I've been going through this tutorial on parallel pipelines and noticed that, while there is definitely a considerable difference in throughput, couldn't it be even better if the compression stage also took on a read job since it's just waiting around anyway? The same thing goes for the write stage... I mean, why not take on a third compression and then switch over to writing two, and then have one of those cores go back to compressing while the other wraps up the third write, and so on?
I apologize if this is obvious. I imagine this is standard practice and is called something, I'm just not sure what. Is their any overhead involved with switching jobs like this?
And I know this might be the wrong forum for this last question, but can the GPU switch jobs like this or should the programmable shaders/CUDA cores pretty much be left alone after being programmed?
EDIT: I guess I also don't understand how taking the same six-cores used in the 2 cores/stage example would be faster than just giving each of the six cores all three stages. Sure, there would be two cores that would do two, but that's still faster than the top scenario. I would understand it better in the GPU's case since there is specialized hardware involved for certain computations, but generally speaking, I don't see it. Maybe this example is weak or something because I know the parallel processing is here to stay.
This is definitely an issue with pipelining and there are a number of different ways to try and mitigate it.
With specialized hardware the hardware will often be tuned to try and balance the time taken in each stage for typical workloads. Fixed function stages in GPUs for example are typically balanced around the needs of a sample of representative game rendering workloads with transistors being allocated to try and balance the time taken in each stage. With static balancing like this there will usually be some wasted performance still however.
An alternative approach that can be used in both software and hardware to balance a pipeline is to break the longer stages down into multiple shorter steps. This is a common strategy in CPU instruction pipelines but can also be useful in software. In your example, the longer running compression step could potentially be broken down into multiple shorter pipeline stages. Depending on the task this may be difficult or impossible to do efficiently however.
Task scheduling systems can be used to help balance workloads across CPUs in a software pipeline. In a task scheduling system, you have a number of worker threads (usually around one per hardware thread) and any task can run on any worker thread. You have an API to set up dependencies between tasks and the task scheduler is responsible for scheduling tasks to run wherever CPU time is available once their dependencies are satisfied. In your example, the cores with idle time running the Read and Write tasks could help out with Compress tasks rather than sitting idle as long as the Compress tasks had their Read task dependencies satisfied.
Traditional OS thread schedulers can give some of the same benefits of a task scheduling system. In your example, if the Read threads waited on a semaphore when their work queues were empty (to be signalled when new work was added to the queues), the OS could schedule Compress threads to run on those idle cores. This can work reasonably well for relatively long running pipeline stages (10s of milliseconds) but for shorter pipeline stages (sub 1ms) the overhead of the OS thread scheduling and the length of the thread time slice will likely mean a task scheduling system would give better performance.
Your points are valid. The tutorial is lacking.
If the read, compress, and write operations can all occur at once, independently, the simple non-pipelined case would be the fastest for the six cores. Also notice that in the six core diagram, the reads and writes never overlap, so they could be the same ones. You only need four cores.
But consider a case where the reads all access the same disk so issuing too many read operations in parallel makes the reads take longer because they interfere with each other. In this case you can gain by pipelining the reads since you start the first compress steps sooner and they limit
the overall performance.
Related
I have 12 tasks to run on an octo-core machine. All tasks are CPU intensive and each will max out a core.
Is there a theoretical reason to avoid stacking tasks on a maxed out core (such as overhead, swapping across tasks) or is it faster to queue everything?
Task switching is a waste of CPU time. Avoid it if you can.
Whatever the scheduler timeslice is set to, the CPU will waste its time every time slice by going into the kernel, saving all the registers, swapping the memory mappings and starting the next task. Then it has to load in all its CPU cache, etc.
Much more efficient to just run one task at a time.
Things are different of course if the tasks use I/O and aren't purely compute bound.
Yes it's called queueing theory https://en.wikipedia.org/wiki/Queueing_theory. There are many different models https://en.wikipedia.org/wiki/Category:Queueing_theory for a range of different problems I'd suggest you scan them and pick the one most applicable to your workload then go and read up on how to avoid the worst outcomes for that model, or pick a different, better, model for dispatching your workload.
Although the graph at this link https://commons.wikimedia.org/wiki/File:StochasticQueueingQueueLength.png applies to Traffic it will give you an idea of what is happening to response times as your CPU utilisation increases. It shows that you'll reach an inflection point after which things get slower and slower.
More work is arriving than can be processed with subsequent work waiting longer and longer until it can be dispatched.
The more cores you have the further to the right you push the inflection point but the faster things go bad after you reach it.
