If a 64bit program wants to consume lot of memory, does it matter if memory is allocated in process heap or from memory map file/s? I understand other benefits of memory map file like sharing across two or more processes, however, in my case, data in memory maps is not shared across processes.
It's not entirely clear what you mean would be the difference, especially given that large allocations [by some definition of large that depends on settings in the C library] are typically make by using anonymous mmap regions (that is, memory mapped files that don't actually have a real file backing them - the OS uses /dev/zero as the "file", so when memory is paged in from the "file" it reads as zero. It is never written back...].
In other words, whilst "heap" is memory managed by the C library, and if you manually manage memory mapped files you have to do the "management" in your code for that, it's otherwise the same thing.
Edit:
In response to the comment:
It's really going to depend on:
The amount of memory in the system. If you have 1TB+, then you will probably be able to use either method with approximately the same result.
How large the sections are from file - if you are reading little portions (significantly less than 4KB) in many different places, then malloc will probably win. If the sections of file you are working on is much larger, then either method will have about the same memory usage factor.
Either method will not give decent performance if you have a lot less memory than the actual amount of data you are processing, because too much time is spent reading/writing data to/from disk, and/or allocating/deallocating memory.
In general, mapping files to memory is the fastest way of loading the data into memory (there is fewer times the OS has to copy the data on the way from the disk to the final location in memory). But for any relatively large files, the actual speed the data comes off the disk will be the main factor, and no matter what you do, that will dominate the time it takes to read 1TB of file(s).
Related
POSIX environments provide at least two ways of accessing files. There's the standard system calls open(), read(), write(), and friends, but there's also the option of using mmap() to map the file into virtual memory.
When is it preferable to use one over the other? What're their individual advantages that merit including two interfaces?
mmap is great if you have multiple processes accessing data in a read only fashion from the same file, which is common in the kind of server systems I write. mmap allows all those processes to share the same physical memory pages, saving a lot of memory.
mmap also allows the operating system to optimize paging operations. For example, consider two programs; program A which reads in a 1MB file into a buffer creating with malloc, and program B which mmaps the 1MB file into memory. If the operating system has to swap part of A's memory out, it must write the contents of the buffer to swap before it can reuse the memory. In B's case any unmodified mmap'd pages can be reused immediately because the OS knows how to restore them from the existing file they were mmap'd from. (The OS can detect which pages are unmodified by initially marking writable mmap'd pages as read only and catching seg faults, similar to Copy on Write strategy).
mmap is also useful for inter process communication. You can mmap a file as read / write in the processes that need to communicate and then use synchronization primitives in the mmap'd region (this is what the MAP_HASSEMAPHORE flag is for).
One place mmap can be awkward is if you need to work with very large files on a 32 bit machine. This is because mmap has to find a contiguous block of addresses in your process's address space that is large enough to fit the entire range of the file being mapped. This can become a problem if your address space becomes fragmented, where you might have 2 GB of address space free, but no individual range of it can fit a 1 GB file mapping. In this case you may have to map the file in smaller chunks than you would like to make it fit.
Another potential awkwardness with mmap as a replacement for read / write is that you have to start your mapping on offsets of the page size. If you just want to get some data at offset X you will need to fixup that offset so it's compatible with mmap.
And finally, read / write are the only way you can work with some types of files. mmap can't be used on things like pipes and ttys.
One area where I found mmap() to not be an advantage was when reading small files (under 16K). The overhead of page faulting to read the whole file was very high compared with just doing a single read() system call. This is because the kernel can sometimes satisify a read entirely in your time slice, meaning your code doesn't switch away. With a page fault, it seemed more likely that another program would be scheduled, making the file operation have a higher latency.
mmap has the advantage when you have random access on big files. Another advantage is that you access it with memory operations (memcpy, pointer arithmetic), without bothering with the buffering. Normal I/O can sometimes be quite difficult when using buffers when you have structures bigger than your buffer. The code to handle that is often difficult to get right, mmap is generally easier. This said, there are certain traps when working with mmap.
As people have already mentioned, mmap is quite costly to set up, so it is worth using only for a given size (varying from machine to machine).
