Linux-kselftest Archive on lore.kernel.org
 help / color / Atom feed
From: Mina Almasry <almasrymina@google.com>
To: Mike Kravetz <mike.kravetz@oracle.com>
Cc: shuah <shuah@kernel.org>, David Rientjes <rientjes@google.com>,
	Shakeel Butt <shakeelb@google.com>,
	Greg Thelen <gthelen@google.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	open list <linux-kernel@vger.kernel.org>,
	linux-mm@kvack.org, linux-kselftest@vger.kernel.org,
	cgroups@vger.kernel.org
Subject: Re: [PATCH v12 7/9] hugetlb: support file_region coalescing again
Date: Tue, 18 Feb 2020 23:54:34 -0800
Message-ID: <CAHS8izOTipknnYaKz=FdzL-7yW-Z61ck1yPnYWixyMSJuTUYLQ@mail.gmail.com> (raw)
In-Reply-To: <cb402ae6-8424-c1f7-35ff-6acc68f9a23b@oracle.com>

On Tue, Feb 18, 2020 at 7:31 PM Mike Kravetz <mike.kravetz@oracle.com> wrote:
>
> On 2/11/20 1:31 PM, Mina Almasry wrote:
> > An earlier patch in this series disabled file_region coalescing in order
> > to hang the hugetlb_cgroup uncharge info on the file_region entries.
> >
> > This patch re-adds support for coalescing of file_region entries.
> > Essentially everytime we add an entry, we call a recursive function that
> > tries to coalesce the added region with the regions next to it. The
> > worst case call depth for this function is 3: one to coalesce with the
> > region next to it, one to coalesce to the region prev, and one to reach
> > the base case.
> >
> > This is an important performance optimization as private mappings add
> > their entries page by page, and we could incur big performance costs for
> > large mappings with lots of file_region entries in their resv_map.
> >
> > Signed-off-by: Mina Almasry <almasrymina@google.com>
> >
> > ---
> >
> > Changes in v12:
> > - Changed logic for coalescing. Instead of checking inline to coalesce
> > with only the region on next or prev, we now have a recursive function
> > that takes care of coalescing in both directions.
> > - For testing this code I added a bunch of debug code that checks that
> > the entries in the resv_map are coalesced appropriately. This passes
> > with libhugetlbfs tests.
> >
> > ---
> >  mm/hugetlb.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++++++++
> >  1 file changed, 85 insertions(+)
> >
> > diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> > index 2d62dd35399db..45219cb58ac71 100644
> > --- a/mm/hugetlb.c
> > +++ b/mm/hugetlb.c
> > @@ -276,6 +276,86 @@ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg,
> >  #endif
> >  }
> >
> > +static bool has_same_uncharge_info(struct file_region *rg,
> > +                                struct file_region *org)
> > +{
> > +#ifdef CONFIG_CGROUP_HUGETLB
> > +     return rg && org &&
> > +            rg->reservation_counter == org->reservation_counter &&
> > +            rg->css == org->css;
> > +
> > +#else
> > +     return true;
> > +#endif
> > +}
> > +
> > +#ifdef CONFIG_DEBUG_VM
> > +static void dump_resv_map(struct resv_map *resv)
> > +{
> > +     struct list_head *head = &resv->regions;
> > +     struct file_region *rg = NULL;
> > +
> > +     pr_err("--------- start print resv_map ---------\n");
> > +     list_for_each_entry(rg, head, link) {
> > +             pr_err("rg->from=%ld, rg->to=%ld, rg->reservation_counter=%px, rg->css=%px\n",
> > +                    rg->from, rg->to, rg->reservation_counter, rg->css);
> > +     }
> > +     pr_err("--------- end print resv_map ---------\n");
> > +}
> > +
> > +/* Debug function to loop over the resv_map and make sure that coalescing is
> > + * working.
> > + */
> > +static void check_coalesce_bug(struct resv_map *resv)
> > +{
> > +     struct list_head *head = &resv->regions;
> > +     struct file_region *rg = NULL, *nrg = NULL;
> > +
> > +     list_for_each_entry(rg, head, link) {
> > +             nrg = list_next_entry(rg, link);
> > +
> > +             if (&nrg->link == head)
> > +                     break;
> > +
> > +             if (nrg->reservation_counter && nrg->from == rg->to &&
> > +                 nrg->reservation_counter == rg->reservation_counter &&
> > +                 nrg->css == rg->css) {
> > +                     dump_resv_map(resv);
> > +                     VM_BUG_ON(true);
> > +             }
> > +     }
> > +}
> > +#endif
> > +
> > +static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)
> > +{
> > +     struct file_region *nrg = NULL, *prg = NULL;
> > +
> > +     prg = list_prev_entry(rg, link);
> > +     if (&prg->link != &resv->regions && prg->to == rg->from &&
> > +         has_same_uncharge_info(prg, rg)) {
> > +             prg->to = rg->to;
> > +
> > +             list_del(&rg->link);
> > +             kfree(rg);
> > +
> > +             coalesce_file_region(resv, prg);
> > +             return;
> > +     }
> > +
> > +     nrg = list_next_entry(rg, link);
> > +     if (&nrg->link != &resv->regions && nrg->from == rg->to &&
> > +         has_same_uncharge_info(nrg, rg)) {
> > +             nrg->from = rg->from;
> > +
> > +             list_del(&rg->link);
> > +             kfree(rg);
> > +
> > +             coalesce_file_region(resv, nrg);
> > +             return;
> > +     }
> > +}
> > +
> >  /* Must be called with resv->lock held. Calling this with count_only == true
> >   * will count the number of pages to be added but will not modify the linked
> >   * list. If regions_needed != NULL and count_only == true, then regions_needed
> > @@ -327,6 +407,7 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
> >                               record_hugetlb_cgroup_uncharge_info(h_cg, h,
> >                                                                   resv, nrg);
> >                               list_add(&nrg->link, rg->link.prev);
> > +                             coalesce_file_region(resv, nrg);
> >                       } else if (regions_needed)
> >                               *regions_needed += 1;
> >               }
> > @@ -344,11 +425,15 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
> >                               resv, last_accounted_offset, t);
> >                       record_hugetlb_cgroup_uncharge_info(h_cg, h, resv, nrg);
> >                       list_add(&nrg->link, rg->link.prev);
> > +                     coalesce_file_region(resv, nrg);
> >               } else if (regions_needed)
> >                       *regions_needed += 1;
> >       }
> >
> >       VM_BUG_ON(add < 0);
> > +#ifdef CONFIG_DEBUG_VM
> > +     check_coalesce_bug(resv);
> > +#endif
>
> Some distros have CONFIG_DEBUG_VM on in their default kernels.  Fedora comes
> to mind.  Yes, this means 'VM_BUG_ON()' become 'BUG_ON()'.  That is somewhat
> accepted.  I don't think we want this debug code behind CONFIG_DEBUG_VM and
> called each time a file region is added.  It may be overkill to make it a
> debug option via the config system.  Perhaps, just make it something like
> CONFIG_DEBUG_HUGETLB_RSV_REGION and let hugetlb developers turn it on if
> they would like?
>

