news@daver.bungi.com (09/23/90)
An addition thought I forgot to include in my previous message today. >> By the way, the hold-off at least wrt tape reads, appears at the >> very beginning of each 'datain' phase and during streaming breaks. > I would have hoped that the tape would only interrupt (via scsi) when the > data was 'really' ready to be read. Is this an embedded controller type with > a reasonable local buffer or a 'dumb' external controller? Standing back, its not clear to me at the moment that efficient use of interrupts will in this instance increase disk-to-tape or tape-to-disk throughput under Minix. With or without interrupts, the FS process will remain blocked until the device driver task completes. Of course, avoiding prolonged assertion of /nrdy or busy waits by prudent use of interrupts will permit other scheduled processes to run in the mean time. best regards, johnc --