Messages in this thread | | | Date | Tue, 21 Jan 1997 10:36:59 -0800 | From | Gordon Chaffee <> | Subject | Re: Good point of Linux over Windows NT |
| |
David S. Miller wrote: > Kernel level support for async-IO is something that should be at least > thought about. From the UNIX's that I've heard actually do it, they > limit you to one outstanding async-IO request per task/thread. This > seems to suggest it is not a trivial problem to solve at all. > > From what I've heard NT allows numerous (unlimited?) outstanding > async-IO requests to be queued to the system, and programmers love > this. Can someone validate this? It's what I've heard, I want to > know if it is true.
This is true. What NT has is an IRP (I/O request packet) stack. Each new request for I/O gets thrown on the stack. (Actually, it is really a fifo, but they call it a stack.) The system will handle this by default, but the device driver can choose to manage it own IRP queues. When a packet has been processed, you can mark the packet as done. This signals the user level that the packet has been emptied or filled or whatever.
Gordon Chaffee chaffee@home.com
| |