Ah, I feel like adding a whole config to accommodate this function is
overkill and will end up being dead code anyway as no-one remembers to
turn it on. If it's the same to you I'll take it out of the patch and
leave it as a local change for me to test with.

> Other than that, the code looks good.
> --
> Mike Kravetz
>
> >       return add;
> >  }
> >
> > --
> > 2.25.0.225.g125e21ebc7-goog
> >

  reply index

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-11 21:31 [PATCH v12 1/9] hugetlb_cgroup: Add hugetlb_cgroup reservation counter Mina Almasry
2020-02-11 21:31 ` [PATCH v12 2/9] hugetlb_cgroup: add interface for charge/uncharge hugetlb reservations Mina Almasry
2020-02-15  0:50   ` Mike Kravetz
2020-02-16  1:21     ` David Rientjes
2020-02-11 21:31 ` [PATCH v12 3/9] hugetlb_cgroup: add reservation accounting for private mappings Mina Almasry
2020-02-11 21:31 ` [PATCH v12 4/9] hugetlb: disable region_add file_region coalescing Mina Almasry
2020-02-15  1:27   ` Mike Kravetz
2020-02-16  1:25   ` David Rientjes
2020-02-11 21:31 ` [PATCH v12 5/9] hugetlb_cgroup: add accounting for shared mappings Mina Almasry
2020-02-16  1:29   ` David Rientjes
2020-02-18 18:07   ` Mike Kravetz
2020-02-11 21:31 ` [PATCH v12 6/9] hugetlb_cgroup: support noreserve mappings Mina Almasry
2020-02-18 20:57   ` Mike Kravetz
2020-02-11 21:31 ` [PATCH v12 7/9] hugetlb: support file_region coalescing again Mina Almasry
2020-02-16  1:29   ` David Rientjes
2020-02-19  3:28   ` Mike Kravetz
2020-02-19  7:54     ` Mina Almasry [this message]
2020-02-11 21:31 ` [PATCH v12 8/9] hugetlb_cgroup: Add hugetlb_cgroup reservation tests Mina Almasry
2020-02-12  8:50   ` Sandipan Das
2020-02-20  0:05     ` Mina Almasry
2020-02-21  0:52   ` Mike Kravetz
2020-02-11 21:31 ` [PATCH v12 9/9] hugetlb_cgroup: Add hugetlb_cgroup reservation docs Mina Almasry
2020-02-20  0:03   ` Mina Almasry
2020-02-20  0:18   ` Mike Kravetz
2020-02-11 23:19 ` [PATCH v12 1/9] hugetlb_cgroup: Add hugetlb_cgroup reservation counter Andrew Morton
2020-02-18 14:21   ` Qian Cai
2020-02-18 18:35     ` Mina Almasry
2020-02-18 18:41       ` Qian Cai
2020-02-18 19:14       ` Mike Kravetz
2020-02-18 19:25         ` Mina Almasry
2020-02-18 21:36           ` Mina Almasry
2020-02-18 21:41             ` Mike Kravetz
2020-02-18 22:27               ` Mina Almasry
2020-02-19 19:05   ` Mina Almasry
2020-02-19 21:06     ` Andrew Morton
2020-02-20 19:22       ` Mina Almasry
2020-02-21  0:28         ` Andrew Morton
2020-02-21  0:41           ` Mike Kravetz
2020-02-21  1:52             ` Mina Almasry
2020-02-21 20:19       ` Mina Almasry

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='CAHS8izOTipknnYaKz=FdzL-7yW-Z61ck1yPnYWixyMSJuTUYLQ@mail.gmail.com' \
    --to=almasrymina@google.com \
    --cc=akpm@linux-foundation.org \
    --cc=cgroups@vger.kernel.org \
    --cc=gthelen@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mike.kravetz@oracle.com \
    --cc=rientjes@google.com \
    --cc=shakeelb@google.com \
    --cc=shuah@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-kselftest Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-kselftest/0 linux-kselftest/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-kselftest linux-kselftest/ https://lore.kernel.org/linux-kselftest \
		linux-kselftest@vger.kernel.org
	public-inbox-index linux-kselftest

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kselftest


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git