Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1470038

Re: what is the purpose of SLAB and SLUB (was: Re: [PATCH v3] mm/slab: Improve performance of gathering slabinfo) stats

Show all headers | View raw

On Wed, Aug 24, 2016 at 11:01:43PM -0500, Christoph Lameter wrote:
> On Wed, 24 Aug 2016, Mel Gorman wrote:
> > If/when I get back to the page allocator, the priority would be a bulk
> > API for faster allocs of batches of order-0 pages instead of allocating
> > a large page and splitting.
> >
> 
> OMG. Do we really want to continue this? There are billions of Linux
> devices out there that require a reboot at least once a week. This is now
> standard with certain Android phones. In our company we reboot all
> machines every week because fragmentation degrades performance
> significantly. We need to finally face up to it and deal with the issue
> instead of continuing to produce more half ass-ed solutions.
> 

Flipping the lid aside, there will always be a need for fast management
of 4K pages. The primary use case is networking that sometimes uses
high-order pages to avoid allocator overhead and amortise DMA setup.
Userspace-mapped pages will always be 4K although fault-around may benefit
from bulk allocating the pages. That is relatively low hanging fruit that
would take a few weeks given a free schedule.

Dirty tracking of pages on a 4K boundary will always be required to avoid IO
multiplier effects that cannot be side-stepped by increasing the fundamental
unit of allocation.

Batching of tree_lock during reclaim for large files and swapping is also
relatively low hanging fruit that also is doable in a week or two.

A high-order per-cpu cache for SLUB to reduce zone->lock contention is
also relatively low hanging fruit with the caveat it makes per_cpu_pages
larger than a cache line.

If you want to rework the VM to use a larger fundamental unit, track
sub-units where required and deal with the internal fragmentation issues
then by all means go ahead and deal with it.
 
-- 
Mel Gorman
SUSE Labs

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH v3] mm/slab: Improve performance of gathering slabinfo stats Aruna Ramakrishna <aruna.ramakrishna@oracle.com> - 2016-08-17 20:30 +0200
  Re: [PATCH v3] mm/slab: Improve performance of gathering slabinfo  stats Eric Dumazet <eric.dumazet@gmail.com> - 2016-08-17 21:10 +0200
    Re: [PATCH v3] mm/slab: Improve performance of gathering slabinfo  stats Aruna Ramakrishna <aruna.ramakrishna@oracle.com> - 2016-08-17 21:30 +0200
  Re: [PATCH v3] mm/slab: Improve performance of gathering slabinfo  stats Michal Hocko <mhocko@kernel.org> - 2016-08-18 14:00 +0200
    Re: [PATCH v3] mm/slab: Improve performance of gathering slabinfo  stats aruna.ramakrishna@oracle.com - 2016-08-19 07:50 +0200
    Re: [PATCH v3] mm/slab: Improve performance of gathering slabinfo  stats Joonsoo Kim <iamjoonsoo.kim@lge.com> - 2016-08-23 04:10 +0200
      what is the purpose of SLAB and SLUB (was: Re: [PATCH v3] mm/slab:  Improve performance of gathering slabinfo) stats Michal Hocko <mhocko@kernel.org> - 2016-08-23 17:40 +0200
        Re: what is the purpose of SLAB and SLUB Andi Kleen <andi@firstfloor.org> - 2016-08-23 18:00 +0200
          Re: what is the purpose of SLAB and SLUB Christoph Lameter <cl@linux.com> - 2016-08-25 06:40 +0200
            Re: what is the purpose of SLAB and SLUB Michal Hocko <mhocko@kernel.org> - 2016-08-25 09:40 +0200
              Re: what is the purpose of SLAB and SLUB Christoph Lameter <cl@linux.com> - 2016-08-25 22:00 +0200
        Re: what is the purpose of SLAB and SLUB (was: Re: [PATCH v3]  mm/slab: Improve performance of gathering slabinfo) stats Joonsoo Kim <iamjoonsoo.kim@lge.com> - 2016-08-24 03:10 +0200
          Re: what is the purpose of SLAB and SLUB (was: Re: [PATCH v3]  mm/slab: Improve performance of gathering slabinfo) stats Michal Hocko <mhocko@kernel.org> - 2016-08-24 10:10 +0200
        Re: what is the purpose of SLAB and SLUB (was: Re: [PATCH v3]  mm/slab: Improve performance of gathering slabinfo) stats Mel Gorman <mgorman@suse.de> - 2016-08-24 10:30 +0200
          Re: what is the purpose of SLAB and SLUB (was: Re: [PATCH v3] mm/slab:  Improve performance of gathering slabinfo) stats Christoph Lameter <cl@linux.com> - 2016-08-25 06:40 +0200
            Re: what is the purpose of SLAB and SLUB (was: Re: [PATCH v3]  mm/slab: Improve performance of gathering slabinfo) stats Mel Gorman <mgorman@suse.de> - 2016-08-25 12:10 +0200
              Re: what is the purpose of SLAB and SLUB (was: Re: [PATCH v3] mm/slab:  Improve performance of gathering slabinfo) stats Christoph Lameter <cl@linux.com> - 2016-08-25 22:00 +0200
                Re: what is the purpose of SLAB and SLUB Andi Kleen <andi@firstfloor.org> - 2016-08-26 22:50 +0200
                Re: what is the purpose of SLAB and SLUB Michal Hocko <mhocko@kernel.org> - 2016-08-29 15:50 +0200
                Re: what is the purpose of SLAB and SLUB Christoph Lameter <cl@linux.com> - 2016-08-29 16:50 +0200
                Re: what is the purpose of SLAB and SLUB (was: Re: [PATCH v3]  mm/slab: Improve performance of gathering slabinfo) stats Mel Gorman <mgorman@suse.de> - 2016-08-30 11:50 +0200
                Re: what is the purpose of SLAB and SLUB (was: Re: [PATCH v3] mm/slab:  Improve performance of gathering slabinfo) stats Christoph Lameter <cl@linux.com> - 2016-08-30 21:40 +0200

csiph-web