Re: [v2 PATCH -mm] mm: account deferred split THPs into MemAvailable

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Wed, Aug 28, 2019 at 06:02:24PM +0200, Michal Hocko wrote:
> > > 
> > > Any idea about a bad case?
> > 
> > Not really.
> > 
> > How bad you want it to get? How many processes share the page? Access
> > pattern? Locking situation?
> 
> Let's say how hard a regular user can make this?

It bumped to ~170 ms if each THP was mapped 5 times.

Adding ptl contention (tight loop of MADV_DONTNEED) in 3 processes that
maps the page, the time to split bumped to ~740ms.

Overally, it's reasonable to take ~100ms per GB of huge pages as rule of
thumb.

-- 
 Kirill A. Shutemov




[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux