NA(1.00)[];
	NEURAL_HAM_MEDIUM(-1.00)[-1.000];
	NEURAL_SPAM_SHORT(0.36)[0.361];
	FORGED_SENDER(0.30)[brooks@freebsd.org,brooks@spindle.one-eyed-alien.net];
	MIME_GOOD(-0.10)[text/plain];
	ONCE_RECEIVED(0.10)[];
	TO_DN_NONE(0.00)[];
	R_SPF_NA(0.00)[no SPF record];
	ARC_NA(0.00)[];
	RCVD_COUNT_ONE(0.00)[1];
	R_DKIM_NA(0.00)[];
	ASN(0.00)[asn:36236, ipnet:199.48.128.0/22, country:US];
	MIME_TRACE(0.00)[0:+];
	TO_MATCH_ENVRCPT_ALL(0.00)[];
	MLMMJ_DEST(0.00)[freebsd-fs@freebsd.org];
	RCVD_TLS_LAST(0.00)[];
	DMARC_NA(0.00)[freebsd.org];
	FREEFALL_USER(0.00)[brooks];
	FROM_HAS_DN(0.00)[];
	FROM_NEQ_ENVFROM(0.00)[brooks@freebsd.org,brooks@spindle.one-eyed-alien.net];
	RCPT_COUNT_ONE(0.00)[1];
	TO_DOM_EQ_FROM_DOM(0.00)[]
X-Rspamd-Queue-Id: 4S99mx1WR0z4L7J

On Tue, Oct 17, 2023 at 11:33:27PM +0100, void wrote:
> What's the perfomance penalty on zvols of compression?
> The impact on the host?
> 
> I've searched and cannot find figures. I'm not looking for exact numbers,
> more rather would zstd-9 or zstd-6 be better, more suited to zvol (compression
> and speed) than lz4, possibly because it's more recent? Or would no
> compression at all be 'best'?

With compression, it's always going to depend on your data.

You might find Rich Ercolani's talk on ZFS compression at last year's
OpenZFS DevSummit useful:

https://openzfs.org/wiki/OpenZFS_Developer_Summit_2022

-- Brooks