NUMA hotplug emulator

RFC Superseded Shaohui Zheng 8 participants 21 messages May 13, 2010 – May 24, 2010

Subsystems (4)

Memory management x86 Driver core Memory hot(un)plug

lore

Share & tools

lore

Shaohui Zheng

author

2010-05-13 12:04 UTC #0 lore raw

RFC 6/7 NUMA hotplug emulator

hotplug emulator:extend memory probe interface to support NUMA

Extend memory probe interface to support an extra paramter nid, the reserved memory can be added into this node if node exists.

Add a memory section(128M) to node 3(boots with mem=1024m)

	echo 0x40000000,3 > memory/probe

And more we make it friendly, it is possible to add memory to do

	echo 3g > memory/probe
	echo 1024m,3 > memory/probe

It maintains backwards compatibility.

Signed-off-by Shaohui Zheng <[email protected]>

Signed-off-by Haicheng Li <[email protected]>

Signed-off-by Wu Fengguang <[email protected]>

---

arch/x86/Kconfig +11 -0

index 54ccb0d..787024f 100644
@@ -1239,6 +1239,17 @@ config ARCH_CPU_PROBE_RELEASE
 	  is for cpu hot-add/hot-remove to specified node in software method.
 	  This is for debuging and testing purpose
 
+config ARCH_MEMORY_PROBE
+	def_bool y
+	bool "Memory hotplug emulation"
+	depends on NUMA_HOTPLUG_EMU
+	---help---
+	  Enable memory hotplug emulation. Reserve memory with grub parameter
+	  "mem=N"(such as mem=1024M), where N is the initial memory size, the
+	  rest physical memory will be removed from e820 table; the memory probe
+	  interface is for memory hot-add to specified node in software method.
+	  This is for debuging and testing purpose
+
 config NODES_SHIFT
 	int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP
 	range 1 10

drivers/base/memory.c +21 -3

index 933442f..1c2d83d 100644
@@ -329,6 +329,8 @@ static int block_size_init(void)
  * will not need to do it from userspace.  The fake hot-add code
  * as well as ppc64 will do all of their discovery in userspace
  * and will require this interface.
+ *
+ * Parameter format: start_addr, nid
  */
 #ifdef CONFIG_ARCH_MEMORY_PROBE
 static ssize_t

@@ -339,10 +341,26 @@ memory_probe_store(struct class *class, struct class_attribute *attr,
 	int nid;
 	int ret;
 
-	phys_addr = simple_strtoull(buf, NULL, 0);
+	char *p = strchr(buf, ',');
+
+	if (p != NULL && strlen(p+1) > 0) {
+		/* nid specified */
+		*p++ = '\0';
+		nid = simple_strtoul(p, NULL, 0);
+		phys_addr = memparse(buf, NULL);
+	} else {
+		phys_addr = memparse(buf, NULL);
+		nid = memory_add_physaddr_to_nid(phys_addr);
+	}
 
-	nid = memory_add_physaddr_to_nid(phys_addr);
-	ret = add_memory(nid, phys_addr, PAGES_PER_SECTION << PAGE_SHIFT);
+	if (nid < 0 || nid > nr_node_ids - 1) {
+		printk(KERN_ERR "Invalid node id %d(0<=nid<%d).\n", nid, nr_node_ids);
+	} else {
+		printk(KERN_INFO "Add a memory section to node: %d.\n", nid);
+		ret = add_memory(nid, phys_addr, PAGES_PER_SECTION << PAGE_SHIFT);
+		if (ret)
+			count = ret;
+	}
 
 	if (ret)
 		count = ret;

Signature · 2 lines

Thanks & Regards,
Shaohui

hotplug emulator:extend memory probe interface to support NUMA

Extend memory probe interface to support an extra paramter nid, the reserved memory can be added into this node if node exists.

Add a memory section(128M) to node 3(boots with mem=1024m)

	echo 0x40000000,3 > memory/probe

And more we make it friendly, it is possible to add memory to do

	echo 3g > memory/probe
	echo 1024m,3 > memory/probe

It maintains backwards compatibility.