For pure sequential accesses to the file, it is also not always the better solution, though an appropriate call to madvise can mitigate the problem.
You have to be careful with alignment restrictions of your architecture(SPARC, itanium), with read/write IO the buffers are often properly aligned and do not trap when dereferencing a casted pointer.
You also have to be careful that you do not access outside of the map. It can easily happen if you use string functions on your map, and your file does not contain a \0 at the end. It will work most of the time when your file size is not a multiple of the page size as the last page is filled with 0 (the mapped area is always in the size of a multiple of your page size).
In addition to other nice answers, a quote from Linux system programming written by Google's expert Robert Love:
Advantages of mmap( )
Manipulating files via mmap( ) has a handful of advantages over the
standard read( ) and write( ) system calls. Among them are:
Reading from and writing to a memory-mapped file avoids the
extraneous copy that occurs when using the read( ) or write( ) system
calls, where the data must be copied to and from a user-space buffer.
Aside from any potential page faults, reading from and writing to a memory-mapped file does not incur any system call or context switch
overhead. It is as simple as accessing memory.
When multiple processes map the same object into memory, the data is shared among all the processes. Read-only and shared writable
mappings are shared in their entirety; private writable mappings have
their not-yet-COW (copy-on-write) pages shared.
Seeking around the mapping involves trivial pointer manipulations. There is no need for the lseek( ) system call.
For these reasons, mmap( ) is a smart choice for many applications.
Disadvantages of mmap( )
There are a few points to keep in mind when using mmap( ):
Memory mappings are always an integer number of pages in size. Thus, the difference between the size of the backing file and an
integer number of pages is "wasted" as slack space. For small files, a
significant percentage of the mapping may be wasted. For example, with
4 KB pages, a 7 byte mapping wastes 4,089 bytes.
The memory mappings must fit into the process' address space. With a 32-bit address space, a very large number of various-sized mappings
can result in fragmentation of the address space, making it hard to
find large free contiguous regions. This problem, of course, is much
less apparent with a 64-bit address space.
There is overhead in creating and maintaining the memory mappings and associated data structures inside the kernel. This overhead is
generally obviated by the elimination of the double copy mentioned in
the previous section, particularly for larger and frequently accessed
files.
For these reasons, the benefits of mmap( ) are most greatly realized
when the mapped file is large (and thus any wasted space is a small
percentage of the total mapping), or when the total size of the mapped
file is evenly divisible by the page size (and thus there is no wasted
space).
Memory mapping has a potential for a huge speed advantage compared to traditional IO. It lets the operating system read the data from the source file as the pages in the memory mapped file are touched. This works by creating faulting pages, which the OS detects and then the OS loads the corresponding data from the file automatically.
This works the same way as the paging mechanism and is usually optimized for high speed I/O by reading data on system page boundaries and sizes (usually 4K) - a size for which most file system caches are optimized to.
An advantage that isn't listed yet is the ability of mmap() to keep a read-only mapping as clean pages. If one allocates a buffer in the process's address space, then uses read() to fill the buffer from a file, the memory pages corresponding to that buffer are now dirty since they have been written to.
Dirty pages can not be dropped from RAM by the kernel. If there is swap space, then they can be paged out to swap. But this is costly and on some systems, such as small embedded devices with only flash memory, there is no swap at all. In that case, the buffer will be stuck in RAM until the process exits, or perhaps gives it back withmadvise().
Non written to mmap() pages are clean. If the kernel needs RAM, it can simply drop them and use the RAM the pages were in. If the process that had the mapping accesses it again, it cause a page fault the kernel re-loads the pages from the file they came from originally. The same way they were populated in the first place.
This doesn't require more than one process using the mapped file to be an advantage.
My program works with large data sets that need to be stored in contiguous memory (several Gigabytes). Allocating memory using std::allocator (i.e. malloc or new) causes system stalls as large portions of virtual memory are reserved and physical memory gets filled up.
Since the program will mostly only work on small portions at a time, my question is if using memory mapped files would provide an advantage (i.e. mmap or the Windows equivalent.) That is creating a large sparse temporary file and mapping it to virtual memory. Or is there another technique that would change the system's pagination strategy such that less pages are loaded into physical memory at a time.
