Span vs profitap and garland taps

WWW.THETECHFIRM.COM © 2016, The Technology Firm

The primary goal of this lab is to document latency when using a span port compared to a TAP.

The methodology for the various tests was fairly straight forward;

•100,000 frames were generated by the Optiview to another Optiview and captured by another Optiview.

•We chose to only generate a 9% load to best resemble an average loaded gigabit port. The point being that ports under greater load would result in more latency.

•The Optiview was chosen since it can capture with a 10 nanosecond resolution and packet slicing was used to reduce the trace file size.

•The remaining trace file was filtered by the IP identifier since the Optiview keeps this value constant for all packets.

•This trace file was then converted to a CSV file using Wireshark and the filtered output’s delta’s time was graphed using Excel.

The order of the tests are quite important; the first test was a baseline of 2 Optiviews back to back, the second test was to introduce a switch, the third test was to use a tap and lastly we used a span port.

Here is a summary of the packet latency results:

•Back to Back = 68 – 69 microseconds

•Switch = 56 – 80 microseconds

•TAP = 55 – 80 microseconds

•Span Port = 50 – 88 microseconds

The conclusion of our tests highlight that the span port used created more latency between packets as well as per packet latency where the TAP resulted in very little latency .

The slides below document products used, any settings or configuration notes.

Tony FortunatoSr Network Performance Specialist

The Technology Firmwww.thetechfirm.com

Getting things to work better - bit by bit-

Span vs TAP

© 2016, The Technology Firm WWW.THETECHFIRM.COM

Netscout (Fluke Networks) Optiview XG Tablet

• Traffic Generator

• Capture with 10 nanosecond resolution

Cisco 3750 Switch and patch cables

Garland P1GCCB 1GB Copper TAP

ProfiTap’s ProfiShark Product

Items Used


Traffic Generator

3


Capture Configuration and Packet Slicing

4


Methodology

Start Capture from all 3 Optiview XG’s (when required)Start Traffic Generation from 1 Optiview XGCollect trace file or filesRun XG clean up script to remove trace files and produce .cap fileFilter out any unnecessary packets and save filtered trace file as …filtered.capExport filtered trace file using Wireshark to a CSV fileProcess data in Excel

5


Test 4 – Back to Back - Baseline

Generate traffic OptiviewXGb8192.168.111.2

OptiviewXG98192.168.111.1


Test 4 – Back to Back

Range is between 68 – 69 microseconds


Test 1 – Traffic Through Switch

Generate trafficOptiviewXGb810.99.10.104

Port 27

Blue

Port 25 Yellow

Port 29

Pink



No traffic will be captured here since the target

address is 10.99.10.101


Test 1 – Traffic Through Cisco Switch - Baseline

9



Test 5: Optiview XG to XG with ProfiShark

Generate traffic

USB 3.0

OptiviewXGb810.99.10.104




ProfiShark Results

11



Test 5: Optiview XG to XG with P1GCCB TAP





TAP Results

13



Test 2 - Span

Span port


Port 27

Blue

Port 25 Yellow

Port 29

Pink




Cisco 3750 Configuration Notes

15

Dexter#config terminalDexter(config)# monitor session 1 source interface gig2/0/29Dexter(config)# monitor session 1 destination interface gig2/0/25

Check current monitor session configuration:

Dexter# show monitor session 1Session 1------------Type : Local SessionSource Ports :

Both : Gi2/0/29Destination Ports : Gi2/0/25 Encapsulation : Native Ingress : Disabled


Test 2 – Span Port Results

16
