Another item that's somewhat confusing in the code is that
generic_readpage() is FREEING the page by setting PG_free_after in the
page->flags then calling __free_page() in after_unlock_page() which
would seem to indicate that right after going through the overhead of
writing data into the page, we free it after the IO completes (???).
Doesn't the page with the data we just copied get cached in the page
cache, or is there yet another copy operation somewhere else?
What's the deal here?
Jeff
-
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/