I'm trying to avoid building a streaming mechanism that loads portions of a file at a time and instead rely on the system's vm pagination.
Yes, mmap has the potential to speed things up.
Things to consider:
Remember the VMM will page things in and out in page size blocked (4k on Linux)
If your memory access is well localised over time, this will work well. But if you do random access over your entire file, you will end up with a lot of seeking and thrashing (still). So, consider whether your 'small portions' correspond with localised bits of the file.
For large allocations, malloc and free will use mmap with MAP_ANON anyway. So the difference in memory mapping a file is simply that you are getting the VMM to do the I/O for you.
Consider using madvise with mmap to assist the VMM in paging well.
When you use open and read (plus, as erenon suggests, posix_fadvise), your file is still held in buffers anyway (i.e. it's not immediately written out) unless you also use O_DIRECT. So in both situations, you are relying on the kernel for I/O scheduling.
If the data is already in a file, it would speed up things, especially in the non-sequential case. (In the sequential case, read wins)
If using open and read, consider using posix_fadvise as well.
This really depends on your mmap() implementation. Mapping a file into memory has several advantages that can be exploited by the kernel:
The kernel knows that the contents of the mmap() pages is already present on disk. If it decides to evict these pages, it can omit the write back.
You reduce copying operations: read() operations typically first read the data into kernel memory, then copy it over to user space.
The reduced copies also mean that less memory is used to store data from the file, which means more memory is available for other uses, which can reduce paging as well.
This is also, why it is generally a bad idea to use large caches within an I/O library: Modern kernels already cache everything they ever read from disk, caching a copy in user space means that the amount of data that can be cached is actually reduced.
Of course, you also avoid a lot of headaches that result from buffering data of unknown size in your application. But that is just a convenience for you as a programmer.
However, even though the kernel can exploit these properties, it does not necessarily do so. My experience is that LINUX mmap() is generally fine; on AIX, however, I have witnessed really bad mmap() performance. So, if your goal is performance, it's the old measure-compare-decide stand by.
Whenever a new / malloc is used, OS create a new(or reuse) heap memory segment, aligned to the page size and return it to the calling process. All these allocations will constitute to the Process's virtual memory. In 32bit computing, any process can scale only upto 4 GB. Higher the heap allocation, the rate of increase of process memory is higher. Though there are lot of memory management / memory pools available, all these utilities end up again in creating a heap and reusing it effeciently.
mmap (Memory mapping) on the other hand, provides the ablity to visualize a file as memory stream, and enables the program to use pointer manipulations directly on file. But here again, mmap is actually allocating the range of addresses in the process space. So if we mmap a 3GB file with size 3GB and take a pmap of the process, you could see the total memory consumed by the process is >= 3GB.
My question is, is it possible to have a file based memory pool [just like mmaping a file], however, does not constitute the process memory space. I visualize something like a memory DB, which is backed by a file, which is so fast for read/write, which supports pointer manipulations [i.e get a pointer to the record and store anything as if we do using new / malloc], which can grow on the disk, without touching the process virtual 4GB limit.
Is it possible ? if so, what are some pointers for me to start working.
I am not asking for a ready made solution / links, but to conceptually understand how it can be achieved.
It is generally possible but very coplicated. You would have to re-map if you wanted to acces different 3Gb segments of your file, which would probably kill the performance in case of scattered access. Pointers would only get much more difficult to work with, as remmpaing changes data but leaves the adresses the same.
I have seen STXXL project that might be interesting to you; or it might not. I have never used it so I cannot give you any other advice about it.
What you are looking for, is in principle, a memory backed file-cache. There are many such things in for example database implementations (where the whole database is way larger than the memory of the machine, and the application developer probably wants to have a bit of memory left for application stuff). This will involve having some sort of indirection - an index, hash or some such to indicate what area of the file you want to access, and using that indirection to determine if the memory is in memory or on disk. You would essentially have to replicate what the virtual memory handling of the OS and the processor does, by having tables that indicate where in physical memory your "virtual heap" is, and if it's not present in physical memory, read it in (and if the cache is full, get rid of some - and if it's been written, write it back again).
