Linux-RDMA Archive on lore.kernel.org
 help / color / Atom feed
From: Roman Penyaev <r.peniaev@gmail.com>
To: Bart Van Assche <bvanassche@acm.org>
Cc: Danil Kipnis <danil.kipnis@cloud.ionos.com>,
	Jack Wang <jinpuwang@gmail.com>,
	linux-block@vger.kernel.org, linux-rdma@vger.kernel.org,
	Jens Axboe <axboe@kernel.dk>,
	Christoph Hellwig <hch@infradead.org>,
	Sagi Grimberg <sagi@grimberg.me>,
	Jason Gunthorpe <jgg@mellanox.com>,
	Doug Ledford <dledford@redhat.com>,
	rpenyaev@suse.de, Jack Wang <jinpu.wang@cloud.ionos.com>
Subject: Re: [PATCH v4 17/25] ibnbd: client: main functionality
Date: Fri, 27 Sep 2019 10:52:37 +0200
Message-ID: <CACZ9PQU8=4DaSAUQ7czKdcWio2H5HB1ro-pXaY2VP9PhgTxk7g@mail.gmail.com> (raw)
In-Reply-To: <e2056b1d-b428-18c7-8e22-2f37b91917c8@acm.org>

On Thu, Sep 26, 2019 at 5:01 PM Bart Van Assche <bvanassche@acm.org> wrote:
>
> On 9/26/19 2:55 AM, Roman Penyaev wrote:
> > As I remember correctly I could not reuse the whole machinery with those
> > restarts from block core because shared tags are shared only between
> > hardware queues, i.e. different hardware queues share different tags sets.
> > IBTRS has many hardware queues (independent RDMA connections) but only one
> > tags set, which is equally shared between block devices.  What I dreamed
> > about is something like BLK_MQ_F_TAG_GLOBALLY_SHARED support in block
> > layer.
>
> A patch series that adds support for sharing tag sets across hardware
> queues is pending. See also "[PATCH V3 0/8] blk-mq & scsi: fix reply
> queue selection and improve host wide tagset"
> (https://lore.kernel.org/linux-block/20180227100750.32299-1-ming.lei@redhat.com/).
> Would that patch series allow to remove the queue management code from
> ibnbd?

Hi Bart,

No, it seems this thingy is a bit different.  According to my
understanding patches 3 and 4 from this patchset do the
following: 1# split equally the whole queue depth on number
of hardware queues and 2# return tag number which is unique
host-wide (more or less similar to unique_tag, right?).

2# is not needed for ibtrs, and 1# can be easy done by dividing
queue_depth on number of hw queues on tag set allocation, e.g.
something like the following:

    ...
    tags->nr_hw_queues = num_online_cpus();
    tags->queue_depth  = sess->queue_deph / tags->nr_hw_queues;

    blk_mq_alloc_tag_set(tags);


And this trick won't work out for the performance.  ibtrs client
has a single resource: set of buffer chunks received from a
server side.  And these buffers should be dynamically distributed
between IO producers according to the load.  Having a hard split
of the whole queue depth between hw queues we can forget about a
dynamic load distribution, here is an example:

   - say server shares 1024 buffer chunks for a session (do not
     remember what is the actual number).

   - 1024 buffers are equally divided between hw queues, let's
     say 64 (number of cpus), so each queue is 16 requests depth.

   - only several CPUs produce IO, and instead of occupying the
     whole "bandwidth" of a session, i.e. 1024 buffer chunks,
     we limit ourselves to a small queue depth of an each hw
     queue.

And performance drops significantly when number of IO producers
is smaller than number of hw queues (CPUs), and it can be easily
tested and proved.

So for this particular ibtrs case tags should be globally shared,
and seems (unfortunately) there is no any other similar requirements
for other block devices.

