netdev - Re: [EXT] [PATCH] aquantia: Remove the build

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]

Message-ID: <5b6ae6ab-be6d-3a18-341d-c18719ffaaad@marvell.com>
Date:   Tue, 24 Nov 2020 17:29:22 +0300
From:   Igor Russkikh <irusskikh@...vell.com>
To:     "Ramsay, Lincoln" <Lincoln.Ramsay@...i.com>,
        "David S. Miller" <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>, <netdev@...r.kernel.org>,
        "Dmitry Bogdanov [C]" <dbogdanov@...vell.com>
Subject: Re: [EXT] [PATCH] aquantia: Remove the build_skb path



On 23/11/2020 7:20 am, Ramsay, Lincoln wrote:
>> Yep, that could be the only way to fix this for now.
>> Have you tried to estimate any performance drops from this?
> 
> Unfortunately, I am not in a very good position to do this. The 10G
> interfaces on our device don't actually have enough raw PCI bandwidth
> available to hit 10G transfer rates.
> 
> I did use iperf3 and saw bursts over 2Gbit/sec (with average closer to
> 1.3Gbit/sec on a good run). There was no significant difference between
> running with and without the patch. I am told that this is about as good
> as can be expected.
> 
> Make of that what you will :)

Thats not very useful, but since we anyway have to fix that - lets do it.

I'll try to estimate potential perf drop on my setup when possible.

Thanks,
  Igor