How to find the max no of threads spawned by one system? - linux

Is there a way / program to find out the maximum no of threads a system can spawn ? i am creating a application and i am in a dilemma whether to go with event looping model or multi threaded model . so wanted to test the systems capabilities on how many threads it can handle ?

The "maximum number of threads" is not as useful a metric as you might think:
There is usually a system-wide maximum number of threads imposed by either the operating system or the available hardware resources.
The per-process maximum number of threads is often configurable and can even change on-the-fly.
In most cases the actual restriction comes from your hardware resources - rather than any imposed limit. Much like any other resource (e.g. memory) you have to check if you were successfull, rather than rely on some kind of limit.
In general, multi-threading has only two advantages when compared to event loops:
It can utilise more than one processor. Depending on the operating system you can also use multiple processes (rather than the more lightweight threads) to do that.
Depending on the operating system, it may offer some degree of privlilege separation.
Other than that multi-threading is usually more expensive in both memory and processing resources. A large number of threads can bring your system to a halt regardless if what they are doing is resource-intensive or not.
In most cases the best solution is a hybrid of both models i.e. a number of threads with an event loop in each one.
EDIT:
On modern Linux systems, the /proc/sys/kernel/threads-max file provides a system-wide limit for the number of threads. The root user can change that value if they wish to:
echo 100000 > /proc/sys/kernel/threads-max
As far as I know, the kernel does not specifically impose a per-process limit on the number of threads.
sysconf() can be used to query system limits. There are some semi-documented thread-related query variables defined in /usr/include/bits/confname.h (the _SC_THREAD* variables).
getrlimit() can be used to query per-session limits - in this case the RLIMIT_NPROC resource is related to threads.
The threading implementation in glibc may also impose its own limits on a per-process basis.
Keep in mind that, depending on your hardware and software configuration, none of these limits may be of use. On Linux a main limiting factor on the number of threads comes from the fact that each thread requires memory in the stack - if you start launching threads you can easily come upon this limit before any others.
If you really want to find the actual limit, then the only way is to start launching threads until you cannot do so any more. Even that will only give you a rough limit that is only valid at the time you run the program. It can easily change if e.g. your threads start doing actual work and increase their resource usage.
In my opinion if you are launching more than 3-4 threads per processor you should reconsider your design.

On Linux, you can find the total number of threads running by checking /proc/loadavg
# cat /proc/loadavg
0.02 0.03 0.04 1/389 7017
In the above, 389 is the total number of threads.

it can handel as many threads as provided by OS and you never know the limit.
But as a general measures if a normal LOB application having more than 25 threads at a time can lead to problems and have serious design issue.

The current upper global limit is 4 million threads, because once reached, you have run out of PIDs (see futex.h).

Related

Thrift maximum possible of threads

I'm using a TThreadPoolServer with a ThreadManager along with the PosixThreadFactory.
I set the number of workers to 100 which allows 100 simultaneous connections if my understanding is good.
I was wondering how far can I set the number of threads. So I tried to progressively increment the number and the max I could reach before my stress tests crash was 160.
My question is this: what are the parameters to take into account to correctly set the number of threads?
Second question: is there a solution to handle more than this number (kind of clustering maybe?)
What are the parameters to take into account to correctly set the number of threads?
The maximum number of threads is not so much depending on a particular libary or product, it is more depending on how the threads are used. Just a few points to consider, without even attempting to provide an exhaustive list:
Each thread eats some resources by the pure fact of its existence. What the per-thread impact is in concrete, depends highly on the underlying OS and whether we talk about real OS threads, or things like goroutines.
Unless a thread is waiting for some event, it uses the CPU, RAM and I/O bandwith. What the impact is exactly, depends on the workload these threads are actually supposed to handle. Is the system as a whole primarily CPU bound, I/O bound or maybe bound to another shared resource?
Sharing resources across threads may lead to effects like lock contention, which have the potential to slow down the whole system the more concurrent accesses they have to handle. Again this depends on the nature of work and the architecture of the system.
Second question: is there a solution to handle more than this number (kind of clustering maybe?
Now that's a reeeeaaaalllly broad question on its own.

