From: Paolo Bonzini <pbonzini@redhat.com>
To: Dan Williams <dan.j.williams@intel.com>,
qemu-devel@nongnu.org, Eduardo Habkost <ehabkost@redhat.com>,
Peter Crosthwaite <crosthwaite.peter@gmail.com>,
Stefan Hajnoczi <stefanha@gmail.com>,
Xiao Guangrong <guangrong.xiao@gmail.com>,
Igor Mammedov <imammedo@redhat.com>,
Richard Henderson <rth@twiddle.net>
Subject: Re: [Qemu-devel] [RESEND PATCH 2/2] hostmem-file: add an attribute 'align' to set its alignment
Date: Tue, 30 May 2017 14:17:04 +0200 [thread overview]
Message-ID: <dcee001b-755c-1a88-234b-0ca663958584@redhat.com> (raw)
In-Reply-To: <CAPcyv4hbf0RrjK5t5eN2Cs271JJUEYuiDNZqvso8g7QG4m4hDw@mail.gmail.com>
On 26/05/2017 16:24, Dan Williams wrote:
>> For DAX device only, QEMU can figure out the proper alignment by
>> itself. However, I'm not sure whether there are other non-DAX cases
>> requiring non-default alignment, so I think it's better to just add an
>> interface (i.e. align attribute) in QEMU and let other management
>> tools (e.g. libvirt?) fill a proper value.
> I can't imagine any cases where you would want to specify an
> alignment. If it's regular file mmap any alignment is fine, and if
> it's device-dax only the configured alignment of the device instance
> is allowed. So, I don't think this should be a configurable option,
> just read it from the device instance and you're done.
A 2M or 1G alignment lets KVM use EPT hugepages if the host physical
addresses are contiguous and 2M- or 1G-aligned.
QEMU only does this for hugetlbfs currently, where the requirement on
the host physical addresses is always satisfied. Would the same apply
to NVDIMM device DAX?
Thanks,
Paolo
next prev parent reply other threads:[~2017-05-30 12:17 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-05-26 2:32 [Qemu-devel] [RESEND PATCH 1/2] nvdimm: warn if the backend is not a DAX device Haozhong Zhang
2017-05-26 2:32 ` [Qemu-devel] [RESEND PATCH 2/2] hostmem-file: add an attribute 'align' to set its alignment Haozhong Zhang
2017-05-26 6:39 ` Marc-André Lureau
[not found] ` <20170526065132.ayapfebbft5lyigd@hz-desktop>
2017-05-26 7:05 ` Marc-André Lureau
[not found] ` <20170526071654.kxcqflvpo2tvcrvu@hz-desktop>
2017-05-26 14:24 ` Dan Williams
2017-05-26 18:55 ` Eduardo Habkost
2017-05-26 20:50 ` Dan Williams
2017-05-27 1:04 ` Haozhong Zhang
2017-05-30 12:17 ` Paolo Bonzini [this message]
2017-05-30 19:16 ` Dan Williams
2017-05-26 3:34 ` [Qemu-devel] [RESEND PATCH 1/2] nvdimm: warn if the backend is not a DAX device Dan Williams
2017-05-26 4:30 ` Haozhong Zhang
2017-05-26 14:28 ` Dan Williams
2017-05-26 14:38 ` Daniel P. Berrange
2017-05-26 15:25 ` Dan Williams
2017-05-27 1:13 ` Haozhong Zhang
2017-05-30 9:20 ` Daniel P. Berrange
2017-05-30 11:41 ` Dan Williams
2017-06-01 12:00 ` Xiao Guangrong
2017-06-01 13:53 ` Dan Williams
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=dcee001b-755c-1a88-234b-0ca663958584@redhat.com \
--to=pbonzini@redhat.com \
--cc=crosthwaite.peter@gmail.com \
--cc=dan.j.williams@intel.com \
--cc=ehabkost@redhat.com \
--cc=guangrong.xiao@gmail.com \
--cc=imammedo@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=rth@twiddle.net \
--cc=stefanha@gmail.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).