I would also note that unless you've got some really serious cooling in place you are going to cook your CPU. Depending on it's design it will either slow itself down, making your problem worse, or you'll trigger it's thermal overload protection.
So a simplistic design for 8 cores would be, 1 thread to manage things and add tasks to the work queue and 7 threads that are pulling tasks from the work queue. If the tasks need to be performed within a certain time you can add a TimeToLive value so that they can be discarded rather than executed needlessly. As you are almost certainly running your application in an OS that uses a pre-emptive threading model consider things like using processor affinity where possible because as #Zan-Lynx says task/context switching hurts. Be careful not to try to build your OS'es thread management again as you'll probably wind up in conflict with it.
tl;dr: cache thrash is Bad
You have a dozen tasks. Each will have to do a certain amount of work.
At an app level they each processed a thousand customer records or whatever. That is fixed, it is a constant no matter what happens on the hardware.
At the the language level, again it is fixed, C++, java, or python will execute a fixed number of app instructions or bytecodes. We'll gloss over gc overhead here, and page fault and scheduling details.
At the assembly level, again it is fixed, some number of x86 instructions will execute as the app continues to issue new instructions.
But you don't care about how many instructions, you only care about how long it takes to execute those instructions. Many of the instructions are reads which MOV a value from RAM to a register. Think about how long that will take. Your computer has several components to implement the memory hierarchy - which ones will be involved? Will that read hit in L1 cache? In L2? Will it be a miss in last-level cache so you wait (for tens or hundreds of cycles) until RAM delivers that cache line? Did the virtual memory reference miss in RAM, so you wait (for milliseconds) until SSD or Winchester storage can page in the needed frame? You think of your app as issuing N reads, but you might more productively think of it as issuing 0.2 * N cache misses. Running at a different multi-programming level, where you issue 0.3 * N cache misses, could make elapsed time quite noticeably longer.
Every workload is different, and can place larger or smaller demands on memory storage. But every level of the memory hierarchy depends on caching to some extent, and higher multi-programming levels are guaranteed to impact cache hit rates. There are network- and I/O-heavy workloads where very high multi-programming levels absolutely make sense. But for CPU- and memory-intensive workloads, when you benchmark elapsed times you may find that less is more.
I'm new to Elixir, and I'm starting to read through Dave Thomas's excellent Programming Elixir. I was curious how far I could take the concurrency of the "pmap" function, so I iteratively boosted the number of items to square from 1,000 to 10,000,000. Out of curiosity, I watched the output of htop as I did so, usually peaking out with CPU usage similar to that shown below:
After showing the example in the book, Dave says:
And, yes, I just kicked off 1,000 background processes, and I used all the cores and processors on my machine.
My question is, how come on my machine only cores 1, 3, 5, and 7 are lighting up? My guess would be that it has to do with my iex process being only a single OS-level process and OSX is managing the reach of that process. Is that what's going on here? Is there some way to ensure all cores get utilized for performance-intensive tasks?
Great comment by #Thiago Silveira about first line of iex's output. The part [smp:8:8] says how many operating system level processes is Erlang using. You can control this with flag --smp if you want to disable it:
iex --erl '-smp disable'
This will ensure that you have only one system process. You can achieve similar result by leaving symmetric multiprocessing enabled, but setting directly NumberOfShcedulers:NumberOfSchedulersOnline.
iex --erl '+S 1:1'
Each operating system process needs to have its own scheduler for Erlang processes, so you can easily see how many of them do you have currently:
:erlang.system_info(:schedulers_online)
To answer your question about performance. If your processors are not working at full capacity (100%) and non of them is doing nothing (0%) then it is probable that making the load more evenly distributed will not speed things up. Why?
The CPU usage is measured by probing the processor state at many points in time. This states are either "working" or "idle". 82% CPU usage means that you can perform couple of more tasks on this CPU without slowing other tasks.
Erlang schedulers try to be smart and not migrate Erlang processes between cores unless they have to because it requires copying. The migration occurs for example when one of schedulers is idle. It can then borrow a process from others scheduler run queue.
Next thing that may cause such a big discrepancy between odd and even cores is Hyper Threading. On my dual core processor htop shows 4 logical cores. In your case you probably have 4 physical cores and 8 logical because of HT. It might be the case that you are utilizing your physical cores with 100%.
Another thing: pmap needs to calculate result in separate process, but at the end it sends it to the caller which may be a bottleneck. The more you send messages the less CPU utilization you can achieve. You can try for fun giving the processes a task that is really CPU intensive like calculating Ackerman function. You can even calculate how much of your job is the sequential part and how much is parallel using Amdahl's law and measuring execution times for different number of cores.
