Re: [Dvdrtools-users] Re: [Fwd: Re: Is my MSI DR8-A2 broken?]

[John]

On Wed, 4 Jan 2006 05:15 am, Bryan J. Smith wrote:
> Svante Signell <address@hidden> wrote:
> > The drive can only be mounted with Master/Slave straps set
> > or in Cable Select. Are you proposing Cable Select here??
> > I don't think so!
>
> Now you're nitpicking.  ;->  I mean _never_ configure the
> drive for slave.  Nearly all new ATA and ATAPI devices come
> configured with a "slave" jumper option for legacy
> compatibility, but default to a single device on its own
> channel.  In legacy terms, this is "master" although there is
> a difference between a single device and master device, but
> most devices can detect if there is a slave on the same
> channel.

I loathe these retarded drives that have a different jumper setting for
"single" and "master". Stupid things, but its still common.

As far as having a master and slave both using DMA on the same 
IDE bus... my opinion (without having read ATA specs) is that it 
*SHOULD* not be dangerous.

But, my brother has had horrific disk corruption problems from a 
bad VIA ide controller, under linux. And we have pored through the 
ide driver code put out by VIA and it is(or at least was) absolutely 
APALLING. Those VIA guys couldnt code their way out of a nutsack.

So, as with many of these things, it depends on hardware and software. 
Some Nvidia Nforce controllers have also had BAD corruption issues 
(caused more by driver software than hardware, again, i believe) forcing 
users to run in PIO mode to avoid corruption when they have 2 devices 
on the same ide bus.

I believe ide corruption issues these days are more dependant 
on the ide controller and software than the hard disks/burners, 
though there is no doubt they could also cause the same issues 
if they dont behave properly. It would seem to be a simpler job to design 
one device that fits the ATA spec, than it is to design an ide controller 
and write the drivers for it.

After what my bro has been through i will only ever use a 
decent intel ide controller. I just wouldnt touch anything else.
Not when i am a slack bastard when it comes to backing up,
life is too short to waste your time with computers that corrupt 
your work, which they can, and do...

Anyway as i understand it, the difference between a master and 
a slave is that the master can take control of the bus whenever it 
wants, and the slave has to release it within certain time limit or be 
forced off.

Hence good for your burner to be master on on 1 IDE bus and 
the hard disk you burn from, to be master on the other bus -that 
way data can go into memory on one bus while it goes out on the 
other. If you have burn from/to devices on the same bus, the bus must 
transfer to memory, allow slave to take control, then transfer out to 
slave. The device being read from cannot burst any data into 
memory while the slave is transferring data, which is a recipe for 
disaster when burning DVDs at high speed these days, especially 
when your hard disk is nearly full, and your files are fragmented or
small (and the hard disk has to work hard to pick up bits from 
all over the place)

>
> > Can you explain the difference with file transfer between
> > /dev/hda and /dev/hdb using DMA with writing a file on
> > dev/hdc to a burner at /dev/hdd using DMA then!
>
> No difference if they are on the _same_ channel.  They cannot
> handle transfers simultaneously without resetting the bus as
> each takes control.

i think the point Sven is making is that hda and hdb ARE on 
the same channel, and so are hdc and hdd. So hes asking 
whats the difference between transferring between 2 hard disks
and between a hard disk and a burner.

I would say the answer is simply that you wont ever get a 
coaster when transferring between 2 hard disks. If the 
destination drive has nothing to write at any given time, it will 
just wait for the other drive/OS to give it some data to write. 

Plus, dvd burners burn at a very respectable speed these 
days, but have crappy little buffers, just 2 MB often, its pathetic.
So if the burner is a slave on the same channel as the device 
being read from, it is going to have to take control of the bus 
at much more frequent intervals than a hard disk with an 8 MB 
buffer. It doesnt work well...

The bandwidth of an ide bus *SHOULD* easily be large enough to 
burn from a hard disk on the same bus as the burner, as long as 
the hard disk has a large enough buffer in main memory that small 
small sections with bad file fragmentation doesnt cause the system 
to run out of data to give to the burner. But for some reason,  it 
doesnt. The overheads associated with DMA transfer of so many 
little 2 MB chunks to the burner must leave the hard disks 
unable to empty a full buffer into memory at times, and thus lowers 
their performance enough to cause severe problems.

It beats me why burning programs dont allocate more memory to 
buffer incoming data from the hard drives... it would have to help..
everyone knows hard drive speed can drop extremely low when 
reading large numbers of small files (or fragments). I find this to 
be the biggest problem with burning dvds, but LG drives seem 
to cope extremely well with buffer underruns, so much less of a 
problem these days


> If they are on different channels, say /dev/hda to /dev/hdc,
> then the bus is setup *1* time (typically at initial boot)
> and the drives copy to/from memory as transfers occur.
>
> That's why it's much, much faster with *1* device per
> channel.