I'm learning about embedded Linux. I can't seem to find proper answers for my questions below.
My understanding is, when user-space applications are executing, if we want to perform IO for example, a system call is made which will cause a SW interrupt, generally causing the MCU to switch from non-privileged mode to privileged mode and the kernel will perform the IO on behalf of the application.
Similarity when a hardware interrupt occurs, I'm guessing this will cause the modes to switch again and execute an interrupt handler within the kernel.
What's not clear to me is, are these the only times when the kernel code gets control of the CPU?
With only one core for example, if user application code is running, shouldn't the kernel be getting control of the CPU from time to time to check things, regardless of whether an interrupt has occurred or not. Perhaps there is a periodic timer interrupt allowing this?
Also, if we have multiple cores, could the kernel just be running all the time on one core while user applications on another?
Read Operating Systems: Three Easy Pieces since an entire book is needed to answer your questions. Later, study the source code of the kernel, with the help of https://kernelnewbies.org/
Interrupts happen really often (perhaps hundreds, or even thousands, per second). Try cat /proc/interrupts (see proc(5)) a few times in a terminal.
the kernel will perform the IO on behalf of the application.
Not always immediately. If you read a file, its content could be in the page cache (and then no physical IO is needed). If disk access (or networking) is required, the kernel will schedule (read about preemptive scheduling) some IO to happen and context switch to other runnable tasks. Much later, several interrupts have been handled (some of which may be triggered by physical devices related to your IO), and finally (many milliseconds later) your process could return -in user space- from the read(2) system call and be running again. During that delay, other processes have been running.
Also, if we have multiple cores, could the kernel just be running all the time on one core while user applications on another?
It depends a lot (even on the kernel version). Probably the kernel is not running on the same core. YMMV.
What's not clear to me is, are these the only times when the kernel code gets control of the CPU?
Yes, kernel can not interrupt user code from running. But Kernel will setup up a timer hardware, which will generate timer interrupt between consistent time period. Kernel utilize it to implement task schedule.
Also, if we have multiple cores, could the kernel just be running all the time on one core while user applications on another?
You can consider multiple cores system as multiple machines but they share memory, and are able to send interrupt to each other.
Related
Some web searching results told me that the only deficiency of kernel-level thread is the slow speed of its management(create, switch, terminate, etc.). It seems that if the operation on the kernel-level thread is all through system calls, the answer to my question will be true. However, I've searched a lot to find whether the management of kernel-level thread is all through system call but find nothing. And I always have an instinct that such management should be done by the OS automatically because only OS knows which thread would be suitable to run at a specific time. So it seems impossible for programmers to write some explicit system calls to manage threads. I'm appreciative of any ideas.
Some web searching results told me that the only deficiency of kernel-level thread is the slow speed of its management(create, switch, terminate, etc.).
It's not that simple. To understand, think about what causes task switches. Here's a (partial) list:
a device told a device driver that an operation completed (some data arrived, etc) causing a thread that was waiting for the operation to unblock and then preempt the currently running thread. For this case you're running kernel code when you find out that a task switch is needed, so kernel task switching is faster.
enough time passed; either causing an "end of time slice" task switch, or causing a sleeping thread to unblock and preempt. For this case you're running kernel code when you find out that a task switch is needed, so kernel task switching is faster.
the thread accessed virtual memory that isn't currently accessible, triggering the kernel's page fault handler which finds out that the current task has to wait while the kernel fetches data from from swap space or from a file (if the virtual memory is part of a memory mapped file), or has to wait for kernel to free up RAM by sending other pages to swap space (if virtual memory was involved in some kind of "copy on write"); causing a task switch because the currently running task can't continue. For this case you're running kernel code when you find out that a task switch is needed, so kernel task switching is faster.
a new process is being created, and its initial thread preempts the currently running thread. For this case you're running kernel code when you find out that a task switch is needed, so kernel task switching is faster.