--
Roman

  reply index

Thread overview: 123+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20190620150337.7847-1-jinpuwang@gmail.com>
2019-06-20 15:03 ` [PATCH v4 01/25] sysfs: export sysfs_remove_file_self() Jack Wang
2019-09-23 17:21   ` Bart Van Assche
2019-09-25  9:30     ` Danil Kipnis
2019-07-09  9:55 ` [PATCH v4 00/25] InfiniBand Transport (IBTRS) and Network Block Device (IBNBD) Danil Kipnis
2019-07-09 11:00   ` Leon Romanovsky
2019-07-09 11:17     ` Greg KH
2019-07-09 11:57       ` Jinpu Wang
2019-07-09 13:32       ` Leon Romanovsky
2019-07-09 15:39       ` Bart Van Assche
2019-07-09 11:37     ` Jinpu Wang
2019-07-09 12:06       ` Jason Gunthorpe
2019-07-09 13:15         ` Jinpu Wang
2019-07-09 13:19           ` Jason Gunthorpe
2019-07-09 14:17             ` Jinpu Wang
2019-07-09 21:27             ` Sagi Grimberg
2019-07-19 13:12               ` Danil Kipnis
2019-07-10 14:55     ` Danil Kipnis
2019-07-09 12:04   ` Jason Gunthorpe
2019-07-09 19:45   ` Sagi Grimberg
2019-07-10 13:55     ` Jason Gunthorpe
2019-07-10 16:25       ` Sagi Grimberg
2019-07-10 17:25         ` Jason Gunthorpe
2019-07-10 19:11           ` Sagi Grimberg
2019-07-11  7:27             ` Danil Kipnis
2019-07-11  8:54     ` Danil Kipnis
2019-07-12  0:22       ` Sagi Grimberg
2019-07-12  7:57         ` Jinpu Wang
2019-07-12 19:40           ` Sagi Grimberg
2019-07-15 11:21             ` Jinpu Wang
2019-07-12 10:58         ` Danil Kipnis
     [not found] ` <20190620150337.7847-26-jinpuwang@gmail.com>
2019-07-09 15:10   ` [PATCH v4 25/25] MAINTAINERS: Add maintainer for IBNBD/IBTRS modules Leon Romanovsky
2019-07-09 15:18     ` Jinpu Wang
2019-07-09 15:51       ` Leon Romanovsky
2019-09-13 23:56   ` Bart Van Assche
2019-09-19 10:30     ` Jinpu Wang
     [not found] ` <20190620150337.7847-16-jinpuwang@gmail.com>
2019-09-13 22:10   ` [PATCH v4 15/25] ibnbd: private headers with IBNBD protocol structs and helpers Bart Van Assche
2019-09-15 14:30     ` Jinpu Wang
2019-09-16  5:27       ` Leon Romanovsky
2019-09-16 13:45         ` Bart Van Assche
2019-09-17 15:41           ` Leon Romanovsky
2019-09-17 15:52             ` Jinpu Wang
2019-09-16  7:08       ` Danil Kipnis
2019-09-16 14:57       ` Jinpu Wang
2019-09-16 17:25         ` Bart Van Assche
2019-09-17 12:27           ` Jinpu Wang
2019-09-16 15:39       ` Jinpu Wang
2019-09-18 15:26         ` Bart Van Assche
2019-09-18 16:11           ` Jinpu Wang
     [not found] ` <20190620150337.7847-17-jinpuwang@gmail.com>
2019-09-13 22:25   ` [PATCH v4 16/25] ibnbd: client: private header with client structs and functions Bart Van Assche
2019-09-17 16:36     ` Jinpu Wang
2019-09-25 23:43       ` Danil Kipnis
2019-09-26 10:00         ` Jinpu Wang
     [not found] ` <20190620150337.7847-18-jinpuwang@gmail.com>
2019-09-13 23:46   ` [PATCH v4 17/25] ibnbd: client: main functionality Bart Van Assche
2019-09-16 14:17     ` Danil Kipnis
2019-09-16 16:46       ` Bart Van Assche
2019-09-17 11:39         ` Danil Kipnis
2019-09-18  7:14           ` Danil Kipnis
2019-09-18 15:47             ` Bart Van Assche
2019-09-20  8:29               ` Danil Kipnis
2019-09-25 22:26               ` Danil Kipnis
2019-09-26  9:55                 ` Roman Penyaev
2019-09-26 15:01                   ` Bart Van Assche
2019-09-27  8:52                     ` Roman Penyaev [this message]
2019-09-27  9:32                       ` Danil Kipnis
2019-09-27 12:18                         ` Danil Kipnis
2019-09-27 16:37                       ` Bart Van Assche
2019-09-27 16:50                         ` Roman Penyaev
2019-09-27 17:16                           ` Bart Van Assche
2019-09-17 13:09     ` Jinpu Wang
2019-09-17 16:46       ` Bart Van Assche
2019-09-18 12:02         ` Jinpu Wang
2019-09-18 16:05     ` Jinpu Wang
2019-09-14  0:00   ` Bart Van Assche
     [not found] ` <20190620150337.7847-25-jinpuwang@gmail.com>
2019-09-13 23:58   ` [PATCH v4 24/25] ibnbd: a bit of documentation Bart Van Assche
2019-09-18 12:22     ` Jinpu Wang
     [not found] ` <20190620150337.7847-19-jinpuwang@gmail.com>
2019-09-18 16:28   ` [PATCH v4 18/25] ibnbd: client: sysfs interface functions Bart Van Assche
2019-09-19 15:55     ` Jinpu Wang
     [not found] ` <20190620150337.7847-21-jinpuwang@gmail.com>
