From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from psmtp.com (na3sys010amx126.postini.com [74.125.245.126]) by kanga.kvack.org (Postfix) with SMTP id C041C6B0033 for ; Wed, 17 Jul 2013 04:13:14 -0400 (EDT) Received: by mail-oa0-f46.google.com with SMTP id h1so2128932oag.5 for ; Wed, 17 Jul 2013 01:13:12 -0700 (PDT) Message-ID: <51E65210.6040103@gmail.com> Date: Wed, 17 Jul 2013 04:13:04 -0400 From: Hush Bensen MIME-Version: 1.0 Subject: Re: [PATCH 05/10] mm: compaction: don't require high order pages below min wmark References: <1373982114-19774-1-git-send-email-aarcange@redhat.com> <1373982114-19774-6-git-send-email-aarcange@redhat.com> In-Reply-To: <1373982114-19774-6-git-send-email-aarcange@redhat.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: owner-linux-mm@kvack.org List-ID: To: Andrea Arcangeli Cc: linux-mm@kvack.org, Mel Gorman , Rik van Riel , Hugh Dickins , Richard Davies , Shaohua Li , Rafael Aquini On 07/16/2013 09:41 AM, Andrea Arcangeli wrote: > The min wmark should be satisfied with just 1 hugepage. And the other > wmarks should be adjusted accordingly. We need to succeed the low > wmark check if there's some significant amount of 0 order pages, but > we don't need plenty of high order pages because the PF_MEMALLOC paths > don't require those. Creating a ton of high order pages that cannot be > allocated by the high order allocation paths (no PF_MEMALLOC) is quite > wasteful because they can be splitted in lower order pages before > anybody has a chance to allocate them. > > Signed-off-by: Andrea Arcangeli > --- > mm/page_alloc.c | 17 +++++++++++++++++ > 1 file changed, 17 insertions(+) > > diff --git a/mm/page_alloc.c b/mm/page_alloc.c > index db8fb66..d94503d 100644 > --- a/mm/page_alloc.c > +++ b/mm/page_alloc.c > @@ -1643,6 +1643,23 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, > > if (free_pages - free_cma <= min + lowmem_reserve) > return false; > + if (!order) > + return true; > + > + /* > + * Don't require any high order page under the min > + * wmark. Invoking compaction to create lots of high order > + * pages below the min wmark is wasteful because those > + * hugepages cannot be allocated without PF_MEMALLOC and the > + * PF_MEMALLOC paths must not depend on high order allocations > + * to succeed. > + */ > + min = mark - z->watermark[WMARK_MIN]; > + WARN_ON(min < 0); > + if (alloc_flags & ALLOC_HIGH) > + min -= min / 2; > + if (alloc_flags & ALLOC_HARDER) > + min -= min / 4; __zone_watermark_ok has these operations for mark, why do it again? > for (o = 0; o < order; o++) { > /* At the next order, this order's pages become unavailable */ > free_pages -= z->free_area[o].nr_free << o; -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org