the currently running thread asked kernel to do something with a file and kernel got "VFS cache miss" that prevents the request from being performed without any task switches. For this case you're running kernel code when you find out that a task switch is needed, so kernel task switching is faster.
the currently running thread releases a mutex or sends some data (e.g. using a pipe or socket); causing a thread that belongs to a different process to unblock and preempt. For this case you're running kernel code when you find out that a task switch is needed, so kernel task switching is faster.
the currently running thread releases a mutex or sends some data (e.g. using a pipe or socket); causing a thread that belongs to the same process to unblock and preempt. For this case you're running user-space code when you find out that a task switch is needed, so in theory user-space task switching is faster, but in practice it can just as easily be an indicator of poor design (using too many threads and/or far too much lock contention).
a new thread is being created for the same process; and the new thread preempts the currently running thread. For this case you're running user-space code when you find out that a task switch is needed, so in user-space task switching is faster; but only if kernel isn't informed (e.g. so that utilities like "top" can properly display details for threads) - if kernel is informed anyway then it doesn't make much difference where the task switch happens.
For most software (which doesn't use very many threads); doing task switches in the kernel is faster. Of course it's also (hopefully) fairly irrelevant for performance (because time spent switching tasks should be tiny compared to time spend doing other work).
And I always have an instinct that such management should be done by the OS automatically because only OS knows which thread would be suitable to run at a specific time.
Yes; but possibly not for the reason you think.
Another problem with user-space threading (besides making most task switches slower) is that it can't support global thread priorities without becoming a severe security disaster. Specifically; a process can't know if its own thread is higher or lower priority than a thread belonging to a different process (unless it has information about all threads for the entire OS, which is information that normal processes shouldn't be trusted to have); so user-space threading leads to wasting CPU time doing unimportant work (for one process) when there's important work to do (for a different process).
Another problem with user-space threading is that (for some CPUs - e.g. most 80x86 CPUs) the CPUs are not independent, and there may be power management decisions involved with scheduling. For examples; most 80x86 CPUs have hyper-threading (where a core is shared by 2 logical processors), where a smart scheduler may say "one logical processor in the core is running a high priority/important thread, so the other logical processor in the same core should not run a low priority/unimportant thread because that would make the important work slower"; most 80x86 CPUs have "turbo boost" (with similar "don't let low priority threads ruin the turbo-boost/performance of high priority thread" possibilities); and most CPUs have thermal management (where scheduler might say "Hey, these threads are all low priority, so let's underclock the CPU so that it cools down and can go faster later (has more thermal headroom) when there's high priority/more important work to do!").
Would it makes the kernel level thread clearly preferable to user level thread if system calls is as fast as procedure calls?
If system calls were as fast as normal procedure calls, then the performance differences between user-space threading and kernel threading would disappear (but all the other problems with user-space threading would remain). However, the reason why system calls are slower than normal procedure calls is that they pass through a kind of "isolation barrier" (that isolates kernel's code and data from malicious user-space code); so to make system calls as fast as normal procedure calls you'd have to get rid of the isolation (effectively turning the kernel into a kind of "global shared library" that can be dynamically linked) but without that isolation you'll have an extreme security disaster. In other words; to have any hope of achieving acceptable security, system calls must be slower than normal procedure calls.
Your basic premise is wrong. System calls are much slower than procedure calls in almost every interesting architecture.
The perceived cpu throughput is based on pipelining, speculative execution and fetching. The syscall stops the pipeline, invalidates the speculative execution and halts the speculative fetching, is a store and instruction barrier, and may flush the write fifo.
So, the processor slows down to its ‘spec’ speed around the syscall, accelerating back up until the syscall return, whereupon it does about the exact same thing.
Attempts to optimise this area have given rise to lots of papers named after fictional James Bond organizations, and not conciliatory enough apologies from not embarrassed enough cpu product managers. Google spectre as an example, then follow the associated links.
The other cost of syscall
A bit over 30 years ago, some smart guys wrote a paper about least privilege. Conceptually, it is a stunner. The basic premise is that whatever your program is doing, it should do it with the least privilege possible.
