Re: How to verify speed of a 1Gb/s network?

2006-04-27 Thread Eric Schuele

Mike Tancsa wrote:

On Tue, 25 Apr 2006 20:16:06 -0700 (PDT), in
sentex.lists.freebsd.questions you wrote:


Hi,

How can I verify that a 1Gb/s network is indeed
operating at its optimal speed? I tried this:


There are some useful tools in /usr/src/tools/tools/netrate/ to
generate a lot of traffic.   Also, /usr/ports/benchmarks/iperf


I'll second the iperf vote.  That's definitely the way to go.



---Mike


Mike Tancsa, Sentex communications http://www.sentex.net
Providing Internet Access since 1994
[EMAIL PROTECTED], (http://www.tancsa.com)
___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to [EMAIL PROTECTED]




--
Regards,
Eric
___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to [EMAIL PROTECTED]


Re: How to verify speed of a 1Gb/s network?

2006-04-26 Thread Chris Howells

Rob wrote:


How can I verify that a 1Gb/s network is indeed
operating at its optimal speed? I tried this:


By transferring large amounts of data using a light-weight protocol 
(maybe FTP) and timing the amount of time it takes.


Also various testing utilities, for instance ttcp.


[master]$ ping -s 65507 node
65515 bytes from node: icmp_seq=0 ttl=64 time=1.97 ms
65515 bytes from node: icmp_seq=1 ttl=64 time=1.95 ms
65515 bytes from node: icmp_seq=2 ttl=64 time=1.94 ms
65515 bytes from node: icmp_seq=3 ttl=64 time=1.97 ms


This is a measure of latency only.

For instance, I can easily get 10ms pings on 512kbit/sec ADSL. It can 
only transfer data at ~60 KB/sec though.


I can get these values on a very lightly loaded 100Mbit/sec network:

[EMAIL PROTECTED] ping 10.0.0.5
PING 10.0.0.5 (10.0.0.5): 56 data bytes
64 bytes from 10.0.0.5: icmp_seq=0 ttl=128 time=0.844 ms
64 bytes from 10.0.0.5: icmp_seq=1 ttl=128 time=0.740 ms


PS: I verified my calculation method for two
computers here on a 100Mbit/s network, from which
I get:
   time with ping: 12.4 ms
   ideal calculated time: 10 ms


Sounds like your 100Mbit/s network is very heavily loaded, you would 
expect ~1ms pings.

___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to [EMAIL PROTECTED]


Re: How to verify speed of a 1Gb/s network?

2006-04-26 Thread Andrew Pantyukhin
On 4/26/06, Rob [EMAIL PROTECTED] wrote:
 Hi,

 How can I verify that a 1Gb/s network is indeed
 operating at its optimal speed? I tried this:

 [master]$ ping -s 65507 node
 65515 bytes from node: icmp_seq=0 ttl=64 time=1.97 ms
 65515 bytes from node: icmp_seq=1 ttl=64 time=1.95 ms
 65515 bytes from node: icmp_seq=2 ttl=64 time=1.94 ms
 65515 bytes from node: icmp_seq=3 ttl=64 time=1.97 ms

 (I tried many times, over a long period of time
 to get these typical values).
 From this I conclude that it takes about 1.95 ms
 for 65515 x 8 bits to go forth and back between
 master and node.

 Ideally, on a 1Gbit/s network, the time should be:
   65515 x 8 x 2 / (10243) = 0.98 ms
 (x 2 for the roundtrip signal forth and back
 and 10243 is the 1G of the network)

Nopes. There's a number of 10Gig+ lines where you can't
get less than 100ms, damn the light speed :-)

ICMP echo service is pretty much always the lowest priority
of any host. I get 2000ms+ rtt from cheap d-link devices on
a gigabit network. I get 500ms+ from $10k cisco switches
on any networks.

Use iperf or other such tools for real testing.
___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to [EMAIL PROTECTED]


Re: How to verify speed of a 1Gb/s network?

2006-04-26 Thread Jonathan Horne
On Tuesday 25 April 2006 23:17, Chad Leigh -- Shire.Net LLC wrote:
 On Apr 25, 2006, at 9:16 PM, Rob wrote:
  Hi,
 
  How can I verify that a 1Gb/s network is indeed
  operating at its optimal speed? I tried this:
 
  [master]$ ping -s 65507 node
  65515 bytes from node: icmp_seq=0 ttl=64 time=1.97 ms
  65515 bytes from node: icmp_seq=1 ttl=64 time=1.95 ms
  65515 bytes from node: icmp_seq=2 ttl=64 time=1.94 ms
  65515 bytes from node: icmp_seq=3 ttl=64 time=1.97 ms
 
  (I tried many times, over a long period of time
  to get these typical values).
 
