I have read several times that turning on compression in HDF5 can lead to better read/write performance.
I wonder what ideal settings can be to achieve good read/write performance at:
data_df.to_hdf(..., format='fixed', complib=..., complevel=..., chunksize=...)
I'm already using fixed format (i.e. h5py) as it's faster than table. I have strong processors and do not care much about disk space.
I often store DataFrames of float64 and str types in files of approx. 2500 rows x 9000 columns.
There are a couple of possible compression filters that you could use.
Since HDF5 version 1.8.11 you can easily register a 3rd party compression filters.
Regarding performance:
It probably depends on your access pattern because you probably want to define proper dimensions for your chunks so that it aligns well with your access pattern otherwise your performance will suffer a lot. For example if you know that you usually access one column and all rows you should define your chunk shape accordingly (1,9000). See here, here and here for some infos.
However AFAIK pandas usually will end up loading the entire HDF5 file into memory unless you use read_table and an iterator (see here) or do the partial IO yourself (see here) and thus doesn't really benefit that much of defining a good chunk size.
Nevertheless you might still benefit from compression because loading the compressed data to memory and decompressing it using the CPU is probably faster than loading the uncompressed data.
Regarding your original question:
I would recommend to take a look at Blosc. It is a multi-threaded meta-compressor library that supports various different compression filters:
BloscLZ: internal default compressor, heavily based on FastLZ.
LZ4: a compact, very popular and fast compressor.
LZ4HC: a tweaked version of LZ4, produces better compression ratios at the expense of speed.
Snappy: a popular compressor used in many places.
Zlib: a classic; somewhat slower than the previous ones, but achieving better compression ratios.
These have different strengths and the best thing is to try and benchmark them with your data and see which works best.
Related
I'm in the process of switching over to Julia from other programming languages and one of the things that Julia will let you hang yourself on is memory. I think this is likely a good thing, a programming language where you actually have to think about some amount of memory management forces the coder to write more efficient code. This would be in contrast to something like R where you can seemingly load datasets that are larger than the allocated memory. Of course, you can't actually do that, so I wonder how does R get around that problem?
Part of what I've done in other programming languages is work on large tabular datasets, often converted over to a R dataframe or a matrix. I think the way this is handled in Julia is to stream data in wherever possible, so my main question is this:
Is it better to use readline("my_file.txt") to access data or is it better to use open("my_file.txt", "w")? If possible, wouldn't it be better to access a large dataset all at once for speed? Or would it be better to always stream data?
I hope this makes sense. Any further resources would be greatly appreciated.
I'm not an extensive user of Julia's data-ecosystem packages, but CSV.jl offers the Chunks and Rows alternatives to File, and these might let you process the files incrementally.
While it may not be relevant to your use case, the mechanisms mentioned in #Przemyslaw Szufel's answer are used other places as well. Two I'm familiar with are the TiffImages.jl and NRRD.jl packages, both I/O packages mostly for loading image data into Julia. With these, you can load terabyte-sized datasets on a laptop. There may be more packages that use the same mechanism, and many package maintainers would probably be grateful to receive a pull request that supports optional memory-mapping when applicable.
In R you cannot have a data frame larger than memory. There is no magical buffering mechanism. However, when running R-based analytics you could use a disk.frame package for that.
Similarly, in Julia if you want to process data frames larger than memory you need to use am appropriate package. The most reasonable and natural option in Julia ecosystem is JuliaDB.
If you want to do something more low-level solution have a look at:
Mmap that provides Memory-mapped I/O that exactly solves the issue of conveniently handling data too large to fit into memory
SharedArrays that offers a disk mapped array with implementation based on Mmap.
In conclusion, if your data is data frame based - try JuliaDB, otherwise have a look at Mmap and SharedArrays (look at the filename parameter)
I have been reading about RecordIO here and there and checking different implementations on github here, and there.
I'm simply trying to wrap my head around the pros of such a file format.
The pros I see are the following:
Block compression. It will be faster if you need to read only a few records because less to decompress.
Because of the somehow indexed structure you could lookup a specific record in acceptable time (assuming keys are sorted). This can be useful to quickly locate a record in an adhoc fashion.
I can also imagine that with such a file format you can have finer sharding strategies. Instead of sharding per file you can shard per block.
