Re: [PATCH v3 01/11] block: make generic_make_request handle arbitrarily sized bios

[Jeff Moyer <jmoyer@redhat.com>]

Ming Lin <mlin@kernel.org> writes:

> On Mon, May 18, 2015 at 9:52 AM, Jeff Moyer <jmoyer@redhat.com> wrote:
>> Ming Lin <mlin@kernel.org> writes:
>>
>>> diff --git a/block/blk-core.c b/block/blk-core.c
>>> index fd154b9..909f317 100644
>>> --- a/block/blk-core.c
>>> +++ b/block/blk-core.c
>>> @@ -617,6 +617,10 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
>>>       if (q->id < 0)
>>>               goto fail_q;
>>>
>>> +     q->bio_split = bioset_create(4, 0);
>>> +     if (!q->bio_split)
>>> +             goto fail_id;
>>> +
>>
>> Arbitrary numbers should be documented.
>
> Kent,
>
> Is there specific reason to choose number 4?
> If no, I may change it to BIO_POOL_SIZE which is 2.

Here's what he had to say last time around:

  On Mon, Nov 25, 2013 at 10:09:21PM -0800, Christoph Hellwig wrote:
  > > +   q->bio_split = bioset_create(4, 0);
  > > +   if (!q->bio_split)
  > > +      goto fail_id;
  > 
  > How did we arrive at a mempool size of 4 to make sure we can always make
  > progress with arbitrarily sized bios?  Shouldn't we document the design
  > decision somewhere?

  It just has to be nonzero to guarantee forward progress - the
  bio_alloc_bioset() rescuer thing I did awhile back guarantees that.

link:  https://lkml.org/lkml/2013/11/26/47

Cheers,
Jeff