Different performance between sendto and recvfrom - c

I have noticed that there is a difference of performance between sendto and recvfrom (UDP). I send about 100Kbytes from a server to a client, using WiFi (the estimated bandwidth is about 30Mb/s in both directions), and the sending time is about 4-5 ms (it depends, but this value is comparable to the ideal one, 3ms). On the client, the receiving time is ten-fifteen times higher, like 50-60ms. I'd like to have the two elapsed times quite similar. Any idea?

and the sending time is about 4-5 ms (it depends, but this value is comparable to the ideal one, 3ms)
30Mb/s (where the b means bits) is approximately (give or take to account for headers etc) 3 MB/s (where the B means bytes). It should take roughly 30 milliseconds to transmit 100kBytes.
The sendto is returning as soon as it has written all the data to the local buffer of the network stack of the sending machine. The recv obviously has to wait for the data to be transmitted, including latency and stuff needed for all the layers of protocols.

Related

Receiving RAW socket packets with microseconds level accuracy

I am writing a code, which receives raw ethernet packets (no TCP/UDP) every 1ms from the server. For every packet received, my application has to reply with 14 raw packets. If the server doesn't receive the 14 packets before it sends it's packet scheduled for every 1ms, then the server raises an alarm and the application has to break out. The server-client communication is a one to one link.
The server is a hardware (FPGA) which generates packets at precise 1ms interval. The client application runs on a Linux (RHEL/Centos 7) machine with 10G SolarFlare NIC.
My first version of code is like this
while(1)
{
while(1)
{
numbytes = recvfrom(sockfd, buf, sizeof(buf), 0, NULL, NULL);
if(numbytes > 0)
{
//Some more lines here, to read packet number
break;
}
}
for (i=0;i<14;i++)
{
if (sendto(sockfd,(void *)(sym) , sizeof(sym), 0, NULL, NULL) < 0)
perror("Send failed\n");
}
}
I measure the receive time by taking timestamps (using clock_gettime) before the recvfrom call and one after it, I print the time differences of these timestamps and print them whenever the time difference exceeds allowable range of 900-1100 us.
The problem I am facing is that the packet receive time is fluctuating.Something like this (the prints are in microseconds)
Decode Time : 1234
Decode Time : 762
Decode Time : 1593
Decode Time : 406
Decode Time : 1703
Decode Time : 257
Decode Time : 1493
Decode Time : 514
and so on..
And sometimes the decode times exceed 2000us and application would break.
In this situation, application would break anywhere between 2 seconds to a few minutes.
Options tried by me till now.
Setting affinity to a particular isolated core.
Setting scheduling priorities to maximum with SCHED_FIFO
Increase socket buffer sizes
Setting network interface interrupt affinity to the same core which processes application
Spinning over recvfrom using poll(),select() calls.
All these options give a significant improvement over initial version of code. Now the application would run for ~1-2 hours. But this is still not enough.
A few observations:
I get a a huge dump of these decode time prints, whenever I take ssh sessions to Linux machine while the application is running (which makes me think network communication over other 1G Ethernet interface is creating interference with the 10G Ethernet interface).
The application performs better in RHEL (run times of about 2-3 hours) than Centos (run times of about 30 mins - 1.5 hours)
The run times is also varying with Linux machines with different hardware configurations with same OS.
Please suggest if there are any other methods to improve the run-time of the application.
Thanks in advance.
First, you need to verify the accuracy of the timestamping method; clock_gettime. The resolution is nanoseconds, but the accuracy and precision is in question. That is not the answer to your problem, but informs on how reliable the timestamping is before proceeding. See Difference between CLOCK_REALTIME and CLOCK_MONOTONIC? for why CLOCK_MONOTONIC should be used for your application.
I suspect the majority of the decode time fluctuation is either due to a variable number of operations per decode, context switching of the operating system, or IRQs.
Operations per decode I cannot comment on since the code has been simplified in your post. This issue can also be profiled and inspected.
Context switching per process can be easily inspected and monitored https://unix.stackexchange.com/a/84345
As Ron stated, these are very strict timing requirements for a network. It must be an isolated network, and single purpose. Your observation regarding decode over-time when ssh'ing indicates all other traffic must be prevented. This is disturbing, given separate NICs. Thus I suspect IRQs are the issue. See /proc/interrupts.
To achieve consistent decode times over long intervals (hours->days) will require drastically simplifying the OS. Removing unnecessary processes and services, hardware, and perhaps building your own kernel. All for the goal of reducing context switching and interrupts. At which point a real-time OS should be considered. This will only improve the probability of consistent decode time, not guarantee.
My work is developing a data acquisition system that is a combination of FPGA ADC, PC, and ethernet. Inevitably, the inconsistency of a multi-purpose PC means certain features must be moved to dedicated hardware. Consider the Pros/Cons of developing your application for PC versus moving it to hardware.

