Hi, [EMAIL PROTECTED] (2006-01-20 at 1649.29 +0100): > > A FIFO allows you to survive a period with low input data rates. > > If everything goes faster, you need to increase the size of the FIFO > > proportional to the size improvements. > But if *everything* goes faster, why not that period > with low data rates too ?
As someone already mentioned, disk max speed has gone up, but min speed has progressed slowly. Top SCSI ones are 15K RPM (normally 10K), average seek of 3-5 ms and out of order capability, while modern (S)ATA are 7.2K, seek of 8-10 ms and in most cases no out of order (if you search a bit, you can get SATA with specs that look a lot like mid level SCSI... and the price too). So if the data is spread due multiple files or one single but fragmented file... the disk is going to serve data at few MB/s at best, even if for linear reads it can do above 50 MB/s. Add that DVD recorders have 1-2 MB of cache, when in the past you could get CD ones with 2 and even 4, and things start to match. The output has to be high speed with low acceleration, but the input is not warrantied at all... you have to put a cushion, maybe bigger than you would expect, as the unbalance seems to be higher. After all this rant, I think the issue could be resumed in that you have to use the minimum point of view, not the maximum. Same way nobody put over the table that a SATA 150 disk is going to be clearly faster than the same mechanics using ATA 100. Look at the balance: disk minimum speed due mechanics and file system vs writer minimum consumption speed required and avaliable cache... in that sense, things have not gone so good. GSR -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
