[Drbd-dev] inter-arch PAGE_SIZE problem
philipp.reisner at linbit.com
Mon Sep 27 16:04:18 CEST 2004
Am Freitag, 24. September 2004 14:37 schrieb Lars Ellenberg:
> int drbd_make_request_26(request_queue_t *q, struct bio *bio)
> * what we "blindly" assume:
> D_ASSERT(bio->bi_size > 0);
> D_ASSERT( (bio->bi_size & 0x1ff) == 0);
> D_ASSERT(bio->bi_size <= PAGE_SIZE);
> D_ASSERT(bio->bi_vcnt == 1);
> D_ASSERT(bio->bi_idx == 0);
> we are going to send PAGE_SIZE requests over the wire,
> but the other side may have a different PAGE_SIZE...
> // mirrored write
> int receive_Data(drbd_dev *mdev,Drbd_Header* h)
> /* I expect a block to be a multiple of 512 byte, and
> * no more than 4K (PAGE_SIZE). is this too restrictive?
> ERR_IF(data_size == 0) return FALSE;
> ERR_IF(data_size & 0x1ff) return FALSE;
> ERR_IF(data_size > PAGE_SIZE) return FALSE;
> we need to agree to use fixed 4K, I guess. optionally negotiate a
> higher "drbd_page_size" during the initial connection handshake.
Right. we should consider this. But I think a general high performace
solution is not neccesary, since cluster of machines with
different PAGE_SIZE are of academic interest only. (IMHO)
I think for drbd-0.8 it is sufficient to inform the user about the fact...
> does that all make sense?
More information about the drbd-dev