Re: Thread implementations...
Larry McVoy (lm@bitmover.com)
Fri, 26 Jun 1998 08:36:51 -0700
: A couple of reasons, access patterns like:
:
: read(from,buf,len);
: write(from,buf,len);
:
: can me optimized to DMA to memory, twiddle some pages for the process, and
: avoid the costly copy to/from buffer cache that presently limits disk IO
: throughput (preserving the buffer cache using COW).
SGI has an open flag, O_DIRECT, which says "do the DMA right into my pages,
skipping the buffer cache completely". Using this flag, SGI has demonstrated
file system I/O of up to 7Gbytes/second (obvioulsy to/from a striped logical
partition).
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu