public inbox for linux-nvme@lists.infradead.org
 help / color / mirror / Atom feed
From: Daniel Wagner <dwagner@suse.de>
To: linux-nvme@lists.infradead.org
Cc: linux-kernel@vger.kernel.org, linux-block@vger.kernel.org,
	Chaitanya Kulkarni <kch@nvidia.com>,
	Shin'ichiro Kawasaki <shinichiro@fastmail.com>,
	Daniel Wagner <dwagner@suse.de>
Subject: [PATCH blktests v2 0/9] nvme testsuite runtime optimization
Date: Thu, 20 Apr 2023 20:31:09 +0200	[thread overview]
Message-ID: <20230420183121.4489-1-dwagner@suse.de> (raw)

Refactored v1 into more smaller bits and fixed a bunch of bugs alongside. For
example the fio jobs size for rand rw used --jobs=$(nproc) which needs to fit
with the test device size.

The loop transport runs a few more test but the largest contributer why it runs
so much longer are the iteratons in 002. So I made them also configurable.

nvme_num_iter=100 nvme_img_size=350M (new defaults)

loop
  real    4m3.524s
  user    0m7.931s
  sys     1m35.871s

rdma
  real    4m20.559s
  user    0m8.895s
  sys     1m5.714s

tcp
  real    3m55.292s
  user    0m8.654s
  sys     1m15.314s

fc
  real    3m18.977s
  user    0m8.868s
  sys     0m58.655s

nvme_num_iter=1000 nvme_img_size=1G (previous/ defaults)

loop
  real    8m22.109s
  user    0m27.582s
  sys     3m0.484s

rdma
  real    9m1.784s
  user    0m14.274s
  sys     2m5.479s

tcp
  real    8m28.443s
  user    0m13.952s
  sys     2m55.544s

fc
  real    6m24.426s
  user    0m13.944s
  sys     2m2.489s

The fc tests are bit faster because some of them are failing.

changes:
v2:
  - made image size configurable via nvme_img_size env
  - make number of iteration configurable via nvme_num_iter
	- do not hard code test values
  - calculate job size
	- use runtime for fio background jobs

v1:
  - initial version
  - https://lore.kernel.org/linux-nvme/20230419085643.25714-1-dwagner@suse.de/

Daniel Wagner (9):
  nvme-rc: Auto convert test device size info
  nvme: Do not hard code device size for dd test
  common-xfs: Make size argument optional for _xfs_run_fio_verify_io
  nvme: Use runtime fio background jobs
  nvme: Make test image size configurable
  nvme-rc: Add minimal test image size requirement
  nvme-rc: Calculate IO size for fio jobs
  nvme-rc: Move discovery generation counter code to rc
  nvme: Make the number iterations configurable

 common/rc          |   30 +-
 common/xfs         |    6 +
 tests/nvme/002     |    6 +-
 tests/nvme/002.out | 3004 --------------------------------------------
 tests/nvme/004     |    2 +-
 tests/nvme/005     |    2 +-
 tests/nvme/006     |    2 +-
 tests/nvme/007     |    2 +-
 tests/nvme/008     |    2 +-
 tests/nvme/009     |    2 +-
 tests/nvme/010     |    6 +-
 tests/nvme/011     |    6 +-
 tests/nvme/012     |    5 +-
 tests/nvme/013     |    5 +-
 tests/nvme/014     |   12 +-
 tests/nvme/015     |   12 +-
 tests/nvme/016     |    2 +-
 tests/nvme/017     |    4 +-
 tests/nvme/018     |    2 +-
 tests/nvme/019     |    2 +-
 tests/nvme/020     |    2 +-
 tests/nvme/021     |    2 +-
 tests/nvme/022     |    2 +-
 tests/nvme/023     |    2 +-
 tests/nvme/024     |    2 +-
 tests/nvme/025     |    2 +-
 tests/nvme/026     |    2 +-
 tests/nvme/027     |    2 +-
 tests/nvme/028     |    2 +-
 tests/nvme/029     |    2 +-
 tests/nvme/030     |   22 +-
 tests/nvme/031     |    2 +-
 tests/nvme/032     |    6 +-
 tests/nvme/034     |    4 +-
 tests/nvme/035     |    4 +-
 tests/nvme/040     |    9 +-
 tests/nvme/041     |    2 +-
 tests/nvme/042     |    2 +-
 tests/nvme/043     |    2 +-
 tests/nvme/044     |    2 +-
 tests/nvme/045     |    6 +-
 tests/nvme/047     |    8 +-
 tests/nvme/048     |    2 +-
 tests/nvme/rc      |   50 +
 44 files changed, 176 insertions(+), 3079 deletions(-)

-- 
2.40.0



             reply	other threads:[~2023-04-20 18:31 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-04-20 18:31 Daniel Wagner [this message]
2023-04-20 18:31 ` [PATCH blktests v2 1/9] nvme-rc: Auto convert test device size info Daniel Wagner
2023-04-20 18:31 ` [PATCH blktests v2 2/9] nvme: Do not hard code device size for dd test Daniel Wagner
2023-04-20 18:31 ` [PATCH blktests v2 2/4] nvme: Make test image size configurable Daniel Wagner
2023-04-20 18:31 ` [PATCH blktests v2 3/9] common-xfs: Make size argument optional for _xfs_run_fio_verify_io Daniel Wagner
2023-04-20 18:31 ` [PATCH blktests v2 3/4] nvme-rc: Move discovery generation counter code to rc Daniel Wagner
2023-04-20 18:31 ` [PATCH blktests v2 4/4] nvme: Make the number iterations configurable Daniel Wagner
2023-04-20 18:31 ` [PATCH blktests v2 4/9] nvme: Use runtime fio background jobs Daniel Wagner
2023-04-20 18:31 ` [PATCH blktests v2 5/9] nvme: Make test image size configurable Daniel Wagner
2023-04-20 18:31 ` [PATCH blktests v2 6/9] nvme-rc: Add minimal test image size requirement Daniel Wagner
2023-04-20 18:31 ` [PATCH blktests v2 7/9] nvme-rc: Calculate IO size for fio jobs Daniel Wagner
2023-04-20 18:31 ` [PATCH blktests v2 8/9] nvme-rc: Move discovery generation counter code to rc Daniel Wagner
2023-04-20 18:31 ` [PATCH blktests v2 9/9] nvme: Make the number iterations configurable Daniel Wagner
2023-04-21  5:59 ` [PATCH blktests v2 0/9] nvme testsuite runtime optimization Daniel Wagner

Reply instructions:

You may reply publicly 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=20230420183121.4489-1-dwagner@suse.de \
    --to=dwagner@suse.de \
    --cc=kch@nvidia.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=shinichiro@fastmail.com \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox