Hi Michael,
On 12/21/2012 08:46 PM, Michel Lespinasse wrote:
> I wanted to ask if you could check the sanity of the following patches
> in nommu configurations. My understanding is that these always
> populate mappings when they are created, so that MAP_POPULATE and
> MAP_LOCKED are actually
Hi Michael,
On 12/21/2012 08:46 PM, Michel Lespinasse wrote:
I wanted to ask if you could check the sanity of the following patches
in nommu configurations. My understanding is that these always
populate mappings when they are created, so that MAP_POPULATE and
MAP_LOCKED are actually no-ops.
On Fri, Jan 4, 2013 at 10:16 AM, Andy Lutomirski wrote:
> I still have quite a few instances of 2-6 ms of latency due to
> "call_rwsem_down_read_failed __do_page_fault do_page_fault
> page_fault". Any idea why? I don't know any great way to figure out
> who is holding mmap_sem at the time.
On Thu, Dec 20, 2012 at 4:49 PM, Michel Lespinasse wrote:
> We have many vma manipulation functions that are fast in the typical case,
> but can optionally be instructed to populate an unbounded number of ptes
> within the region they work on:
> - mmap with MAP_POPULATE or MAP_LOCKED flags;
> -
On Thu, Dec 20, 2012 at 4:49 PM, Michel Lespinasse wal...@google.com wrote:
We have many vma manipulation functions that are fast in the typical case,
but can optionally be instructed to populate an unbounded number of ptes
within the region they work on:
- mmap with MAP_POPULATE or MAP_LOCKED
On Fri, Jan 4, 2013 at 10:16 AM, Andy Lutomirski l...@amacapital.net wrote:
I still have quite a few instances of 2-6 ms of latency due to
call_rwsem_down_read_failed __do_page_fault do_page_fault
page_fault. Any idea why? I don't know any great way to figure out
who is holding mmap_sem at
On Sat, Dec 22, 2012 at 1:37 AM, Michel Lespinasse wrote:
> On Fri, Dec 21, 2012 at 6:16 PM, Andy Lutomirski wrote:
>> On Fri, Dec 21, 2012 at 5:59 PM, Michel Lespinasse wrote:
>>> Could you share your test case so I can try reproducing the issue
>>> you're seeing ?
>>
>> Not so easy. My test
On Sat, Dec 22, 2012 at 1:37 AM, Michel Lespinasse wal...@google.com wrote:
On Fri, Dec 21, 2012 at 6:16 PM, Andy Lutomirski l...@amacapital.net wrote:
On Fri, Dec 21, 2012 at 5:59 PM, Michel Lespinasse wal...@google.com wrote:
Could you share your test case so I can try reproducing the issue
Hi Michel,
On 12/21/2012 08:46 PM, Michel Lespinasse wrote:
I wanted to ask if you could check the sanity of the following patches
in nommu configurations. My understanding is that these always
Sure. I think it is worth CC'ing David Howells on these as well,
he has spent a fair bit of time in
On Fri, Dec 21, 2012 at 6:16 PM, Andy Lutomirski wrote:
> On Fri, Dec 21, 2012 at 5:59 PM, Michel Lespinasse wrote:
>> Could you share your test case so I can try reproducing the issue
>> you're seeing ?
>
> Not so easy. My test case is a large chunk of a high-frequency
> trading system :)
On Fri, Dec 21, 2012 at 6:16 PM, Andy Lutomirski l...@amacapital.net wrote:
On Fri, Dec 21, 2012 at 5:59 PM, Michel Lespinasse wal...@google.com wrote:
Could you share your test case so I can try reproducing the issue
you're seeing ?
Not so easy. My test case is a large chunk of a
Hi Michel,
On 12/21/2012 08:46 PM, Michel Lespinasse wrote:
I wanted to ask if you could check the sanity of the following patches
in nommu configurations. My understanding is that these always
Sure. I think it is worth CC'ing David Howells on these as well,
he has spent a fair bit of time in
On Fri, Dec 21, 2012 at 5:59 PM, Michel Lespinasse wrote:
> On Fri, Dec 21, 2012 at 5:09 PM, Andy Lutomirski wrote:
>> On Fri, Dec 21, 2012 at 4:59 PM, Michel Lespinasse wrote:
>>> On Fri, Dec 21, 2012 at 4:36 PM, Andy Lutomirski
>>> wrote:
Something's buggy here. My evil test case is
On Fri, Dec 21, 2012 at 5:09 PM, Andy Lutomirski wrote:
> On Fri, Dec 21, 2012 at 4:59 PM, Michel Lespinasse wrote:
>> On Fri, Dec 21, 2012 at 4:36 PM, Andy Lutomirski wrote:
>>> Something's buggy here. My evil test case is stuck with lots of
>>> threads spinning at 100% system time.
