All of lore.kernel.org
 help / color / mirror / Atom feed
From: Alexander Duyck <alexander.h.duyck@linux.intel.com>
To: linux-kernel@vger.kernel.org, gregkh@linuxfoundation.org
Cc: len.brown@intel.com, bvanassche@acm.org,
	linux-pm@vger.kernel.org, alexander.h.duyck@linux.intel.com,
	rafael@kernel.org, jiangshanlai@gmail.com,
	linux-nvdimm@lists.01.org, pavel@ucw.cz, zwisler@kernel.org,
	tj@kernel.org, akpm@linux-foundation.org
Subject: [driver-core PATCH v5 9/9] libnvdimm: Schedule device registration on node local to the device
Date: Mon, 05 Nov 2018 13:12:25 -0800	[thread overview]
Message-ID: <154145234526.29224.2575533246153120029.stgit@ahduyck-desk1.jf.intel.com> (raw)
In-Reply-To: <154145223352.29224.8912797012647157172.stgit@ahduyck-desk1.jf.intel.com>

This patch is meant to force the device registration for nvdimm devices to
be closer to the actual device. This is achieved by using either the NUMA
node ID of the region, or of the parent. By doing this we can have
everything above the region based on the region, and everything below the
region based on the nvdimm bus.

By guaranteeing NUMA locality I see an improvement of as high as 25% for
per-node init of a system with 12TB of persistent memory.

Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
---
 drivers/nvdimm/bus.c |   11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index f1fb39921236..b1e193541874 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -23,6 +23,7 @@
 #include <linux/ndctl.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/cpu.h>
 #include <linux/fs.h>
 #include <linux/io.h>
 #include <linux/mm.h>
@@ -513,11 +514,15 @@ void __nd_device_register(struct device *dev)
 		set_dev_node(dev, to_nd_region(dev)->numa_node);
 
 	dev->bus = &nvdimm_bus_type;
-	if (dev->parent)
+	if (dev->parent) {
 		get_device(dev->parent);
+		if (dev_to_node(dev) == NUMA_NO_NODE)
+			set_dev_node(dev, dev_to_node(dev->parent));
+	}
 	get_device(dev);
-	async_schedule_domain(nd_async_device_register, dev,
-			&nd_async_domain);
+
+	async_schedule_dev_domain(nd_async_device_register, dev,
+				  &nd_async_domain);
 }
 
 void nd_device_register(struct device *dev)

_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

WARNING: multiple messages have this Message-ID (diff)
From: Alexander Duyck <alexander.h.duyck@linux.intel.com>
To: linux-kernel@vger.kernel.org, gregkh@linuxfoundation.org
Cc: linux-nvdimm@lists.01.org, tj@kernel.org,
	akpm@linux-foundation.org, linux-pm@vger.kernel.org,
	jiangshanlai@gmail.com, rafael@kernel.org, len.brown@intel.com,
	pavel@ucw.cz, zwisler@kernel.org, dan.j.williams@intel.com,
	dave.jiang@intel.com, bvanassche@acm.org,
	alexander.h.duyck@linux.intel.com
Subject: [driver-core PATCH v5 9/9] libnvdimm: Schedule device registration on node local to the device
Date: Mon, 05 Nov 2018 13:12:25 -0800	[thread overview]
Message-ID: <154145234526.29224.2575533246153120029.stgit@ahduyck-desk1.jf.intel.com> (raw)
In-Reply-To: <154145223352.29224.8912797012647157172.stgit@ahduyck-desk1.jf.intel.com>

This patch is meant to force the device registration for nvdimm devices to
be closer to the actual device. This is achieved by using either the NUMA
node ID of the region, or of the parent. By doing this we can have
everything above the region based on the region, and everything below the
region based on the nvdimm bus.

By guaranteeing NUMA locality I see an improvement of as high as 25% for
per-node init of a system with 12TB of persistent memory.

Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
---
 drivers/nvdimm/bus.c |   11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index f1fb39921236..b1e193541874 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -23,6 +23,7 @@
 #include <linux/ndctl.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
+#include <linux/cpu.h>
 #include <linux/fs.h>
 #include <linux/io.h>
 #include <linux/mm.h>
@@ -513,11 +514,15 @@ void __nd_device_register(struct device *dev)
 		set_dev_node(dev, to_nd_region(dev)->numa_node);
 
 	dev->bus = &nvdimm_bus_type;
-	if (dev->parent)
+	if (dev->parent) {
 		get_device(dev->parent);
+		if (dev_to_node(dev) == NUMA_NO_NODE)
+			set_dev_node(dev, dev_to_node(dev->parent));
+	}
 	get_device(dev);
-	async_schedule_domain(nd_async_device_register, dev,
-			&nd_async_domain);
+
+	async_schedule_dev_domain(nd_async_device_register, dev,
+				  &nd_async_domain);
 }
 
 void nd_device_register(struct device *dev)


  parent reply	other threads:[~2018-11-05 21:12 UTC|newest]

