wiki:Experimenters/FAQ

How do I use the UNIX command line interface (CLI)?

Please see How to Use the UNIX CLI and How to Use UNIX Networking CLI commands.

Why do I see poor bandwidth on my stitched links with iperf?

Answer (provided by Nick Bastin):

The window size is way too small if you want single-flow throughput to be high, particularly given the latency in WAN connections (the resultant bandwidth delay product will be much too high for iperf's default window sizes).

You simply need to set the window size larger on both the server and client and your performance should be better for a single flow, regardless of raw-pc or xen VM. (The default raw PC window size is likely a lot larger, hiding this problem, but if you want deterministic performance from iperf you always need to set the window sizes you're going to use, otherwise it makes a guess at a default that is going to be highly intolerant of any latency in your connection).

Barring any other shaping going on, the throughput you're getting with a 23.5K window means you have a connection with roughly 12ms of delay. To get 100 Mbits (or close to it) on this connection, you'd need a window size of 150K or larger (and make sure your buffer sizes on both end can support that large of a window).

Brecht Vermeulen adds: typically also handy in debugging link performance is to throw in an UDP iperf to see what is possible on the links and when packet loss begins to start: server side: iperf -s -u client side: iperf -c xxx -b 50M

so you can vary bandwidth and packet size and see what happens

For the whole thread that lead to this discussion see:

https://groups.google.com/d/msg/geni-users/Pqgs_BpSZPc/3LOLHwrkbPYJ

Should I use a raw PC for my experiment?

Many aggregates in GENI have only a couple of raw PCs and thus are a scarce resource, since when a user reserves one, no one else can use them. Moreover, some AMs have policies in place that do not allow a user to renew slivers with raw PCs for a long time.

When you are designing your experiment only include a raw PC if you absolutely need to. In most cases you can do everything you want with a Virtual Machine (VM). This way you will leave the raw PCs to experimenters that really need them. If you are not sure if a VM is appropriate for your experiment don't hesitate to send an email to geni-users@googlegroups.com.

Why do I only see traffic on one interface on my multi-homed system? Or how do I turn off reverse path filtering?

When does this apply?

You have a multi-homed system (i.e. it has multiple data plane interfaces) which appears to only be able to receive traffic from a given traffic source on one interface.

What's happening?

Reverse path filtering may be enabled. We most often see this issue on Ubuntu systems because reverse path filtering is enabled by default.

How do I fix it?

On Ubuntu 12.04 run the following command:

sudo sysctl -w net.ipv4.conf.all.rp_filter=0

Why can't I install iperf (or standard package X) on CentOS

When I try to install iperf on a node running CentOS, I get the following error:

$ sudo yum install iperf
Loaded plugins: fastestmirror
Determining fastest mirrors
 * base: mirror.raystedman.net
 * elrepo: ftp.osuosl.org
 * extras: mirrors.unifiedlayer.com
 * updates: mirror.compevo.com
base                                                     | 3.7 kB     00:00
elrepo                                                   | 2.9 kB     00:00
elrepo/primary_db                                        | 696 kB     00:00
extras                                                   | 3.3 kB     00:00
extras/primary_db                                        |  19 kB     00:00
updates                                                  | 3.4 kB     00:00
updates/primary_db                                       | 5.3 MB     00:01
Setting up Install Process
No package iperf available.
Error: Nothing to do

How do I fix it?

On CentOS you need to add the EPEL repo:

sudo rpm -ivh http://dl.fedoraproject.org/pub/epel/6/x86_64/epel-release-6-8.noarch.rpm

Then you should be able to install iperf as normal using yum.

I need access to Flack from the GENI Portal

As of August 4th 2015, Flack links have been removed from the GENI Portal. If you still need to access Flack for your slice you can still do so by:

  1. Locate your slice in the slice Dashboard
  2. Load your slice by clicking on its name
  3. The address bar of your browser should look like: https://portal1.geni.net/secure/slice.php?slice_id=0a7dc448-8df6-4b7c-b469-e33258bee00a
  4. In the URL replace slice.php with flack.php and press enter to load the new page.
Last modified 19 months ago Last modified on 06/07/17 13:19:13