Signed-off-by Shaohui Zheng <[email protected]>

Signed-off-by Haicheng Li <[email protected]>

Signed-off-by Wu Fengguang <[email protected]>

---

arch/x86/Kconfig +11 -0

index 54ccb0d..787024f 100644
@@ -1239,6 +1239,17 @@ config ARCH_CPU_PROBE_RELEASE
 	  is for cpu hot-add/hot-remove to specified node in software method.
 	  This is for debuging and testing purpose
 
+config ARCH_MEMORY_PROBE
+	def_bool y
+	bool "Memory hotplug emulation"
+	depends on NUMA_HOTPLUG_EMU
+	---help---
+	  Enable memory hotplug emulation. Reserve memory with grub parameter
+	  "mem=N"(such as mem=1024M), where N is the initial memory size, the
+	  rest physical memory will be removed from e820 table; the memory probe
+	  interface is for memory hot-add to specified node in software method.
+	  This is for debuging and testing purpose
+
 config NODES_SHIFT
 	int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP
 	range 1 10

drivers/base/memory.c +21 -3

index 933442f..1c2d83d 100644
@@ -329,6 +329,8 @@ static int block_size_init(void)
  * will not need to do it from userspace.  The fake hot-add code
  * as well as ppc64 will do all of their discovery in userspace
  * and will require this interface.
+ *
+ * Parameter format: start_addr, nid
  */
 #ifdef CONFIG_ARCH_MEMORY_PROBE
 static ssize_t

@@ -339,10 +341,26 @@ memory_probe_store(struct class *class, struct class_attribute *attr,
 	int nid;
 	int ret;
 
-	phys_addr = simple_strtoull(buf, NULL, 0);
+	char *p = strchr(buf, ',');
+
+	if (p != NULL && strlen(p+1) > 0) {
+		/* nid specified */
+		*p++ = '\0';
+		nid = simple_strtoul(p, NULL, 0);
+		phys_addr = memparse(buf, NULL);
+	} else {
+		phys_addr = memparse(buf, NULL);
+		nid = memory_add_physaddr_to_nid(phys_addr);
+	}
 
-	nid = memory_add_physaddr_to_nid(phys_addr);
-	ret = add_memory(nid, phys_addr, PAGES_PER_SECTION << PAGE_SHIFT);
+	if (nid < 0 || nid > nr_node_ids - 1) {
+		printk(KERN_ERR "Invalid node id %d(0<=nid<%d).\n", nid, nr_node_ids);
+	} else {
+		printk(KERN_INFO "Add a memory section to node: %d.\n", nid);
+		ret = add_memory(nid, phys_addr, PAGES_PER_SECTION << PAGE_SHIFT);
+		if (ret)
+			count = ret;
+	}
 
 	if (ret)
 		count = ret;

Greg KH

2010-05-13 16:56 UTC #1 lore raw

Quoted 7 lines · Shaohui Zheng

hotplug emulator:extend memory probe interface to support NUMA
Extend memory probe interface to support an extra paramter nid, the reserved memory can be added into this node if node exists.
Add a memory section(128M) to node 3(boots with mem=1024m)

Quoted 8 lines

	echo 0x40000000,3 > memory/probe
And more we make it friendly, it is possible to add memory to do
	echo 3g > memory/probe
	echo 1024m,3 > memory/probe
It maintains backwards compatibility.

Again, please document this.

thanks,

greg k-h

Dave Hansen

2010-05-13 18:03 UTC #2 lore raw

Quoted 9 lines · Greg KH

Quoted 8 lines · Shaohui Zheng
hotplug emulator:extend memory probe interface to support NUMA
Extend memory probe interface to support an extra paramter nid, the reserved memory can be added into this node if node exists.
Add a memory section(128M) to node 3(boots with mem=1024m)
      echo 0x40000000,3 > memory/probe

I dunno. If we're going to put multiple values into the file now and add to the ABI, can we be more explicit about it?

	echo "physical_address=0x40000000 numa_node=3" > memory/probe

I'd *GREATLY* prefer that over this new syntax. The existing mechanism is obtuse enough, and the ',3' makes it more so.

We should have the code around to parse arguments like that, too, since we use it for the boot command-line.