To sum up: the CPU utilization from screenshot looks really great! You don't have to change anything for more performance-intensive tasks.
Concurrency is not Parallelism
In order to get good parallel performance out of Elixir/BEAM coding you need to have some understanding of how the BEAM scheduler works.
This is a very simplistic model, but the BEAM scheduler gives each process 2000 reductions before it swaps out the process for the next process. Reductions can be thought of as function calls. By default a process runs on the core/scheduler that spawned it. Processes only get moved between schedulers if the queue of outstanding processes builds up on a given scheduler. By default the BEAM runs a scheduling thread on each available core.
What this implies is that in order to get the most use of the processors you need to break up your tasks into large enough pieces of work that will exceed the standard "reduction" slice of work. In general, pmap style parallelism only gives significant speedup when you chunk many items into a single task.
The other thing to be aware of is that some parts of the BEAM use a spin/wait loop when awaiting work and that can skew usage when you use
a tool like htop to examine CPU usage. You'll get a much better understanding of your program's performance by using :observer.
I have a CSV file with over 1 million rows. I also have a database that contains such data in a formatted way.
I want to check and verify the data in the CSV file and the data in the database.
Is it beneficial/reduces time to thread reading from the CSV file and use a connection pool to the database?
How well does Ruby handle threading?
I am using MongoDB, also.
It's hard to say without knowing some more details about the specifics of what you want the app to feel like when someone initiates this comparison. So, to answer, some general advice that should apply fairly well regardless of the problem you might want to thread.
Threading does NOT make something computationally less costly
Threading doesn't make things less costly in terms of computation time. It just lets two things happen in parallel. So, beware that you're not falling into the common misconception that, "Threading makes my app faster because the user doesn't wait for things." - this isn't true, and threading actually adds quite a bit of complexity.
So, if you kick off this DB vs. CSV comparison task, threading isn't going to make that comparison take any less time. What it might do is allow you to tell the user, "Ok, I'm going to check that for you," right away, while doing the comparison in a separate thread of execution. You still have to figure out how to get back to the user when the comparison is done.
Think about WHY you want to thread, rather than simply approaching it as whether threading is a good solution for long tasks
Like I said above, threading doesn't make things faster. At best, it uses computing resources in a way that is either more efficient, or gives a better user experience, or both.
If the user of the app (maybe it's just you) doesn't mind waiting for the comparison to run, then don't add threading because you're just going to add complexity and it won't be any faster. If this comparison takes a long time and you'd rather "do it in the background" then threading might be an answer for you. Just be aware that if you do this you're then adding another concern, which is, how do you update the user when the background job is done?
Threading involves extra overhead and app complexity, which you will then have to manage within your app - tread lightly
There are other concerns as well, such as, how do I schedule that worker thread to make sure it doesn't hog the computing resources? Are the setting of thread priorities an option in my environment, and if so, how will adjusting them affect the use of computing resources?
Threading and the extra overhead involved will almost definitely make your comparison take LONGER (in terms of absolute time it takes to do the comparison). The real advantage is if you don't care about completion time (the time between when the comparison starts and when it is done) but instead the responsiveness of the app to the user, and/or the total throughput that can be achieved (e.g. the number of simultaneous comparisons you can be running, and as a result the total number of comparisons you can complete within a given time span).
Threading doesn't guarantee that your available CPU cores are used efficiently
See Green Threads vs. native threads - some languages (depending on their threading implementation) can schedule threads across CPUs.
Threading doesn't necessarily mean your threads wind up getting run in multiple physical CPU cores - in fact in many cases they definitely won't. If all your app's threads run on the same physical core, then they aren't truly running in parallel - they are just splitting CPU time in a way that may make them look like they are running in parallel.
For these reasons, depending on the structure of your app, it's often less complicated to send background tasks to a separate worker process (process, not thread), which can easily be scheduled onto available CPU cores at the OS level. Separate processes (as opposed to separate threads) also remove a lot of the scheduling concerns within your app, because you essentially offload the decision about how to schedule things onto the OS itself.
This last point is pretty important. OS schedulers are extremely likely to be smarter and more efficiently designed than whatever algorithm you might come up with in your app.
I want to run a batch say 20 CPU intensive comps (basically really long nested for loop) on a machine.
Each of these 20 jobs doesn't share data with the other 19.
If the machine has N cores, should I spin off N-1 of these jobs then? Or N? Or should I just launch all 20, and have Windows figure out how to schedule them?
Unfortunately, there is no simple answer. The only way to know for sure is to implement and then profile your application.
