Bandwidth throughput

I have question about bandwidth throughput. Here's what I have:
Private link between Las Vegas, NV and Waterloo Canada
100Mb
69ms latency
Max. Theoretical throughput would be 7Mbps
If I copy a file on windows 7 computers to/from, should it be achieving the 7Mbps over the link; in perfect conditions? If it is less than that, and no other network problems are present, should I be contacting the provider to have them look at the link?
For Ex.
254MB file took 9m45s to copy
254MB/9.75 = MB per minute
26 MB per minute
*8 (to change to bits)
208000000 Mbpm
/60 (60s in a minute)
3.47Mps (about half of the theoretical max)
If I am the only one using that link, should I be getting 7Mbps every single time?
I also did some iperf tests with a 64K window. It almost matches the theoretical limit.
iperf results:
[156] 0.0-600.1 sec 591 MBytes 8.26 Mbits/sec

Hi,
What's bad in contacting the provider to have them look at the link?
Regards
Thanveer
"Everybody is genius. But if you judge a fish by its ability to climb a tree, it will live its whole life believing that it is a stupid."

Similar Messages

Bandwidth throughput Cisco 1800 Series

Hi All,
Currently looking at upgrading our 10mb leased line to 30mb. We currently have a a Cisco 1800 series which Cisco's technical manual says supports up to 40mb throughput, however our ISP are saying we should upgrade to a Cisco 1921 to support the additional bandwidth.. Has anyone run into this before? Any ideas if what our ISP are telling us is correct?
Thanks in advance,
J

Dear Joe,
Thank you for reaching the Small Business Support Community.
I am afraid you posted your comment, or request for comment, on the wrong community forum. This one is only for Small Business routers where your inquiry is about enterprise ones. I suggest you to move over this post to the LAN, Switching and Routing group from the "Actions" panel on the top right corner of this window or just open up a new one there;
https://supportforums.cisco.com/community/netpro/network-infrastructure/switching
I apologize for the inconvenience and please do not hesitate to reach me back if there is any further assistance we may help you with.
Kind regards,
Jeffrey Rodriguez S. .:|:.:|:.
Cisco Customer Support Engineer
*Please rate the Post so other will know when an answer has been found.

DHCP Clients Bandwidth Throughput?

Hi, I've set up a Leopard Server as DHCP/NAT. Everything is working perfectly. Only thing is I'd like to monitor the bandwidth usage of the DHCP clients, since we are experiencing some bottlenecks due to exhaustive bandwidth usage by some clients from time to time. I've already tried ntop but it was a bit of an overkill.
Is there something like a script for the CLI that outputs something like this:
192.168.1.20 - 37KB/s
192.168.1.12 - 7KB/s
192.168.1.53 - 193KB/s
192.168.1.34 - 97KB/s
etc.
Thanks in advance!
Chris
Message was edited by: criuz

You can see what's hitting the NICs on the server (network traffic either starting at or ending at or traversing a dual-NIC server), but DHCP is not (AFAIK) relevant here. You'll only see the traffic that traverses the local host, or (depending on what widget and what role you're monitoring) the IP router. (You specifically mention "between" clients, and that traffic -- on a typical WiFi or LAN with a typical subnet-- can effectively be direct; it won't necessarily traverse any routers.)
DHCP is how client hosts get (managed) IP addresses, and -- once the client hosts have received addresses -- then DHCP is basically (save for address renewals) out of the way.
Except when the NIC is operating in promiscuous mode or when it receives a packet addressed to one of the MAC (the network "MAC", and not the computer named "Mac") addresses it is listening for, the NIC and the host don't really pay attention to what traffic is passing by out on the LAN.
There might well be a way of extracting this per-host traffic data via SNMP (SNMP does have substantial data available, I've simply not confirmed that the per-host network traffic is one of the gaziilions of data points that are monitored), but that'll require some software for retrieval and consolidation of the data.
As Camelot mentions, aggregate network traffic is best monitored from a (managed) network switch or from a network probe. A promiscuous-mode host can be used, but packet traffic can really load a server; managed switches make better and more economical network probes.
GbE (Gigabit Ethernet) can be a cheap upgrade, too, assuming you're on Cat5enh wiring or better. (There are two Cat5e specs around. One does have a GbE rating (Cat5enh), and the other doesn't.) And low-end managed switches aren't all that expensive these days.

