From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <owner-linux-mm@kvack.org>
Received: from mail-io0-f199.google.com (mail-io0-f199.google.com [209.85.223.199])
	by kanga.kvack.org (Postfix) with ESMTP id BC5B56B0028
	for <linux-mm@kvack.org>; Wed, 21 Mar 2018 13:39:35 -0400 (EDT)
Received: by mail-io0-f199.google.com with SMTP id l19so4879855ioc.22
        for <linux-mm@kvack.org>; Wed, 21 Mar 2018 10:39:35 -0700 (PDT)
Received: from resqmta-ch2-05v.sys.comcast.net (resqmta-ch2-05v.sys.comcast.net. [2001:558:fe21:29:69:252:207:37])
        by mx.google.com with ESMTPS id p15-v6si3472108itc.133.2018.03.21.10.39.34
        for <linux-mm@kvack.org>
        (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128);
        Wed, 21 Mar 2018 10:39:34 -0700 (PDT)
Date: Wed, 21 Mar 2018 12:39:33 -0500 (CDT)
From: Christopher Lameter <cl@linux.com>
Subject: Re: [PATCH] slab: introduce the flag SLAB_MINIMIZE_WASTE
In-Reply-To: <alpine.DEB.2.20.1803211226350.3174@nuc-kabylake>
Message-ID: <alpine.DEB.2.20.1803211233290.3384@nuc-kabylake>
References: <alpine.LRH.2.02.1803200954590.18995@file01.intranet.prod.int.rdu2.redhat.com> <20180320173512.GA19669@bombadil.infradead.org> <alpine.DEB.2.20.1803201250480.27540@nuc-kabylake> <alpine.LRH.2.02.1803201510030.21066@file01.intranet.prod.int.rdu2.redhat.com>
 <alpine.DEB.2.20.1803201536590.28319@nuc-kabylake> <alpine.LRH.2.02.1803201740280.21066@file01.intranet.prod.int.rdu2.redhat.com> <alpine.DEB.2.20.1803211024220.2175@nuc-kabylake> <alpine.LRH.2.02.1803211153320.16017@file01.intranet.prod.int.rdu2.redhat.com>
 <alpine.DEB.2.20.1803211226350.3174@nuc-kabylake>
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Sender: owner-linux-mm@kvack.org
List-ID: <linux-mm.kvack.org>
To: Mikulas Patocka <mpatocka@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>, Pekka Enberg <penberg@kernel.org>, David Rientjes <rientjes@google.com>, Joonsoo Kim <iamjoonsoo.kim@lge.com>, Andrew Morton <akpm@linux-foundation.org>, linux-mm@kvack.org, dm-devel@redhat.com, Mike Snitzer <msnitzer@redhat.com>

One other thought: If you want to improve the behavior for large scale
objects allocated through kmalloc/kmemcache then we would certainly be
glad to entertain those ideas.

F.e. you could optimize the allcations > 2x PAGE_SIZE so that they do not
allocate powers of two pages. It would be relatively easy to make
kmalloc_large round the allocation to the next page size and then allocate
N consecutive pages via alloc_pages_exact() and free the remainder unused
pages or some such thing.