linux-kernel - Re: [RFC PATCH v5] IV Generation algorithms for dm-crypt

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Mon, 10 Apr 2017 16:00:39 +0200
From:   Milan Broz <gmazyland@...il.com>
To:     Binoy Jayan <binoy.jayan@...aro.org>, Oded <oded.golombek@....com>,
        Ofir <Ofir.Drang@....com>
Cc:     Herbert Xu <herbert@...dor.apana.org.au>,
        "David S. Miller" <davem@...emloft.net>,
        linux-crypto@...r.kernel.org, Mark Brown <broonie@...nel.org>,
        Arnd Bergmann <arnd@...db.de>, linux-kernel@...r.kernel.org,
        Alasdair Kergon <agk@...hat.com>,
        Mike Snitzer <snitzer@...hat.com>, dm-devel@...hat.com,
        Shaohua Li <shli@...nel.org>, linux-raid@...r.kernel.org,
        Rajendra <rnayak@...eaurora.org>,
        Milan Broz <gmazyland@...il.com>, Gilad <gilad@...yossef.com>
Subject: Re: [RFC PATCH v5] IV Generation algorithms for dm-crypt

On 04/07/2017 12:47 PM, Binoy Jayan wrote:
> ===============================================================================
> dm-crypt optimization for larger block sizes
> ===============================================================================
...
> Tests with dd [direct i/o]
> 
> Sequential read            -0.134 %
> Sequential Write           +0.091 %
> 
> Tests with fio [Aggregate bandwidth - aggrb]
> 
> Random Read                +0.358 %
> Random Write               +0.010 %
> 
> Tests with bonnie++ [768 MiB File, 384 MiB Ram]
> after mounting dm-crypt target as ext4
> 
> Sequential o/p [per-char]  -2.876 %
> Sequential o/p [per-blk]   +0.992 %
> Sequential o/p [re-write]  +4.465 %
> 
> Sequential i/p [per-char] -0.453 %
> Sequential i/p [per-blk]  -0.740 %
> 
> Sequential create         -0.255 %
> Sequential delete         +0.042 %
> Random create             -0.007 %
> Random delete             +0.454 %
> 
> NB: The '+' sign shows improvement and '-' shows degradation.
>     The tests were performed with minimal cpu load.
>     Tests with higher cpu load to be done

Well, it is good that there is no performance degradation but it
would be nice to have some user of it that proves it is really
working for your hw.

FYI - with patch that increases dmcrypt sector size to 4k
I can see improvement in speed usually in 5-15% with sync AES-NI
(depends on access pattern), with dmcrypt mapped to memory
it is even close to 20% speed up (but such a configuration is
completely artificial).

I wonder why increased dmcrypt sector size does not work for your hw,
it should help as well (and can be combiuned later with this IV approach).
(For native 4k drives this should be used in future anyway...)

Milan