However, it's most likely that in today's world, you have a machine capable of 64-bit addressing, and thus, it would be much easier to recompile the application as a 64-bit application, usemmap or similar to access the large memory. In this case, even if RAM isn't sufficient, you can access the memory of the file via the virtual memory system, and it takes care of all the mapping back and forth between disk and RAM (physical memory).
Environment:
Windows 8 64 bit, Windows 2008 server 64 bit
Visual Studio (professional) 2012 64 bits
list L; //I have 1000s of large CMyObject in my program that I cache, which is shared by different threads in my windows service program.
For our SaaS middleware product, we cache in memory 1000s of large C++ objects (read only const objects, each about 4MB in size), which runs the system out of memory. Can we associate a disk file (or some other persistent mechanism that is OS managed) to our C++ objects? There is no need for sharing / inter-process communication.
The disk file will suffice if it works for the duration of the process (our windows service program). The read-only const C++ objects are shared by different threads in the same windows service.
I was even considering using object databases (like mongoDB) to store the objects, which will then be loaded / unloaded at each use. Though faster than reading our serialized file (hopefully), it will still spoil the performance.
The purpose is to retain caching of C++ objects for performance reason and avoid having to load / unload the serialized C++ object every time. It would be great if this disk file is OS managed and requires minimal tweaking in our code.
Thanks in advance for your responses.
The only thing which is OS managed in the manner you describe is swap file. You can create a separate application (let it be called "cache helper"), which loads all the objects into memory and waits for requests. Since it does not use it's memory pages, OS will eventually displace the pages to the swap file, recalling it only if/when needed.
Communication with the applciation can be done through named pipes or sockets.
Disadvantages of such approach are that the performance of such cache will be highly volatile, and it may degrade performance of the whole server.
I'd recommend to write your own caching algorithm/application, as you may later need to adjust its properties.
One solution is of course to simply load every object, and let the OS deal with swapping it in from/out to disk as required. (Or dynamically load, but never discard unless the object is absolutely being destroyed). This approach will work well if there are are number of objects that are more frequently used than others. And the loading from swapspace is almost certainly faster than anything you can write. The exception to this is if you do know beforehand what objects are more likely or less likely to be used next, and can "throw out" the right objects in case of low memory.
You can certainly also use a memory mapped file - this will allow you to read from and write to the file as if it was memory (and the OS will cache the content in RAM as memory is available). On WIndows, you will be using CreateFileMapping or OpenFileMapping to create/open the filemapping, and then MapViewOfFile to map the file into memory. When finished, use UnmapViewOfFile to "unmap" the memory, and then CloseHandle to close the FileMapping.
The only worry about a filemapping is that it may not appear at the same address in memory next time around, so you can't have pointers within the filemapping and load the same data as binary next time. It would of course work fine to create a new filemapping each time.
So your thousands of massive objects have constructor, destructor, virtual functions and pointers. This means you can't easily page them out. The OS can do it for you though, so your most practical approach is simply to add more physical memory, possibly an SSD swap volume, and use that 64-bit address space. (I don't know how much is actually addressable on your OS, but presumably enough to fit your ~4G of objects).
Your second option is to find a way to just save some memory. This might be using a specialized allocator to reduce slack, or removing layers of indirection. You haven't given enough information about your data for me to make concrete suggestions on this.
A third option, assuming you can fit your program in memory, is simply to speed up your deserialization. Can you change the format to something you can parse more efficiently? Can you somehow deserialize objects quickly on-demand?
The final option, and the most work, is to manually manage a swapfile. It would be sensible as a first step to split your massive polymorphic classes into two: a polymorphic flyweight (with one instance per concrete subtype), and a flattened aggregate context structure. This aggregate is the part you can swap in and out of your address space safely.
Now you just need a memory-mapped paging mechanism, some kind of cache tracking which pages are currently mapped, possibly a smart pointer replacing your raw pointer with a page+offset which can map data in on-demand, etc. Again, you haven't given enough information on your data structure and access patterns to make more detailed suggestions.
I have a situation where I need to work with a number (15-30) of large (several hundreds mb) data structures. They won't fit into memory all at the same time. To make things worse, the algorithms operating on them work across all those structures, i.e. not first one, then the other etc. I need to make this as fast as possible.
