[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <0b1092f0-889d-ad8b-7678-5037f3181f95@gmail.com>
Date: Tue, 9 Jan 2018 08:16:43 -0800
From: John Fastabend <john.fastabend@...il.com>
To: Jesper Dangaard Brouer <brouer@...hat.com>
Cc: ast@...nel.org, daniel@...earbox.net, netdev@...r.kernel.org
Subject: Re: [bpf-next PATCH 4/7] bpf: sockmap sample, report bytes/sec
On 01/09/2018 05:27 AM, Jesper Dangaard Brouer wrote:
> On Mon, 08 Jan 2018 10:05:58 -0800
> John Fastabend <john.fastabend@...il.com> wrote:
>
>> Report bytes/sec sent as well as total bytes. Useful to get rough
>> idea how different configurations and usage patterns perform with
>> sockmap.
>
> Why BYTES per second, and not BITS per sec?
>
Memory bandwidths is commonly reported in MB/s not bits/sec and
also application throughput tends to be reported in B/s as well.
In general it seemed more natural to map application performance
to B/s. A toggle would be easy enough to report in both or just
bits. On the other hand iperf/netperf seem to report bits per sec.
.John
Powered by blists - more mailing lists