Scsi disks, IDE disks, and MD (software raid) all are block devices, and as
such
fill out a struct file_operations before they call register_blkdev().
ide.c, md.c, and sd.c all register with block_read() and block_write()
functions
for the read and write fields in their file_operations struct.
block_read() and block_write() are in fs/block_dev.c
In block_read(), I see : copy_to_user(buf,offset+(*bhe)->b_data,chars);
In block_write(), I see : copy_from_user(p,buf, chars);
I don't think you've found an 'ide bottleneck'. Maybe you should run
'memperf' with mode 2 (load and copy test) and see what it gets on that
particular machine.
-- Adam Radford Software Engineer 3ware, Inc./* snip */ > bug1 wrote: > > > With the tests below i cant get more than total read speed of 30MB/s > > irrespective of how many drives i read from in parallel, but by using > > hdparm -T simultaneously on two seperate drives i could could get > > 45MB/s, which would indicate an ide bottleneck of 90MB/s. > > /* snip */
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Thu Jun 15 2000 - 21:00:33 EST