From: Arnd Bergmann <arnd@arndb.de>
To: linux-arm-kernel@lists.infradead.org
Cc: wei.liu2@citrix.com, ian.campbell@citrix.com,
stefano.stabellini@eu.citrix.com, linux-kernel@vger.kernel.org,
"Julien Grall" <julien.grall@citrix.com>,
"David Vrabel" <david.vrabel@citrix.com>,
xen-devel@lists.xenproject.org, boris.ostrovsky@oracle.com,
"Roger Pau Monné" <roger.pau@citrix.com>
Subject: Re: [PATCH v4 00/20] xen/arm64: Add support for 64KB page in Linux
Date: Tue, 15 Sep 2015 15:24:06 +0200 [thread overview]
Message-ID: <1539842.T2XY1FNaDl__11091.8904458687$1442323580$gmane$org@wuerfel> (raw)
In-Reply-To: <55F819A1.8070609@citrix.com>
On Tuesday 15 September 2015 14:14:09 David Vrabel wrote:
> On 14/09/15 12:32, Arnd Bergmann wrote:
> > On Monday 14 September 2015 13:04:59 Roger Pau Monné wrote:
> >>> TBH, I'm expecting a small impact to the performance. It would be hard
> >>> to get the exactly the same performance as today if we keep the helpers
> >>> to avoid the backend dealing himself with the splitting and page
> >>> granularity.
> >>>
> >>> Although, if the performance impact is not acceptable, it may be
> >>> possible to optimize gnttab_foreach_grant_in_range by moving the
> >>> function inline. The current way to the loop is the fastest I've found
> >>> (I've wrote a small program to test different way) and we will need it
> >>> when different of size will be supported.
> >>
> >> I don't expect the performance to drop massively with this patches
> >> applied, but it would be good to al least have an idea of the impact.
> >
> > Note that using 64kb pages in Linux tends to destroy performance
> > in Linux in any case, as the memory consumption for most workloads
> > explodes. In a virtualized environment you already tend to be
> > memory constrained, so any measurement should take that into account
> > and put the extra overhead into perspective to the massive overhead
> > of running 64kb pages when RAM is tight.
>
> If this is the case, why are some distros using 64 KiB pages then?
I believe that IBM started this on PowerPC64 when they found that it
performs better in microbenchmarks and for certain database workloads
when you do have enough memory and do not work with small files or
many processes.
I also believe that the AIX memory management code is designed differently
enough that it suffers less from large pages (or suffers more from
small pages), so the hardware designers pushed Linux to do the same as AIX.
Why you'd do it on ARM64 I have no idea at all, other than copying what
IBM did on PowerPC. If your TLB is too small, hardware designers may
of course try to push the OS to using pages as large as possible for the
low-level benchmarks to suck less, but in general, you'd be better off
with transparent hugepages and 4kb or 8kb pages for real workloads.
Arnd
next prev parent reply other threads:[~2015-09-15 13:24 UTC|newest]
Thread overview: 144+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-09-07 15:33 [PATCH v4 00/20] xen/arm64: Add support for 64KB page in Linux Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 01/20] net/xen-netback: xenvif_gop_frag_copy: move GSO check out of the loop Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 02/20] arm/xen: Drop pte_mfn and mfn_pte Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 03/20] xen: Add Xen specific page definition Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 04/20] xen/grant: Introduce helpers to split a page into grant Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 05/20] xen/grant: Add helper gnttab_page_grant_foreign_access_ref_one Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 06/20] block/xen-blkfront: Split blkif_queue_request in 2 Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 07/20] block/xen-blkfront: Store a page rather a pfn in the grant structure Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 08/20] block/xen-blkfront: split get_grant in 2 Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 09/20] xen/biomerge: Don't allow biovec's to be merged when Linux is not using 4KB pages Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 10/20] xen/xenbus: Use Xen page definition Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 11/20] tty/hvc: xen: Use xen " Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 12/20] xen/balloon: Don't rely on the page granularity is the same for Xen and Linux Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 16:39 ` Stefano Stabellini
