netdev - Re: [PATCH RFC 11/11] net/mlx5e: XDP TX xmit more

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 for Android: free password hash cracker in your pocket

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

Message-ID: <a36a195c-a796-847e-3770-e5a79ce2638b@hpe.com>
Date:   Thu, 8 Sep 2016 11:48:50 -0700
From:   Rick Jones <rick.jones2@....com>
To:     Tom Herbert <tom@...bertland.com>,
        Jesper Dangaard Brouer <brouer@...hat.com>
Cc:     John Fastabend <john.fastabend@...il.com>,
        Saeed Mahameed <saeedm@....mellanox.co.il>,
        Eric Dumazet <eric.dumazet@...il.com>,
        Saeed Mahameed <saeedm@...lanox.com>,
        iovisor-dev <iovisor-dev@...ts.iovisor.org>,
        Linux Netdev List <netdev@...r.kernel.org>,
        Tariq Toukan <tariqt@...lanox.com>,
        Brenden Blanco <bblanco@...mgrid.com>,
        Alexei Starovoitov <alexei.starovoitov@...il.com>,
        Martin KaFai Lau <kafai@...com>,
        Daniel Borkmann <daniel@...earbox.net>,
        Eric Dumazet <edumazet@...gle.com>,
        Jamal Hadi Salim <jhs@...atatu.com>,
        Achiad Shochat <achiad@...lanox.com>
Subject: Re: [PATCH RFC 11/11] net/mlx5e: XDP TX xmit more

On 09/08/2016 11:16 AM, Tom Herbert wrote:
> On Thu, Sep 8, 2016 at 10:19 AM, Jesper Dangaard Brouer
> <brouer@...hat.com> wrote:
>> On Thu, 8 Sep 2016 09:26:03 -0700
>> Tom Herbert <tom@...bertland.com> wrote:
>>> Shouldn't qdisc bulk size be based on the BQL limit? What is the
>>> simple algorithm to apply to in-flight packets?
>>
>> Maybe the algorithm is not so simple, and we likely also have to take
>> BQL bytes into account.
>>
>> The reason for wanting packets-in-flight is because we are attacking a
>> transaction cost.  The tailptr/doorbell cost around 70ns.  (Based on
>> data in this patch desc, 4.9Mpps -> 7.5Mpps (1/4.90-1/7.5)*1000 =
>> 70.74). The 10G wirespeed small packets budget is 67.2ns, this with
>> fixed overhead per packet of 70ns we can never reach 10G wirespeed.
>>
> But you should be able to do this with BQL and it is more accurate.
> BQL tells how many bytes need to be sent and that can be used to
> create a bulk of packets to send with one doorbell.

With small packets and the "default" ring size for this NIC/driver 
combination, is the BQL large enough that the ring fills before one hits 
the BQL?

rick jones