If your program is inverting arrays, according to the notion of least privilege, it should not be able to disable interrupts. Disabling interrupts can cause a very difficult to diagnose system failure. Simple user code should not have this ability.
The notion of user and kernel modes of execution evolved from early computer systems, and (with the possible exception of the iax32 / 80286 ) are increasingly showing their inadequacy in the connected computer environment. At one point in time you could say "this is a single user system"; but the IoT dweebs have made everything multi-user.
Least privilege insists that all code should execute with the minimum privilege required to complete the task at hand. Thus, nothing should be in the kernel that absolutely doesn't need to be. If you think that is a radical thought, in Ken Thompson's 1977(?) paper on the UNIX kernel he states exactly the same thing.
So no, putting your junk in the kernel just means you have increased the attack surface for no valid reason. Try to think in terms of exposing minimum risk, it leads to better software and better sleep.
I read that Linux kernel is preemptive, which is different from most Unix kernels. So, what does it really mean for a kernal to be preemptive?
Some analogies or examples would be better than pure theoretical explanation.
ADD 1 -- 11:00 AM 12/7/2018
Preemptive is just one paradigm of multi-tasking. There are others like Cooperative Multi-tasking. A better understanding can be achieved by comparing them.
Prior to Linux kernel version 2.5.4, Linux Kernel was not preemptive which means a process running in kernel mode cannot be moved out of processor until it itself leaves the processor or it starts waiting for some input output operation to get complete.
Generally a process in user mode can enter into kernel mode using system calls. Previously when the kernel was non-preemptive, a lower priority process could priority invert a higher priority process by denying it access to the processor by repeatedly calling system calls and remaining in the kernel mode. Even if the lower priority process' timeslice expired, it would continue running until it completed its work in the kernel or voluntarily relinquished control. If the higher priority process waiting to run is a text editor in which the user is typing or an MP3 player ready to refill its audio buffer, the result is poor interactive performance. This way non-preemptive kernel was a major drawback at that time.
Imagine the simple view of preemptive multi-tasking. We have two user tasks, both of which are running all the time without using any I/O or performing kernel calls. Those two tasks don't have to do anything special to be able to run on a multi-tasking operating system. The kernel, typically based on a timer interrupt, simply decides that it's time for one task to pause to let another one run. The task in question is completely unaware that anything happened.
However, most tasks make occasional requests of the kernel via syscalls. When this happens, the same user context exists, but the CPU is running kernel code on behalf of that task.
Older Linux kernels would never allow preemption of a task while it was busy running kernel code. (Note that I/O operations always voluntarily re-schedule. I'm talking about a case where the kernel code has some CPU-intensive operation like sorting a list.)
If the system allows that task to be preempted while it is running kernel code, then we have what is called a "preemptive kernel." Such a system is immune to unpredictable delays that can be encountered during syscalls, so it might be better suited for embedded or real-time tasks.
For example, if on a particular CPU there are two tasks available, and one takes a syscall that takes 5ms to complete, and the other is an MP3 player application that needs to feed the audio pipe every 2ms, you might hear stuttering audio.
The argument against preemption is that all kernel code that might be called in task context must be able to survive preemption-- there's a lot of poor device driver code, for example, that might be better off if it's always able to complete an operation before allowing some other task to run on that processor. (With multi-processor systems the rule rather than the exception these days, all kernel code must be re-entrant, so that argument isn't as relevant today.) Additionally, if the same goal could be met by improving the syscalls with bad latency, perhaps preemption is unnecessary.
A compromise is CONFIG_PREEMPT_VOLUNTARY, which allows a task-switch at certain points inside the kernel, but not everywhere. If there are only a small number of places where kernel code might get bogged down, this is a cheap way of reducing latency while keeping the complexity manageable.
Traditional unix kernels had a single lock, which was held by a thread while kernel code was running. Therefore no other kernel code could interrupt that thread.
This made designing the kernel easier, since you knew that while one thread using kernel resources, no other thread was. Therefore the different threads cannot mess up each others work.