How is processor speed distributed across threads?

Objective:
I am trying to estimate how fast my code will execute when run concurrently in multiple threads.
Question 1)
If I know exactly how fast my code runs for a single request in one thread is their any way of estimating how fast it will run amongst multiple threads?
Question 2)
What impact, if any, does the presence of other threads effect the execution speed of each other thread?
My Situation:
I traverse a graph in memory of worst case size 1 million nodes. It's simply accessing 1 million memory addresses 1 at a time. Takes Half a second on 1 thread and I was worried how this will scale with multiple users performing the same query. Every user requests is handled by a separate thread so 100 simultaneous users will require 100 simultaneous threads. Each thread is sharing the same resource but read only. No writing. Is there any chance I could get each user to see roughly the same execution time?
Note: I know it will depend upon a number of factors but surely there must be some way of identifying whether or not your code will scale if you find it takes x amount of time for a single thread given x hardware. As final note I'd like to add I have limited experience with computer hardware architecture and how multi-threading works under the hood.
These are all interesting questions, but there is, unfortunately, no straightforward answer, because the answer will depend on a lot of different factors.
Most modern machines are multi-core: in an ideal situation, a four-thread process has the ability to scale up almost linearly in a four-core machine (i.e. run four times as fast).
Most programs, though, spend most of their time waiting for things: disk or database access, the memory bus, network I/O, user input, and other resources. Faster machines don't generally make these things appreciably faster.
The way that most modern operating systems, including Windows, Unix/Linux, and MacOS, use the processor is by scheduling processor time to processes and threads in a more-or-less round-robin manner: at any given time there may be threads that are waiting for processor time (this is a bit simplistic, as they all have some notions of process prioritization, so that high-criticality processes get pushed up the queue earlier than less important ones).
When a thread is using a processor core, it gets it all for as long as its time slice lasts: indeed, only one thing at a time is actually running on a single core. When the process uses up its time slice, or requests some resource that isn't immediately available, it its turn at the processor core is ended, and the next scheduled task will begin. This tends to make pretty optimal use of the processor resources.
So what are the factors that determine how well a process will scale up?
What portion of its run time does a single process spend waiting for
I/O and user input?
Do multiple threads hit the same resources, or different ones?
How much communication has to happen between threads? Between individual threads and your processes main thread? This takes synchronization, and introduces waiting.
How "tight" are the hotspots of the active thread? Can the body of it fit into the processor's memory, or does the (much slower) bus memory have to be accessed?
As a general rule, the more independent individual threads are of one another, the more linearly your application will scale. In real-world business applications, though, that is far from the case. The best way to increase the scaling ability of your process is to understand it--and its dependencies--well, and then use a profiler to find out where the most waiting occurs, and see if you can devise technical strategies to obviate them.
If I know exactly how fast my code runs for a single request in one thread is their any way of estimating how fast it will run amongst multiple threads?
No, you should determine it empirically.
What impact, if any, does the presence of other threads effect the execution speed of each other thread?
Computation-bound tasks will likely scale very well and be mostly independent of other threads. Interestingly enough, some CPU manufacturers implement features which can increase the clock of a lone-busy CPU core to compensate for the all the idle cores. This sort of feature might confound your measurements and expectations about scaling.
Cache/Memory/disk-bound tasks will start to contend with each other except for where resource partitions exist.
I know it will depend upon a number of factors
Absolutely! So I recommend that you prototype it and measure it. And then find out why it didn't scale as well as you'd hoped and try a different algorithm. Iterate.
but surely there must be some way of identifying whether or not your code will scale
Yes, but unfortunately it requires a detailed description of the algorithm implemented by the code. Your results will be heavily dependent on the ratio of your code's activity among these general regions, and your target's capability for these:
disk I/O
network I/O
memory I/O
computation
My Situation: My application runs in an app server that assigns one thread for every user request. If my application executes in 2 seconds for 1 user I can't assume it will be always take 2 seconds if say 100 users are simultaneously running the same operation correct?
If your app server computes pi to 100 digits for each user request, it will likely scale reasonably well until you encounter the core limit of your target.
If your app server does database queries for each user request, it will likely scale only as well as the target hardware can sustain the necessary load.
EDIT given specifics:
I traverse a graph in memory of worst case size 1 million nodes. It's simply accessing 1 million memory addresses 1 at a time.
Your problem sounds memory+cache-bound. You should study the details of your target CPU/mem deployment or if you are designing it, opt for high memory throughput.
A NUMA system ("resource partitioning" for memory) can likely maximize your overall concurrent memory throughput. Note that since your problem seems to dictate concurrent access to the same memory pages, a NUMA system would penalize the process doing remote memory accesses. In this case, consider creating multiple copies of the data at initialization time.
Depending on the pattern of traversal, TLB pressure might be a factor. Consider experimenting with huge (aka "large") pages.
Cache contention may be a factor in scaling as well.
Your specific algorithm could easily end up dominating over any of the specific system effects, depending on how far apart the best and worst cases are.
limited experience with computer hardware architecture and how multi-threading works under the hood.
Profile the query using CPU performance counters with a tool like Intel's VTune, perf, or oprofile. It can tell you where expensive operations are executing in your code. With this information you can optimize your query to perform well (individually and in aggregate).

