Re: Bugs and wishes in memory management area

Mike Jagdis (
Thu, 21 Nov 1996 09:41:22 GMT

>But GFP_ATOMIC allocation could be improved because we could discard
>unmodified pages I think. Correct me if I am wrong.

Yes, try_to_free_page almost but not quite handles no wait requests
suitably (ipc shrinking ignores no wait at least). There are one
or two other stunts we can pull to make DMA requests for multiple
pages more reliable.

I've been working on page_alloc.c and kmalloc.c for a while now
but I got side tracked with the Cyrix stuff which turned out to
be more involved than I thought :-(.


|  Mike Jagdis                  |  Internet:   |
|  Roan Technology Ltd.         |                                      |
|  54A Peach Street, Wokingham  |  Telephone:  +44 118 989 0403        |
|  RG40 1XG, ENGLAND            |  Fax:        +44 118 989 1195        |