On Thu, Apr 24, 2014 at 05:41:20PM +, Luck, Tony wrote:
> >>The BIOS always sends CPU hot-addition events before memory
> >> hot-addition events, so it's hard to change the order.
> >>And we couldn't completely solve this performance penalty because the
> >> affected code tries to
>> The BIOS always sends CPU hot-addition events before memory
>> hot-addition events, so it's hard to change the order.
>> And we couldn't completely solve this performance penalty because the
>> affected code tries to allocate memory for all possible
>> CPUs instead of onlined CPUs.
>
On Thu, Apr 24, 2014 at 10:59:45AM +0800, Jiang Liu wrote:
> On 2014/4/24 1:46, Luck, Tony wrote:
> 1) Handle CPU hot-addition event
> 1.a) gather platform specific information
> 1.b) associate hot-added CPU with a node
> 1.c) create CPU device
> 2) User online hot-added
On Thu, Apr 24, 2014 at 10:59:45AM +0800, Jiang Liu wrote:
On 2014/4/24 1:46, Luck, Tony wrote:
1) Handle CPU hot-addition event
1.a) gather platform specific information
1.b) associate hot-added CPU with a node
1.c) create CPU device
2) User online hot-added CPUs through sysfs:
2.a)
The BIOS always sends CPU hot-addition events before memory
hot-addition events, so it's hard to change the order.
And we couldn't completely solve this performance penalty because the
affected code tries to allocate memory for all possible
CPUs instead of onlined CPUs.
So the
On Thu, Apr 24, 2014 at 05:41:20PM +, Luck, Tony wrote:
The BIOS always sends CPU hot-addition events before memory
hot-addition events, so it's hard to change the order.
And we couldn't completely solve this performance penalty because the
affected code tries to allocate memory
On 2014/4/24 1:46, Luck, Tony wrote:
1) Handle CPU hot-addition event
1.a) gather platform specific information
1.b) associate hot-added CPU with a node
1.c) create CPU device
2) User online hot-added CPUs through sysfs:
2.a) cpu_up()
2.b)
> > > 1) Handle CPU hot-addition event
> > > 1.a) gather platform specific information
> > > 1.b) associate hot-added CPU with a node
> > > 1.c) create CPU device
> > > 2) User online hot-added CPUs through sysfs:
> > > 2.a) cpu_up()
> > > 2.b) ->try_online_node()
> > > 2.c)
1) Handle CPU hot-addition event
1.a) gather platform specific information
1.b) associate hot-added CPU with a node
1.c) create CPU device
2) User online hot-added CPUs through sysfs:
2.a) cpu_up()
2.b) -try_online_node()
2.c)
On 2014/4/24 1:46, Luck, Tony wrote:
1) Handle CPU hot-addition event
1.a) gather platform specific information
1.b) associate hot-added CPU with a node
1.c) create CPU device
2) User online hot-added CPUs through sysfs:
2.a) cpu_up()
2.b) -try_online_node()
2.c)
On Wed, Apr 23, 2014 at 07:32:13AM +0200, Peter Zijlstra wrote:
> On Wed, Apr 23, 2014 at 10:45:13AM +0800, Jiang Liu wrote:
> > Hi Peter,
> > It's not for memoryless node, but to solve a race window
> > in CPU hot-addition. The related CPU hot-addition flow is:
> > 1) Handle CPU hot-addition
On 2014/4/23 13:32, Peter Zijlstra wrote:
> On Wed, Apr 23, 2014 at 10:45:13AM +0800, Jiang Liu wrote:
>> Hi Peter,
>> It's not for memoryless node, but to solve a race window
>> in CPU hot-addition. The related CPU hot-addition flow is:
>> 1) Handle CPU hot-addition event
>> 1.a) gather
On Wed, Apr 23, 2014 at 10:45:13AM +0800, Jiang Liu wrote:
> Hi Peter,
> It's not for memoryless node, but to solve a race window
> in CPU hot-addition. The related CPU hot-addition flow is:
> 1) Handle CPU hot-addition event
> 1.a) gather platform specific information
> 1.b) associate
On 2014/4/23 9:59, David Rientjes wrote:
> On Tue, 22 Apr 2014, Peter Zijlstra wrote:
>
>> On Tue, Apr 22, 2014 at 01:01:51PM -0700, Andrew Morton wrote:
>>> On Tue, 22 Apr 2014 10:15:15 +0200 Peter Zijlstra
>>> wrote:
>>>
On Tue, Apr 22, 2014 at 01:27:15PM +0800, Jiang Liu wrote:
>
Hi Peter,
It's not for memoryless node, but to solve a race window
in CPU hot-addition. The related CPU hot-addition flow is:
1) Handle CPU hot-addition event
1.a) gather platform specific information
1.b) associate hot-added CPU with a node
1.c) create CPU device
2) User online hot-added
On Tue, 2014-04-22 at 22:04 +0200, Peter Zijlstra wrote:
> On Tue, Apr 22, 2014 at 01:01:51PM -0700, Andrew Morton wrote:
> > On Tue, 22 Apr 2014 10:15:15 +0200 Peter Zijlstra
> > wrote:
> >
> > > On Tue, Apr 22, 2014 at 01:27:15PM +0800, Jiang Liu wrote:
> > > > When calling
On Tue, 22 Apr 2014, Peter Zijlstra wrote:
> On Tue, Apr 22, 2014 at 01:01:51PM -0700, Andrew Morton wrote:
> > On Tue, 22 Apr 2014 10:15:15 +0200 Peter Zijlstra
> > wrote:
> >
> > > On Tue, Apr 22, 2014 at 01:27:15PM +0800, Jiang Liu wrote:
> > > > When calling kzalloc_node(size, flags,
On Tue, Apr 22, 2014 at 01:01:51PM -0700, Andrew Morton wrote:
> On Tue, 22 Apr 2014 10:15:15 +0200 Peter Zijlstra
> wrote:
>
> > On Tue, Apr 22, 2014 at 01:27:15PM +0800, Jiang Liu wrote:
> > > When calling kzalloc_node(size, flags, node), we should first check
> > > whether node is onlined,
On Tue, 22 Apr 2014 10:15:15 +0200 Peter Zijlstra wrote:
> On Tue, Apr 22, 2014 at 01:27:15PM +0800, Jiang Liu wrote:
> > When calling kzalloc_node(size, flags, node), we should first check
> > whether node is onlined, otherwise it may cause invalid memory access
> > as below.