Selecting number of threads in a multiprocess multiprocessor environment

I went through a few questions such as POSIX Threads on a Multiprocessor System and Concurrency of posix threads in multiprocessor machine and Threads & Processes Vs MultiThreading & Multi-Core/MultiProcessor : How they are mapped?
Based on these and few other Wiki articles , I believe for a system having three basic works viz, Input , Processing and Output
For a CPU - bound processing number of CPU -intensive threads (No. of Application * Thread per application) should be apprx 1 to 1.5 times the number of cores of processor.
Input and Output threads must be sufficiently large, so as to remove any bottlenecks. For example for a communication system which is based on query/query-ack and response/response - ack model, time must not be wasted in I/O waiting states.
If there is a large requirement for dynamic memory, its better to go with greater number of processes than threads (to avoid memory sync ups).
Are these arguments fairly consistent while determining number of threads to have in our application ? Do we need to look into any other paramters??
'1 to 1.5 times the number of cores' - this appears to be OS/langauge dependent. On Windows/C++, for example, with large numbers of CPU-intensive tasks, the optimum seems to be much more than twice the number of cores with the performance spread very small. If such environments, it seems you may as well just allocate 64 threads on a pool and not bother with the number of cores.
'query/query-ack and response/response - ack model, time must not be wasted in I/O waiting states' - this is unavoidable with such protocols with the high latency of most networks. The delay is enforced by the 'ping-pong' protocol & so there will, inevitably be an I/O wait. Async I/O just moves this wait into the kernel - it's still there!
'large requirement for dynamic memory, its better to go with greater number of processes than threads' - not really. 'large requirement for dynamic memory' usually means that large data buffers are going to be moved about. Large buffers can only be efficiently moved around by reference. This is very easy and quick between threads because of the shared memory space. With processes, you are stuck with awkward and slow inter-process comms.
'Determining number of threads to have in our application' - well, so difficult on several fronts. Given an unknown architecture, design. language and OS, the only advice I have is to try and make everything as flexible and configurable as you reasonably can. If you have a thread pool, make its size a run-time parameter you can tweak. If you have an object pool, try to design it so that you can change its depth. Have some default values that work on your test boxes and then, at installation or while running, you can make any specific changes and tweaks for a particular system.
The other thing with flexible/configurable designs is that you can, at test time, tweak away and fix many of the incorrect decisions, assumptions and guesstimates made by architects, designers, developers and, most of all, customers

Dual-Core Hyperthreading: Should I use 4 threads or 3 or 2?

