From: Paolo Bonzini <pbonzini@redhat.com>
To: "Radim Krčmář" <rkrcmar@redhat.com>, linux-kernel@vger.kernel.org
Cc: kvm@vger.kernel.org, Yuki Shibuya <shibuya.yk@ncos.nec.co.jp>,
Rik van Riel <riel@redhat.com>
Subject: Re: [PATCH v2 01/14] KVM: x86: change PIT discard tick policy
Date: Thu, 18 Feb 2016 17:13:29 +0100 [thread overview]
Message-ID: <56C5EDA9.9030204@redhat.com> (raw)
In-Reply-To: <1455736496-374-2-git-send-email-rkrcmar@redhat.com>
On 17/02/2016 20:14, Radim Krčmář wrote:
> Discard policy uses ack_notifiers to prevent injection of PIT interrupts
> before EOI from the last one.
>
> This patch changes the policy to always try to deliver the interrupt,
> which makes a difference when its vector is in ISR.
> Old implementation would drop the interrupt, but proposed one injects to
> IRR, like real hardware would.
This seems like what libvirt calls the "merge" policy:
Merge the missed tick(s) into one tick and inject. The guest time
may be delayed, depending on how the OS reacts to the merging of
ticks
where the merged tick is the one placed into IRR. Unlike discard,
"merge" can starve the guest through an interrupt storm.
Rik, I think you originally worked on the missed tick policies in Xen.
Is the above correct?
If so, do you recall what would be the reason to use the merge policy
instead of the discard policy?
Paolo
next prev parent reply other threads:[~2016-02-18 16:13 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-02-17 19:14 [PATCH v2 00/14] KVM: x86: change PIT discard policy and untangle related code Radim Krčmář
2016-02-17 19:14 ` [PATCH v2 01/14] KVM: x86: change PIT discard tick policy Radim Krčmář
2016-02-18 16:13 ` Paolo Bonzini [this message]
2016-02-18 16:56 ` Radim Krčmář
2016-02-18 17:33 ` Paolo Bonzini
2016-02-18 17:55 ` Paolo Bonzini
2016-02-19 14:44 ` Radim Krčmář
2016-02-25 12:34 ` Peter Krempa
2016-02-25 13:38 ` Paolo Bonzini
2016-02-25 17:36 ` Radim Krčmář
2016-02-25 19:11 ` Paolo Bonzini
2016-02-26 13:44 ` Radim Krčmář
2016-02-18 18:49 ` Paolo Bonzini
2016-02-17 19:14 ` [PATCH v2 02/14] KVM: x86: simplify atomics in kvm_pit_ack_irq Radim Krčmář
2016-02-18 18:04 ` Paolo Bonzini
2016-02-19 15:51 ` Radim Krčmář
2016-02-19 15:56 ` Paolo Bonzini
2016-02-17 19:14 ` [PATCH v2 03/14] KVM: x86: add kvm_pit_reset_reinject Radim Krčmář
2016-02-17 19:14 ` [PATCH v2 04/14] KVM: x86: use atomic_t instead of pit.inject_lock Radim Krčmář
2016-02-17 19:14 ` [PATCH v2 05/14] KVM: x86: tone down WARN_ON pit.state_lock Radim Krčmář
2016-02-17 19:14 ` [PATCH v2 06/14] KVM: x86: pass struct kvm_pit instead of kvm in PIT Radim Krčmář
2016-02-17 19:14 ` [PATCH v2 07/14] KVM: x86: remove unnecessary uses of PIT state lock Radim Krčmář
2016-02-18 18:03 ` Paolo Bonzini
2016-02-19 14:45 ` Radim Krčmář
2016-02-17 19:14 ` [PATCH v2 08/14] KVM: x86: remove notifiers from PIT discard policy Radim Krčmář
2016-02-18 18:05 ` Paolo Bonzini
2016-02-18 18:08 ` Paolo Bonzini
2016-02-19 15:04 ` Radim Krčmář
2016-02-19 15:06 ` Paolo Bonzini
2016-02-19 15:09 ` Radim Krčmář
2016-02-17 19:14 ` [PATCH v2 09/14] KVM: x86: refactor kvm_create_pit Radim Krčmář
2016-02-17 19:14 ` [PATCH v2 10/14] KVM: x86: refactor kvm_free_pit Radim Krčmář
2016-02-17 19:14 ` [PATCH v2 11/14] KVM: x86: remove pit and kvm from kvm_kpit_state Radim Krčmář
2016-02-17 19:14 ` [PATCH v2 12/14] KVM: x86: remove pointless dereference of PIT Radim Krčmář
2016-02-17 19:14 ` [PATCH v2 13/14] KVM: x86: don't assume layout of kvm_kpit_state Radim Krčmář
2016-02-17 19:14 ` [PATCH v2 14/14] KVM: x86: move PIT timer function initialization Radim Krčmář
2016-02-18 18:11 ` [PATCH v2 00/14] KVM: x86: change PIT discard policy and untangle related code Paolo Bonzini
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=56C5EDA9.9030204@redhat.com \
--to=pbonzini@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=riel@redhat.com \
--cc=rkrcmar@redhat.com \
--cc=shibuya.yk@ncos.nec.co.jp \
/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.