But I fail to see how such a file format is faster for reading over some plain protobuf with compression.
Essentially I fail to see a big pro in this format.
I am trying to better understand how RavenDB uses disk space.
My application has many small documents (approximately 140 bytes each). Presently, there are around 81,000 documents which would give a total data size of around 11MB. However, the size of the database is just over 70MB.
Is most of the actual space being used by indexes?
I had read somewhere else that there may be a minimum overhead of around 600 bytes per document. This would consume around 49MB, which is more in the ballpark of the actual use I am seeing.
Would using the compression bundle provide much benefit in this scenario (many small documents), or is it targeted towards helping reduce the size of databases with very large documents?
I have done some further testing on my own and determined, in answer to my own question, that:
Indexes are not the main consumer of disk space in my scenario. In this case, indexes represent < 25% of the disk space used.
Adding the compression bundle for a database with a large number of small documents does not really reduce the total amount of disk space used. This is likely due to some minimum data overhead that each document requires. Compression would benefit documents that are very large.
Is most of the actual space being used by indexes?
Yes, that's likely. Remember that Raven creates indexes for different queries you make. You can fire up Raven Studio to see what indexes it's created for you:
Would using the compression bundle provide much benefit in this
scenario (many small documents), or is it targeted towards helping
reduce the size of databases with very large documents?
Probably wouldn't benefit your scenario of small documents. The compression bundle works on individual documents, not on indexes. But it might be worth trying to see what results you get.
Bigger question: since hard drive space is cheap and only getting cheaper, and 70MB is a spec on the map, why are you concerned about hard drive space? Databases often trade disk space for speed (e.g. multiple indexes, like Raven), and this is usually a good trade off for most apps.
I'm working with some very large files residing on P2 (Panasonic) cards. Part of the process we employ is to first generate a checksum of the file we are going to copy, then copy the file, then run a checksum on the file to confirm that it copied OK. The problem is, is that files are large (70 GB+) and take a long time to complete. It's an issue since we will eventually be dealing with thousands of these files.
I would like to find a faster way to generate the checksum other than using the System.Security.Cryptography.MD5CryptoServiceProvider
I don't care if this means using a specialized hardware card, provided it works and is not to ungodly expensive. I would prefer to have a method of encoding that provided some feedback as to how far the process has gone along so I can display it like I do now.
The application is written in vb.net. I would prefer to be able to use it as component, library, reference within my application, but I'm willing to call an outside application if there is enough improvement in the speed of generating the checksum.
Needless to say, the checksum must be consistent and correct. :-)
Thank you in advance for your time and efforts,
Richard
I see one potential way to speed up this process: calculate the MD5 of the source file while performing the copy, not prior to it. This will reduce the number of times you'll need to read the entire file from 3 (source hash, copy, destination hash) to 2 (copy, destination hash).
The downside of this all is that you'll have to write your own copying code (as opposed to just relying on System.IO.File.Copy), and there's a non-zero chance that this will turn out to be slower in the end anyway than the 3-step process.
Other than that, I don't think there's much you can do here, as the entire process is I/O bound by design. You're spending most of your time reading/writing the file, and even at 100MB/s (a respectable I/O speed for your typical SATA drive), you'll do about 5.8GB/min at best.
With a modern processor, the overhead of calculating the MD5 (or anything else) doesn't factor into things very much, so speeding it up won't improve your overall throughput. Crypto accelerators in particular won't help you here, as unless the driver implementation is very efficient, they'll add more overhead due to context switches required to feed the data to the external card than they'll save.
What you do want to improve is the I/O speed. The .NET framework is already pretty efficient when it comes to this (using nicely-sized buffers, overlapped I/O and such), but it's possible an optimized native Windows application will perform better here. My advice: Google around for a few native MD5 calculators, and see how they compare to your current .NET implementation. If the difference in hash calculation speed is >10%, it's worth switching to using said external app.
The correct answer is to avoid using MD5. MD5 is a cryptographic hash function, designed to provide certain cryptographic features. For merely detecting accidental corruption, it is way over-engineered and slow. There are many faster checksums, the design of which can be understood by examining the literature of error detection and correction. Some common examples are the CRC checksums, of which CRC32 is very common, but you can also relatively easily compute 64 or 128 bit or even larger CRCs much much faster than an MD5 hash.