Thread overview: 90+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-05 21:11 [driver-core PATCH v5 0/9] Add NUMA aware async_schedule calls Alexander Duyck
2018-11-05 21:11 ` Alexander Duyck
2018-11-05 21:11 ` [driver-core PATCH v5 1/9] workqueue: Provide queue_work_node to queue work near a given NUMA node Alexander Duyck
2018-11-05 21:11   ` Alexander Duyck
2018-11-05 21:11   ` Alexander Duyck
2018-11-06  0:42   ` Bart Van Assche
2018-11-06  0:42     ` Bart Van Assche
2018-11-06  0:42     ` Bart Van Assche
2018-11-06 16:27     ` Alexander Duyck
2018-11-06 16:27       ` Alexander Duyck
2018-11-06 16:27       ` Alexander Duyck
2018-11-05 21:11 ` [driver-core PATCH v5 2/9] async: Add support for queueing on specific " Alexander Duyck
2018-11-05 21:11   ` Alexander Duyck
2018-11-05 21:11   ` Alexander Duyck
2018-11-07  0:50   ` Bart Van Assche
2018-11-07  0:50     ` Bart Van Assche
2018-11-07  0:50     ` Bart Van Assche
2018-11-05 21:11 ` [driver-core PATCH v5 3/9] device core: Consolidate locking and unlocking of parent and device Alexander Duyck
2018-11-05 21:11   ` Alexander Duyck
2018-11-05 21:11   ` Alexander Duyck
2018-11-05 21:11 ` [driver-core PATCH v5 4/9] driver core: Move async_synchronize_full call Alexander Duyck
2018-11-05 21:11   ` Alexander Duyck
2018-11-06  1:04   ` Bart Van Assche
2018-11-06  1:04     ` Bart Van Assche
2018-11-06  1:04     ` Bart Van Assche
2018-11-06 16:18     ` Alexander Duyck
2018-11-06 16:18       ` Alexander Duyck
2018-11-06 16:18       ` Alexander Duyck
2018-11-06 17:22       ` Bart Van Assche
2018-11-06 17:22         ` Bart Van Assche
2018-11-06 17:22         ` Bart Van Assche
2018-11-05 21:12 ` [driver-core PATCH v5 5/9] driver core: Establish clear order of operations for deferred probe and remove Alexander Duyck
2018-11-05 21:12   ` Alexander Duyck
2018-11-05 21:12   ` Alexander Duyck
2018-11-06  4:10   ` kbuild test robot
2018-11-06  4:10     ` kbuild test robot
2018-11-06  4:10     ` kbuild test robot
2018-11-06 23:51     ` Bart Van Assche
2018-11-06 23:51       ` Bart Van Assche
2018-11-06 23:51       ` Bart Van Assche
2018-11-07  0:52       ` Alexander Duyck
2018-11-07  0:52         ` Alexander Duyck
2018-11-23  1:23       ` Rong Chen
2018-11-23  1:23         ` Rong Chen
2018-11-23  1:23         ` Rong Chen
2018-11-23 14:19         ` Bart Van Assche
2018-11-23 14:19           ` Bart Van Assche
2018-11-06 23:48   ` Bart Van Assche
2018-11-06 23:48     ` Bart Van Assche
2018-11-06 23:48     ` Bart Van Assche
2018-11-07  1:34     ` Joe Perches
2018-11-07  1:34       ` Joe Perches
2018-11-07  1:34       ` Joe Perches
2018-11-08 23:42       ` Bart Van Assche
2018-11-08 23:42         ` Bart Van Assche
2018-11-08 23:42         ` Bart Van Assche
2018-11-11 14:31     ` Pavel Machek
2018-11-27  2:35   ` Dan Williams
2018-11-27  2:35     ` Dan Williams
2018-11-27 16:49     ` Alexander Duyck
2018-11-27 16:49       ` Alexander Duyck
2018-11-05 21:12 ` [driver-core PATCH v5 6/9] driver core: Probe devices asynchronously instead of the driver Alexander Duyck
2018-11-05 21:12   ` Alexander Duyck
2018-11-05 21:12   ` Alexander Duyck
2018-11-07  0:22   ` Bart Van Assche
2018-11-07  0:22     ` Bart Van Assche
2018-11-07  0:22     ` Bart Van Assche
2018-11-05 21:12 ` [driver-core PATCH v5 7/9] driver core: Attach devices on CPU local to device node Alexander Duyck
2018-11-05 21:12   ` Alexander Duyck
2018-11-05 21:12   ` Alexander Duyck
2018-11-07  0:24   ` Bart Van Assche
2018-11-07  0:24     ` Bart Van Assche
2018-11-07  0:24     ` Bart Van Assche
2018-11-05 21:12 ` [driver-core PATCH v5 8/9] PM core: Use new async_schedule_dev command Alexander Duyck
2018-11-05 21:12   ` Alexander Duyck
2018-11-05 21:12   ` Alexander Duyck
2018-11-07  0:24   ` Bart Van Assche
2018-11-07  0:24     ` Bart Van Assche
2018-11-07  0:24     ` Bart Van Assche
2018-11-05 21:12 ` Alexander Duyck [this message]
2018-11-05 21:12   ` [driver-core PATCH v5 9/9] libnvdimm: Schedule device registration on node local to the device Alexander Duyck
2018-11-07  0:26   ` Bart Van Assche
2018-11-07  0:26     ` Bart Van Assche
2018-11-07  0:26     ` Bart Van Assche
2018-11-06  0:50 ` [driver-core PATCH v5 0/9] Add NUMA aware async_schedule calls Bart Van Assche
2018-11-06  0:50   ` Bart Van Assche
2018-11-06  0:50   ` Bart Van Assche
2018-11-06 16:25   ` Alexander Duyck
2018-11-06 16:25     ` Alexander Duyck
2018-11-06 16:25     ` Alexander Duyck

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=154145234526.29224.2575533246153120029.stgit@ahduyck-desk1.jf.intel.com \
    --to=alexander.h.duyck@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=bvanassche@acm.org \
    --cc=gregkh@linuxfoundation.org \
    --cc=jiangshanlai@gmail.com \
    --cc=len.brown@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=pavel@ucw.cz \
    --cc=rafael@kernel.org \
    --cc=tj@kernel.org \
    --cc=zwisler@kernel.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.