Aironet 350 Bandwidth throughput

Hi I have a Aironet 350 point to point wireless bridge. It will operate at 10Mb/s half duplex. What is the maximum data throuput that I can achieve I have been quoted a figure of 3.4Mb/s? Is there any general documentation that can help me?

For Wireless Ip phones se "Network Sizing" on the following link:
http://www.cisco.com/en/US/partner/products/hw/phones/ps379/products_white_paper09186a00801ca827.shtml#network_sizing

1142N bandwidth throughput and max number of users

Im using AIR-LAP1142N-N-K9 access points (it supports b/g/n). Somestimes the AP has up to 80 users connect to it.
SOme recommends the AP should have between 25-35 users max.
Any one know the recommend maximum number of users connect to a AP? And how can you tell the traffic going through the AP is congested?
Cheers

SOme recommends the AP should have between 25-35 users max.
Cisco recommends no more than 25 authenticated users. Maybe the 80 users are both authenticated (can go to the internet) and associated (not able to).
Remember that wireless is like a hub: When one client talks, everyone stops to listen and waits for their turn.

Wireless 1410 Throughput Test and Security Configuration

Hi Team
Could you please address on the security configuration of the 1410 bridge and on how to test the bandwidth/throughput between two 1410 Bridges setup for point-to-point connectivity.
We have setup this in one of our Client sites.
Awaiting your reply.
Thanks in advance!
Regards
Unni Kannan
Systems Engineer

Bandwitdh testing is usually done with Iperf with an iperf PC standing at each side of the bridge.
I'm not sure what you mean with "address on the security configuration" though ...

How do I ping a specific port (from a specific por...

Does anyone know of any software that will allow me to measure the bandwidth/throughput/travel time/etc of packets from a specific port to a specific port on another network? Ping gives the travel time, but doesn't allow specified ports. Iperf allows you to specify the port you connect to, but not the port you connect from. Wireshark doesn't send packets, though I think it does record traffic by port. Pathping is the same as ping in that it doesn't "do" ports & neither does tracert (and ping/pathping/tracert traffic may well be blocked where normal traffic isn't). So, does anyone have any ideas (or is friendly with their comapny's network admin)?

Llama8
did a quick google and came up with this:-
http://www.elifulkerson.com/projects/tcping.php
seems to do the trick but not sure you can specify the source port on the pinging machine
its a start though
Never tried this so caveat emptor
banz

RV042 - Load Balancing question

Hi, I have the RV042 (firmware 1.3.13.02-tm) in Load Balancing mode. When I do a speedtest, the result is the total bandwidth available on my 2 connections, i.e. 8-9,000 Kbit/Sec (each line is approx 4,500 Kbit/Sec). When I stream from Netflix, the bandwidth throughput is about 4-4,5000 Kbit/Sec. Should not the RV042 stream Netflix as the combined speed between WAN 1 and 2, i.e. at 8-9,000?

Load balance permits more available bandwidth. It may effective double the speed because the requests have more pipe available to utilize but not because it increases the over all speed of your connection. If your connections are 5 mbit they remain 5 mbit.
-Tom
Please mark answered for helpful posts

How to use SNMP to access interface counters for WAN port when not in bridged mode

Hi All,
Can't fault my timecapsule, however just struggling to get one little bit of functionality working. I'm keen to get access to the WAN port interface counter information via SNMP, so I can track total bandwidth/throughput & also volume.
I have no issue getting SNMP to work & can see the 2.4 & 5.0GHz network counters, also total number of WIFI clients, wlan0, wlan1 and bridge0 interfaces. Trouble is none of these are the WAN/external ethernet port.
I see that it is likely that I'm trying to find the vlan1 port, however from what I'm reading this may only be available when the device is running in a routed mode (I'm running in bridge mode).
Anyone able to suggest anything?