Strange lag when sending large message using tcp_nodelay

I'm writing a c program that sends the output of a bash shell over a tcp connection. To make my program more responsive, I used setsockopt() to enable TCP_NODELAY, which disables Nagle's buffering algorithm. This worked great, except rarely there is a lag in large messages. As in, if the message is more than around 500 bytes (probably 512). The first 500 bytes will go through (quickly in small messages), then there'll be a 1-2 second delay before the rest is received all at once. This only happens once every 10-15 times a large message is received. On the server side, the message is being written to the socket one byte at a time, and all of the bytes are available, so this behavior is unexpected to me.
My best guess is that there's a 512 byte buffer somewhere in the socket that's causing a block? I did some time tests to see where the lag is, and I'm pretty sure it's the socket itself where the lag is occurring. All of the data on the server side is written without blocking, but the client receives the end of the message after a lag. However I used getsockopt() to find the socket's receive and send buffers, and they are well over 512 bytes - 66000 and 130000 respectively. On the client side, I'm using express js to receive the data in a handler (app.on('data', function(){})). But I read that this express function does not buffer data?
Would anyone have a guess why this is happening? Thanks!
Since TCP_NODELAY means send every piece of data as a packet as soon as possible without combining data together, it sounds like you are sending tons of packets. Since you are writing one byte at a time it could send packets with just one byte of payload and a much bigger frame. This would work fine most of the time but as soon as the first packet drops for whatever reason the receiver would need to go into error-correction mode on the TCP socket to ask for retransmission of the dropped packet. That would incur at least one round-trip latency and perhaps several. It sounds like you are getting lucky for the first several hundred packets (500 bytes worth) and then typically hitting your first packet drop and slowing way down due to error correction. One simple solution might be to write in larger chunks, say 10 bytes at a time, instead of 1 byte so that the chance of hitting a dropped packet is much less. Then you would expect to see this problem as often as you do only for messages around 5000 bytes or so. In general setting TCP_NODELAY will cause things to go faster at first but wind up hitting the first dropped packet sooner simply because TCP_NODELAY will not decrease the number of packets you send per amount of data. So it increases or leaves the number of packets the same which means your chance of hitting a dropped packet within a certain amount of data will go up. There is a tradeoff here between interactive feel and first hiccup. By avoiding TCP_NODELAY you can delay the typical amount of data that will be sent before the first error retransmission is hit on average.
Get a network capture using tcpdump or wire-shark. Review the packet transmission time line, this will help distinguish network problems from software implementation issues. If you see retransmissions you may have a network issue, if you see slow acks you might find it better to NOT use 'No Delay' since Ack delay can stall a 'No Delay' connection.