-- Dave

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

Greg KH

2010-05-13 18:45 UTC #3 lore raw

Quoted 14 lines · Dave Hansen

Quoted 9 lines · Greg KH
Quoted 8 lines · Shaohui Zheng
hotplug emulator:extend memory probe interface to support NUMA
Extend memory probe interface to support an extra paramter nid, the reserved memory can be added into this node if node exists.
Add a memory section(128M) to node 3(boots with mem=1024m)
      echo 0x40000000,3 > memory/probe
I dunno. If we're going to put multiple values into the file now and add to the ABI, can we be more explicit about it?

Quoted 7 lines

	echo "physical_address=0x40000000 numa_node=3" > memory/probe
I'd *GREATLY* prefer that over this new syntax. The existing mechanism is obtuse enough, and the ',3' makes it more so.
We should have the code around to parse arguments like that, too, since we use it for the boot command-line.

If you are going to be doing something like this, please use configfs, that is what it is designed for, not sysfs.

thanks,

greg k-h

Dave Hansen

2010-05-13 18:49 UTC #4 lore raw

Quoted 10 lines · Greg KH

Quoted 7 lines
      echo "physical_address=0x40000000 numa_node=3" > memory/probe
I'd *GREATLY* prefer that over this new syntax. The existing mechanism is obtuse enough, and the ',3' makes it more so.
We should have the code around to parse arguments like that, too, since we use it for the boot command-line.
If you are going to be doing something like this, please use configfs, that is what it is designed for, not sysfs.

That's probably a really good point, especially since configfs didn't even exist when we made this 'probe' file thingy. It never was a great fit for sysfs anyway.

-- Dave

Greg KH

2010-05-13 19:07 UTC #5 lore raw

Quoted 9 lines · Dave Hansen

Quoted 8 lines · Greg KH
Quoted 7 lines
      echo "physical_address=0x40000000 numa_node=3" > memory/probe
I'd *GREATLY* prefer that over this new syntax. The existing mechanism is obtuse enough, and the ',3' makes it more so.
We should have the code around to parse arguments like that, too, since we use it for the boot command-line.

Quoted 6 lines

Quoted 2 lines
If you are going to be doing something like this, please use configfs, that is what it is designed for, not sysfs.
That's probably a really good point, especially since configfs didn't even exist when we made this 'probe' file thingy. It never was a great fit for sysfs anyway.

Really? configfs was added in 2.6.16, when was this probe file added?

thanks,

greg k-h

Dave Hansen

2010-05-13 19:17 UTC #6 lore raw

Quoted 5 lines · Greg KH

Quoted 3 lines
That's probably a really good point, especially since configfs didn't even exist when we made this 'probe' file thingy. It never was a great fit for sysfs anyway.
Really? configfs was added in 2.6.16, when was this probe file added?

$ git name-rev 3947be19
3947be19 tags/v2.6.15-rc1~728^2~12

-- Dave

Greg KH

2010-05-13 19:38 UTC #7 lore raw

Quoted 9 lines · Dave Hansen

Quoted 5 lines · Greg KH
Quoted 3 lines
That's probably a really good point, especially since configfs didn't even exist when we made this 'probe' file thingy. It never was a great fit for sysfs anyway.
Really? configfs was added in 2.6.16, when was this probe file added?
$ git name-rev 3947be19
3947be19 tags/v2.6.15-rc1~728^2~12

Ah, so close, off by 3 months :)

thanks,

greg k-h

Shaohui Zheng

author

2010-05-18 05:49 UTC #8 lore raw

In reply to Dave Hansen

Quoted 9 lines · Dave Hansen

Quoted 8 lines · Greg KH
Quoted 7 lines
      echo "physical_address=0x40000000 numa_node=3" > memory/probe
I'd *GREATLY* prefer that over this new syntax. The existing mechanism is obtuse enough, and the ',3' makes it more so.
We should have the code around to parse arguments like that, too, since we use it for the boot command-line.

Quoted 8 lines

Quoted 2 lines
If you are going to be doing something like this, please use configfs, that is what it is designed for, not sysfs.
That's probably a really good point, especially since configfs didn't even exist when we made this 'probe' file thingy. It never was a great fit for sysfs anyway.
-- Dave

the configfs was introduced in 2005, you can refer to http://lwn.net/Articles/148973/.

