[Cerowrt-devel] [Bloat] fast lanes
dave.taht at gmail.com
Fri May 16 04:12:20 EDT 2014
On Fri, May 16, 2014 at 1:08 AM, Laurent GUERBY <laurent at guerby.net> wrote:
> On Thu, 2014-05-15 at 18:03 -0700, Dave Taht wrote:
>> A side note: It's taken me a long time to finally realize what was
>> wrong with level3's recent blog posting here:
>> The loss chart on the right here that they show to support their
>> argument that the current interconnects are "incurring excessive delay
>> and loss" fails utterly to support their argument -
>> It SHOULD show diurnal variance, and doesn't. The loss rates it shows
>> are both consistent and quite low, compared to the bandwidth being
>> used up, (indicating more of a cabling problem? or excessive load on
>> the other switch? or?)
> The right graph is in log scale while the left i linear,
> I'd say they show the same pattern.
No, loss is flat where bandwidth is maxed, they should - even with a log scale
have a huge increase in loss when bandwidth is maxed.
> As for loss rate, may be the real "big" loss number is on another
> interface in the chain.
All I'm saying is the graph doesn't seem to back the assertions, and
merely seems to be
tracking a background errors on the link.
Yes, I'd love the loss and delay numbers.
More information about the Cerowrt-devel