On May 27, 2015, at 1:10 PM, Minchan Kim wrote:
> Hello Jungseok,
Hi, Minchan,
> On Tue, May 26, 2015 at 08:29:59PM +0900, Jungseok Lee wrote:
>> On May 25, 2015, at 11:40 PM, Minchan Kim wrote:
>>> Hello Jungseok,
>>
>> Hi, Minchan,
>>
>>> On Mon, May 25, 2015 at 01:02:20AM +0900, Jungseok
On May 27, 2015, at 4:31 PM, Arnd Bergmann wrote:
> On Wednesday 27 May 2015 15:22:50 Sergey Senozhatsky wrote:
>> On (05/27/15 13:10), Minchan Kim wrote:
>>> On Tue, May 26, 2015 at 08:29:59PM +0900, Jungseok Lee wrote:
if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
On May 27, 2015, at 1:24 PM, Minchan Kim wrote:
Hi, Minchan,
> On Tue, May 26, 2015 at 09:10:11PM +0900, Jungseok Lee wrote:
>> On May 25, 2015, at 11:58 PM, Minchan Kim wrote:
>>> On Mon, May 25, 2015 at 07:01:33PM +0900, Jungseok Lee wrote:
On May 25, 2015, at 2:49 AM, Arnd Bergmann
On Wednesday 27 May 2015 15:22:50 Sergey Senozhatsky wrote:
> On (05/27/15 13:10), Minchan Kim wrote:
> > On Tue, May 26, 2015 at 08:29:59PM +0900, Jungseok Lee wrote:
> > >
> > > if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
> > > goto nopage;
> > >
> > > IMHO, a reclaim
On (05/27/15 13:10), Minchan Kim wrote:
> On Tue, May 26, 2015 at 08:29:59PM +0900, Jungseok Lee wrote:
> > On May 25, 2015, at 11:40 PM, Minchan Kim wrote:
> > > Hello Jungseok,
> >
> > Hi, Minchan,
> >
> > > On Mon, May 25, 2015 at 01:02:20AM +0900, Jungseok Lee wrote:
> > >> Fork-routine
On May 27, 2015, at 4:31 PM, Arnd Bergmann wrote:
On Wednesday 27 May 2015 15:22:50 Sergey Senozhatsky wrote:
On (05/27/15 13:10), Minchan Kim wrote:
On Tue, May 26, 2015 at 08:29:59PM +0900, Jungseok Lee wrote:
if (test_thread_flag(TIF_MEMDIE) !(gfp_mask __GFP_NOFAIL))
goto nopage;
On May 27, 2015, at 1:24 PM, Minchan Kim wrote:
Hi, Minchan,
On Tue, May 26, 2015 at 09:10:11PM +0900, Jungseok Lee wrote:
On May 25, 2015, at 11:58 PM, Minchan Kim wrote:
On Mon, May 25, 2015 at 07:01:33PM +0900, Jungseok Lee wrote:
On May 25, 2015, at 2:49 AM, Arnd Bergmann wrote:
On
On May 27, 2015, at 1:10 PM, Minchan Kim wrote:
Hello Jungseok,
Hi, Minchan,
On Tue, May 26, 2015 at 08:29:59PM +0900, Jungseok Lee wrote:
On May 25, 2015, at 11:40 PM, Minchan Kim wrote:
Hello Jungseok,
Hi, Minchan,
On Mon, May 25, 2015 at 01:02:20AM +0900, Jungseok Lee wrote:
On (05/27/15 13:10), Minchan Kim wrote:
On Tue, May 26, 2015 at 08:29:59PM +0900, Jungseok Lee wrote:
On May 25, 2015, at 11:40 PM, Minchan Kim wrote:
Hello Jungseok,
Hi, Minchan,
On Mon, May 25, 2015 at 01:02:20AM +0900, Jungseok Lee wrote:
Fork-routine sometimes fails to get
On Wednesday 27 May 2015 15:22:50 Sergey Senozhatsky wrote:
On (05/27/15 13:10), Minchan Kim wrote:
On Tue, May 26, 2015 at 08:29:59PM +0900, Jungseok Lee wrote:
if (test_thread_flag(TIF_MEMDIE) !(gfp_mask __GFP_NOFAIL))
goto nopage;
IMHO, a reclaim operation would be not
On Tue, May 26, 2015 at 09:10:11PM +0900, Jungseok Lee wrote:
> On May 25, 2015, at 11:58 PM, Minchan Kim wrote:
> > On Mon, May 25, 2015 at 07:01:33PM +0900, Jungseok Lee wrote:
> >> On May 25, 2015, at 2:49 AM, Arnd Bergmann wrote:
> >>> On Monday 25 May 2015 01:02:20 Jungseok Lee wrote:
>
Hello Jungseok,
On Tue, May 26, 2015 at 08:29:59PM +0900, Jungseok Lee wrote:
> On May 25, 2015, at 11:40 PM, Minchan Kim wrote:
> > Hello Jungseok,
>
> Hi, Minchan,
>
> > On Mon, May 25, 2015 at 01:02:20AM +0900, Jungseok Lee wrote:
> >> Fork-routine sometimes fails to get a physically
On Tuesday 26 May 2015 01:36:29 Catalin Marinas wrote:
>
> > There are a lot of workloads that would benefit from having lower
> > per-thread memory cost.
>
> If we keep the 16KB stack, is there any advantage in a separate IRQ one
> (assuming
> that we won't overflow 16KB)?
It makes possible
On May 26, 2015, at 1:47 AM, Catalin Marinas wrote:
> On 25 May 2015, at 13:01, Jungseok Lee wrote:
>
>>> Could the stack size be reduced to 8KB perhaps?
>>
>> I guess probably not.
>>
>> A commit, 845ad05e, says that 8KB is not enough to cover SpecWeb benchmark.
>
> We could go back to 8KB
On May 25, 2015, at 11:58 PM, Minchan Kim wrote:
> On Mon, May 25, 2015 at 07:01:33PM +0900, Jungseok Lee wrote:
>> On May 25, 2015, at 2:49 AM, Arnd Bergmann wrote:
>>> On Monday 25 May 2015 01:02:20 Jungseok Lee wrote:
Fork-routine sometimes fails to get a physically contiguous region for
On May 25, 2015, at 11:40 PM, Minchan Kim wrote:
> Hello Jungseok,
Hi, Minchan,
> On Mon, May 25, 2015 at 01:02:20AM +0900, Jungseok Lee wrote:
>> Fork-routine sometimes fails to get a physically contiguous region for
>> thread_info on 4KB page system although free memory is enough. That is,
>>
On May 26, 2015, at 11:52 AM, yalin wang wrote:
> 2015-05-25 0:02 GMT+08:00 Jungseok Lee :
>> Fork-routine sometimes fails to get a physically contiguous region for
>> thread_info on 4KB page system although free memory is enough. That is,
>> a physically contiguous region, which is currently
Hello Jungseok,
On Tue, May 26, 2015 at 08:29:59PM +0900, Jungseok Lee wrote:
On May 25, 2015, at 11:40 PM, Minchan Kim wrote:
Hello Jungseok,
Hi, Minchan,
On Mon, May 25, 2015 at 01:02:20AM +0900, Jungseok Lee wrote:
Fork-routine sometimes fails to get a physically contiguous region
On Tue, May 26, 2015 at 09:10:11PM +0900, Jungseok Lee wrote:
On May 25, 2015, at 11:58 PM, Minchan Kim wrote:
On Mon, May 25, 2015 at 07:01:33PM +0900, Jungseok Lee wrote:
On May 25, 2015, at 2:49 AM, Arnd Bergmann wrote:
On Monday 25 May 2015 01:02:20 Jungseok Lee wrote:
Fork-routine
On May 25, 2015, at 11:40 PM, Minchan Kim wrote:
Hello Jungseok,
Hi, Minchan,
On Mon, May 25, 2015 at 01:02:20AM +0900, Jungseok Lee wrote:
Fork-routine sometimes fails to get a physically contiguous region for
thread_info on 4KB page system although free memory is enough. That is,
a
On May 25, 2015, at 11:58 PM, Minchan Kim wrote:
On Mon, May 25, 2015 at 07:01:33PM +0900, Jungseok Lee wrote:
On May 25, 2015, at 2:49 AM, Arnd Bergmann wrote:
On Monday 25 May 2015 01:02:20 Jungseok Lee wrote:
Fork-routine sometimes fails to get a physically contiguous region for
On May 26, 2015, at 11:52 AM, yalin wang wrote:
2015-05-25 0:02 GMT+08:00 Jungseok Lee jungseokle...@gmail.com:
Fork-routine sometimes fails to get a physically contiguous region for
thread_info on 4KB page system although free memory is enough. That is,
a physically contiguous region, which
On May 26, 2015, at 1:47 AM, Catalin Marinas wrote:
On 25 May 2015, at 13:01, Jungseok Lee jungseokle...@gmail.com wrote:
Could the stack size be reduced to 8KB perhaps?