So I figured I'd allocate memory on disk, in files that are basically direct binary representations of the data when it's loaded into memory, and use memory mapped files to access the data. I use mmap 'views' of for example 50 megabytes (50 mb of the files are loaded into memory at a time), so when I have 15 data sets, my process uses 750 mb of memory for the data. Which was OK initially (for testing), when I have more data I adjust the 50 mb down at the cost of some speed.
However this heuristic is hard-coded for now (I know the size of the data set I will test with). 'In the wild', my software will need to be able to determine the 'right' amount of memory to allocate to maximize performance. I could say 'I will target a memory use of 500 mb' and then divide 500 by the amount of data structures to come to a mmap view size. I have found that when trying to set this 'target memory usage' too high, that the virtual memory manager disk thrashing will (almost) lock up the machine and render it unusable until the processing finishes. This is to be avoided in my 'production' solution.
So my questions, all somewhat different approaches to the problem:
What is the 'best' target size for a single process? Should I just try to max out the 2gb that I have (assuming 32 bit Win XP and up, non-/3GB for now) or try to keep my process size smaller so that my software won't hog the machine? When I have 2 Visual Studio's, Outlook and a Firefox open on my machine, those use 1/2 gb of virtual memory easily by themselves - if I let my software use 2 gb of virtual memory the swapping will severely slow down the machine. But then how do I determine the 'best' process size.
What can I do to keep performance of the machine in check when working with memory-mapped files? My application does fairly simple numerical operations on the data, which basically means that it zips over hundreds of megabytes of data real quick, causing the whole memory-mapped files (several gigabytes) to be loaded into memory and swapped out again very quickly, again and again (think Monte Carlo style simulation).
Is there any chance that not using memory-mapped files and just using fseek/fgets is going to be faster or less intrusive than using memory mapped files?
Any articles, papers or books I can read about this? Either with 'cookbook' style solutions or fundamental concepts.
Thanks.
It occurs to me that you could set some predefined threshold for "too darn slow" and use the computer's wall-clock to make your alterations on the fly.
Start conservatively low. If this is below your "too darn slow" threshold, bump the size up a little bit for the next file. do this iteratively. When you go above the threshold, slowly back the size off iteratively.
I think it's a good place to try Address Windowing Extensions: http://msdn.microsoft.com/en-us/library/aa366527(v=VS.85).aspx
It will allow to use more than 4GB of memory by providing a sliding window. The drawback is that not all versions of windows have it.
I probably wouldn't use a memory-mapped file for this app. Memory-mapped files work best when you have a large virtual address space (at least relative to the size of the data you're processing). You map the entire file, and let the OS decide which pieces remain resident.
However, if you're repeatedly mapping and unmapping segments of the file (rather than the entire file), you'll probably end up doing just as well by reading chunks via fseek and fread -- note, however, that you do not want to read individual pieces of data this way (ie, do one large read rather than a lot of small reads).
The one way that manually segmented memory-mapped files might win is if you have sparse reads: if you'll only be touching, say 10% of a given file. In this case, memory mapping means the OS will read only those pages that are touched, whereas explicit reads will load the entire file.
Oh, and I would definitely not spend time trying to control my resource consumption. The OS will do that better than you can, because it knows about all competing processes.
It will probably be best to fix the size of the memory mapped file to be a some percentage of the total system memory with probably a set minimum.
Remember that the operating system will effectively load a whole memory page when you access a single byte, this may well happen in the background but will only be fast if sequential data accesses tend to be close together.
You should therefore try to keep sequential accesses to your data as close together in memory/the file as possible. You can also look a preloading strategies access your data speculatively before actually requiring the data. These are the same considerations that you will need when optimizing for memory cache efficiency.
If sequential data accesses are scattered widely in your file, you may be better off using fseek and fread to access the data since this will give you better fine-grain control of what data is written to memory when.
Also remember that there are no hard and fast rules. Optimizations can sometimes be counter-intuitive so try a whole bunch of different things and see which works best on the platform that this will need to operate on.
Perhaps you can use /LARGEADDRESSAWARE for you linker of Visual Studio, and use bcdedit for your process to use memory larger than 2GB.