Re: [dpdk-dev] [PATCH v2 2/5] mem: use address hint for mapping hugepages

["Burakov, Anatoly" <anatoly.burakov@intel.com>]

On 04-Oct-18 2:15 PM, Alejandro Lucero wrote:
> 
> 
> On Thu, Oct 4, 2018 at 1:08 PM Burakov, Anatoly 
> <anatoly.burakov@intel.com <mailto:anatoly.burakov@intel.com>> wrote:
> 
>     On 04-Oct-18 12:43 PM, Alejandro Lucero wrote:
>      >
>      >
>      > On Wed, Oct 3, 2018 at 1:50 PM Burakov, Anatoly
>      > <anatoly.burakov@intel.com <mailto:anatoly.burakov@intel.com>
>     <mailto:anatoly.burakov@intel.com
>     <mailto:anatoly.burakov@intel.com>>> wrote:
>      >
>      >     On 31-Aug-18 1:50 PM, Alejandro Lucero wrote:
>      >      > Linux kernel uses a really high address as starting
>     address for
>      >      > serving mmaps calls. If there exist addressing limitations and
>      >      > IOVA mode is VA, this starting address is likely too high for
>      >      > those devices. However, it is possible to use a lower
>     address in
>      >      > the process virtual address space as with 64 bits there is
>     a lot
>      >      > of available space.
>      >      >
>      >      > This patch adds an address hint as starting address for 64
>     bits
>      >      > systems.
>      >      >
>      >      > Signed-off-by: Alejandro Lucero
>     <alejandro.lucero@netronome.com <mailto:alejandro.lucero@netronome.com>
>      >     <mailto:alejandro.lucero@netronome.com
>     <mailto:alejandro.lucero@netronome.com>>>
>      >      > ---
>      >
>      >     <snip>
>      >
>      >      >
>      >      >               mapped_addr = mmap(requested_addr,
>     (size_t)map_sz,
>      >     PROT_READ,
>      >      >                               mmap_flags, -1, 0);
>      >      > +
>      >      >               if (mapped_addr == MAP_FAILED && allow_shrink)
>      >
>      >     Unintended whitespace change?
>      >
>      >
>      > Yes. I'll fix it.
>      >
>      >      >                       *size -= page_sz;
>      >      > -     } while (allow_shrink && mapped_addr == MAP_FAILED
>     && *size
>      >      > 0);
>      >      > +
>      >      > +             if (mapped_addr != MAP_FAILED && addr_is_hint &&
>      >      > +                 mapped_addr != requested_addr) {
>      >      > +                     /* hint was not used. Try with another
>      >     offset */
>      >      > +                     munmap(mapped_addr, map_sz);
>      >      > +                     mapped_addr = MAP_FAILED;
>      >      > +                     next_baseaddr =
>     RTE_PTR_ADD(next_baseaddr,
>      >     0x100000000);
>      >
>      >     Why not increment by page size? Sure, it could take some more
>     time to
>      >     allocate, but will result in less wasted memory.
>      >
>      >
>      > I though the same or even using smaller increments than hugepage
>     size.
>      > Increment the address in such amount does not mean we are wasting
>     memory
>      > but just leaving space if some mmap fails. I think it is better
>     to leave
>      > as much as space as possible just in case the data allocated in the
>      > conflicted area would need to grow in the future.
> 
>     Not sure i follow. Could you give an example of a scenario where
>     leaving
>     huge chunks of memory free would be preferable to just adding page size
>     and starting from page-size-aligned address next time we allocate?
> 
> 
> Usually there is nothing at 4GB address in 64 bit processes, usually the 
> text section being the first process region mapped and currently at far 
> higher than 4GB. If there is something mapped there before executing the 
> EAL hugepage/memory initialization code, not sure what it will be for, 
> but maybe it needs to grow using contiguous virtual addresses. As I say, 
> no idea what this could be used for, but the shorter the space when 
> trying again in this code, the less likely that flexibility could be there.

But you're already leaving holes there, what difference does it make? I 
mean, it's not important, i'm just not sure why the arbitrary 
0x100000000 increment instead of page size. Most of the calls into this 
function are from init code, and with init code we're usually calling 
this function quite a few times in succession (especially during memseg 
list allocations), so you are skipping space that could've been used for 
that.

(btw if you are to use this constant, it should be a macro, not a raw 
constant)

-- 
Thanks,
Anatoly