Messages in this thread | | | Date | Thu, 21 Dec 2023 13:18:33 +0000 | Subject | Re: [PATCH v2 00/16] block atomic writes | From | John Garry <> |
| |
On 21/12/2023 12:57, Christoph Hellwig wrote: > On Thu, Dec 21, 2023 at 12:48:24PM +0000, John Garry wrote: >>>> - ubuf / iovecs need to be PAGE-aligned >>>> - each iovec needs to be length of multiple of atomic_write_unit_min. If >>>> total length > PAGE_SIZE, each iovec also needs to be a multiple of >>>> PAGE_SIZE. >>>> >>>> I'd rather something simpler. Maybe it's ok. >>> If we decided to not support atomic writes on anything setting a virt >>> boundary we don't have to care about the alignment of each vector, >> >> ok, I think that alignment is not so important, but we still need to >> consider a minimum length per iovec, such that we will always be able to >> fit a write of length atomic_write_unit_max in a bio. > > I don't think you man a minim length per iovec for that, but a maximum > number of iovecs instead.
That would make sense, but I was thinking that if the request queue has a limit on segments then we would need to specify a iovec min length.
> For SGL-capable devices that would be > BIO_MAX_VECS, otherwise 1.
ok, but we would need to advertise that or whatever segment limit. A statx field just for that seems a bit inefficient in terms of space.
| |