[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-Id: <20170223.113218.2219144071313988229.davem@davemloft.net>
Date: Thu, 23 Feb 2017 11:32:18 -0500 (EST)
From: David Miller <davem@...emloft.net>
To: nitin.m.gupta@...cle.com
Cc: mike.kravetz@...cle.com, akpm@...ux-foundation.org,
julian.calaby@...il.com, hughd@...gle.com,
adam.buchbinder@...il.com, kirill.shutemov@...ux.intel.com,
sfr@...b.auug.org.au, paul.gortmaker@...driver.com,
thomas.tai@...cle.com, chris.hyser@...cle.com,
khalid.aziz@...cle.com, atish.patra@...cle.com, mhocko@...e.com,
sparclinux@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v6] sparc64: Multi-page size support
From: Nitin Gupta <nitin.m.gupta@...cle.com>
Date: Wed, 1 Feb 2017 16:16:36 -0800
> Add support for using multiple hugepage sizes simultaneously
> on mainline. Currently, support for 256M has been added which
> can be used along with 8M pages.
>
> Page tables are set like this (e.g. for 256M page):
> VA + (8M * x) -> PA + (8M * x) (sz bit = 256M) where x in [0, 31]
>
> and TSB is set similarly:
> VA + (4M * x) -> PA + (4M * x) (sz bit = 256M) where x in [0, 63]
>
> - Testing
>
> Tested on Sonoma (which supports 256M pages) by running stream
> benchmark instances in parallel: one instance uses 8M pages and
> another uses 256M pages, consuming 48G each.
>
> Boot params used:
>
> default_hugepagesz=256M hugepagesz=256M hugepages=300 hugepagesz=8M
> hugepages=10000
>
> Signed-off-by: Nitin Gupta <nitin.m.gupta@...cle.com>
Applied, thanks.
Powered by blists - more mailing lists