From: gt8134b@prism.gatech.EDU (Howlin' Bob) Subject: Re: SCSI Performance (Yet Again) Date: 24 Aug 1993 16:03:43 GMT
muts@compi.hobby.nl (Peter Mutsaers) writes:
> JH> Again, on my ST, there was a program that bypassed the
> JH> filesystem completely to test raw disk i/o, and somehow they
>Should not be hard to write. Something like
> buf=malloc(16*1024*1024);
> fd=open("/dev/hda",O_RDWR);
Nope. All block devices under Linux are buffered.