UDP sendto performance over loopback

Background
I have a very high throughput / low latency network app (goal is << 5 usec per packet) and I wanted to add some monitoring/metrics to it. I have heard about the statsd craze and seems a simple way to collect metrics and feed them into our time series database. Sending metrics is done via a small udp packet write to a daemon (typically running on same server).
I wanted to characterize the effects of sending ~5-10 udp packets in my data path to understand how much latency it would add and was surprised at how bad it is. I know this is a very obscure micro-benchmark but just wanted to get a rough idea on where it lands.
The question I have
I am trying to understand why it takes so long (relatively speaking) to send a UDP packet to localhost versus a remote host. Are there any tweaks I can make to reduce the latency to send a UDP packet? I am thinking the solution for me to push metric collection to an auxiliary core or actually run the statsd daemon on a seperate host.
My setup/benchmarks
CentOS 6.5 with some beefy server hardware.
The client test program I have been using is available here: https://gist.github.com/rishid/9178261
Compiled with gcc 4.7.3 gcc -O3 -std=gnu99 -mtune=native udp_send_bm.c -lrt -o udp_send_bm
The receiver side is running nc -ulk 127.0.0.1 12000 > /dev/null (ip change per IF)
I have ran this micro-benchmark with the following devices.
Some benchmark results:
loopback
Packet Size 500 // Time per sendto() 2159 nanosec // Total time 2.159518
integrated 1 Gb mobo controller
Packet Size 500 // Time per sendto() 397 nanosec // Total time 0.397234
intel ixgbe 10 Gb
Packet Size 500 // Time per sendto() 449 nanosec // Total time 0.449355
solarflare 10 Gb with userspace stack (onload)
Packet Size 500 // Time per sendto() 317 nanosec // Total time 0.317229
Writing to loopback will not be an efficient way to communicate inter-process for profiling. Generally the buffer will be copied multiple times before it's processed, and you run the risk of dropping packets since you're using udp. You're also making additional calls into the operating system, so you add to the risk of context switching (~2us).
goal is << 5 usec per packet
Is this a hard real-time requirement, or a soft requirement? Generally when you're handling things in microseconds, profiling should be zero overhead. You're using solarflare?, so I think you're serious. The best way I know to do this is tapping into the physical line, and sniffing traffic for metrics. A number of products do this.
i/o to disk or the network is very slow if you are incorporating it in a very tight (real time) processing loop. A solution might be to offload the i/o to a separate lower priority task. Let the real time loop pass the messages to the i/o task through a (best lock-free) queue.

Unix domain socket : Make Latency constant

Issue summary: AF_UNIX stable sending, bursty receiving.
I have an application B that receives data over unix domain datagram socket. There is peer application A that sends data to it. Both A and B are running continuously (and are SCHED_FIFO). My application A also prints the time of reception.
The peer application B can send data at varying timings (varying in terms of milliseconds only). Ideally (what I expect) the packet send delay should exactly match with reception delay. For example:
A sends in time : 5ms 10ms 15ms 21ms 30ms 36ms
B should receive in time : 5+x ms 10+x ms 15+x ms 21+x ms ...
Where x is a constant delay.
But when I experimented what I observe in B is :
A sends in time : 5ms 10ms 15ms 21ms 30ms 36ms
B received in time : 5+w ms 10+x ms 15+y ms 21+z ms ...
(w,x,y,z are different constant delays). So I cannot predict reception time when sending time is given).
Is it because some buffering is involved in unix domain socket ? Please suggest some workaround for the issue so that the reception time is predicable from send time. I need 1 millisecond accuracy.
(I am using vanilla Linux 3.0 kernel)
As you are using blocking recv(), when no datagram is available your program will be unscheduled. This is bad for your use case--you want your program to stay hot. So make your recv() non-blocking, and handle EAGAIN by simply busy waiting. This will consume 100% of one core, but I think you'll find it helps you achieve your goal.

How to test the speed for Socket?

I write a program which can forward ip packets between 2 servers, so how to test the speed of the program ? thanks!
There are a number of communication metrics that may be of interest to your potential users.
Latency is the amount of time to send a message, usually quoted in microseconds for co-located devices and in milliseconds for all other scenarios. It is usually quoted as the "zero-byte latency", meaning the time required to transmitted the meta-data of a message. Lower is better.
Bandwidth is measured in bits per second. It is often quoted as "peak bandwidth" and can be obtained by sending a massive amount of data over the line. Higher is better.
CPU utilization is the percent of CPU time required to transmit a message. Network protocols that can offload a message's transmission have low utilization, which means that the communication can "overlap" some other computation in the user's application, which has the effect of hiding latency. Lower is better.
All of these are measured simply by a variation of the ping test, usually called the "ping-pong":
Node 1:
for n = 1 to MAXSIZE, step via n*=2
send message of size n bytes
receive a response of size n bytes
Node 2:
for n = 1 to MAXSIZE, step via n*=2
receive a message of size n bytes
send response of size n bytes
There's also a "ping-ping" test, in which both nodes write to each other at the same time. This requires non-blocking communication to set-up.
Just output n and the time required for each iteration. The first time is the zero-byte latency. The largest sustainable n/time is the bandwidth (convert to bits per second to be industry standard). You can also measure the CPU utilization required to run the larger iterations, but that's a tricky topic for a whole different question.
Take a look at iperf. You can find it at http://sourceforge.net/projects/iperf/ If you google around you will find tutorials for it. You can look at the source and might get some good ideas of how he does it. I use it for routine testing and it is quite robust

Resources