home *** CD-ROM | disk | FTP | other *** search
-
- Hard disc speed test
- --------------------
-
- This program is © David Holden 1993,1994. Permission is given for it to
- be freely used and copied by private individuals for their own use.
-
- Distribution by any commercial organisation or any commercial use
- or use to demonstrate or promote any product, whether for profit or
- otherwise, without prior permission, is absolutely forbidden.
-
-
- This is a very simple program for testing the speed of a hard disc
- drive. It can be used to test any type of discs, even floppies, on any
- filing system. The only requirements are that it must be a standard
- Filecore filing system and respond to normal OS_File commands. It was
- originally written entirely for my own use and so isn't particularly
- fancy or sophisticated. I have looked at lots of hard disc speed
- programs and this is the only one I have seen where the test results
- obtained correspond with the 'subjective' feel I get from the drive when
- I use it. In recent years I have tried many different types of drive and
- interface and I have never yet found one which gave test results which
- were at odds with the 'feel' of the drive when I use it. In fact I never
- use this test first, I try the drive, form an opinion and THEN test it,
- as this way my subjective opinion can't be influenced by the test.
-
- This program, unlike most of those supplied by hard disc distributors,
- is NOT designed to show up the best points of a particular drive or
- interface. I am not interested in phony Mb/sec statistics because they
- are absolutely meaningless. (When was the last time you sat in front of
- a Mode 0 screen swapping 20Md chunks of data around?). The tests used
- are intended to reflect the way that drives are used in the real world,
- and to return results which, although perhaps not meaningful in absolute
- terms, can be directly compared with the results obtained when the
- program is used with another drive or interface to give a comparison
- between the performance you will experience when you put them to work
- for normal everyday use.
-
- Using HD Speed
- --------------
- To use the program just copy it to the drive you want to test and
- double-click on the icon. It will then run as a single-tasking utility
- displaying results in a text window. It does not poll the Wimp because
- this would upset the results. Similarly it uses whatever screen mode you
- have chosen, thus the results will be repeated when you use the drive
- 'for real'.
-
- Because you copy it to the drive you want to try it automaticlly 'knows'
- which drive and filing system to test. Obviously this drive must have
- enough free space for the test files to be created.
-
- The tests used are divided into two sections, random access and block
- load/save.
-
-
- Random access tests
- -------------------
- First a large test file is created. By default this is 8Mb but you can
- easily change it as it is set by the variable 'rnd_file%' at the start
- of the program. The first test reads 50K sequentially from this file,
- the next test writes 50K sequentially. This should give a fairly fast
- result. The next two tests do the same with 500K. These sizes were
- chosen because most cached drives have at least a 64K cache so the first
- test will use this but none have a chache as large as 500K so the drive
- will need to read directly from the disc frequently. Unless you have a
- very small drive the head should only need to step once or twice during
- this test so step speed should not be a significant factor.
-
- The next four tests are much more demanding. These uses the same random
- access file but read and write 1,000 bytes to anywhere in the file at
- random. (In fact the random number generator is 'seeded' so that the
- same random sequence is generated each time). The first pair just
- write to the first 50K so not much track switching should be needed
- and in fact a well managed cache could 'field' much of this. The second
- test reads and writes over the whole file. 1,000 operations might not
- sound like a lot, but of you have an 8Mb file the disc head will have to
- do a LOT of rushing about as it zooms from one end of the file to the
- other. It is a superb trial of drive 'step' and 'seek' speed and is
- perhaps the most demanding test used. A large modern drive should
- perform well here but if you have an old ST506 drive go and put the
- kettle on first - it really will take ages!
-
- Block load/save
- ---------------
- These use standard OS_File commands to load and save a block of memory.
- The first two test load and save a 50Kb file. This isn't a very large
- file but it about the average file used by most programs. The next two
- test again load and save but this time the block of memory is very much
- larger. By deafult this is 2Mb but it is set by the variable
- 'blockfile%' at the start of the program so you can easily change it.
- Obvioulsy you will need at least 4Mb of RAM to retain it at this size,
- so if you have only 2Mb I suggest you change its value to 1024
-
- The next three tests are a variation on this theme. The first
- alternately loads and saves a 50K block, the second a 512K block and the
- third alternately loads and saves the large block file.
-
- The reason for the choice of these three sizes are that 50K will
- probably be held in the cache of a cached drive as many modern drives
- have a 64K cache. Since 50K is a reasonable average file size on a
- Archimedes it gives a good indication of repeatedly loading/saving a wp
- or program source file and hence the 'hold-up time' you are likely to
- experience if you have some sort of 'automatic save' system. 512K
- certainly won't be held in the cache so this is a good test of loading
- and saving larger DTP, graphics, spreadsheet etc files.
-
- Results of each test are shown as the total time taken in hundredths of
- a second. After this is shown the percentage speed increase over a
- 'baseline' which was derived from carrying out the same tests on an A400
- series machine fitted with the standard Acorn interface and a 20 Mb
- Western Digital 65ms ST506 drive. Obviously if you change the size of
- the test files the percentages will be innacurate.
-
- Saving the results
- ------------------
- When the tests are complete you will be prompted for a filename. Type a
- suitable name and press RETURN. The results will then be saved in the
- sub-directory 'Results' of the application directory. DON'T FORGET that
- they will be saved in the actual program you have RUN. If you want to
- preserve them youwill have to copy the file to you main disc. I know
- this sin't 100% satisfactory but it's very simple and if you are
- carrying out a lot of tests on different drives you will probably have a
- copy of the program on a floppy disc anyway, so all you need to do is to
- copy the results to this after each test.
-
- General
- -------
- You must obvioulsy have enough space on the drive to hold the temporary
- file. In order to get the best results you must ensure that this file is
- contiguous, ie. not fragmented. If the drive you are testing has been in
- use for some time it could well be that although it might have 20Mb of
- free space theis is all in small chunks. When you create the test file
- it could be split up into several pieces spread about all over the disc
- and you will get extremely disapointing results, especially to the large
- file random access tests. You should therefore Compact the disc first so
- that all the empty space is in a contiguous block. If the interface
- doesn't support a proper Compact where the data is physically moved then
- you might get poor results, but these will reflect the real state which
- will exist when your drive gets full.
-
- This program is written entirely in Basic and I make no claims that is
- particularly optimised for speed. This isn't important because it is
- intended for comparison and not to give artificially optimised results
- to promote a product. The 'program' overhead will be only a very small
- part of the time taken and will, in any event, be the same whatever
- drive or interface you are using, so it doesn't really matter. Using
- Basic means that you can easily change any of the values used if you
- wish to. For the same reason although the 'working' version is
- 'crunched' you will also find a version called 'Source' which isn't.
- The crunching has been done is such a way thst you can load it into an
- editor and change it without problems.
-
- While you may alter the program for your own personal use you MUST NOT
- distribute any altered version. If you wish to to so you should place a
- copy of your version of the program in a sub-directory of the
- application directory with a text file explaining the changes you have
- made so that users can choose your version if they wish. Please also
- send me a copy as I certainly don;t claim that the program is definitive
- and will add any worthwhile routines to the main program.
-
-
- David Holden
- 39 Knighton Park Road
- Sydenham
- London SE26 5RN
-