| Message ID | 154818223154.18753.12374915684623789884.stgit@ahduyck-desk1.amr.corp.intel.com (mailing list archive) |
|---|---|
| Headers | show |
| Series | Add NUMA aware async_schedule calls | expand |
On Tue, Jan 22, 2019 at 10:39:05AM -0800, Alexander Duyck wrote: > 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 Thanks for sticking with this, now all queued up. greg k-h
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(-) --