Skip to content

Add NUMA aware async_schedule calls

Alexander Duyck linux-nvdimm linux-pm lkml nvdimm 10 versions – In review

Get series with b4
b4 am 154818223154.18753.12374915684623789884.stgit@ahduyck-desk1.amr.corp.intel.com

Versions newest first · linked by author and title

  1. v10 Latest9 patches 3 repliesIn review
  2. v99 patches 8 repliesSuperseded
  3. v89 patches 11 repliesSuperseded
Earlier versions · 7
VersionPostedPatchesRepliesStatus
v79 patches10 repliesSuperseded
v69 patches34 repliesSuperseded
v59 patches22 repliesSuperseded
v46 patches8 repliesSuperseded
v35 patches2 repliesSuperseded
v25 patches8 repliesSuperseded
v15 patches3 repliesSuperseded

Changes in v10 from the cover letter

Moved "dead" from device struct to device_private struct Added Reviewed-by from Rafael to patch 1
Rebased on latest linux-next

Patches in v10 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/9driver core: Establish order of operations for device_add and device_del via bitflagdrivers/base/base.h drivers/base/core.c drivers/base/dd.c+26 -110 replies
2/9device core: Consolidate locking and unlocking of parent and devicedrivers/base/base.h drivers/base/bus.c drivers/base/dd.c+81 -390 replies
3/9driver core: Probe devices asynchronously instead of the driverdrivers/base/base.h drivers/base/bus.c drivers/base/dd.c+48 -201 reply
4/9workqueue: Provide queue_work_node to queue work near a given NUMA nodeinclude/linux/workqueue.h kernel/workqueue.c+86 -00 replies
5/9async: Add support for queueing on specific NUMA nodeinclude/linux/async.h kernel/async.c+108 -270 replies
6/9driver core: Attach devices on CPU local to device nodedrivers/base/dd.c+2 -21 reply
7/9PM core: Use new async_schedule_dev commanddrivers/base/power/main.c+6 -60 replies
8/9libnvdimm: Schedule device registration on node local to the devicedrivers/nvdimm/bus.c+8 -30 replies
9/9driver core: Rewrite test_async_driver_probe to cover serialization and NUMA affinitydrivers/base/test/test_async_driver_probe.c+201 -600 replies

Reviews trailers per patch

8 of 9 patches have a Reviewed-by or Acked-by.

PatchDan WilliamsRafael J. WysockiLuis ChamberlainBart Van AsscheTejun Heo
1/9R-b R-b
2/9R-b R-b R-b R-b
3/9R-b R-b R-b
4/9A-b R-b A-b
5/9R-b R-b
6/9R-b R-b R-b
7/9R-b R-b R-b
8/9R-b
9/9

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes. Scroll the table sideways for all 5 reviewers.

Read the v10 thread

Cover letter [driver-core PATCH v10 0/9] Add NUMA aware async_schedule calls

This patch set provides functionality that will help to improve the locality of the async_schedule calls used to provide deferred initialization.

This patch set originally started out focused on just the one call to async_schedule_domain in the nvdimm tree that was being used to defer the device_add call however after doing some digging I realized the scope of this was much broader than I had originally planned. As such I went through and reworked the underlying infrastructure down to replacing the queue_work call itself with a function of my own and opted to try and provide a NUMA aware solution that would work for a broader audience.

In addition I have added several tweaks and/or clean-ups to the front of the patch set. Patches 1 through 3 address a number of issues that actually were causing the existing async_schedule calls to not show the performance that they could due to either not scaling on a per device basis, or due to issues that could result in a potential race. For example, patch 3 addresses the fact that we were calling async_schedule once per driver instead of once per device, and as a result we would have still ended up with devices being probed on a non-local node without addressing this first.

I have also updated the kernel module used to test async driver probing so that it can expose the original issue I was attempting to address. It will fail on a system of asynchronous work either takes longer than it takes to load a single device and a single driver with a device already added. It will also fail if the NUMA node that the driver is loaded on does not match the NUMA node the device is associated with.

RFC->v1:
Dropped nvdimm patch to submit later.
It relies on code in libnvdimm development tree.
Simplified queue_work_near to just convert node into a CPU. Split up drivers core and PM core patches.
v1->v2:
Renamed queue_work_near to queue_work_node
Added WARN_ON_ONCE if we use queue_work_node with per-cpu workqueue
v2->v3:
Added Acked-by for queue_work_node patch
Continued rename from _near to _node to be consistent with queue_work_node
Renamed async_schedule_near_domain to async_schedule_node_domain Renamed async_schedule_near to async_schedule_node
Added kerneldoc for new async_schedule_XXX functions
Updated patch description for patch 4 to include data on potential gains
v3->v4
Added patch to consolidate use of need_parent_lock
Make asynchronous driver probing explicit about use of drvdata
v4->v5
Added patch to move async_synchronize_full to address deadlock Added bit async_probe to act as mutex for probe/remove calls Added back nvdimm patch as code it relies on is now in Linus's tree Incorporated review comments on parent & device locking consolidation Rebased on latest linux-next
v5->v6:
Drop the "This patch" or "This change" from start of patch descriptions. Drop unnecessary parenthesis in first patch
Use same wording for "selecting a CPU" in comments added in first patch Added kernel documentation for async_probe member of device Fixed up comments for async_schedule calls in patch 2
Moved code related setting async driver out of device.h and into dd.c Added Reviewed-by for several patches
v6->v7:
Fixed typo which had kernel doc refer to "lock" when I meant "unlock" Dropped "bool X:1" to "u8 X:1" from patch description
Added async_driver to device_private structure to store driver Dropped unecessary code shuffle from async_probe patch Reordered patches to move fixes up to front
Added Reviewed-by for several patches
Updated cover page and patch descriptions throughout the set
v7->v8:
Replaced async_probe value with dead, only apply dead in device_del Dropped Reviewed-by from patch 2 due to significant changes Added Reviewed-by for patches reviewed by Luis Chamberlain
v8->v9:
Dropped patch 1 as it was applied, shifted remaining patches by 1 Added new patch 9 that adds test framework for NUMA and sequential init Tweaked what is now patch 1, and added Reviewed-by from Dan Williams
v9->v10:
Moved "dead" from device struct to device_private struct Added Reviewed-by from Rafael to patch 1
Rebased on latest linux-next

---

Alexander Duyck (9):
driver core: Establish order of operations for device_add and device_del via bitflag device core: Consolidate locking and unlocking of parent and device driver core: Probe devices asynchronously instead of the driver
workqueue: Provide queue_work_node to queue work near a given NUMA node
async: Add support for queueing on specific NUMA node
driver core: Attach devices on CPU local to device node
PM core: Use new async_schedule_dev command
libnvdimm: Schedule device registration on node local to the device driver core: Rewrite test_async_driver_probe to cover serialization and NUMA affinity

 drivers/base/base.h                         |    8 +
 drivers/base/bus.c                          |   46 +----
 drivers/base/core.c                         |   11 +
 drivers/base/dd.c                           |  160 +++++++++++++----
 drivers/base/power/main.c                   |   12 +
 drivers/base/test/test_async_driver_probe.c |  261 +++++++++++++++++++++------
 drivers/nvdimm/bus.c                        |   11 +
 include/linux/async.h                       |   82 ++++++++
 include/linux/workqueue.h                   |    2 
 kernel/async.c                              |   53 +++--
 kernel/workqueue.c                          |   84 +++++++++
 11 files changed, 564 insertions(+), 166 deletions(-)

--