2015-09-07 16:39 ` Stefano Stabellini
2015-09-07 16:39 ` Stefano Stabellini
2015-09-07 15:33 ` [PATCH v4 13/20] xen/events: fifo: Make it running on 64KB granularity Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 14/20] xen/grant-table: " Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 15/20] block/xen-blkfront: Make it running on 64KB page granularity Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 16/20] block/xen-blkback: " Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 17/20] net/xen-netfront: " Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 18/20] net/xen-netback: " Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 16:57 ` Wei Liu
2015-09-07 16:57 ` Wei Liu
2015-09-07 16:57 ` Wei Liu
2015-09-08 11:07 ` [Xen-devel] " Julien Grall
2015-09-08 11:07 ` Julien Grall
2015-09-08 11:09 ` Wei Liu
2015-09-08 11:09 ` Wei Liu
2015-09-08 11:09 ` Wei Liu
2015-09-08 11:07 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 19/20] xen/privcmd: Add support for Linux " Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` [PATCH v4 20/20] arm/xen: Add support for " Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-07 15:33 ` Julien Grall
2015-09-11 19:39 ` [PATCH v4 00/20] xen/arm64: Add support for 64KB page in Linux Julien Grall
2015-09-11 19:39 ` [Xen-devel] " Julien Grall
2015-09-11 19:39 ` Julien Grall
2015-09-14 8:56 ` Roger Pau Monné
2015-09-14 8:56 ` Roger Pau Monné
2015-09-14 10:40 ` Julien Grall
2015-09-14 10:40 ` Julien Grall
2015-09-14 11:04 ` Roger Pau Monné
2015-09-14 11:04 ` Roger Pau Monné
2015-09-14 11:21 ` Julien Grall
2015-09-14 11:21 ` Julien Grall
2015-09-14 12:08 ` Roger Pau Monné
2015-09-14 12:08 ` Roger Pau Monné
2015-09-14 12:08 ` Roger Pau Monné
2015-09-14 12:47 ` Julien Grall
2015-09-14 12:47 ` Julien Grall
2015-09-14 12:47 ` Julien Grall
2015-09-14 14:29 ` Roger Pau Monné
2015-09-14 14:29 ` Roger Pau Monné
2015-09-14 14:46 ` Julien Grall
2015-09-14 14:46 ` Julien Grall
2015-09-14 14:46 ` Julien Grall
2015-09-14 14:54 ` Stefano Stabellini
2015-09-14 14:54 ` Stefano Stabellini
2015-09-14 14:54 ` Stefano Stabellini
2015-09-14 15:23 ` Roger Pau Monné
2015-09-14 15:23 ` Roger Pau Monné
2015-09-22 10:59 ` Ian Campbell
2015-09-22 10:59 ` Ian Campbell
2015-09-22 10:59 ` Ian Campbell
2015-10-06 9:28 ` Roger Pau Monné
2015-10-06 9:28 ` Roger Pau Monné
2015-10-06 10:17 ` Ian Campbell
2015-10-06 10:17 ` Ian Campbell
2015-10-06 10:17 ` Ian Campbell
2015-10-06 13:55 ` Stefano Stabellini
2015-10-06 13:55 ` Stefano Stabellini
2015-10-06 13:55 ` Stefano Stabellini
2015-10-06 9:28 ` Roger Pau Monné
2015-09-14 15:23 ` Roger Pau Monné
2015-09-14 14:29 ` Roger Pau Monné
2015-09-18 14:10 ` Julien Grall
2015-09-18 14:10 ` Julien Grall
2015-09-18 14:10 ` Julien Grall
2015-09-14 11:21 ` Julien Grall
2015-09-14 11:32 ` Arnd Bergmann
2015-09-14 11:32 ` Arnd Bergmann
2015-09-14 11:32 ` Arnd Bergmann
2015-09-15 13:14 ` [Xen-devel] " David Vrabel
2015-09-15 13:14 ` David Vrabel
2015-09-15 13:24 ` Arnd Bergmann [this message]
2015-09-15 13:24 ` Arnd Bergmann
2015-09-15 13:24 ` Arnd Bergmann
2015-09-15 13:14 ` David Vrabel
2015-09-14 11:04 ` Roger Pau Monné
2015-09-14 10:40 ` Julien Grall
2015-09-14 8:56 ` Roger Pau Monné
2015-09-29 16:27 ` David Vrabel
2015-09-29 16:27 ` [Xen-devel] " David Vrabel
2015-09-29 16:27 ` David Vrabel
2015-09-29 16:33 ` Julien Grall
2015-09-29 16:33 ` Julien Grall
2015-09-29 16:36 ` David Vrabel
2015-09-29 16:36 ` [Xen-devel] " David Vrabel
2015-09-29 16:36 ` David Vrabel
2015-09-29 16:33 ` Julien Grall
-- strict thread matches above, loose matches on Subject: below --
2015-09-07 15:33 Julien Grall
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='1539842.T2XY1FNaDl__11091.8904458687$1442323580$gmane$org@wuerfel' \
--to=arnd@arndb.de \
--cc=boris.ostrovsky@oracle.com \
--cc=david.vrabel@citrix.com \
--cc=ian.campbell@citrix.com \
--cc=julien.grall@citrix.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=roger.pau@citrix.com \
--cc=stefano.stabellini@eu.citrix.com \
--cc=wei.liu2@citrix.com \
--cc=xen-devel@lists.xenproject.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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.