I enabled the configfs, and I see that the configfs is not so popular as we expected, I mount configfs to /sys/kernel/config, I get an empty directory. It means that nobody is using this file system, it is an interesting thing, is it means that configfs is deprecated? If so, it might not be nessarry to develop a configfs interface for hotplug.

Dave & Greg,
Can you provide an exmample to use configfs as interface in Linux kernel, I want to get
a live demo, thanks.

Signature · 8 lines

Thanks & Regards,
Shaohui

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to [email protected].  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

Dave Hansen

2010-05-18 07:27 UTC #9 lore raw

Quoted 7 lines · Shaohui Zheng

On Thu, May 13, 2010 at 11:49:38AM -0700, Dave Hansen wrote:
the configfs was introduced in 2005, you can refer to http://lwn.net/Articles/148973/.
I enabled the configfs, and I see that the configfs is not so popular as we expected, I mount configfs to /sys/kernel/config, I get an empty directory. It means that nobody is using this file system, it is an interesting thing, is it means that configfs is deprecated? If so, it might not be nessarry to develop a configfs interface for hotplug.

Uh, deprecated? What would make you think that? It does look like the users are a we bit obscure, but that's a bit far from deprecated.

Quoted 3 lines

Dave & Greg,
Can you provide an exmample to use configfs as interface in Linux kernel, I want to get
a live demo, thanks.

Heh. There are some great tools out there called cscope and grep. I have them on my system and I bet you can get them on yours too.

That said, you're right. There don't seem to be a ton of users of it these days. But, the LWN article you referenced also pointed to at least one user. So, please try and put a wee bit of effort into it.

Maybe configfs isn't the way to go. I just think extending the 'probe' file is a bad idea, especially in the way your patch did it. I'm open to other alternatives. Since this is only for testing, perhaps debugfs applies better. What other alternatives have you explored? How about a Systemtap set to do it? :)

-- Dave

Shaohui Zheng

author

2010-05-18 08:05 UTC #10 lore raw

Quoted 16 lines · Dave Hansen

Quoted 7 lines · Shaohui Zheng
On Thu, May 13, 2010 at 11:49:38AM -0700, Dave Hansen wrote:
the configfs was introduced in 2005, you can refer to http://lwn.net/Articles/148973/.
I enabled the configfs, and I see that the configfs is not so popular as we expected, I mount configfs to /sys/kernel/config, I get an empty directory. It means that nobody is using this file system, it is an interesting thing, is it means that configfs is deprecated? If so, it might not be nessarry to develop a configfs interface for hotplug.
Uh, deprecated? What would make you think that? It does look like the users are a we bit obscure, but that's a bit far from deprecated.
Quoted 3 lines
Dave & Greg,
Can you provide an exmample to use configfs as interface in Linux kernel, I want to get
a live demo, thanks.

Quoted 6 lines

Heh. There are some great tools out there called cscope and grep. I have them on my system and I bet you can get them on yours too.
That said, you're right. There don't seem to be a ton of users of it these days. But, the LWN article you referenced also pointed to at least one user. So, please try and put a wee bit of effort into it.

I am trying to put a few efforts on it, and we hope to support both sysfs and configfs.

because of the history reason, sysfs is more popular. I bet that only vew few users know
configfs, so sysfs is still the prefered way.

Quoted 8 lines

Maybe configfs isn't the way to go. I just think extending the 'probe' file is a bad idea, especially in the way your patch did it. I'm open to other alternatives. Since this is only for testing, perhaps debugfs applies better. What other alternatives have you explored? How about a Systemtap set to do it? :)
-- Dave

Did not try other alternatives until now. Thanks for Dave's suggestions, Systemtap and debugfs
seems to be good methods, too.

Signature · 8 lines

Thanks & Regards,
Shaohui

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to [email protected].  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

Andi Kleen

2010-05-18 08:55 UTC #11 lore raw

In reply to Dave Hansen

Quoted 7 lines

Maybe configfs isn't the way to go. I just think extending the 'probe' file is a bad idea, especially in the way your patch did it. I'm open to other alternatives. Since this is only for testing, perhaps debugfs applies better. What other alternatives have you explored? How about a Systemtap set to do it? :)

First this is a debugging interface. It doesn't need to have the most pretty interface in the world, because it will be only used for QA by a few people.

