Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1674941

Re: [PATCH v2 00/51] block: support multipage bvec

Show all headers | View raw

On 06/26/2017 06:09 AM, Ming Lei wrote:
> Hi,
> 
> This patchset brings multipage bvec into block layer:
> 
> 1) what is multipage bvec?
> 
> Multipage bvecs means that one 'struct bio_bvec' can hold
> multiple pages which are physically contiguous instead
> of one single page used in linux kernel for long time.
> 
> 2) why is multipage bvec introduced?
> 
> Kent proposed the idea[1] first. 
> 
> As system's RAM becomes much bigger than before, and 
> at the same time huge page, transparent huge page and
> memory compaction are widely used, it is a bit easy now
> to see physically contiguous pages from fs in I/O.
> On the other hand, from block layer's view, it isn't
> necessary to store intermediate pages into bvec, and
> it is enough to just store the physicallly contiguous
> 'segment' in each io vector.
> 
> Also huge pages are being brought to filesystem and swap
> [2][6], we can do IO on a hugepage each time[3], which
> requires that one bio can transfer at least one huge page
> one time. Turns out it isn't flexiable to change BIO_MAX_PAGES
> simply[3][5]. Multipage bvec can fit in this case very well.
> 
> With multipage bvec:
> 
> - segment handling in block layer can be improved much
> in future since it should be quite easy to convert
> multipage bvec into segment easily. For example, we might 
> just store segment in each bvec directly in future.
> 
> - bio size can be increased and it should improve some
> high-bandwidth IO case in theory[4].
> 
> - Inside block layer, both bio splitting and sg map can
> become more efficient than before by just traversing the
> physically contiguous 'segment' instead of each page.
> 
> - there is opportunity in future to improve memory footprint
> of bvecs. 
> 
> 3) how is multipage bvec implemented in this patchset?
> 
> The 1st 18 patches comment on some special cases and deal with
> some special cases of direct access to bvec table.
> 
> The 2nd part(19~29) implements multipage bvec in block layer:
> 
> 	- put all tricks into bvec/bio/rq iterators, and as far as
> 	drivers and fs use these standard iterators, they are happy
> 	with multipage bvec
> 
> 	- use multipage bvec to split bio and map sg
> 
> 	- bio_for_each_segment_all() changes
> 	this helper pass pointer of each bvec directly to user, and
> 	it has to be changed. Two new helpers(bio_for_each_segment_all_sp()
> 	and bio_for_each_segment_all_mp()) are introduced. 
> 
> The 3rd part(30~49) convert current users of bio_for_each_segment_all()
> to bio_for_each_segment_all_sp()/bio_for_each_segment_all_mp().
> 
> The last part(50~51) enables multipage bvec.
> 
> These patches can be found in the following git tree:
> 
> 	https://github.com/ming1/linux/commits/mp-bvec-1.4-v4.12-rc
> 
> Thanks Christoph for looking at the early version and providing
> very good suggestions, such as: introduce bio_init_with_vec_table(),
> remove another unnecessary helpers for cleanup and so on.
> 
> Any comments are welcome!

I'll take some time to review this over the next week or so. In any
case, it's a little late to stuff into 4.13 and get a decent amount
of exposure and testing on it. A 4.14 target for this would be the
way to go, imho.


-- 
Jens Axboe

Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

[PATCH v2 00/51] block: support multipage bvec Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:20 +0200
  [PATCH v2 29/51] block: bio: introduce single/multi page version of bio_for_each_segment_all() Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:20 +0200
  [PATCH v2 43/51] xfs: convert to bio_for_each_segment_all_sp() Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 22/51] block: introduce bio_for_each_segment_mp() Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 18/51] block: bounce: don't access bio->bi_io_vec in copy_to_high_bio_irq Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 20/51] block: introduce multipage/single page bvec helpers Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 51/51] block: bio: pass segments to bio if bio_add_page() is bypassed Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 32/51] btrfs: use bvec_get_last_page to get bio's last page Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 41/51] fs/iomap: convert to bio_for_each_segment_all_sp() Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 14/51] btrfs: avoid to access bvec table directly for a cloned bio Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
    Re: [PATCH v2 14/51] btrfs: avoid to access bvec table directly for  a cloned bio Liu Bo <bo.li.liu@oracle.com> - 2017-06-26 20:10 +0200
  [PATCH v2 46/51] exofs: convert to bio_for_each_segment_all_sp() Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 49/51] fs/direct-io: convert to bio_for_each_segment_all_sp() Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 39/51] fs/mpage: convert to bio_for_each_segment_all_sp() Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 40/51] fs/block: convert to bio_for_each_segment_all_sp() Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 37/51] dm-crypt: don't clear bvec->bv_page in crypt_free_buffer_pages() Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 47/51] fs: crypto: convert to bio_for_each_segment_all_sp() Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 44/51] gfs2: convert to bio_for_each_segment_all_sp() Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 45/51] f2fs: convert to bio_for_each_segment_all_sp() Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 50/51] block: enable multipage bvecs Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 48/51] fs/btrfs: convert to bio_for_each_segment_all_sp() Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 33/51] block: deal with dirtying pages for multipage bvec Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 36/51] md: raid1: convert to bio_for_each_segment_all_sp() Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  [PATCH v2 42/51] ext4: convert to bio_for_each_segment_all_sp() Ming Lei <ming.lei@redhat.com> - 2017-06-26 14:30 +0200
  Re: [PATCH v2 00/51] block: support multipage bvec David Sterba <dsterba@suse.cz> - 2017-06-26 18:50 +0200
  Re: [PATCH v2 00/51] block: support multipage bvec Jens Axboe <axboe@kernel.dk> - 2017-06-26 18:50 +0200

csiph-web