I guess probably not.
A commit, 845ad05e, says that 8KB is not enough to cover SpecWeb benchmark.
We could go back
On Tuesday 26 May 2015 01:36:29 Catalin Marinas wrote:
There are a lot of workloads that would benefit from having lower
per-thread memory cost.
If we keep the 16KB stack, is there any advantage in a separate IRQ one
(assuming
that we won't overflow 16KB)?
It makes possible errors
2015-05-25 0:02 GMT+08:00 Jungseok Lee :
> Fork-routine sometimes fails to get a physically contiguous region for
> thread_info on 4KB page system although free memory is enough. That is,
> a physically contiguous region, which is currently 16KB, is not available
> since system memory is
On 25 May 2015, at 23:29, Arnd Bergmann wrote:
> On Monday 25 May 2015 19:47:15 Catalin Marinas wrote:
>> On 25 May 2015, at 13:01, Jungseok Lee wrote:
Could the stack size be reduced to 8KB perhaps?
>>>
>>> I guess probably not.
>>>
>>> A commit, 845ad05e, says that 8KB is not enough to
On Monday 25 May 2015 19:01:33 Jungseok Lee wrote:
> On May 25, 2015, at 2:49 AM, Arnd Bergmann wrote:
> > Could the stack size be reduced to 8KB perhaps?
>
> I guess probably not.
>
> A commit, 845ad05e, says that 8KB is not enough to cover SpecWeb benchmark.
> The stack size is 16KB on
On Monday 25 May 2015 19:47:15 Catalin Marinas wrote:
> On 25 May 2015, at 13:01, Jungseok Lee wrote:
>
> >> Could the stack size be reduced to 8KB perhaps?
> >
> > I guess probably not.
> >
> > A commit, 845ad05e, says that 8KB is not enough to cover SpecWeb benchmark.
>
> We could go back
On 25 May 2015, at 13:01, Jungseok Lee wrote:
>> Could the stack size be reduced to 8KB perhaps?
>
> I guess probably not.
>
> A commit, 845ad05e, says that 8KB is not enough to cover SpecWeb benchmark.
We could go back to 8KB stacks if we implement support for separate IRQ
stack on arm64.
