From: Paolo Bonzini <pbonzini@redhat.com>
To: Igor Mammedov <imammedo@redhat.com>
Cc: Peter Maydell <peter.maydell@linaro.org>,
Eduardo Habkost <ehabkost@redhat.com>,
Sergio Lopez <slp@redhat.com>,
"Michael S. Tsirkin" <mst@redhat.com>,
qemu-devel@nongnu.org, Shannon Zhao <shannon.zhaosl@gmail.com>,
qemu-arm@nongnu.org, Gerd Hoffmann <kraxel@redhat.com>,
Richard Henderson <rth@twiddle.net>
Subject: Re: [PATCH v3 14/22] microvm: use 2G split unconditionally
Date: Wed, 27 May 2020 16:54:34 +0200 [thread overview]
Message-ID: <cdeb8406-eb41-160e-817a-010241ccd457@redhat.com> (raw)
In-Reply-To: <20200527162646.694b2d47@redhat.com>
On 27/05/20 16:26, Igor Mammedov wrote:
> On Wed, 27 May 2020 15:06:28 +0200
> Paolo Bonzini <pbonzini@redhat.com> wrote:
>
>> On 27/05/20 14:25, Igor Mammedov wrote:
>>>> (2) we loose a gigabyte page.
>>> I'm not sure waht exactly we loose in this case.
>>> Lets assume we allocating guest 5G of continuous RAM using 1G huge pages,
>>> in this case I'd think that on host side MMIO overlay won't affect RAM blob
>>> on guest side pagetables will be fragmented due to MMIO holes, but guest still
>>> could use huge pages smaller ones in fragmented area and 1G where there is no fragmentation.
>>
>> Access to the 3G-4G area would not be able to use 1G EPT pages.
> Could it use 2Mb pages instead of 1Gb?
Yes, probably a mix of 2 MiB pages and 4 KiB pages around the memslot
splits.
> Do we really care about 1 gigabyte huge page in microvm intended usecase?
> (fast starting VMs for microservices like FaaS, which unlikely would use much memory to begin with)
I honestly don't think it's measurable, but at least in theory we care
because such workloads could have more TLB misses (relative to the
execution time) than long-lasting VMs.
Paolo
next prev parent reply other threads:[~2020-05-27 14:55 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-20 13:19 [PATCH v3 00/22] microvm: add acpi support Gerd Hoffmann
2020-05-20 13:19 ` [PATCH v3 01/22] microvm: name qboot binary qboot.bin Gerd Hoffmann
2020-05-20 13:25 ` Philippe Mathieu-Daudé
2020-05-25 11:02 ` Gerd Hoffmann
2020-05-25 12:26 ` Philippe Mathieu-Daudé
2020-05-20 13:19 ` [PATCH v3 02/22] [testing] seabios: update submodule to master snapshot Gerd Hoffmann
2020-05-20 13:19 ` [PATCH v3 03/22] [testing] seabios: update config & build rules Gerd Hoffmann
2020-05-20 13:19 ` [PATCH v3 04/22] [testing] seabios: update binaries to master snapshot Gerd Hoffmann
2020-05-20 13:19 ` [PATCH v3 05/22] acpi: make build_madt() more generic Gerd Hoffmann
2020-05-20 13:19 ` [PATCH v3 06/22] acpi: create acpi-common.c and move madt code Gerd Hoffmann
2020-05-20 13:31 ` Philippe Mathieu-Daudé
2020-05-20 13:19 ` [PATCH v3 07/22] acpi: madt: skip pci override on pci-less systems Gerd Hoffmann
2020-05-20 13:19 ` [PATCH v3 08/22] acpi: fadt: add hw-reduced sleep register support Gerd Hoffmann