Some cable modem you can turn off NAT.. and then use the TC in router mode.. or even use DMZ if the cable router allows that.
Have you ever looked at gargoyle router firmware and its ability to count and quota all clients connecting to internet service.. it is a simply fantastic firmware and can be loaded onto a router that costs $70-130 dollars.. it is 3rd party but very solid if you choose the right combo.
http://www.gargoyle-router.com/wiki/doku.php?id=screenshots

Will RAC's performance bottleneck be the shared disk storage ?

Hi All
I'm studying RAC and I'm concerned about RAC's I/O performance bottleneck.
If I have 10 nodes and they use the same storage disk to hold database, then
they will do I/Os to the disk simultaneously.
Maybe we got more latency ...
Will that be a performance problem?
How does RAC solve this kind of problem?
Thanks.

J.Laurence wrote:
I see FC can solve the problem with bandwidth(throughput),There are a couple of layers in the I/O subsystem for RAC.
There is CacheFusion as already mentioned. Why read a data block from disk when another node has it in is buffer cache and can provide that instead (over the Interconnect communication layer).
Then there is the actual pipes between the server nodes and the storage system. Fibre is slow and not what the latest RAC architecture (such as Exadata) uses.
Traditionally, you pop a HBA card into the server that provides you with 2 fibre channel pipes to the storage switch. These usually run at 2Gb/s and the I/O driver can load balance and fail over. So it in theory can scale to 4Gb/s and provide redundancy should one one fail.
Exadata and more "+modern+" RAC systems use HCA cards running Infiniband (IB). This provides scalability of up to 40Gb/s. Also dual port, which means that you have 2 cables running into the storage switch.
IB supports a protocol called RDMA (Remote Direct Memory Access). This essentially allow memory to be "+shared+" across the IB fabric layer - and is used to read data blocks from the storage array's buffer cache into the local Oracle RAC instance's buffer cache.
Port to port latency for a properly configured IB layer running QDR (4 speed) can be lower than 70ns.
And this does not stop there. You can of course add a huge memory cache in the storage array (which is essentially a server with a bunch of disks). Current x86-64 motherboard technology supports up to 512GB RAM.
Exadata takes it even further as special ASM software on the storage node reconstructs data blocks on the fly to supply the RAC instance with only relevant data. This reduces the data volume to push from the storage node to the database node.
So fibre channels in this sense is a bit dated. As is GigE.
But what about the hard drive's reading & writing I/O? Not a problem as the storage array deals with that. A RAC instance that writes a data block, writes it into storage buffer cache.. where the storage array s/w manages that cache and will do the physical write to disk.
Of course, it will stripe heavily and will have 24+ disk controllers available to write that data block.. so do not think of I/O latency ito of the actual speed of a single disk.

Extremely slow client view

Hello all!
I'm being able to observe the client I've set up. But the speed at which my view as server is refreshed is so slow that I can't possibly monitor what is being done on the client computer. Just to load the desktop took about 5 minutes.
Both computers are under the same ISP with 10Mbit lines but still, monitoring my bandwidth usage, I never download faster than 5k/sec. Is it a bandwidth issue? Is there any setting I can put in order to make this run faster? There's no point in using ARD if I can't see what goes on on the client computer...
Thank you for any suggestion!
Z

I just installed the 3.2.2 update and it runs much faster. I noticed that now my bandwidth throughput reaches 20k/sec, which means it was originally ARD limiting it. Unfortunately it's still not enough to effectively monitor and operate the client computer.
Anyone know of a way to solve this issue?
Cheers!
Z

Expresscard 34 Port. Do I have version 1 or version 2.0 on my Macbook Pro

Hi,
Would like to know which version of Expresscard 34 I have on my Macbook Pro 17" (unibody core-duo) early 2009, currently running Snow Leopard 10.6.4.
Would it be version 1 only (and restricted if hardware based only)?
OR would the heavens have smiled and possibly be version 2.0 expresscard standard (having 5Gbit/s bandwidth capability) from maybe a recent firmware update within a recent OSX update?
Any advice appreciated, thanx.
(references: http://en.wikipedia.org/wiki/ExpressCard#ExpressCard_2.0 )