  From this I conclude that it takes about 1.95 ms
 
  for 65515 x 8 bits to go forth and back between
  master and node.
 
  Ideally, on a 1Gbit/s network, the time should be:
65515 x 8 x 2 / (10243) = 0.98 ms
  (x 2 for the roundtrip signal forth and back
  and 10243 is the 1G of the network)
 
  May I now conclude that the real-time is about
  two times the ideal-time? I wonder if this indicates
  a problem of the network?
  And is this a proper test of this Gbit/s network?
 
  Thanks,
  Rob.
 
  PS: I verified my calculation method for two
  computers here on a 100Mbit/s network, from which
  I get:
 time with ping: 12.4 ms
 ideal calculated time: 10 ms
  which is an acceptable difference

 I would suspect that a ping is not a valid test as it does not test
 throughput and the send and reception phases have a large influence
 on the out come.  Ie, the time for the send and reception to take
 place is long enough compared to the fast network that the results
 are skewed.  Try an ftp or other non-encrypted data transfer with a
 large enough file that the startup and wind-down won't affect and
 skew it.  Probably still not a definitive test

 btw, here is a test of my gbit network using your ping test

 15 packets transmitted, 15 packets received, 0% packet loss
 round-trip min/avg/max/stddev = 0.128/0.227/0.342/0.061 ms

a few years back, i had a gigabit fiber switch, and 2 intel gigabit fiber 
cards that i put in my 2 fastest computers (at the time, dual p3 1000 and 
dual p3 933).  they both had 10k rpm ultra160 SCSI drives.  the fastest i 
could get for continuous transfer (i made some gigantic zip files containing 
several .iso files) was about 250mbit.

jonathan
___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to [EMAIL PROTECTED]


Re: How to verify speed of a 1Gb/s network?

2006-04-26 Thread Andrew Pantyukhin
On 4/26/06, Jonathan Horne [EMAIL PROTECTED] wrote:
 a few years back, i had a gigabit fiber switch, and 2 intel gigabit fiber
 cards that i put in my 2 fastest computers (at the time, dual p3 1000 and
 dual p3 933).  they both had 10k rpm ultra160 SCSI drives.  the fastest i
 could get for continuous transfer (i made some gigantic zip files containing
 several .iso files) was about 250mbit.

No wonder, really. I bet that hard drives were the bottleneck.
Today 2-3 cheap SATA drives can easily saturate gigabit
links. And if you enable jumbo frames, then CPU will be idle
on large file transfers.
___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to [EMAIL PROTECTED]


Re: How to verify speed of a 1Gb/s network?

2006-04-26 Thread Daniel A.
On 4/26/06, Chris Howells [EMAIL PROTECTED] wrote:
 Rob wrote:

  How can I verify that a 1Gb/s network is indeed
  operating at its optimal speed? I tried this:

 By transferring large amounts of data using a light-weight protocol
 (maybe FTP) and timing the amount of time it takes.

 Also various testing utilities, for instance ttcp.

  [master]$ ping -s 65507 node
  65515 bytes from node: icmp_seq=0 ttl=64 time=1.97 ms
  65515 bytes from node: icmp_seq=1 ttl=64 time=1.95 ms
  65515 bytes from node: icmp_seq=2 ttl=64 time=1.94 ms
  65515 bytes from node: icmp_seq=3 ttl=64 time=1.97 ms

 This is a measure of latency only.

 For instance, I can easily get 10ms pings on 512kbit/sec ADSL. It can
 only transfer data at ~60 KB/sec though.

 I can get these values on a very lightly loaded 100Mbit/sec network:

 [EMAIL PROTECTED] ping 10.0.0.5
 PING 10.0.0.5 (10.0.0.5): 56 data bytes
 64 bytes from 10.0.0.5: icmp_seq=0 ttl=128 time=0.844 ms
 64 bytes from 10.0.0.5: icmp_seq=1 ttl=128 time=0.740 ms

  PS: I verified my calculation method for two
  computers here on a 100Mbit/s network, from which
  I get:
 time with ping: 12.4 ms
 ideal calculated time: 10 ms

 Sounds like your 100Mbit/s network is very heavily loaded, you would
 expect ~1ms pings.
Please notice that he is transferring 65515 bytes, not 64 (Like you did)
___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to [EMAIL PROTECTED]


Re: How to verify speed of a 1Gb/s network?

