Re: [PATCH v20 02/12] Add infrastructure for copy offload in block and request layer.

[Nitesh Shetty]

On 22/05/24 11:05AM, Bart Van Assche wrote:
> On 5/20/24 03:20, Nitesh Shetty wrote:
> > We add two new opcode REQ_OP_COPY_DST, REQ_OP_COPY_SRC.
> > Since copy is a composite operation involving src and dst sectors/lba,
> > each needs to be represented by a separate bio to make it compatible
> > with device mapper.
> > We expect caller to take a plug and send bio with destination information,
> > followed by bio with source information.
> > Once the dst bio arrives we form a request and wait for source
> > bio. Upon arrival of source bio we merge these two bio's and send
> > corresponding request down to device driver.
> > Merging non copy offload bio is avoided by checking for copy specific
> > opcodes in merge function.
>
> Plugs are per task. Can the following happen?
We rely on per-context plugging to avoid this.
> * Task A calls blk_start_plug()
> * Task B calls blk_start_plug()
> * Task A submits a REQ_OP_COPY_DST bio and a REQ_OP_COPY_SRC bio.
Lets say this forms request A and stored in plug A
> * Task B submits a REQ_OP_COPY_DST bio and a REQ_OP_COPY_SRC bio.
Lets say this forms request B and stored in plug B
> * Task A calls blk_finish_plug()
> * Task B calls blk_finish_plug()
> * The REQ_OP_COPY_DST bio from task A and the REQ_OP_COPY_SRC bio from
>  task B are combined into a single request.
Here task A picks plug A and hence request A
> * The REQ_OP_COPY_DST bio from task B and the REQ_OP_COPY_SRC bio from
>  task A are combined into a single request.
same as above, request B

So we expect this case not to happen.

Thank you,
Nitesh Shetty