No one knows?
Reason for needing to know this, is for making an informed decision for having an interface, i.e.:-
Possible SATA II interface. SATA II is I believe 3 gigabit and most express-card 34 adapters out there have 2x SATA II ports to use which equals 6 gigabit combined bandwidth through the express card.
Therefore if the Mac's express-card 34 port is Version 1, then according to some data sheet references for Version 1 specification it is 2.5 gigabit throughput (or 480Mbps if operating USB mode), which would be pointless benefitting from 2x SATA II connections on an express-card inserted into a mac.
If however the Express card 34 port on the Mac is Version 2, then version 2 is stated as having 5 gigabit bandwidth/throughput which would not impune the benefits of having two SATA II connections for external drives i.e. for HD video editing.
Does anyone know?

Workstations down (disconnection)

My work stations, leaving the system with the following message to the whole time:
My workstations down Thu Mar 13 20:17:38 2008
Network error of client T31, NiBufReceive (-6: NIECONN_BROKEN), dp_tm_status=3
Client address of T31 is 128.1.0.19(camioss)
***LOG Q04=> DpRTmPrep, NiBufReceive (62 JOSILENE 31 CAN-BALA-CAG)
RM-T31, U62, 400     JOSILENE, CAN-BALA-CAG-03, 20:17:38, M0, W0, ZARM, 2/1
ERROR => DpRqCheck: T31 in state TM_SLOT_FREE
***LOG Q0G=> DpRqBadHandle, bad_req ( DIA)
ERROR => BAD REQUEST - Reason: DpRqCheck failed (line 6054):
-IN-- sender_id DISPATCHER        tid 31    wp_ca_blk   -1      wp_id -1
-IN-- action    SEND_TO_WP        uid 62    appc_ca_blk -1      type DIA
-IN-- new_stat NO_CHANGE         mode 0     len         -1      rq_id 2558
-IN-- req_info LOGOFF CANCELMODE
Thu Mar 13 20:27:59 2008
***LOG Q0I=> NiIRead: recv (10054: WSAECONNRESET: Connection reset by peer)
ERROR => NiIRead: SiRecv failed for hdl 9 / sock 160
    (SI_ECONN_BROKEN/10054; I4; ST; 172.22.25.9:1660)
Network error of client T37, NiBufReceive (-6: NIECONN_BROKEN), dp_tm_status=3
Client address of T37 is 172.22.25.9(JAT-BAL-CAGL-04)
***LOG Q04=> DpRTmPrep, NiBufReceive (72 NADIA 37 JAT-BAL-CAGL)
RM-T37, U72, 400        NADIA, JAT-BAL-CAGL-04, 20:27:40, M0, W0, ZARM, 3/1
Thu Mar 13 20:29:05 2008
***LOG Q0I=> NiIRead: recv (10054: WSAECONNRESET: Connection reset by peer)
ERROR => NiIRead: SiRecv failed for hdl 9 / sock 160
    (SI_ECONN_BROKEN/10054; I4; ST; 172.22.25.9:1663)
Network error of client T37, NiBufReceive (-6: NIECONN_BROKEN), dp_tm_status=3
Client address of T37 is 172.22.25.9(JAT-BAL-CAGL-04)
***LOG Q04=> DpRTmPrep, NiBufReceive (74 NADIA 37 JAT-BAL-CAGL)
RM-T37, U74, 400        NADIA, JAT-BAL-CAGL-04, 20:28:46, M0, W0, ZARM, 3/1
Thank´s
Pamplona

