Efficient tape I/O, Followup.

[Larry Williamson]

A bit of a followup and a request for more info.

Most of the suggestions that I've received so far are good ideas, but
they have not helped.  I must be doing something else wrong. 

In article <317 at focsys.UUCP> I wrote:
| 
| Streaming tape I/O with 386/ix seems to be rather slow.  The drive
| is not streaming very well.  It spends most of it's time stopping
| and starting.

I received mail from a number of people and there have been a number
of articles posted answering my query. Without exception, everyone
has suggested essentially the same thing, namely increase the size
of the buffer that is being written to the tape. Recommendations on
how best to do this differs from individual to individual.

I've tried most of the suggestions. I used the 'stream' utility
that came with our Bell Tech system. I used the "undocumented"
cpio option '-Cn' (where n is the buffer size to write in bytes).
I've used pdtar, I've piped through dd. The only thing that I've
not tried yet was ...

In article <8513 at alice.UUCP> debra at alice.UUCP (Paul De Bra) writes:
| A solution which also works for other applications is to use "cat":
|	find . -print | cpio -ovc | cat | cat > /dev/rmt0

I've run the system in single user mode, I've run it with 'nice -n'
to give me greater priority, still no better.

A 500k write takes about an hour!

This same hardware works fine on our Microport SV/AT system. I was never
able to use it on the Bell Tech system because the interface board was
not BT's special version.

Any other suggestions??

Larry
-- 
Larry Williamson  -- Focus Systems -- Waterloo, Ontario
                  watmath!focsys!larry  (519) 746-4918