Requiring setting parameters in two different file systems doesn't sound that appealing to me.

systemtap for configuration also doesn't seem right.

I liked Dave's earlier proposal to do a command line parameter like interface for "probe". Perhaps that can be done. It shouldn't need a lot of code.

In fact there are already two different parser libraries for this:
lib/parser.c and lib/params.c. One could chose the one that one likes better :-)

Anything that needs a lot of code is a bad idea for this I think. A simple parser using one of the existing libraries should be simple enough though.

Again it's just a QA interface, not the next generation of POSIX.

-Andi

Dave Hansen

2010-05-18 15:46 UTC #12 lore raw

Quoted 2 lines · Andi Kleen

I liked Dave's earlier proposal to do a command line parameter like interface for "probe". Perhaps that can be done. It shouldn't need a lot of code.

After looking at the code, configfs doesn't look to me like it can be done horribly easily. It takes a least a subsystem and then a few structures to get things up and running. There also doesn't appear to be a good subsystem to plug into.

Quoted 3 lines

In fact there are already two different parser libraries for this:
lib/parser.c and lib/params.c. One could chose the one that one likes better :-)

Agreed. But, I do see why Greg is suggesting configfs here. Superficially, it seems like a good configfs fit, but I think configfs is only a good fit when you need to cram a _bunch_ of stuff into a _new_ interface. Here, we have a relatively tiny amount of data that has half of what it needs from an existing interface.

-- Dave

Nicholas A. Bellinger

2010-05-18 07:44 UTC #13 lore raw

In reply to Shaohui Zheng

Quoted 17 lines · Shaohui Zheng

Quoted 16 lines · Dave Hansen
Quoted 10 lines · Greg KH
Quoted 7 lines
      echo "physical_address=0x40000000 numa_node=3" > memory/probe
I'd *GREATLY* prefer that over this new syntax. The existing mechanism is obtuse enough, and the ',3' makes it more so.
We should have the code around to parse arguments like that, too, since we use it for the boot command-line.
If you are going to be doing something like this, please use configfs, that is what it is designed for, not sysfs.
That's probably a really good point, especially since configfs didn't even exist when we made this 'probe' file thingy. It never was a great fit for sysfs anyway.

Quoted 7 lines

Quoted 1 line
-- Dave
the configfs was introduced in 2005, you can refer to http://lwn.net/Articles/148973/.
I enabled the configfs, and I see that the configfs is not so popular as we expected, I mount configfs to /sys/kernel/config, I get an empty directory. It means that nobody is using this file system, it is an interesting thing, is it means that configfs is deprecated?

Ohhhhhh, no. ConfigFS is the evolution of the original SysFS design to to allow for kernel data structure configuration to be driven by userspace syscalls in a number of very significant ways.

Quoted 2 lines

If so, it might not be nessarry to develop a configfs interface for hotplug.

The usage of ConfigFS to provide a kernel <-> user configuration layout really best depends on the protocol in question for particular data structure state machine and parameter/attribute set. Using ConfigFS involves Linux/VFS representing dependencies between data structures both on a inter and intra kernel module context containing struct config_groups driven by userspace mkdir(2) and link(2) syscall ops.

Quoted 3 lines

Dave & Greg,
Can you provide an exmample to use configfs as interface in Linux kernel, I want to get
a live demo, thanks.

The TCM 4.0 design brings fabric module independent >= SPC-3 compatible SCSI WWN target ports and a generic set of struct config_groups and CPP macros to individual storage backstores using TCM target mode fabric plugins across Linux/SCSI, Linux/BLOCK, and Linux/VFS subsystems. So far, this has been implemented for SAS, FC, and iSCSI fabric protocols:

http://git.kernel.org/?p=linux/kernel/git/nab/lio-core-2.6.git;a=blob;f=drivers/target/target_core_configfs.c;hb=refs/heads/lio-4.0
http://git.kernel.org/?p=linux/kernel/git/nab/lio-core-2.6.git;a=blob;f=include/target/configfs_macros.h;hb=refs/heads/lio-4.0
http://git.kernel.org/?p=linux/kernel/git/nab/lio-core-2.6.git;a=blob;f=drivers/target/target_core_fabric_configfs.c;hb=refs/heads/lio-4.0
http://git.kernel.org/?p=linux/kernel/git/nab/lio-core-2.6.git;a=blob;f=include/target/target_core_fabric_configfs.h;hb=refs/heads/lio-4.0

http://git.kernel.org/?p=linux/kernel/git/nab/lio-core-2.6.git;a=blob;f=drivers/target/tcm_fc/tfc_conf.c;hb=refs/heads/lio-4.0
http://git.kernel.org/?p=linux/kernel/git/nab/lio-core-2.6.git;a=blob;f=drivers/target/tcm_loop/tcm_loop_configfs.c;hb=refs/heads/lio-4.0
http://git.kernel.org/?p=linux/kernel/git/nab/lio-core-2.6.git;a=blob;f=drivers/target/lio-target/iscsi_target_configfs.c;hb=refs/heads/lio-4.0

Best,

--nab

Paul Mundt

2010-05-18 07:45 UTC #14 lore raw

In reply to Shaohui Zheng

Quoted 17 lines · Shaohui Zheng

Quoted 16 lines · Dave Hansen
Quoted 10 lines · Greg KH
Quoted 7 lines
      echo "physical_address=0x40000000 numa_node=3" > memory/probe
I'd *GREATLY* prefer that over this new syntax. The existing mechanism is obtuse enough, and the ',3' makes it more so.
We should have the code around to parse arguments like that, too, since we use it for the boot command-line.
If you are going to be doing something like this, please use configfs, that is what it is designed for, not sysfs.
That's probably a really good point, especially since configfs didn't even exist when we made this 'probe' file thingy. It never was a great fit for sysfs anyway.

Quoted 9 lines

Quoted 1 line
-- Dave
the configfs was introduced in 2005, you can refer to http://lwn.net/Articles/148973/.
I enabled the configfs, and I see that the configfs is not so popular as we expected, I mount configfs to /sys/kernel/config, I get an empty directory. It means that nobody is using this file system, it is an interesting thing, is it means that configfs is deprecated? If so, it might not be nessarry to develop a configfs interface for hotplug.

configfs is certainly not deprecated, but there are also not that many users of it at present. dlm/ocfs2 were the first users as far as I recall, and netconsole as well. The fact you have an empty directory just indicates that you don't have support for any of these enabled.

Note that there are also a lot of present-day sysfs and debugfs users that could/should be converted to configfs but haven't quite gotten there yet. In the sysfs case abuses are hard to rollback once they've made become part of the ABI, but that's not grounds for continuing sysfs abuse once cleaner methods become available. Many of the sysfs abuses were implemented before configfs existed.

You can also find usage guidelines and example implementations in Documentation/filesystems/configfs, which should give you a pretty good idea of whether it's a good interface fit for your particular problem or not.

These days sysfs seems to be the new procfs. It certainly helps to put a bit of planning in to the interface before you're invariably stuck with an ABI that's barely limping along.

Shaohui Zheng

author

2010-05-18 08:16 UTC #15 lore raw

Quoted 39 lines · Paul Mundt

Quoted 17 lines · Shaohui Zheng
Quoted 16 lines · Dave Hansen
Quoted 10 lines · Greg KH
Quoted 7 lines
      echo "physical_address=0x40000000 numa_node=3" > memory/probe
I'd *GREATLY* prefer that over this new syntax. The existing mechanism is obtuse enough, and the ',3' makes it more so.
We should have the code around to parse arguments like that, too, since we use it for the boot command-line.
If you are going to be doing something like this, please use configfs, that is what it is designed for, not sysfs.
That's probably a really good point, especially since configfs didn't even exist when we made this 'probe' file thingy. It never was a great fit for sysfs anyway.
Quoted 9 lines
Quoted 1 line
-- Dave
the configfs was introduced in 2005, you can refer to http://lwn.net/Articles/148973/.
I enabled the configfs, and I see that the configfs is not so popular as we expected, I mount configfs to /sys/kernel/config, I get an empty directory. It means that nobody is using this file system, it is an interesting thing, is it means that configfs is deprecated? If so, it might not be nessarry to develop a configfs interface for hotplug.
configfs is certainly not deprecated, but there are also not that many users of it at present. dlm/ocfs2 were the first users as far as I recall, and netconsole as well. The fact you have an empty directory just indicates that you don't have support for any of these enabled.
Note that there are also a lot of present-day sysfs and debugfs users that could/should be converted to configfs but haven't quite gotten there yet. In the sysfs case abuses are hard to rollback once they've made become part of the ABI, but that's not grounds for continuing sysfs abuse once cleaner methods become available. Many of the sysfs abuses were implemented before configfs existed.