>
> But this is
On Tue, Apr 22, 2014 at 01:27:15PM +0800, Jiang Liu wrote:
> When calling kzalloc_node(size, flags, node), we should first check
> whether node is onlined, otherwise it may cause invalid memory access
> as below.
But this is only for memory less node crap, right?
--
To unsubscribe from this
On Tue, Apr 22, 2014 at 01:27:15PM +0800, Jiang Liu wrote:
When calling kzalloc_node(size, flags, node), we should first check
whether node is onlined, otherwise it may cause invalid memory access
as below.
But this is only for memory less node crap, right?
--
To unsubscribe from this list:
On Tue, 22 Apr 2014 10:15:15 +0200 Peter Zijlstra pet...@infradead.org wrote:
On Tue, Apr 22, 2014 at 01:27:15PM +0800, Jiang Liu wrote:
When calling kzalloc_node(size, flags, node), we should first check
whether node is onlined, otherwise it may cause invalid memory access
as below.
On Tue, Apr 22, 2014 at 01:01:51PM -0700, Andrew Morton wrote:
On Tue, 22 Apr 2014 10:15:15 +0200 Peter Zijlstra pet...@infradead.org
wrote:
On Tue, Apr 22, 2014 at 01:27:15PM +0800, Jiang Liu wrote:
When calling kzalloc_node(size, flags, node), we should first check
whether node is
On Tue, 22 Apr 2014, Peter Zijlstra wrote:
On Tue, Apr 22, 2014 at 01:01:51PM -0700, Andrew Morton wrote:
On Tue, 22 Apr 2014 10:15:15 +0200 Peter Zijlstra pet...@infradead.org
wrote:
On Tue, Apr 22, 2014 at 01:27:15PM +0800, Jiang Liu wrote:
When calling kzalloc_node(size, flags,
On Tue, 2014-04-22 at 22:04 +0200, Peter Zijlstra wrote:
On Tue, Apr 22, 2014 at 01:01:51PM -0700, Andrew Morton wrote:
On Tue, 22 Apr 2014 10:15:15 +0200 Peter Zijlstra pet...@infradead.org
wrote:
On Tue, Apr 22, 2014 at 01:27:15PM +0800, Jiang Liu wrote:
When calling
Hi Peter,
It's not for memoryless node, but to solve a race window
in CPU hot-addition. The related CPU hot-addition flow is:
1) Handle CPU hot-addition event
1.a) gather platform specific information
1.b) associate hot-added CPU with a node
1.c) create CPU device
2) User online hot-added
On 2014/4/23 9:59, David Rientjes wrote:
On Tue, 22 Apr 2014, Peter Zijlstra wrote:
On Tue, Apr 22, 2014 at 01:01:51PM -0700, Andrew Morton wrote:
On Tue, 22 Apr 2014 10:15:15 +0200 Peter Zijlstra pet...@infradead.org
wrote:
On Tue, Apr 22, 2014 at 01:27:15PM +0800, Jiang Liu wrote:
On Wed, Apr 23, 2014 at 10:45:13AM +0800, Jiang Liu wrote:
Hi Peter,
It's not for memoryless node, but to solve a race window
in CPU hot-addition. The related CPU hot-addition flow is:
1) Handle CPU hot-addition event
1.a) gather platform specific information
1.b) associate hot-added
On 2014/4/23 13:32, Peter Zijlstra wrote:
On Wed, Apr 23, 2014 at 10:45:13AM +0800, Jiang Liu wrote:
Hi Peter,
It's not for memoryless node, but to solve a race window
in CPU hot-addition. The related CPU hot-addition flow is:
1) Handle CPU hot-addition event
1.a) gather platform
On Wed, Apr 23, 2014 at 07:32:13AM +0200, Peter Zijlstra wrote:
On Wed, Apr 23, 2014 at 10:45:13AM +0800, Jiang Liu wrote:
Hi Peter,
It's not for memoryless node, but to solve a race window
in CPU hot-addition. The related CPU hot-addition flow is:
1) Handle CPU hot-addition event
When calling kzalloc_node(size, flags, node), we should first check
whether node is onlined, otherwise it may cause invalid memory access
as below.
[ 3663.324476] BUG: unable to handle kernel paging request at 1f08
[ 3663.332348] IP: [] __alloc_pages_nodemask+0xb9/0x2d0
[ 3663.339719]
When calling kzalloc_node(size, flags, node), we should first check
whether node is onlined, otherwise it may cause invalid memory access
as below.
[ 3663.324476] BUG: unable to handle kernel paging request at 1f08
[ 3663.332348] IP: [81172219]
32 matches
Mail list logo