Typically, for maximum throughput, if the jobs are pure CPU, you'd want one per core. Depending on the type of work, this would include one per hyperthread code or just one per "true physical core". (If the work is identical for all 20 jobs, then hyperthreading often slows down the overall work...)
If the jobs have any non-CPU functionaltiy (such as reading a file, waiting on anything, etc), then >1 work item per core tends to be much better. For many situations, this will improve.
Generally, if you aren't sharing data, not blocking on IO, and using lots of CPU and nothing else is running on the box (and probably a few more caveats) using all the CPU's (e.g. N threads) is probably the best idea.
The best choice is probably to make it configurable and profile it and see what happens.
You should use a thread pool of some sort, so it's (reasonably) easy to tune the number of threads without affecting the structure of the program.
Once you've done that, it's a fairly simple matter of testing to find a reasonably optimal number of threads relative to the number of processors available. Chances are that even when/if they look like this should be purely CPU bound, you'll get better efficiency with the number of threads >N, but about the only way to be sure is to test.
Imagine I have two (three, four, whatever) tasks that have to run in parallel. Now, the easy way to do this would be to create separate threads and forget about it. But on a plain old single-core CPU that would mean a lot of context switching - and we all know that context switching is big, bad, slow, and generally simply Evil. It should be avoided, right?
On that note, if I'm writing the software from ground up anyway, I could go the extra mile and implement my own task-switching. Split each task in parts, save the state inbetween, and then switch among them within a single thread. Or, if I detect that there are multiple CPU cores, I could just give each task to a separate thread and all would be well.
The second solution does have the advantage of adapting to the number of available CPU cores, but will the manual task-switch really be faster than the one in the OS core? Especially if I'm trying to make the whole thing generic with a TaskManager and an ITask, etc?
Clarification: I'm a Windows developer so I'm primarily interested in the answer for this OS, but it would be most interesting to find out about other OSes as well. When you write your answer, please state for which OS it is.
More clarification: OK, so this isn't in the context of a particular application. It's really a general question, the result on my musings about scalability. If I want my application to scale and effectively utilize future CPUs (and even different CPUs of today) I must make it multithreaded. But how many threads? If I make a constant number of threads, then the program will perform suboptimally on all CPUs which do not have the same number of cores.
Ideally the number of threads would be determined at runtime, but few are the tasks that can truly be split into arbitrary number of parts at runtime. Many tasks however can be split in a pretty large constant number of threads at design time. So, for instance, if my program could spawn 32 threads, it would already utilize all cores of up to 32-core CPUs, which is pretty far in the future yet (I think). But on a simple single-core or dual-core CPU it would mean a LOT of context switching, which would slow things down.
Thus my idea about manual task switching. This way one could make 32 "virtual" threads which would be mapped to as many real threads as is optimal, and the "context switching" would be done manually. The question just is - would the overhead of my manual "context switching" be less than that of OS context switching?
Naturally, all this applies to processes which are CPU-bound, like games. For your run-of-the-mill CRUD application this has little value. Such an application is best made with one thread (at most two).
I don't see how a manual task switch could be faster since the OS kernel is still switching other processes, including yours in out of the running state too. Seems like a premature optimization and a potentially huge waste of effort.
If the system isn't doing anything else, chances are you won't have a huge number of context switches anyway. The thread will use its timeslice, the kernel scheduler will see that nothing else needs to run and switch right back to your thread. Also the OS will make a best effort to keep from moving threads between CPUs so you benefit there with caching.
If you are really CPU bound, detect the number of CPUs and start that many threads. You should see nearly 100% CPU utilization. If not, you aren't completely CPU bound and maybe the answer is to start N + X threads. For very IO bound processes, you would be starting a (large) multiple of the CPU count (i.e. high traffic webservers run 1000+ threads).
Finally, for reference, both Windows and Linux schedulers wake up every millisecond to check if another process needs to run. So, even on an idle system you will see 1000+ context switches per second. On heavily loaded systems, I have seen over 10,000 per second per CPU without any significant issues.
The only advantage of manual switch that I can see is that you have better control of where and when the switch happens. The ideal place is of course after a unit of work has been completed so that you can trash it all together. This saves you a cache miss.
I advise not to spend your effort on this.
Single-core Windows machines are going to become extinct in the next few years, so I generally write new code with the assumption that multi-core is the common case. I'd say go with OS thread management, which will automatically take care of whatever concurrency the hardware provides, now and in the future.
I don't know what your application does, but unless you have multiple compute-bound tasks, I doubt that context switches are a significant bottleneck in most applications. If your tasks block on I/O, then you are not going to get much benefit from trying to out-do the OS.