If you're spawning multiple threads (or processes) concurrently, is it better to spawn as many as the number of physical processors or the number of logical processors, assuming the task is CPU-bound? Or is it better to do something in between (say, 3 threads)?
Does the performance depend on the kind of instructions that are getting executed (say, would non-local memory access be much different from cache hits)? If so, in which cases is it better to take advantage of hyperthreading?
Update:
The reason I'm asking is, I remember reading somewhere that if you have as many tasks as the number of virtual processors, tasks on the same physical core can sometimes starve some CPU resources and prevent each other from getting as many resources as needed, possibly decreasing performance. That's why I'm wondering if having as many threads as virtual cores is a good idea.
The performance depends on a huge variety of factors. Most tasks are not strictly CPU bound, since even if all of the data is in memory it is usually not on-board in the processor cache. I have seen examples (like this one) where memory access patterns can dramatically change the performance profile of a given 'parallel' process.
In short, there is no perfect number for all situations.
Chances are pretty good that you will see a performance improvement running 2 threads per core with HyperThreading enabled. Jobs that appear to be entirely CPU bound usually aren't, and HyperThreading can extract a few "extra" cycles out of the occasional interrupt or context switch.
On the other hand, with a core iX processor that has Turbo Boost, you might actually do better running 1 thread per core to encourage the CPU to overclock itself.
At work, we routinely run many-core servers at full CPU doing various kinds of calculation for days at a time. A while back we measured the performance difference with and without HT. We found that on average, with HyperThreading, and running twice as many jobs at once, we could complete the same amount of jobs about 10% faster than than without HyperThreading.
Assume that 2 × cores is a good place to start, but the bottom line is: measure!
I remember info that hyperthreading can give you up to 30% of performance boost. in general you'd better to treat them as 4 different cores. of course in some specific circumstances (e.g. having the same long running task bound to each core) you can divide your processing better taking into account that some cores are just logical ones
more info about hyperthreading itself here
Using Hyperthreading to run two threads on the same core, when both threads have similar memory access patterns but access disjoint data structures, would be very roughly equivalent to running them on two separate cores each with half the cache. If the memory-access patterns are such that half the cache would be sufficient to prevent thrashing, performance may be good. If the memory-access patterns are such that halving the cache induces thrashing, there may be a ten-fold performance hit (implying one would have been much better off without hyperthreading).
On the other hand, there are some situations where hyperthreading may be a huge win. If many threads will all be reading and writing the same shared data using lock-free data structures, and all threads must see a consistent view of the data, trying to run threads on disjoint processor may cause thrashing since only one processor at a time may have read-write access to any given cache line; running such a threads on two cores may take longer than running only one at a time. Such cache arbitration is not required, however, when a piece of data is accessed by multiple threads on a single core. In those cases, hyperthreading can be a huge win.
Unfortunately, I don't know any way to give the scheduler any "hints" to suggest that some threads should share a core when possible, while others should run separately when possible.
HT allows a boost of approximately 10-30% for mostly cpu-bound tasks that use the extra virtual cores. Although these tasks may seem CPU-bound, unless they are custom made assembly, they will usually suffer from IO waits between RAM and local cache. This allows one thread running on a physical HT-enabled core to work while the other thread is waiting for IO. This does come with a disadvantage though, as two threads share the same cache/bus, which will result in less resources each which may cause both threads to pause while waiting for IO.
In the last case, running a single thread will decrease the maximum simultaneous theoretical processing power(by 10-30%) in favor of running a single thread without the slowdown of cache thrashing which may be very significant in some applications.
Choosing which cores to use is just as important as choosing how many threads to run. If each thread is CPU-bound for roughly the same duration it is best to set the affinity such that threads using mostly different resources find themselves on different physical cores and threads using common resources be grouped to the same physical cores(different virtual core) so that common resources can be used from the same cache without extra IO wait.
Since each program has different CPU-usage characteristics and cache thrashing may or may not be a major slowdown(it usually is) it is impossible to determine what the ideal number of threads should be without profiling first. One last thing to note is that the OS/Kernel will also require some CPU and cache space. It is usually ideal to keep a single (physical)core set aside for the OS if real-time latency is required on CPU-bound threads so as to avoid sharing cache/cpu resources. If threads are often waiting for IO and cache thrashing is not an issue, or if running a real-time OS specifically designed for the application, you can skip this last step.
http://en.wikipedia.org/wiki/Thrashing_(computer_science)
http://en.wikipedia.org/wiki/Processor_affinity
All of the other answers already give lots of excellent info. But, one more point to consider is that the SIMD unit is shared between logical cores on the same die. So, if you are running threads with SSE code, do you run them on all 4 logical cores, or just spawn 2 threads (assuming you have two chips)? For this odd case, best to profile with your app.