2019-09-18 17:41   ` [PATCH v4 20/25] ibnbd: server: main functionality Bart Van Assche
2019-09-20  7:36     ` Danil Kipnis
2019-09-20 15:42       ` Bart Van Assche
2019-09-23 15:19         ` Danil Kipnis
     [not found] ` <20190620150337.7847-22-jinpuwang@gmail.com>
2019-09-18 21:46   ` [PATCH v4 21/25] ibnbd: server: functionality for IO submission to file or block dev Bart Van Assche
2019-09-26 14:04     ` Jinpu Wang
2019-09-26 15:11       ` Bart Van Assche
2019-09-26 15:25         ` Danil Kipnis
2019-09-26 15:29           ` Bart Van Assche
2019-09-26 15:38             ` Danil Kipnis
2019-09-26 15:42               ` Jinpu Wang
     [not found] ` <20190620150337.7847-3-jinpuwang@gmail.com>
2019-09-23 17:44   ` [PATCH v4 02/25] ibtrs: public interface header to establish RDMA connections Bart Van Assche
2019-09-25 10:20     ` Danil Kipnis
2019-09-25 15:38       ` Bart Van Assche
     [not found] ` <20190620150337.7847-7-jinpuwang@gmail.com>
2019-09-23 21:51   ` [PATCH v4 06/25] ibtrs: client: main functionality Bart Van Assche
2019-09-25 17:36     ` Danil Kipnis
2019-09-25 18:55       ` Bart Van Assche
2019-09-25 20:50         ` Danil Kipnis
2019-09-25 21:08           ` Bart Van Assche
2019-09-25 21:16             ` Bart Van Assche
2019-09-25 22:53             ` Danil Kipnis
2019-09-25 23:21               ` Bart Van Assche
2019-09-26  9:16                 ` Danil Kipnis
     [not found] ` <20190620150337.7847-4-jinpuwang@gmail.com>
2019-09-23 22:50   ` [PATCH v4 03/25] ibtrs: private headers with IBTRS protocol structs and helpers Bart Van Assche
2019-09-25 21:45     ` Danil Kipnis
2019-09-25 21:57       ` Bart Van Assche
2019-09-27  8:56     ` Jinpu Wang
     [not found] ` <20190620150337.7847-5-jinpuwang@gmail.com>
2019-09-23 23:03   ` [PATCH v4 04/25] ibtrs: core: lib functions shared between client and server modules Bart Van Assche
2019-09-27 10:13     ` Jinpu Wang
     [not found] ` <20190620150337.7847-6-jinpuwang@gmail.com>
2019-09-23 23:05   ` [PATCH v4 05/25] ibtrs: client: private header with client structs and functions Bart Van Assche
2019-09-27 10:18     ` Jinpu Wang
     [not found] ` <20190620150337.7847-8-jinpuwang@gmail.com>
2019-09-23 23:15   ` [PATCH v4 07/25] ibtrs: client: statistics functions Bart Van Assche
2019-09-27 12:00     ` Jinpu Wang
     [not found] ` <20190620150337.7847-10-jinpuwang@gmail.com>
2019-09-23 23:21   ` [PATCH v4 09/25] ibtrs: server: private header with server structs and functions Bart Van Assche
2019-09-27 12:04     ` Jinpu Wang
     [not found] ` <20190620150337.7847-11-jinpuwang@gmail.com>
2019-09-23 23:49   ` [PATCH v4 10/25] ibtrs: server: main functionality Bart Van Assche
2019-09-27 15:03     ` Jinpu Wang
2019-09-27 15:11       ` Bart Van Assche
2019-09-27 15:19         ` Jinpu Wang
     [not found] ` <20190620150337.7847-12-jinpuwang@gmail.com>
2019-09-23 23:56   ` [PATCH v4 11/25] ibtrs: server: statistics functions Bart Van Assche
2019-10-02 15:15     ` Jinpu Wang
2019-10-02 15:42       ` Leon Romanovsky
2019-10-02 15:45         ` Jinpu Wang
2019-10-02 16:00           ` Leon Romanovsky
     [not found] ` <20190620150337.7847-13-jinpuwang@gmail.com>
2019-09-24  0:00   ` [PATCH v4 12/25] ibtrs: server: sysfs interface functions Bart Van Assche
2019-10-02 15:11     ` Jinpu Wang

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='CACZ9PQU8=4DaSAUQ7czKdcWio2H5HB1ro-pXaY2VP9PhgTxk7g@mail.gmail.com' \
    --to=r.peniaev@gmail.com \
    --cc=axboe@kernel.dk \
    --cc=bvanassche@acm.org \
    --cc=danil.kipnis@cloud.ionos.com \
    --cc=dledford@redhat.com \
    --cc=hch@infradead.org \
    --cc=jgg@mellanox.com \
    --cc=jinpu.wang@cloud.ionos.com \
    --cc=jinpuwang@gmail.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=rpenyaev@suse.de \
    --cc=sagi@grimberg.me \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-RDMA Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-rdma/0 linux-rdma/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-rdma linux-rdma/ https://lore.kernel.org/linux-rdma \
		linux-rdma@vger.kernel.org
	public-inbox-index linux-rdma

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-rdma


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git