Quoted 8 lines

You can also find usage guidelines and example implementations in Documentation/filesystems/configfs, which should give you a pretty good idea of whether it's a good interface fit for your particular problem or not.
These days sysfs seems to be the new procfs. It certainly helps to put a bit of planning in to the interface before you're invariably stuck with an ABI that's barely limping along.

Paul,
Thanks for the clear explanation for configfs, and I kown the importance of the configfs now.
the cpu/memory probe is just an interface, we care more about whether the feature works, but the interface implemented by sysfs or configfs, it is not important. Different paths, the same objective. Both are for us.

we follow up the style of the majority, we also accept the feedbacks from the community. I did not how many efforts costs, but I am trying.

Signature · 8 lines

Thanks & Regards,
Shaohui

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to [email protected].  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

Shaohui Zheng

author

2010-05-14 01:53 UTC #16 lore raw

In reply to Greg KH

Quoted 15 lines · Greg KH

Quoted 14 lines · Shaohui Zheng
hotplug emulator:extend memory probe interface to support NUMA
Extend memory probe interface to support an extra paramter nid, the reserved memory can be added into this node if node exists.
Add a memory section(128M) to node 3(boots with mem=1024m)
	echo 0x40000000,3 > memory/probe
And more we make it friendly, it is possible to add memory to do
	echo 3g > memory/probe
	echo 1024m,3 > memory/probe

Quoted 7 lines

Quoted 1 line
It maintains backwards compatibility.
Again, please document this.
thanks,
greg k-h

okay

Signature · 2 lines

Thanks & Regards,
Shaohui

Wu Fengguang

2010-05-14 02:05 UTC #17 lore raw

Quoted 18 lines · Shaohui

Quoted 17 lines · Greg KH
Quoted 15 lines · Shaohui Zheng
hotplug emulator:extend memory probe interface to support NUMA
Extend memory probe interface to support an extra paramter nid, the reserved memory can be added into this node if node exists.
Add a memory section(128M) to node 3(boots with mem=1024m)
	echo 0x40000000,3 > memory/probe
And more we make it friendly, it is possible to add memory to do
	echo 3g > memory/probe
	echo 1024m,3 > memory/probe
It maintains backwards compatibility.

Quoted 7 lines

Quoted 5 lines
Again, please document this.
thanks,
greg k-h
okay

Shaohui, it's useless to document a wrong interface.
Better to fix the interface _first_, then document becomes meaningful.

Thanks,
Fengguang

Shaohui Zheng

author

2010-05-14 02:12 UTC #18 lore raw

Quoted 21 lines · Wu Fengguang

Quoted 20 lines · Shaohui
Quoted 19 lines · Greg KH
Quoted 7 lines · Shaohui Zheng
hotplug emulator:extend memory probe interface to support NUMA
Extend memory probe interface to support an extra paramter nid, the reserved memory can be added into this node if node exists.
Add a memory section(128M) to node 3(boots with mem=1024m)
Quoted 8 lines
	echo 0x40000000,3 > memory/probe
And more we make it friendly, it is possible to add memory to do
	echo 3g > memory/probe
	echo 1024m,3 > memory/probe
It maintains backwards compatibility.
Again, please document this.

Quoted 8 lines

Quoted 5 lines
Quoted 3 lines
thanks,
greg k-h
okay
Shaohui, it's useless to document a wrong interface.
Better to fix the interface _first_, then document becomes meaningful.