In single processor systems this doesn't cause too many problems.
However in multiprocessor systems, you could have a situation where several threads on different processors or cores all wanted to run kernel code at the same time. This means that depending on the type of workload, you could have lots of processors, but all of them spend most of their time waiting for each other.
In Linux 2.6, the kernel resources were divided up into much smaller units, protected by individual locks, and the kernel code was reviewed to make sure that locks were only held while the corresponding resources were in use. So now different processors only have to wait for each other if they want access to the same resource (for example hardware resource).
The preemption allows the kernel to give the IMPRESSION of parallelism: you've got only one processor (let's say a decade ago), but you feel like all your processes are running simulaneously. That's because the kernel preempts (ie, take the execution out of) the execution from one process to give it to the next one (maybe according to their priority).
EDIT Not preemptive kernels wait for processes to give back the hand (ie, during syscalls), so if your process computes a lot of data and doesn't call any kind of yield function, the other processes won't be able to execute to execute their calls. Such systems are said to be cooperative because they ask for the cooperation of the processes to ensure the equity of the execution time
EDIT 2 The main goal of preemption is to improve the reactivity of the system among multiple tasks, so that's good for end-users, whereas on the other-hand, servers want to achieve the highest througput, so they don't need it: (from the Linux kernel configuration)
Preemptible kernel (low-latency desktop)
Voluntary kernel preemption (desktop)
No forced preemption (server)
The linux kernel is monolithic and give a little computing timespan to all the running process sequentially. It means that the processes (eg. the programs) do not run concurrently, but they are given a give timespan regularly to execute their logic. The main problem is that some logic can take longer to terminate and prevent the kernel to allow time for the next process. This results in system "lags".
A preemtive kernel has the ability to switch context. It means that it can stop a "hanging" process even if it is not finished, and give the computing time to the next process as expected. The "hanging" process will continue to execute when its time has come without any problem.
Practically, it means that the kernel has the ability to achieve tasks in realtime, which is particularly interesting for audio recording and editing.
The ubuntu studio districution packages a preemptive kernel as well as a buch of quality free software devoted to audio and video edition.
It means that the operating system scheduler is free to suspend the execution of the running processes to give the CPU to another process whenever it wants; the normal way to do this is to give to each process that is waiting for the CPU a "quantum" of CPU time to run. After it has expired the scheduler takes back the control (and the running process cannot avoid this) to give another quantum to another process.
This method is often compared with the cooperative multitasking, in which processes keep the CPU for all the time they need, without being interrupted, and to let other applications run they have to call explicitly some kind of "yield" function; naturally, to avoid giving the feeling of the system being stuck, well-behaved applications will yield the CPU often. Still,if there's a bug in an application (e.g. an infinite loop without yield calls) the whole system will hang, since the CPU is completely kept by the faulty program.
Almost all recent desktop OSes use preemptive multitasking, that, even if it's more expensive in terms of resources, is in general more stable (it's more difficult for a sigle faulty app to hang the whole system, since the OS is always in control). On the other hand, when the resources are tight and the application are expected to be well-behaved, cooperative multitasking is used. Windows 3 was a cooperative multitasking OS; a more recent example can be RockBox, an opensource PMP firmware replacement.
I think everyone did a good job of explaining this but I'm just gonna add little more info. in context of Linux IRQ, interrupt and kernel scheduler.
Process scheduler is the component of the OS that is responsible for deciding if current running job/process should continue to run and if not which process should run next.
preemptive scheduler is a scheduler which allows to be interrupted and a running process then can change it's state and then let another process to run (since the current one was interrupted).
On the other hand, non-preemptive scheduler can't take away CPU away from a process (aka cooperative)
FYI, the name word "cooperative" can be confusing because the word's meaning does not clearly indicate what scheduler actually does.
For example, Older Windows like 3.1 had cooperative schedulers.