I need a FAST decompression routine optimized for restricted resource environment like embedded systems on binary (hex data) that has following characteristics:
Data is 8bit (byte) oriented (data bus is 8 bits wide).
Byte values do NOT range uniformly from 0 - 0xFF, but have a poisson distribution (bell curve) in each DataSet.
Dataset is fixed in advanced (to be burnt into Flash) and each set is rarely > 1 - 2MB
Compression can take as much as time required, but decompression of a byte should take 23uS in the worst case scenario with minimal memory footprint as it will be done on a restricted resource environment like an embedded system (3Mhz - 12Mhz core, 2k byte RAM).
What would be a good decompression routine?
The basic Run-length encoding seems too wasteful - I can immediately see that adding a header setion to the compressed data to put to use unused byte values to represent oft repeated patterns would give phenomenal performance!
With me who only invested a few minutes, surely there must already exist much better algorithms from people who love this stuff?
I would like to have some "ready to go" examples to try out on a PC so that I can compare the performance vis-a-vis a basic RLE.
The two solutions I use when performance is the only concern:
LZO Has a GPL License.
liblzf Has a BSD License.
miniLZO.tar.gz This is LZO, just repacked in to a 'minified' version that is better suited to embedded development.
Both are extremely fast when decompressing. I've found that LZO will create slightly smaller compressed data than liblzf in most cases. You'll need to do your own benchmarks for speeds, but I consider them to be "essentially equal". Both are light-years faster than zlib, though neither compresses as well (as you would expect).
LZO, in particular miniLZO, and liblzf are both excellent for embedded targets.
If you have a preset distribution of values that means the propability of each value is fixed over all datasets, you can create a huffman encoding with fixed codes (the code tree has not to be embedded into the data).
Depending on the data, I'd try huffman with fixed codes or lz77 (see links of Brian).
Well, the main two algorithms that come to mind are Huffman and LZ.
The first basically just creates a dictionary. If you restrict the dictionary's size sufficiently, it should be pretty fast...but don't expect very good compression.
The latter works by adding back-references to repeating portions of output file. This probably would take very little memory to run, except that you would need to either use file i/o to read the back-references or store a chunk of the recently read data in RAM.
I suspect LZ is your best option, if the repeated sections tend to be close to one another. Huffman works by having a dictionary of often repeated elements, as you mentioned.
Since this seems to be audio, I'd look at either differential PCM or ADPCM, or something similar, which will reduce it to 4 bits/sample without much loss in quality.
With the most basic differential PCM implementation, you just store a 4 bit signed difference between the current sample and an accumulator, and add that difference to the accumulator and move to the next sample. If the difference it outside of [-8,7], you have to clamp the value and it may take several samples for the accumulator to catch up. Decoding is very fast using almost no memory, just adding each value to the accumulator and outputting the accumulator as the next sample.
A small improvement over basic DPCM to help the accumulator catch up faster when the signal gets louder and higher pitch is to use a lookup table to decode the 4 bit values to a larger non-linear range, where they're still 1 apart near zero, but increase at larger increments toward the limits. And/or you could reserve one of the values to toggle a multiplier. Deciding when to use it up to the encoder. With these improvements, you can either achieve better quality or get away with 3 bits per sample instead of 4.
If your device has a non-linear μ-law or A-law ADC, you can get quality comparable to 11-12 bit with 8 bit samples. Or you can probably do it yourself in your decoder. http://en.wikipedia.org/wiki/M-law_algorithm
There might be inexpensive chips out there that already do all this for you, depending on what you're making. I haven't looked into any.
You should try different compression algorithms with either a compression software tool with command line switches or a compression library where you can try out different algorithms.
Use typical data for your application.
Then you know which algorithm is best-fitting for your needs.
I have used zlib in embedded systems for a bootloader that decompresses the application image to RAM on start-up. The licence is nicely permissive, no GPL nonsense. It does make a single malloc call, but in my case I simply replaced this with a stub that returned a pointer to a static block, and a corresponding free() stub. I did this by monitoring its memory allocation usage to get the size right. If your system can support dynamic memory allocation, then it is much simpler.
http://www.zlib.net/