netdev - Re: [next-queue PATCH v9 0/6] TSN: Add qdisc based config interface for CBS

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: <20171017113550.GA17834@sisyphus.home.austad.us>
Date:   Tue, 17 Oct 2017 13:35:50 +0200
From:   Henrik Austad <henrik@...tad.us>
To:     Vinicius Costa Gomes <vinicius.gomes@...el.com>
Cc:     netdev@...r.kernel.org, intel-wired-lan@...ts.osuosl.org,
        jhs@...atatu.com, xiyou.wangcong@...il.com, jiri@...nulli.us,
        andre.guedes@...el.com, ivan.briano@...el.com,
        jesus.sanchez-palencia@...el.com, boon.leong.ong@...el.com,
        richardcochran@...il.com, levipearson@...il.com,
        rodney.cummings@...com
Subject: Re: [next-queue PATCH v9 0/6] TSN: Add qdisc based config interface
 for CBS

On Mon, Oct 16, 2017 at 06:01:22PM -0700, Vinicius Costa Gomes wrote:
> Hi,

Vinicius; this looks really good to me, testing shows no errors and 
behavior is as expected. I see some differences in received bw for 
offload=1 and 0 though

Just using tsn_talker and tsn_listener:
tc qdisc add dev eth2 parent 8001:1 cbs idleslope 20000 sendslope -980000 \
hicredit 30 locredit -1470 offload 1

with offload=1 (20Mbps BW)
Receiving data rate: 19420 kbps
Receiving data rate: 19410 kbps

Similarly, but with offload=0 (SW, 20Mbps BW)
Receiving data rate: 19980 kbps
Receiving data rate: 20170 kbps

So slightly higer variance in rate when doing SW, which is as expected.

I plan to run this through some more tests tomorrow and measure variance on the 
receiver etc, I'll keep you posted on my findings.

Feel free to add a tested-by though

Tested-by: Henrik Austad <henrik@...tad.us>

and a Vehemently-supported-by: Henrik .. :)

-Henrik

Download attachment "signature.asc" of type "application/pgp-signature" (182 bytes)