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


Groups > linux.kernel > #1473155

Re: [PATCH v5 2/6] mm/cma: introduce new zone, ZONE_CMA

From Joonsoo Kim <iamjoonsoo.kim@lge.com>
Newsgroups linux.kernel
Subject Re: [PATCH v5 2/6] mm/cma: introduce new zone, ZONE_CMA
Date 2016-08-31 10:00 +0200
Message-ID <sc8Bc-80v-41@gated-at.bofh.it> (permalink)
References <sbmZz-36K-3@gated-at.bofh.it> <sbmZz-36K-13@gated-at.bofh.it> <sbOCt-3C0-5@gated-at.bofh.it> <sbQEh-4Xn-13@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


On Tue, Aug 30, 2016 at 06:10:46PM +0530, Aneesh Kumar K.V wrote:
> "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> writes:
> 
> > ....
> >
> >>  static inline void check_highest_zone(enum zone_type k)
> >>  {
> >> -	if (k > policy_zone && k != ZONE_MOVABLE)
> >> +	if (k > policy_zone && k != ZONE_MOVABLE && !is_zone_cma_idx(k))
> >>  		policy_zone = k;
> >>  }
> >>
> >
> >
> > Should we apply policy to allocation from ZONE CMA ?. CMA reserve
> > happens early and may mostly come from one node. Do we want the
> > CMA allocation to fail if we use mbind(MPOL_BIND) with a node mask not
> > including that node on which CMA is reserved, considering CMA memory is
> > going to be used for special purpose.
> 
> Looking at this again, I guess CMA alloc is not going to depend on
> memory policy, but this is for other movable allocation ?

This is for usual file cache or anonymous page allocation. IIUC,
policy_zone is used to determine if mempolicy should be applied or not
and setting policy_zone to ZONE_CMA makes mempolicy less useful.

Thanks.

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


Thread

[PATCH v5 0/6] Introduce ZONE_CMA js1304@gmail.com - 2016-08-29 07:10 +0200
  [PATCH v5 2/6] mm/cma: introduce new zone, ZONE_CMA js1304@gmail.com - 2016-08-29 07:10 +0200
    Re: [PATCH v5 2/6] mm/cma: introduce new zone, ZONE_CMA "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> - 2016-08-30 12:40 +0200
      Re: [PATCH v5 2/6] mm/cma: introduce new zone, ZONE_CMA "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> - 2016-08-30 14:50 +0200
        Re: [PATCH v5 2/6] mm/cma: introduce new zone, ZONE_CMA Joonsoo Kim <iamjoonsoo.kim@lge.com> - 2016-08-31 10:00 +0200
  [PATCH v5 3/6] mm/cma: populate ZONE_CMA js1304@gmail.com - 2016-08-29 07:10 +0200
  [PATCH v5 5/6] mm/cma: remove MIGRATE_CMA js1304@gmail.com - 2016-08-29 07:10 +0200
  [PATCH v5 6/6] mm/cma: remove per zone CMA stat js1304@gmail.com - 2016-08-29 07:10 +0200
  Re: [PATCH v5 0/6] Introduce ZONE_CMA "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> - 2016-08-29 11:30 +0200
    Re: [PATCH v5 0/6] Introduce ZONE_CMA Joonsoo Kim <js1304@gmail.com> - 2016-08-30 10:30 +0200
      Re: [PATCH v5 0/6] Introduce ZONE_CMA "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> - 2016-08-30 12:40 +0200
        Re: [PATCH v5 0/6] Introduce ZONE_CMA Joonsoo Kim <iamjoonsoo.kim@lge.com> - 2016-08-31 10:00 +0200
          Re: [PATCH v5 0/6] Introduce ZONE_CMA "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> - 2016-09-01 07:50 +0200
            Re: [PATCH v5 0/6] Introduce ZONE_CMA Joonsoo Kim <iamjoonsoo.kim@lge.com> - 2016-09-01 08:20 +0200

csiph-web