Messages in this thread | | | Date | Sun, 21 Mar 1999 11:41:17 -0800 (PST) | From | Linus Torvalds <> | Subject | Re: disk head scheduling |
| |
On Sun, 21 Mar 1999, Arvind Sankar wrote: > > Is this as simple as adding a function ptr to blk_dev_struct, and get_request > calling it if it is non-NULL?
Something on that order. I suspect we should really clean up blk_dev_struct a bit more to contain the device sizes too as a function etc, but basically it is not a lot of complexity, mainly just a lot of small details.
> Another quick Q: attempt_merge() is just done to reduce usage of request > structures, right?
No, it partly reduces request structure pressure, but that's not all it does: the drivers will use the information it provides to do some basic IO handling. Think of it as a poor mans scatter-gather thing for simple devices that don't want to look past a single request.
Linus
- 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/
| |