>>>
>>>
On Fri, Dec 21, 2012 at 4:59 PM, Michel Lespinasse wrote:
> On Fri, Dec 21, 2012 at 4:36 PM, Andy Lutomirski wrote:
>> On Thu, Dec 20, 2012 at 4:49 PM, Michel Lespinasse wrote:
>>> We have many vma manipulation functions that are fast in the typical case,
>>> but can optionally be instructed to
On Fri, Dec 21, 2012 at 4:36 PM, Andy Lutomirski wrote:
> On Thu, Dec 20, 2012 at 4:49 PM, Michel Lespinasse wrote:
>> We have many vma manipulation functions that are fast in the typical case,
>> but can optionally be instructed to populate an unbounded number of ptes
>> within the region they
On Thu, Dec 20, 2012 at 4:49 PM, Michel Lespinasse wrote:
> We have many vma manipulation functions that are fast in the typical case,
> but can optionally be instructed to populate an unbounded number of ptes
> within the region they work on:
> - mmap with MAP_POPULATE or MAP_LOCKED flags;
> -
Hi Greg,
I wanted to ask if you could check the sanity of the following patches
in nommu configurations. My understanding is that these always
populate mappings when they are created, so that MAP_POPULATE and
MAP_LOCKED are actually no-ops. Is this an accurate description ?
Thanks,
On Thu, Dec
Hi Greg,
I wanted to ask if you could check the sanity of the following patches
in nommu configurations. My understanding is that these always
populate mappings when they are created, so that MAP_POPULATE and
MAP_LOCKED are actually no-ops. Is this an accurate description ?
Thanks,
On Thu, Dec
On Thu, Dec 20, 2012 at 4:49 PM, Michel Lespinasse wal...@google.com wrote:
We have many vma manipulation functions that are fast in the typical case,
but can optionally be instructed to populate an unbounded number of ptes
within the region they work on:
- mmap with MAP_POPULATE or MAP_LOCKED
On Fri, Dec 21, 2012 at 4:36 PM, Andy Lutomirski l...@amacapital.net wrote:
On Thu, Dec 20, 2012 at 4:49 PM, Michel Lespinasse wal...@google.com wrote:
We have many vma manipulation functions that are fast in the typical case,
but can optionally be instructed to populate an unbounded number of
On Fri, Dec 21, 2012 at 4:59 PM, Michel Lespinasse wal...@google.com wrote:
On Fri, Dec 21, 2012 at 4:36 PM, Andy Lutomirski l...@amacapital.net wrote:
On Thu, Dec 20, 2012 at 4:49 PM, Michel Lespinasse wal...@google.com wrote:
We have many vma manipulation functions that are fast in the
On Fri, Dec 21, 2012 at 5:09 PM, Andy Lutomirski l...@amacapital.net wrote:
On Fri, Dec 21, 2012 at 4:59 PM, Michel Lespinasse wal...@google.com wrote:
On Fri, Dec 21, 2012 at 4:36 PM, Andy Lutomirski l...@amacapital.net wrote:
Something's buggy here. My evil test case is stuck with lots of
On Fri, Dec 21, 2012 at 5:59 PM, Michel Lespinasse wal...@google.com wrote:
On Fri, Dec 21, 2012 at 5:09 PM, Andy Lutomirski l...@amacapital.net wrote:
On Fri, Dec 21, 2012 at 4:59 PM, Michel Lespinasse wal...@google.com wrote:
On Fri, Dec 21, 2012 at 4:36 PM, Andy Lutomirski
We have many vma manipulation functions that are fast in the typical case,
but can optionally be instructed to populate an unbounded number of ptes
within the region they work on:
- mmap with MAP_POPULATE or MAP_LOCKED flags;
- remap_file_pages() with MAP_NONBLOCK not set or when working on a
We have many vma manipulation functions that are fast in the typical case,
but can optionally be instructed to populate an unbounded number of ptes
within the region they work on:
- mmap with MAP_POPULATE or MAP_LOCKED flags;
- remap_file_pages() with MAP_NONBLOCK not set or when working on a
26 matches
Mail list logo