Had the same issue and found that the new servers that have processors on the network cards result in network packet loss with SAP applications. Switch off option on network card to process network via CPU and no the network card processor.
NIPING is a great tool to find the problem! It is a SAP tool that tests the Network Interface Layer (NI) of a SAP a client to a SAP Server (you load it both ends) Download from SAP Market Place. You need the newest NIPING version for this test, please follow SAP note 799428 to get it.
Took this from another site: Option 2 reported network packet loss. Network guys were then able to trace the issue to network card settings.
NIPING Documentation 13 May 2008
Network connection interrupted or poor network performance.
Other terms
Network, SAP GUI, SAPGUI, RFC, ITS, bandwidth, throughput, latency, round trip time, RTT
Solution
To help diagnose the network or measure network metrics you can test the connection using SAP's NIPING program. You can use NIPING to analyze the network connection between any two machines running SAP software, for example between:
Frontend PC and application server
Two application servers, perhaps belonging to different SAP systems
Application server and database server or live cache server
RFC server or client programs and application server
The machines can be connected either by a local area network (LAN) or wide area network (WAN).
In contrast to the normal PING command, NIPING operates on the TCP socket layer, which is the same layer used by SAP application programs. Therefore, NIPING can be used to identify also errors related to the TCP and socket implementation on the platform.
Please fetch the latest version of NIPING from the service market place as described in SAP note 799428. If this is not possible for you, you can use the NIPING which is located in the executables directory on any SAP server.
How to use NIPING
Starting NIPING without arguments displays a short help message. Find a short exlanation of the most important options below:
First start the NIPING server on computer A (e.g., the Application Server) with the command line:
niping -s -I 0 (the last character is zero, not the letter O)
Then start the client (e.g. on the front-end machine) with the command:
niping -c -H [ -B -L -D ]
may also be the host name or the IP address of host A. The remaining arguments are optional.
(default 1000 bytes) determines the size of the data packets. Please test at least the values 500, 1000, 1400, 1500, 4000 and 10000. This test is especially important to find errors related to the maximum transmission unit (MTU). Please also refer to notes 26086, 107407, 67098 and 44803.
is the number of packets sent (default 10). To find spurious erors it may help to simulate high network load using 1000 loops or more. For a permanent test use a number of e.g. 1000000 loops.
If you test during productive hours and don't want to consume too much bandwidth you can set a between requests ( is in milliseconds).
Examples
1) Measuring network metrics (throughput and RTT)
Throughput is the number of bytes per second that an application can send through the network. Measured values will vary according to the actual load of the network. Round trip time (RTT) is the time for a small data packet to be transmitted from the sender to the receiver and back again to the sender. RTT is mainly influenced by network topology and equipment and normally cannot be improved significantly by increasing bandwidth.
Measuring throughput
niping -c -H -B 100000
The use of large blocks reduces impact of network latency. After completion niping will report throughput as value tr2 in kB/s (kilobytes per second).
Measuring RTT
niping -c -H -B 1 -L 100
(The buffersize of 1 may cause an error in older versions of niping. If so please use niping -c -H -B 20 -L 100 instead)
Small blocks and 100 loops are used to measure the average RTT. The value av2 represents the RTT in ms (milliseconds)
2) Long LAN stability test:
niping -c -H -B 10000 -D 100 -L 360000
This test will consume 100000 Bytes/second of bandwidth (about 10% of a 10 mbps Ethernet) and run for 10 hours.
You need the newest NIPING version for this test, please follow SAP note 799428 to get it.
3a) Long WAN test (stability):
niping -c -H -B 200 -D 1000 -L 36000
This test uses about 5% of an ISDN line of 64 kbps and also runs for 10 hours.
Interpreting NIPING's output: In this test, the times measured by NIPING correspond mostly to the network latency (round trip time - RTT). The throughput measurement has no meaning in this case.
3b) Long WAN test (idle timeouts):
niping -c -H -P -D 3600000
This test establishes a TCP connection and sends a test packet every
hour (delay of 3600000ms). It runs for 10 hours. The goal is to see if
the TCP connection is disrupted by some "idle timeout". Most firewalls
apply such timeouts. But SAP applications make use of long lasting TCP
connection and thus may be hit by such idle timeouts.
You need the newest NIPING version for this test, please follow SAP
note 799428 to get it.
4) Short throughput/stability test:
niping -c -H -B 1000000 -L 100
Tests connection with 100 MB of data as fast as possibly. On a 100 Mbps Ethernet this should take about 10 seconds. During the test, other applications may be impaired. On a slow WAN connection, reduce loops to 10 (-L 10).
Interpreting NIPING's output: This test uses large blocks of data. Therefore, it can be used to measure throughput available to NIPING. Check the output "tr2". It states the throughtput in kilo-byte per second measured from all packets except the fastest and the slowest one. Multiply this value by 10 to obtain an estimate of the line bandwidth in kilo-bit per second (kbps). Does this value differ by a large amount (at least a factor of two) from the one expected for the connection you are analyzing? This could be an indication of network problems: Either the line is overloaded, or there are other problems with the connection.
5) MTU test:
See related notes 155147 and 107407 for an explanation of this test (even if you are not analyzing a Windows system).
niping -c -H -B
Vary X according to the values given above (500, 1000, 1400, 1500, 4000, 10000 and 40000)
Note for Windows NT/2000: If client or server are under heavy load while you perform the measurement, you should start NIPING with high priority. To do this, start NIPING with the following command line:
start /b /wait /high niping
Please test the TCP/IP communication between all concerned machines. Using the options described above, you can either do a long time connection test to find intermittent problems or do a short term stress test with large packets to find fundamental connection problems.
NIPING should not abort with an error message under any circumstances. If you can reproduce an error using NIPING then the problem is definitely related to the network layers, not to the application.
Information needed by SAP
If you need further assistance from SAP support, please start both client and server with the additional argument
-V 2 -T
Replace with an appropriate file name for trace output.
Now send both trace files along with a description of what you did to produce the traces to SAP. (For example, attach the files to a problem message).