Full credit to wonderful article here
I think it became preemptive from 2.6. preemptive means when a new process is ready to run, the cpu will be allocated to the new process, it doesn't need the running process be co-operative and give up the cpu.
Linux kernel is preemptive means that The kernel supports preemption.
For example, there are two processes P1(higher priority) and P2(lower priority) which are doing read system calls and they are running in kernel mode. Suppose P2 is running and is in the kernel mode and P2 is scheduled to run.
If kernel preemption is available, then preemption can happen at the kernel level i.e P2 can get preempted and but to sleep and the P1 can continue to run.
If kernel preemption is not available, since P2 is in kernel mode, system simply waits till P2 is complete and then
This is hard to word/ask so please bear with me:
When we see the output of assembly, this is what is going to be executed on the core(s) of the CPU. However, if a CPU has multiple cores- is all of the assembly executed on the same core? At what point would the assembly from the same program begin executed on a different core?
So if I had (assembly pseudo):
ADD x, y, z
SUB p, x, q
how will I know whether ADD and SUB will execute on the same core? Is this linked to affinity? I thought affinity only pinned a process to a CPU, not a core?
I am asking this because I want to try and understand whether you can reasonably predict whether consecutive assembly instructions execute on the same core and whether I can control that they only execute on the same core. I am trying to understand how the decision is made to change executing the same program code from one core, to a different core?
If assembly can change execution (even when using affinity) from CPUA Core1 to Core2, is this where QPI link speed will take effect- and also whether the caches are shared amongst the different CPU cores?
This is a rough overview that hopefully will provide you with the details you need.
Assembly code is translated into machine code; ie binary data, that is run by a CPU.
A CPU is the same as a core on a multi-core processor; ie a CPU is not the same as a processor (chip).
Every CPU has an instruction pointer that points to the instruction to execute next. This is incremented for every instruction executed.
So in a multi-core processor you would have one instruction pointer per core. To support more processes than there are available CPUs (or cores), the operating system will interrupt running processes and store their state (including the instruction pointer) at regular intervals. It will then restore the state of already interrupted processes and let them execute for a bit.
What core the execution is continued on is up to the operating system to decide, and is controlled by the affinity of the running thread (and probably some other settings also).
So to answer your question, there is no way of knowing if two adjacent assembly statements will run on the same core or not.
I'm talking mostly about Linux; but I guess what I am saying should be applicable to other OSes. However, without access to Windows source code, no one can reliably say how it behaves in its detail
I think your "abstraction" of what a computer is doing is inadequate. Basically, a (mono-threaded) process (or just a thread) is running on some "virtual" CPU, whose instruction set is the unpriviledged x86 machine instructions augmented by the ability to enter the kernel thru syscalls (usually, thru a special instruction like SYSENTER). So from an application point of view, system calls to the linux kernel are "atomic". See this and that answers.
Indeed, the processor is getting (at arbitrary instants) some interrupts (on Linux, cat /proc/interrupts repeated twice with a one-second delay would show you how often it is getting interrupted, basically many thousand times per second), and these interrupts are handled by the kernel. The kernel is scheduling tasks (e.g. threads or processes) premptively (they can be interrupted and restarted by the kernel at any time).
From an application point of view, interrupts don't really exist (but the kernel can send signals to the process).
Cores, interrupts and caches are handled by the hardware and/or the kernel, so from the application point of view, they don't really exist -except by "slowing down" the process. cache coherency is mostly dealt with in hardware, and with out-of-order execution makes a given -even tiny- binary program execution time unpredictable. (in other words, you cannot statically predict exactly how many milliseconds some given routine or loop will need; you can only dynamically measure that; read more about worst-case execution time).
Reading the Advanced Linux Programming book and the Linux Assembly Howto would help.
You cannot normally predict where each individial instruction will execute. As long as an individual thread is executing continuously, it will run inside of the same core/processor, but you cannot predict on which instruction the thread will be switched-out. The OS makes that decision, the decision of when to switch it back in, and on which core/processor to put it, based on the workload of the system and priority levels, among other things.
