Ethernet throughput anomalies - tcp

I have run into a few weird blips testing a throughput program. It seems to work fine and is sending messages over a 1Gbps cable. The program works between two computers one side being the master and the other being the slave. The master sends a message to the slave (of size 1,10,100,1000 words chosen by the user) which is then echoed back. This process is repeated for usually about 10,000 messages. The transmission can happen over TCP or UDP again chosen by the user.
What is strange is when multiple instances are run between the same computers, but going to different ports, the total test time actually shrinks, and I can not seem to understand why. I thought that maybe TCP was doing some sort of optimization for larger packets but
a) they are going to and from different ports
b) the same thing happens with UDP
So why would multiple instances actually lower the total transmission time for each individual test?

Related

What happens when ethernet reception buffer is full

I have a quite newbie question : assume that I have two devices communication via Ethernet (TCP/IP) at 100Mbps. In one side, I will be feeding the device with data to transmit. At the other side, I will be consuming the received data. I have the ability to choose the adequate buffer size of both devices.
And now my question is : If data consumption rate from the second device, is slower than data feeding rate at the first one, what will happen then?
I found some, talking about overrun counter.
Is there anything in the ethernet communication indicating that a device is momently busy and can't receive new packets? so I can pause the transmission from the receiver device.
Can some one provide me with a document or documents that explain this issue in detail because I didn't find any.
Thank you by advance
Ethernet protocol runs on MAC controller chip. MAC has two separate RX-ring (for ingress packets) and TX-ring(for egress packets), this means its a full-duplex in nature. RX/TX-rings also have on-chip FIFO but the rings hold PDUs in host memory buffers. I have covered little bit of functionality in one of the related post
Now, congestion can happen but again RX and TX are two different paths and will be due to following conditions
Queue/de-queue of rx-buffers/tx-buffers is NOT fast compared to line rate. This happens when CPU is busy and not honer the interrupts fast enough.
Host memory is slower (ex: DRAM and not SRAM), or not enough memory(due to memory leak)
Intermediate processing of the buffers taking too long.
Now, about the peer device: Back-pressure can be taken care in the a standalone system and when that happens, we usually tail drop the packets. This is agnostics to the peer device, if peer device is slow its that device's problem.
Definition of overrun is: Number of times the receiver hardware was unable to handle received data to a hardware buffer because the input rate exceeded the receiver’s ability to handle the data.
I recommend pick any MAC controller's data-sheet (ex: Intel's ethernet Controller) and you will get all your questions covered. Or if you get to see device-driver for any MAC controller.
TCP/IP is upper layer stack sits inside kernel(this can be in user plane as well), whereas ARPA protocol (ethernet) is inside MAC controller hardware. If you understand this you will understand the difference between router and switches (where there is no TCP/IP stack).

Detect faulty physical links with ping

I would have a question regarding physical problem detection in a link with ping.
If we have a fiber or cable which has a problem and generate some CRC errors on the frame (visible with switch or router interface statistics), it's possible all ping pass because of the default small icmp packet size and statistically fewer possibilities of error. First, can you confirm this ?
Also, my second question, if I ping with a large size like 65000 bytes, one ping will generate approximately 65000 / 1500(mtu) = 43 frames, as ip framgents, then the statistics to get packet loss (because normally if one ip fragment is lost the entire ip packet is lost) with large ping is clearly higher ? Is this assumption is true ?
The global question is, with large ping, could we easier detect a physical problem on a link ?
A link problem is a layer 1 or 2 problem. ping is a layer 3 tool, if you use it for diagnosis you might get completely unexpected results. Port counters are much more precise in diagnosing link problems.
That said, it's quite possible that packet loss for small ping packets is low while real traffic is impacted more severely.
In addition to cable problems - that you'll need to repair - and a statistically random loss of packets there are also some configuration problems that can lead to CRC errors.
Most common in 10/100 Mbit networks is a duplex mismatch where one side uses half-duplex (HDX) transmission with CSMA/CD while the other one uses full-duplex (FDX) - once real data is transmitted, the HDX side will detect collisions, late collisions and possibly jabber while the FDX side will detect FCS errors. Throughput is very low, put ping with its low bandwidth usually works.
Duplex mismatches happen most often when one side is forced to full duplex, thus deactivating auto-negotiation and the other side defaults to half duplex.

how can you count the number of packet losses in a file transfer?

