[Cerowrt-devel] How to address IT Pros to the issue?

[Maciej Soltysiak]

Hello,

Real Example #1:
"We have a 5Mbps CIFS partition and XXX was saturating it so no one could
print, use office applications (e.g. Word would hang trying to get printer
parameters across the network), network shares, anything that uses CIFS
basically. We asked the network profiling guys to investigate and they came
back with XXX as the culprit."

Basically here they had an application that saturated the whole 5 Mbps of
their Class of Service - The XXX application was made the root-cause, not
how the queues were utilized.

Real Example #2:
Introduction of XXX application to "Reduce bandwidth utilization, typically
by 60-95 percent, across all TCP-based applications. Free up bandwidth for
other applications, like VoIP or Citrix, so they can perform better."

Here the problems for VoIP and Citrix are perceived in bandwidth, so
instead of working to reduce latency, they implement TCP mangling gizmos to
compress/coalesce/whatever traffic to reduce bandwidth used. Probably the
good result they are having is not due to bandwidth use reduced but simply
from the amount of packets on wire and less to manage on the droptail
queues.

These 2 examples are real world IT Pros talking. Enterprise might be a huge
pain to debloat!

Regards,
Maciej
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.bufferbloat.net/pipermail/cerowrt-devel/attachments/20121213/0c3c95f2/attachment-0002.html>