All of lore.kernel.org
 help / color / mirror / Atom feed
From: Alexander Duyck <alexander.h.duyck@linux.intel.com>
To: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	linux-nvdimm@lists.01.org
Cc: pavel.tatashin@microsoft.com, mhocko@suse.com,
	dave.hansen@intel.com, jglisse@redhat.com,
	akpm@linux-foundation.org, mingo@kernel.org,
	kirill.shutemov@linux.intel.com
Subject: [PATCH v4 5/5] nvdimm: Schedule device registration on node local to the device
Date: Thu, 20 Sep 2018 15:29:57 -0700	[thread overview]
Message-ID: <20180920222951.19464.39241.stgit@localhost.localdomain> (raw)
In-Reply-To: <20180920215824.19464.8884.stgit@localhost.localdomain>

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.

One additional change I made is that we hold onto a reference to the parent
while we are going through registration. By doing this we can guarantee we
can complete the registration before we have the parent device removed.

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 |   19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 8aae6dcc839f..ca935296d55e 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -487,7 +487,9 @@ static void nd_async_device_register(void *d, async_cookie_t cookie)
 		dev_err(dev, "%s: failed\n", __func__);
 		put_device(dev);
 	}
+
 	put_device(dev);
+	put_device(dev->parent);
 }
 
 static void nd_async_device_unregister(void *d, async_cookie_t cookie)
@@ -504,12 +506,25 @@ static void nd_async_device_unregister(void *d, async_cookie_t cookie)
 
 void __nd_device_register(struct device *dev)
 {
+	int node;
+
 	if (!dev)
 		return;
+
 	dev->bus = &nvdimm_bus_type;
+	get_device(dev->parent);
 	get_device(dev);
-	async_schedule_domain(nd_async_device_register, dev,
-			&nd_async_domain);
+
+	/*
+	 * For a region we can break away from the parent node,
+	 * otherwise for all other devices we just inherit the node from
+	 * the parent.
+	 */
+	node = is_nd_region(dev) ? to_nd_region(dev)->numa_node :
+				   dev_to_node(dev->parent);
+
+	async_schedule_on_domain(nd_async_device_register, dev, node,
+				 &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-mm@kvack.org, linux-kernel@vger.kernel.org,
	linux-nvdimm@lists.01.org
Cc: pavel.tatashin@microsoft.com, mhocko@suse.com,
	dave.jiang@intel.com, mingo@kernel.org, dave.hansen@intel.com,
	jglisse@redhat.com, akpm@linux-foundation.org,
	logang@deltatee.com, dan.j.williams@intel.com,
	kirill.shutemov@linux.intel.com
Subject: [PATCH v4 5/5] nvdimm: Schedule device registration on node local to the device
Date: Thu, 20 Sep 2018 15:29:57 -0700	[thread overview]
Message-ID: <20180920222951.19464.39241.stgit@localhost.localdomain> (raw)
In-Reply-To: <20180920215824.19464.8884.stgit@localhost.localdomain>

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.

One additional change I made is that we hold onto a reference to the parent
while we are going through registration. By doing this we can guarantee we
can complete the registration before we have the parent device removed.

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 |   19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 8aae6dcc839f..ca935296d55e 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -487,7 +487,9 @@ static void nd_async_device_register(void *d, async_cookie_t cookie)
 		dev_err(dev, "%s: failed\n", __func__);
 		put_device(dev);
 	}
+
 	put_device(dev);
+	put_device(dev->parent);
 }
 
 static void nd_async_device_unregister(void *d, async_cookie_t cookie)
@@ -504,12 +506,25 @@ static void nd_async_device_unregister(void *d, async_cookie_t cookie)
 
 void __nd_device_register(struct device *dev)
 {
+	int node;
+
 	if (!dev)
 		return;
+
 	dev->bus = &nvdimm_bus_type;
+	get_device(dev->parent);
 	get_device(dev);
-	async_schedule_domain(nd_async_device_register, dev,
-			&nd_async_domain);
+
+	/*
+	 * For a region we can break away from the parent node,
+	 * otherwise for all other devices we just inherit the node from
+	 * the parent.
+	 */
+	node = is_nd_region(dev) ? to_nd_region(dev)->numa_node :
+				   dev_to_node(dev->parent);
+
+	async_schedule_on_domain(nd_async_device_register, dev, node,
+				 &nd_async_domain);
 }
 
 void nd_device_register(struct device *dev)


  parent reply	other threads:[~2018-09-20 22:30 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-09-20 22:24 [PATCH v4 0/5] Address issues slowing persistent memory initialization Alexander Duyck
2018-09-20 22:24 ` Alexander Duyck
2018-09-20 22:26 ` [PATCH v4 1/5] mm: Provide kernel parameter to allow disabling page init poisoning Alexander Duyck
2018-09-20 22:26   ` Alexander Duyck
2018-09-21 19:04   ` Pasha Tatashin
2018-09-21 19:41     ` Logan Gunthorpe
2018-09-21 19:41       ` Logan Gunthorpe
2018-09-21 19:52       ` Pasha Tatashin
2018-09-20 22:27 ` [PATCH v4 2/5] mm: Create non-atomic version of SetPageReserved for init use Alexander Duyck
2018-09-20 22:27   ` Alexander Duyck
2018-09-21 19:06   ` Pasha Tatashin
2018-09-20 22:29 ` [PATCH v4 3/5] mm: Defer ZONE_DEVICE page initialization to the point where we init pgmap Alexander Duyck
2018-09-20 22:29   ` Alexander Duyck
2018-09-21 19:50   ` Pasha Tatashin
2018-09-21 20:03     ` Alexander Duyck
2018-09-21 20:03       ` Alexander Duyck
2018-09-21 20:14       ` Pasha Tatashin
2018-09-20 22:29 ` [PATCH v4 4/5] async: Add support for queueing on specific node Alexander Duyck
2018-09-20 22:29   ` Alexander Duyck
2018-09-21 14:57   ` Dan Williams
2018-09-21 14:57     ` Dan Williams
2018-09-21 17:02     ` Alexander Duyck
2018-09-21 17:02       ` Alexander Duyck
2018-09-29  8:15   ` [LKP] [async] 06f4f5bfb3: BUG:sleeping_function_called_from_invalid_context_at_include/linux/percpu-rwsem.h kernel test robot
2018-09-29  8:15     ` kernel test robot
2018-09-29  8:15     ` [LKP] " kernel test robot
2018-09-20 22:29 ` Alexander Duyck [this message]
2018-09-20 22:29   ` [PATCH v4 5/5] nvdimm: Schedule device registration on node local to the device Alexander Duyck
2018-09-20 22:59   ` Dan Williams
2018-09-20 22:59     ` Dan Williams
2018-09-21  0:16     ` Alexander Duyck
2018-09-21  0:16       ` Alexander Duyck
2018-09-21  0:36       ` Dan Williams
2018-09-21  0:36         ` Dan Williams
2018-09-21  1:33         ` Alexander Duyck
2018-09-21  1:33           ` Alexander Duyck
2018-09-21  2:46           ` Dan Williams
2018-09-21  2:46             ` Dan Williams
2018-09-21 14:46             ` Alexander Duyck
2018-09-21 14:46               ` Alexander Duyck
2018-09-21 14:56               ` Dan Williams
2018-09-21 14:56                 ` Dan Williams

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=20180920222951.19464.39241.stgit@localhost.localdomain \
    --to=alexander.h.duyck@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=dave.hansen@intel.com \
    --cc=jglisse@redhat.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=mhocko@suse.com \
    --cc=mingo@kernel.org \
    --cc=pavel.tatashin@microsoft.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 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.