How many simultaneous threads in an application is a lot?

5, 100, 1000?
I guess, "it depends", but on what?
What is common in applications that run as server daemons / services?
What are hard limits?
Given that the machine can handle the overall workload, how do I determine at how many threads the overhead starts to have an impact on performance?
What are important differences between OS's?
What else should be considered?
I'm asking because I would like to employ threads in an application to organize subcomponents of my application that do not share data and are designed to do their work in parallel. As the application would also use thread pools for parallelizing some tasks, I was wondering at what point I should start to think about the number of threads that's going to run in total.
I know the n+1 rule as a guideline for determining the number of threads that simultaneously work on the same task to gain performance. However, I want to use threads like one might use processes in a larger scope, i. e. to organize independent tasks that should not interfere with each other.
In this related question, some people advise to minimise the number of threads because of the added complexity. To me it seems that threads can also help to keep things sorted more orderly and actually reduce interference. Isn't that correct?
I can't answer your question about "how much is many" but I agree that you should not use threads for every task possible.
The optimal amount of threads for performance of application is (n+1), where n is the amount of processors/cores your computer/claster has.
The more your actual thread amount differs from n+1, the less optimal it gets and gets your system resources wasted on thread calculations.
So usually you use 1 thread for the UI, 1 thread for some generic tasks, and (n+1) threads for some huge-calculation tasks.
Actually Ajmastrean is a little out of date. Quoting from his own link
The thread pool has a default size of
250 worker threads per available
processor, and 1000 I/O completion
threads. The number of threads in the
thread pool can be changed by using
the SetMaxThreads method.
But generally I think 25 is really where the law of diminishing returns (and programmers abilities to keep track of what is going on) starts coming into effect. Although Max is right, as long as all of the threads are performing non-blocking calculations n+1 is the optimal number, in the real world most of the threading tasks I perform tend to be done on stuff with some kind of IO.
Also depends on your architecture. E.g. in NVIDIA GPGPU lib CUDA you can put on an 8 thread multiprocessor 512 threads simoultanously. You may ask why assign each of the scalar processors 64 threads? The answer is easy: If the computation is not compute bound but memory IO bound, you can hide the mem latencies by executing other threads. Similar applies to normal CPUs. I can remember that a recommendation for the parallel option for make "-j" is to use approx 1.5 times the number of cores you got. Many of the compiling tasks are heavy IO burden and if a task has to wait for harddisk, mem ... whatever, CPU could work on a different thread.
Next you have to consider, how expensive a task/thread switch is. E.g. it is comes free, while CPU has to perform some work for a context switch. So in general you have to estimate if the penalty for two task switches is longer than the time the thread would block (which depends heavily on your applications).
Microsoft's ThreadPool class limits you to 25 threads per processor. The limit is based on context switching between threads and the memory consumed by each thread. So, that's a good guideline if you're on the Windows platform.

Resources