You can usually request to the OS specifically that a thread should always run on the same core, this is called affinity. This is normally a bad idea and it should only be done when absolutely necessary because it takes away from the OS the flexibility to decide what to do where, based on the workload; affinity will almost always result in a performance penalty.
Requesting processor-affinity is an extraordinary request that requires extraordinary proof that it would result in better performance. Don't try to outsmart the OS; the OS knows things about the current running environment that you don't know about.
I recently started to learn how the CPU and the operating system works, and I am a bit confused about the operation of a single-CPU machine with an operating system that provides multitasking.
Supposing my machine has a single CPU, this would mean that, at any given time, only one process could be running.
Now, I can only assume that the scheduler used by the operating system to control the access to the precious CPU time is also a process.
Thus, in this machine, either the user process or the scheduling system process is running at any given point in time, but not both.
So here's a question:
Once the scheduler gives up control of the CPU to another process, how can it regain CPU time to run itself again to do its scheduling work? I mean, if any given process currently running does not yield the CPU, how could the scheduler itself ever run again and ensure proper multitasking?
So far, I had been thinking, well, if the user process requests an I/O operation through a system call, then in the system call we could ensure the scheduler is allocated some CPU time again. But I am not even sure if this works in this way.
On the other hand, if the user process in question were inherently CPU-bound, then, from this point of view, it could run forever, never letting other processes, not even the scheduler run again.
Supposing time-sliced scheduling, I have no idea how the scheduler could slice the time for the execution of another process when it is not even running?
I would really appreciate any insight or references that you can provide in this regard.
The OS sets up a hardware timer (Programmable interval timer or PIT) that generates an interrupt every N milliseconds. That interrupt is delivered to the kernel and user-code is interrupted.
It works like any other hardware interrupt. For example your disk will force a switch to the kernel when it has completed an IO.
Google "interrupts". Interrupts are at the centre of multithreading, preemptive kernels like Linux/Windows. With no interrupts, the OS will never do anything.
While investigating/learning, try to ignore any explanations that mention "timer interrupt", "round-robin" and "time-slice", or "quantum" in the first paragraph – they are dangerously misleading, if not actually wrong.
Interrupts, in OS terms, come in two flavours:
Hardware interrupts – those initiated by an actual hardware signal from a peripheral device. These can happen at (nearly) any time and switch execution from whatever thread might be running to code in a driver.
Software interrupts – those initiated by OS calls from currently running threads.
Either interrupt may request the scheduler to make threads that were waiting ready/running or cause threads that were waiting/running to be preempted.
The most important interrupts are those hardware interrupts from peripheral drivers – those that make threads ready that were waiting on IO from disks, NIC cards, mice, keyboards, USB etc. The overriding reason for using preemptive kernels, and all the problems of locking, synchronization, signaling etc., is that such systems have very good IO performance because hardware peripherals can rapidly make threads ready/running that were waiting for data from that hardware, without any latency resulting from threads that do not yield, or waiting for a periodic timer reschedule.
The hardware timer interrupt that causes periodic scheduling runs is important because many system calls have timeouts in case, say, a response from a peripheral takes longer than it should.
On multicore systems the OS has an interprocessor driver that can cause a hardware interrupt on other cores, allowing the OS to interrupt/schedule/dispatch threads onto multiple cores.
On seriously overloaded boxes, or those running CPU-intensive apps (a small minority), the OS can use the periodic timer interrupts, and the resulting scheduling, to cycle through a set of ready threads that is larger than the number of available cores, and allow each a share of available CPU resources. On most systems this happens rarely and is of little importance.
Every time I see "quantum", "give up the remainder of their time-slice", "round-robin" and similar, I just cringe...
To complement #usr's answer, quoting from Understanding the Linux Kernel:
The schedule( ) Function
schedule( ) implements the scheduler. Its objective is to find a
process in the runqueue list and then assign the CPU to it. It is
invoked, directly or in a lazy way, by several kernel routines.
[...]
