Messages in this thread | | | Date | Tue, 13 Jul 1999 20:36:13 +0200 | From | Jamie Lokier <> | Subject | Re: [RFC] - Some notions that I would like comments on |
| |
cd_smith@ou.edu wrote: > Speculative I/O would appear to be a blocking I/O call, but as > soon as it queued the I/O request, it would return. The result page would > be marked as unreadable and unwriteable, and the actual I/O blocking would > be done on a page fault.
You can do this by calling mmap() and then starting a thread to access a byte from each page sequentially.
Or you can do it by calling mmap() and then starting a thread to read() a byte at inter-page offsets. This is probably faster because the kernel does readahead.
If you want exactly the same results as read, use MAP_PRIVATE and have the reader thread read-then-write, to make local copies of the pages.
disclaimer: I've never done this.
-- Jamie
- 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/
| |