Signal, noise and rate data from router?

I understand how to interpret signal and noise from a previous posting (http://discussions.apple.com/thread.jspa?messageID=7190784&#7190784), however, I am not clear as to what the rate data means (this data can be obtained by clicking on Wireless Clients in the Summary Tab of Airport in the Airport Utility)? Can anyone enlighten me.
Thanks
Tony

There are two measures used (& sometimes mixed up) when it comes to wireless network speed. They are: bandwidth & throughput (data transfer rate).
Both are measured in MBps or Mbps (Megabytes vs Megabits per second). Bandwidth is the maximum speed the wireless media can carry. Obviously the higher the bandwidth the greater the speed that can be obtained. The 802.11 standards typically are stated in bandwidth. For example, 802.11g has a bandwidth of 54 Mbps; 802.11n has a range between 150 & 300 Mbps, depending on which radio band (2.4 or 5 GHz) is being used.
The other measure, throughput, is the more "realistic" measure as it takes into account the effects of RF properties and Wi-Fi interference in the real world.
Think of bandwidth as a road. 802.11b would be a rural route, 802.11g a city highway, and 802.11n, the AutoBahn. Now think of throughput as the impact of the number of vehicles on any of those roads and the current road conditions. Just because you can drive a Porsche on the AutoBahn at its maximum speed, doesn't mean it will be able to obtain it.
Long story, short, the "rate data" values you see in the AirPort Utility reflect throughput speeds.

Program over LAN

If you're making a program that will allow a few programs that are distributed on different computers over a LAN to communicate with each other, from a developer's point of view is this more similar to programming locally, or programming over HTTP?
What things should one be aware of when programming in a LAN environment? In your experience, how is it similar to and different from programming locally and programming over HTTP?
What are the options in terms of how the programs could communicate: are RMI, EJB, and Sockets all viable options, or are some of these not valid for LANs?
Thanks.

Thanks for your response.
Does that mean you can ignore the fact that the
computers are over a LAN, and just program like a
regular application? Program yes. Design no.
That same program could then be
used either over a LAN or over the Internet, with no
changes to the code? Yes.
>
Perhaps I should try to clarify my confusion: If
there are programs that you want to be able to
communicate with each other, and they are distributed
across many computers, what is the difference (from a
programming point of view) whether those computers
are located on a LAN, or whether they are not on the
same network (LAN, WAN, etc) but are all hooked up to
the Internet?No difference.
When you have your program connect to a socket on a server on a LAN, a WAN or something internety makes no difference to your program code. None.
There are of course important design considerations.
1) Security. With properly maintained firewalls the computers on a LAN cannot be accessed from outside the LAN.
2) Performance. LAN performance is better than internet performance. A LAN offers shorter physical differences but more importantly greater speeds and much greater bandwidth throughput.
So yes you should keep those two points in mind when you design how your application works.
But if you write code to connect to a socket on a LAN it will work the same way if you point it at a machine that is not on your LAN.

Bandwidth throughput

Similar Messages

Maybe you are looking for