2020-05-20 13:19 ` [PATCH v3 09/22] acpi: ged: rename event memory region Gerd Hoffmann
2020-05-20 13:33 ` Philippe Mathieu-Daudé
2020-05-21 7:58 ` Igor Mammedow
2020-05-20 13:19 ` [PATCH v3 10/22] acpi: ged: add control regs Gerd Hoffmann
2020-05-21 8:58 ` Igor Mammedov
2020-05-20 13:19 ` [PATCH v3 11/22] acpi: ged: add x86 device variant Gerd Hoffmann
2020-05-21 9:01 ` Igor Mammedov
2020-05-20 13:19 ` [PATCH v3 12/22] acpi: move acpi_dsdt_add_power_button() to ged Gerd Hoffmann
2020-05-20 13:32 ` Philippe Mathieu-Daudé
2020-05-21 9:03 ` Igor Mammedov
2020-05-20 13:19 ` [PATCH v3 13/22] x86: coldplug cpus Gerd Hoffmann
2020-05-20 14:07 ` Igor Mammedov
2020-05-20 13:19 ` [PATCH v3 14/22] microvm: use 2G split unconditionally Gerd Hoffmann
2020-05-20 13:34 ` Philippe Mathieu-Daudé
2020-05-21 9:14 ` Igor Mammedov
2020-05-21 9:29 ` Igor Mammedov
2020-05-25 11:45 ` Gerd Hoffmann
2020-05-25 16:36 ` Igor Mammedov
2020-05-26 4:48 ` Gerd Hoffmann
2020-05-27 12:25 ` Igor Mammedov
2020-05-27 13:06 ` Paolo Bonzini
2020-05-27 14:26 ` Igor Mammedov
2020-05-27 14:35 ` Igor Mammedov
2020-05-27 14:54 ` Paolo Bonzini [this message]
2020-05-28 7:19 ` Gerd Hoffmann
2020-05-28 7:17 ` Gerd Hoffmann
2020-05-20 13:19 ` [PATCH v3 15/22] microvm: make virtio irq base runtime configurable Gerd Hoffmann
2020-05-20 13:29 ` Philippe Mathieu-Daudé
2020-05-25 11:49 ` Gerd Hoffmann
2020-05-25 12:27 ` Philippe Mathieu-Daudé
2020-05-20 13:19 ` [PATCH v3 16/22] microvm/acpi: add minimal acpi support Gerd Hoffmann
2020-05-21 10:09 ` Igor Mammedov
2020-05-20 13:19 ` [PATCH v3 17/22] microvm/acpi: add acpi_dsdt_add_virtio() for x86 Gerd Hoffmann
2020-05-21 10:12 ` Igor Mammedov
2020-05-20 13:19 ` [PATCH v3 18/22] microvm/acpi: use GSI 16-23 for virtio Gerd Hoffmann
2020-05-21 10:13 ` Igor Mammedov
2020-05-20 13:20 ` [PATCH v3 19/22] microvm/acpi: use seabios with acpi=on Gerd Hoffmann
2020-05-21 10:14 ` Igor Mammedov
2020-05-20 13:20 ` [PATCH v3 20/22] microvm/acpi: disable virtio-mmio cmdline hack Gerd Hoffmann
2020-05-20 13:20 ` [PATCH v3 21/22] [RfC] acpi: add per machine type acpi default Gerd Hoffmann
2020-05-21 10:26 ` Igor Mammedov
2020-05-20 13:20 ` [PATCH v3 22/22] [RfC] acpi: flip default to off for microvm Gerd Hoffmann
2020-05-21 10:36 ` Igor Mammedov
2020-05-25 12:11 ` Gerd Hoffmann
2020-05-20 15:46 ` [PATCH v3 00/22] microvm: add acpi support no-reply
2020-05-20 15:50 ` no-reply
2020-05-20 15:51 ` no-reply
2020-05-20 15:53 ` no-reply
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=cdeb8406-eb41-160e-817a-010241ccd457@redhat.com \
--to=pbonzini@redhat.com \
--cc=ehabkost@redhat.com \
--cc=imammedo@redhat.com \
--cc=kraxel@redhat.com \
--cc=mst@redhat.com \
--cc=peter.maydell@linaro.org \
--cc=qemu-arm@nongnu.org \
--cc=qemu-devel@nongnu.org \
--cc=rth@twiddle.net \
--cc=shannon.zhaosl@gmail.com \
--cc=slp@redhat.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).