Lazy invocation
The scheduler can also be invoked in a lazy way by setting the
need_resched field of current [process] to 1. Since a check on the value of this
field is always made before resuming the execution of a User Mode
process (see the section "Returning from Interrupts and Exceptions" in
Chapter 4), schedule( ) will definitely be invoked at some close
future time.
I read that Linux kernel is preemptive, which is different from most Unix kernels. So, what does it really mean for a kernal to be preemptive?
Some analogies or examples would be better than pure theoretical explanation.
ADD 1 -- 11:00 AM 12/7/2018
Preemptive is just one paradigm of multi-tasking. There are others like Cooperative Multi-tasking. A better understanding can be achieved by comparing them.
Prior to Linux kernel version 2.5.4, Linux Kernel was not preemptive which means a process running in kernel mode cannot be moved out of processor until it itself leaves the processor or it starts waiting for some input output operation to get complete.
Generally a process in user mode can enter into kernel mode using system calls. Previously when the kernel was non-preemptive, a lower priority process could priority invert a higher priority process by denying it access to the processor by repeatedly calling system calls and remaining in the kernel mode. Even if the lower priority process' timeslice expired, it would continue running until it completed its work in the kernel or voluntarily relinquished control. If the higher priority process waiting to run is a text editor in which the user is typing or an MP3 player ready to refill its audio buffer, the result is poor interactive performance. This way non-preemptive kernel was a major drawback at that time.
Imagine the simple view of preemptive multi-tasking. We have two user tasks, both of which are running all the time without using any I/O or performing kernel calls. Those two tasks don't have to do anything special to be able to run on a multi-tasking operating system. The kernel, typically based on a timer interrupt, simply decides that it's time for one task to pause to let another one run. The task in question is completely unaware that anything happened.
However, most tasks make occasional requests of the kernel via syscalls. When this happens, the same user context exists, but the CPU is running kernel code on behalf of that task.
Older Linux kernels would never allow preemption of a task while it was busy running kernel code. (Note that I/O operations always voluntarily re-schedule. I'm talking about a case where the kernel code has some CPU-intensive operation like sorting a list.)
If the system allows that task to be preempted while it is running kernel code, then we have what is called a "preemptive kernel." Such a system is immune to unpredictable delays that can be encountered during syscalls, so it might be better suited for embedded or real-time tasks.
For example, if on a particular CPU there are two tasks available, and one takes a syscall that takes 5ms to complete, and the other is an MP3 player application that needs to feed the audio pipe every 2ms, you might hear stuttering audio.
The argument against preemption is that all kernel code that might be called in task context must be able to survive preemption-- there's a lot of poor device driver code, for example, that might be better off if it's always able to complete an operation before allowing some other task to run on that processor. (With multi-processor systems the rule rather than the exception these days, all kernel code must be re-entrant, so that argument isn't as relevant today.) Additionally, if the same goal could be met by improving the syscalls with bad latency, perhaps preemption is unnecessary.
A compromise is CONFIG_PREEMPT_VOLUNTARY, which allows a task-switch at certain points inside the kernel, but not everywhere. If there are only a small number of places where kernel code might get bogged down, this is a cheap way of reducing latency while keeping the complexity manageable.
Traditional unix kernels had a single lock, which was held by a thread while kernel code was running. Therefore no other kernel code could interrupt that thread.
This made designing the kernel easier, since you knew that while one thread using kernel resources, no other thread was. Therefore the different threads cannot mess up each others work.
In single processor systems this doesn't cause too many problems.
However in multiprocessor systems, you could have a situation where several threads on different processors or cores all wanted to run kernel code at the same time. This means that depending on the type of workload, you could have lots of processors, but all of them spend most of their time waiting for each other.
In Linux 2.6, the kernel resources were divided up into much smaller units, protected by individual locks, and the kernel code was reviewed to make sure that locks were only held while the corresponding resources were in use. So now different processors only have to wait for each other if they want access to the same resource (for example hardware resource).