Fenggunag,
greg reminds me to add the docment into Documentation/ABI/, We miss it in
the RFC. Currently, the interface format is not finalized, when we decide the final interface, the last step is documenting it in.

Quoted 3 lines

Thanks,
Fengguang

Signature · 8 lines

Thanks & Regards,
Shaohui

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to [email protected].  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

Ankita Garg

2010-05-21 10:11 UTC #19 lore raw

In reply to Shaohui Zheng

Hi,

Quoted 11 lines · Shaohui Zheng

hotplug emulator:extend memory probe interface to support NUMA
Signed-off-by Shaohui Zheng <[email protected]>
Signed-off-by Haicheng Li <[email protected]>
Signed-off-by Wu Fengguang <[email protected]>
---
arch/x86/Kconfig +0 -0
index 54ccb0d..787024f 100644

arch/x86/Kconfig config ARCH_CPU_PROBE_RELEASE · line 1242

Quoted 4 lines

arch/x86/Kconfig +1 -0

@@ -1239,6 +1239,17 @@ config ARCH_CPU_PROBE_RELEASE
 	  is for cpu hot-add/hot-remove to specified node in software method.
 	  This is for debuging and testing purpose
 
+config ARCH_MEMORY_PROBE

The above symbol exists already...

Quoted 13 lines

arch/x86/Kconfig +10 -0

+	def_bool y
+	bool "Memory hotplug emulation"
+	depends on NUMA_HOTPLUG_EMU
+	---help---
+	  Enable memory hotplug emulation. Reserve memory with grub parameter
+	  "mem=N"(such as mem=1024M), where N is the initial memory size, the
+	  rest physical memory will be removed from e820 table; the memory probe
+	  interface is for memory hot-add to specified node in software method.
+	  This is for debuging and testing purpose
+
 config NODES_SHIFT
 	int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP
 	range 1 10

Signature · 11 lines

Regards,                                                                        
Ankita Garg ([email protected])                                                 
Linux Technology Center                                                         
IBM India Systems & Technology Labs,                                            
Bangalore, India

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to [email protected].  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>

Shaohui Zheng

author

2010-05-24 01:53 UTC #20 lore raw

Quoted 17 lines · Ankita Garg

Hi,
Quoted 14 lines · Shaohui Zheng
hotplug emulator:extend memory probe interface to support NUMA
Signed-off-by Shaohui Zheng <[email protected]>
Signed-off-by Haicheng Li <[email protected]>
Signed-off-by Wu Fengguang <[email protected]>
---
arch/x86/Kconfig +0 -0
index 54ccb0d..787024f 100644
@@ -1239,6 +1239,17 @@ config ARCH_CPU_PROBE_RELEASE
 	  is for cpu hot-add/hot-remove to specified node in software method.
 	  This is for debuging and testing purpose
 

Quoted 3 lines

arch/x86/Kconfig config ARCH_CPU_PROBE_RELEASE · line 1242
Quoted 1 line
arch/x86/Kconfig +1 -0
+config ARCH_MEMORY_PROBE
The above symbol exists already...

Yes, we create CONFIG_NUMA_HOTPLUG_EMU, CONFIG_NODE_HOTPLUG_EMU and CONFIG_ARCH_CPU_PROBE_RELEASE options, and move CONFIG_ARCH_MEMORY_PROBE together with the above 3 options.

Quoted 22 lines

Quoted 14 lines

arch/x86/Kconfig +10 -0

+	def_bool y
+	bool "Memory hotplug emulation"
+	depends on NUMA_HOTPLUG_EMU
+	---help---
+	  Enable memory hotplug emulation. Reserve memory with grub parameter
+	  "mem=N"(such as mem=1024M), where N is the initial memory size, the
+	  rest physical memory will be removed from e820 table; the memory probe
+	  interface is for memory hot-add to specified node in software method.
+	  This is for debuging and testing purpose
+
 config NODES_SHIFT
 	int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP
 	range 1 10

Signature · 5 lines

Regards,                                                                        
Ankita Garg ([email protected])                                                 
Linux Technology Center                                                         
IBM India Systems & Technology Labs,                                            
Bangalore, India

Signature · 8 lines

Thanks & Regards,
Shaohui

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to [email protected].  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>