2006-04-26 Thread Mike Tancsa
On Tue, 25 Apr 2006 20:16:06 -0700 (PDT), in
sentex.lists.freebsd.questions you wrote:

Hi,

How can I verify that a 1Gb/s network is indeed
operating at its optimal speed? I tried this:

There are some useful tools in /usr/src/tools/tools/netrate/ to
generate a lot of traffic.   Also, /usr/ports/benchmarks/iperf

---Mike


Mike Tancsa, Sentex communications http://www.sentex.net
Providing Internet Access since 1994
[EMAIL PROTECTED], (http://www.tancsa.com)
___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to [EMAIL PROTECTED]


How to verify speed of a 1Gb/s network?

2006-04-25 Thread Rob
Hi,

How can I verify that a 1Gb/s network is indeed
operating at its optimal speed? I tried this:

[master]$ ping -s 65507 node
65515 bytes from node: icmp_seq=0 ttl=64 time=1.97 ms
65515 bytes from node: icmp_seq=1 ttl=64 time=1.95 ms
65515 bytes from node: icmp_seq=2 ttl=64 time=1.94 ms
65515 bytes from node: icmp_seq=3 ttl=64 time=1.97 ms

(I tried many times, over a long period of time
to get these typical values).
From this I conclude that it takes about 1.95 ms
for 65515 x 8 bits to go forth and back between
master and node.

Ideally, on a 1Gbit/s network, the time should be:
  65515 x 8 x 2 / (10243) = 0.98 ms
(x 2 for the roundtrip signal forth and back
and 10243 is the 1G of the network)

May I now conclude that the real-time is about
two times the ideal-time? I wonder if this indicates
a problem of the network?
And is this a proper test of this Gbit/s network?

Thanks,
Rob.

PS: I verified my calculation method for two
computers here on a 100Mbit/s network, from which
I get:
   time with ping: 12.4 ms
   ideal calculated time: 10 ms
which is an acceptable difference.


__
Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
http://mail.yahoo.com 
___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to [EMAIL PROTECTED]


Re: How to verify speed of a 1Gb/s network?

2006-04-25 Thread Chad Leigh -- Shire.Net LLC


On Apr 25, 2006, at 9:16 PM, Rob wrote:


Hi,

How can I verify that a 1Gb/s network is indeed
operating at its optimal speed? I tried this:

[master]$ ping -s 65507 node
65515 bytes from node: icmp_seq=0 ttl=64 time=1.97 ms
65515 bytes from node: icmp_seq=1 ttl=64 time=1.95 ms
65515 bytes from node: icmp_seq=2 ttl=64 time=1.94 ms
65515 bytes from node: icmp_seq=3 ttl=64 time=1.97 ms

(I tried many times, over a long period of time
to get these typical values).

From this I conclude that it takes about 1.95 ms

for 65515 x 8 bits to go forth and back between
master and node.

Ideally, on a 1Gbit/s network, the time should be:
  65515 x 8 x 2 / (10243) = 0.98 ms
(x 2 for the roundtrip signal forth and back
and 10243 is the 1G of the network)

May I now conclude that the real-time is about
two times the ideal-time? I wonder if this indicates
a problem of the network?
And is this a proper test of this Gbit/s network?

Thanks,
Rob.

PS: I verified my calculation method for two
computers here on a 100Mbit/s network, from which
I get:
   time with ping: 12.4 ms
   ideal calculated time: 10 ms
which is an acceptable difference


I would suspect that a ping is not a valid test as it does not test  
throughput and the send and reception phases have a large influence  
on the out come.  Ie, the time for the send and reception to take  
place is long enough compared to the fast network that the results  
are skewed.  Try an ftp or other non-encrypted data transfer with a  
large enough file that the startup and wind-down won't affect and  
skew it.  Probably still not a definitive test


btw, here is a test of my gbit network using your ping test

15 packets transmitted, 15 packets received, 0% packet loss
round-trip min/avg/max/stddev = 0.128/0.227/0.342/0.061 ms


---
Chad Leigh -- Shire.Net LLC
Your Web App and Email hosting provider
chad at shire.net



___
freebsd-questions@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-questions
To unsubscribe, send any mail to [EMAIL PROTECTED]