The preemption allows the kernel to give the IMPRESSION of parallelism: you've got only one processor (let's say a decade ago), but you feel like all your processes are running simulaneously. That's because the kernel preempts (ie, take the execution out of) the execution from one process to give it to the next one (maybe according to their priority).
EDIT Not preemptive kernels wait for processes to give back the hand (ie, during syscalls), so if your process computes a lot of data and doesn't call any kind of yield function, the other processes won't be able to execute to execute their calls. Such systems are said to be cooperative because they ask for the cooperation of the processes to ensure the equity of the execution time
EDIT 2 The main goal of preemption is to improve the reactivity of the system among multiple tasks, so that's good for end-users, whereas on the other-hand, servers want to achieve the highest througput, so they don't need it: (from the Linux kernel configuration)
Preemptible kernel (low-latency desktop)
Voluntary kernel preemption (desktop)
No forced preemption (server)
The linux kernel is monolithic and give a little computing timespan to all the running process sequentially. It means that the processes (eg. the programs) do not run concurrently, but they are given a give timespan regularly to execute their logic. The main problem is that some logic can take longer to terminate and prevent the kernel to allow time for the next process. This results in system "lags".
A preemtive kernel has the ability to switch context. It means that it can stop a "hanging" process even if it is not finished, and give the computing time to the next process as expected. The "hanging" process will continue to execute when its time has come without any problem.
Practically, it means that the kernel has the ability to achieve tasks in realtime, which is particularly interesting for audio recording and editing.
The ubuntu studio districution packages a preemptive kernel as well as a buch of quality free software devoted to audio and video edition.
It means that the operating system scheduler is free to suspend the execution of the running processes to give the CPU to another process whenever it wants; the normal way to do this is to give to each process that is waiting for the CPU a "quantum" of CPU time to run. After it has expired the scheduler takes back the control (and the running process cannot avoid this) to give another quantum to another process.
This method is often compared with the cooperative multitasking, in which processes keep the CPU for all the time they need, without being interrupted, and to let other applications run they have to call explicitly some kind of "yield" function; naturally, to avoid giving the feeling of the system being stuck, well-behaved applications will yield the CPU often. Still,if there's a bug in an application (e.g. an infinite loop without yield calls) the whole system will hang, since the CPU is completely kept by the faulty program.
Almost all recent desktop OSes use preemptive multitasking, that, even if it's more expensive in terms of resources, is in general more stable (it's more difficult for a sigle faulty app to hang the whole system, since the OS is always in control). On the other hand, when the resources are tight and the application are expected to be well-behaved, cooperative multitasking is used. Windows 3 was a cooperative multitasking OS; a more recent example can be RockBox, an opensource PMP firmware replacement.
I think everyone did a good job of explaining this but I'm just gonna add little more info. in context of Linux IRQ, interrupt and kernel scheduler.
Process scheduler is the component of the OS that is responsible for deciding if current running job/process should continue to run and if not which process should run next.
preemptive scheduler is a scheduler which allows to be interrupted and a running process then can change it's state and then let another process to run (since the current one was interrupted).
On the other hand, non-preemptive scheduler can't take away CPU away from a process (aka cooperative)
FYI, the name word "cooperative" can be confusing because the word's meaning does not clearly indicate what scheduler actually does.
For example, Older Windows like 3.1 had cooperative schedulers.
Full credit to wonderful article here
I think it became preemptive from 2.6. preemptive means when a new process is ready to run, the cpu will be allocated to the new process, it doesn't need the running process be co-operative and give up the cpu.
Linux kernel is preemptive means that The kernel supports preemption.
For example, there are two processes P1(higher priority) and P2(lower priority) which are doing read system calls and they are running in kernel mode. Suppose P2 is running and is in the kernel mode and P2 is scheduled to run.
If kernel preemption is available, then preemption can happen at the kernel level i.e P2 can get preempted and but to sleep and the P1 can continue to run.
If kernel preemption is not available, since P2 is in kernel mode, system simply waits till P2 is complete and then