One of my networks course projects has to do with 802.11 protocol.
Me and my parther thought about exploring the "hidden terminal" problem, simulating it.
We've set up a private network. We have 2 wireless terminals that will attempt to send a file
to a 3rd terminal that is connected to the router via ethernet. RTS/CTS will be disabled.
To compare results, we'd like to measure the number of packet collisions that occured during the transfer so as to conclude that is due to RTS being disabled.
We've read that it is imposible to measure packet collisions as it is basically noise. We'll have to make do with counting the packets that didnt recieve an "ACK". Basically, the number of retransmitions.
How can we do that?
I suggested that instead of sending a file, we could make the 2 wireless terminals ping the 3rd terminal continually. The ping feature automatically counts the ping packets that didnt recieve the "pong". Do you think its a viable approach?
Thank you very much.
No, you'll get incorrect results. Ping is an application, i.e. working at application (highest) level of the network. 802.11 protocol operates at MAC layer - there are at least 2 layers separating between ping and 802.11. Whatever retransmissions happen at MAC layer - they are hidden by the layers above it. You'll see failure in ping only if all the retransmissions initiated by lower levels have failed.
You need to work on the same level that you're investigating - in your case it's the MAC layer. You can use a sniffer (google for it) to get the statistics you want.

Average UDP packet loss and packet re-ordering

I'd like to garner fellow SO'ers experience with regards to the issue of UDP packet loss (or drop-out).
Initially my understanding is that given direct point to point connections where the NICs are connected via a crossover cable and ample buffer on the NICs and timely processing of said buffers, that there 'should' be no packet loss or packet ordering issues. I believe this is also the case given one good/high-end switch in between the points.
Excluding the above scenario, what is the expected average UDP packet loss over a LAN
What scenarios cause UDP packet ordering issues?
No idea on the UDP packetloss on average LANs. I assume reasonably low on modern switched networks, otherwise your LAN or endpoints are too highly loaded. :)
The re-ordering is probably easiest to achieve when routes are brought up and down; say, one of the switches in your organization is under enough load that re-organizing the tree makes sense and traffic is sent through different switches. More likely is your ISP's peers coming and going, or reaching traffic limits, and the priority of packets through them changes -- old packets were in flight on the heavy-loaded network, new packets are in flight on the lighter-loaded network, and they arrive out of order.
I too am looking for an expected average. I found that from a direct link (PC to PC) packet loss occurs very rarely, although it definitely occurs. Availability was something like 99.9% at 1 kB packets # 50 Hz.
I have seen reordering just by sending and receiving on the same network interface.
I concluded that this occurs because each packet is handled asynchronously so that there is a chance of a newly arrived packet being processed before packets received prior to the newly received one.
On my basic gigabit switched LAN I get zero packet loss at even 50,000 packets per second, with FreeBSD, Solaris or Linux.
However Windows is something quite special, I easily see packet loss on exactly the same hardware at low speeds such as 10,000 per second. This is mainly due to buffer overflow between WinSock and the NIC, if you drive the packets faster you lose more, if you space out the packets you drop less.
There is no magical number, my situation is probably worse due to Broadcom having terrible Windows drivers.
You can easily see packet ordering issues, however it is almost always only the last two packets switched. This is an artifact of how switches function.
Interestingly what you haven't mentioned in Wi-Fi, radio signals are highly subject to interference and environmental conditions.

What does LAN/traffic congestion mean?

While talking about UDP I saw/heard congestion come up a few times. What does that mean?
congestion is when you are trying to send too much data over a limited bandwidth, it cannot send the data faster than the incoming amount so additional packets are dropped.
When congestion occurs, you can see these effects:
Delay due to the queue at one end of the connection being too big, so it takes time for your packet to be transmitted.
Packet loss when new packets are simply dropped, forcing connection resets (and often causing more congestion).
Lower quality of service, protocols like TCP will do a cutback on the transmission rate, so your throughput will be lowered.
Blocking, certain networks have protocol priorities, so your UDP packets may be dropped in favor of allowing TCP traffic through.
Its like a traffic jam, imagine right after a sports game where a parking lot full of cars is trying to empty out into a small side street.
It means that network-connected devices are attempting to send more data across the network than it can handle, e.g. 20 Mbps of data across a 10 Mbps link.
In context of UDP, it's your main source of lost datagrams under ordinary circumstances.
Most LANs use some sort of a collission detection/avoidance system. A congestion typically means that the amount of data which is being transmiited on the medium is causing enough collissions to deteriorate the quality of service defined for that medium.
You may want to read up CSMA/CD at wikipedia.
As UDP packets can often be broadcasted, congestion can occur more often.
Kind regards,
For instance, Ethernet is a broadband protocol. Once a message is sent, every node receives it but ignores if the packet are not sent to them. What happens when two nodes send a packet at the same time? It will cause a collision and data loss.
So, both of the nodes will have to resend the message. To avoid more collisions, nodes are designed to wait a random number of milliseconds. Otherwise they keep going on sending messages simultaneously and packages will collide forever.

Resources