On Mon, May 25, 2015 at 07:01:33PM +0900, Jungseok Lee wrote:
> On May 25, 2015, at 2:49 AM, Arnd Bergmann wrote:
> > On Monday 25 May 2015 01:02:20 Jungseok Lee wrote:
> >> Fork-routine sometimes fails to get a physically contiguous region for
> >> thread_info on 4KB page system although free
Hello Jungseok,
On Mon, May 25, 2015 at 01:02:20AM +0900, Jungseok Lee wrote:
> Fork-routine sometimes fails to get a physically contiguous region for
> thread_info on 4KB page system although free memory is enough. That is,
> a physically contiguous region, which is currently 16KB, is not
On May 25, 2015, at 2:49 AM, Arnd Bergmann wrote:
> On Monday 25 May 2015 01:02:20 Jungseok Lee wrote:
>> Fork-routine sometimes fails to get a physically contiguous region for
>> thread_info on 4KB page system although free memory is enough. That is,
>> a physically contiguous region, which is
On May 25, 2015, at 2:49 AM, Arnd Bergmann wrote:
On Monday 25 May 2015 01:02:20 Jungseok Lee wrote:
Fork-routine sometimes fails to get a physically contiguous region for
thread_info on 4KB page system although free memory is enough. That is,
a physically contiguous region, which is currently
Hello Jungseok,
On Mon, May 25, 2015 at 01:02:20AM +0900, Jungseok Lee wrote:
Fork-routine sometimes fails to get a physically contiguous region for
thread_info on 4KB page system although free memory is enough. That is,
a physically contiguous region, which is currently 16KB, is not available
On 25 May 2015, at 13:01, Jungseok Lee jungseokle...@gmail.com wrote:
Could the stack size be reduced to 8KB perhaps?
I guess probably not.
A commit, 845ad05e, says that 8KB is not enough to cover SpecWeb benchmark.
We could go back to 8KB stacks if we implement support for separate IRQ
On Mon, May 25, 2015 at 07:01:33PM +0900, Jungseok Lee wrote:
On May 25, 2015, at 2:49 AM, Arnd Bergmann wrote:
On Monday 25 May 2015 01:02:20 Jungseok Lee wrote:
Fork-routine sometimes fails to get a physically contiguous region for
thread_info on 4KB page system although free memory is
On Monday 25 May 2015 19:47:15 Catalin Marinas wrote:
On 25 May 2015, at 13:01, Jungseok Lee jungseokle...@gmail.com wrote:
Could the stack size be reduced to 8KB perhaps?
I guess probably not.
A commit, 845ad05e, says that 8KB is not enough to cover SpecWeb benchmark.
We could
On Monday 25 May 2015 19:01:33 Jungseok Lee wrote:
On May 25, 2015, at 2:49 AM, Arnd Bergmann wrote:
Could the stack size be reduced to 8KB perhaps?
I guess probably not.
A commit, 845ad05e, says that 8KB is not enough to cover SpecWeb benchmark.
The stack size is 16KB on x86_64. I am
2015-05-25 0:02 GMT+08:00 Jungseok Lee jungseokle...@gmail.com:
Fork-routine sometimes fails to get a physically contiguous region for
thread_info on 4KB page system although free memory is enough. That is,
a physically contiguous region, which is currently 16KB, is not available
since system
On 25 May 2015, at 23:29, Arnd Bergmann a...@arndb.de wrote:
On Monday 25 May 2015 19:47:15 Catalin Marinas wrote:
On 25 May 2015, at 13:01, Jungseok Lee jungseokle...@gmail.com wrote:
Could the stack size be reduced to 8KB perhaps?
I guess probably not.
A commit, 845ad05e, says that 8KB
On Monday 25 May 2015 01:02:20 Jungseok Lee wrote:
> Fork-routine sometimes fails to get a physically contiguous region for
> thread_info on 4KB page system although free memory is enough. That is,
> a physically contiguous region, which is currently 16KB, is not available
> since system memory is
Fork-routine sometimes fails to get a physically contiguous region for
thread_info on 4KB page system although free memory is enough. That is,
a physically contiguous region, which is currently 16KB, is not available
since system memory is fragmented.
This patch tries to solve the problem as
On Monday 25 May 2015 01:02:20 Jungseok Lee wrote:
Fork-routine sometimes fails to get a physically contiguous region for
thread_info on 4KB page system although free memory is enough. That is,
a physically contiguous region, which is currently 16KB, is not available
since system memory is
Fork-routine sometimes fails to get a physically contiguous region for
thread_info on 4KB page system although free memory is enough. That is,
a physically contiguous region, which is currently 16KB, is not available
since system memory is fragmented.
This patch tries to solve the problem as
44 matches
Mail list logo