[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20220413121051.a363193c726451115c634a69@linux-foundation.org>
Date: Wed, 13 Apr 2022 12:10:51 -0700
From: Andrew Morton <akpm@...ux-foundation.org>
To: Muchun Song <songmuchun@...edance.com>
Cc: corbet@....net, mike.kravetz@...cle.com, mcgrof@...nel.org,
keescook@...omium.org, yzaikin@...gle.com, osalvador@...e.de,
david@...hat.com, masahiroy@...nel.org, linux-doc@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-mm@...ck.org,
duanxiongchun@...edance.com, smuchun@...il.com
Subject: Re: [PATCH v8 4/4] mm: hugetlb_vmemmap: add
hugetlb_optimize_vmemmap sysctl
On Wed, 13 Apr 2022 22:47:48 +0800 Muchun Song <songmuchun@...edance.com> wrote:
> We must add hugetlb_free_vmemmap=on (or "off") to the boot cmdline and
> reboot the server to enable or disable the feature of optimizing vmemmap
> pages associated with HugeTLB pages. However, rebooting usually takes a
> long time. So add a sysctl to enable or disable the feature at runtime
> without rebooting.
Do we really need this feature? Really? What's the use case and what
is the end-user value?
Presumably CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP worsens things for some
setups/workloads? Please tell us much more about that. What is the
magnitude of the deoptimization?
Powered by blists - more mailing lists