From: "Radim Krčmář" <rkrcmar@redhat.com>
To: kvm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, Paolo Bonzini <pbonzini@redhat.com>,
Gleb Natapov <gleb@kernel.org>,
Raghavendra KT <raghavendra.kt@linux.vnet.ibm.com>,
Vinod Chegu <chegu_vinod@hp.com>, Hui-Zhi <hui-zhi.zhao@hp.com>
Subject: [PATCH 0/9] Dynamic Pause Loop Exiting window.
Date: Tue, 19 Aug 2014 22:35:27 +0200 [thread overview]
Message-ID: <1408480536-8240-1-git-send-email-rkrcmar@redhat.com> (raw)
PLE does not scale in its current form. When increasing VCPU count
above 150, one can hit soft lockups because of runqueue lock contention.
(Which says a lot about performance.)
The main reason is that kvm_ple_loop cycles through all VCPUs.
Replacing it with a scalable solution would be ideal, but it has already
been well optimized for various workloads, so this series tries to
alleviate one different major problem while minimizing a chance of
regressions: we have too many useless PLE exits.
Just increasing PLE window would help some cases, but it still spirals
out of control. By increasing the window after every PLE exit, we can
limit the amount of useless ones, so we don't reach the state where CPUs
spend 99% of the time waiting for a lock.
HP confirmed that this series avoids soft lockups and TSC sync errors on
large guests.
---
Design notes and questions:
Alternative to first two patches could be a new notifier.
All values are made changeable because defaults weren't selected after
weeks of benchmarking -- we can get improved performance by hardcoding
if someone is willing to do it.
(Or by presuming that noone is ever going to.)
Then, we can quite safely drop overflow checks: they are impossible to
hit with small increases and I don't think that anyone wants large ones.
Also, I'd argue against the last patch: it should be done in userspace,
but I'm not sure about Linux's policy.
Radim Krčmář (9):
KVM: add kvm_arch_sched_in
KVM: x86: introduce sched_in to kvm_x86_ops
KVM: VMX: make PLE window per-vcpu
KVM: VMX: dynamise PLE window
KVM: VMX: clamp PLE window
KVM: trace kvm_ple_window grow/shrink
KVM: VMX: abstract ple_window modifiers
KVM: VMX: runtime knobs for dynamic PLE window
KVM: VMX: automatic PLE window maximum
arch/arm/kvm/arm.c | 4 ++
arch/mips/kvm/mips.c | 4 ++
arch/powerpc/kvm/powerpc.c | 4 ++
arch/s390/kvm/kvm-s390.c | 4 ++
arch/x86/include/asm/kvm_host.h | 2 +
arch/x86/kvm/svm.c | 6 +++
arch/x86/kvm/trace.h | 29 +++++++++++++
arch/x86/kvm/vmx.c | 93 +++++++++++++++++++++++++++++++++++++++--
arch/x86/kvm/x86.c | 6 +++
include/linux/kvm_host.h | 2 +
virt/kvm/kvm_main.c | 2 +
11 files changed, 153 insertions(+), 3 deletions(-)
--
2.0.4
next reply other threads:[~2014-08-19 20:37 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-08-19 20:35 Radim Krčmář [this message]
2014-08-19 20:35 ` [PATCH 1/9] KVM: add kvm_arch_sched_in Radim Krčmář
2014-08-20 7:47 ` Christian Borntraeger
2014-08-20 12:56 ` Radim Krčmář
2014-08-19 20:35 ` [PATCH 2/9] KVM: x86: introduce sched_in to kvm_x86_ops Radim Krčmář
2014-08-19 20:35 ` [PATCH 3/9] KVM: VMX: make PLE window per-vcpu Radim Krčmář
2014-08-20 7:13 ` Paolo Bonzini
2014-08-20 12:26 ` Radim Krčmář
2014-08-19 20:35 ` [PATCH 4/9] KVM: VMX: dynamise PLE window Radim Krčmář
2014-08-19 20:35 ` [PATCH 5/9] KVM: VMX: clamp " Radim Krčmář
2014-08-20 7:18 ` Paolo Bonzini
2014-08-20 12:46 ` Radim Krčmář
2014-08-19 20:35 ` [PATCH 6/9] KVM: trace kvm_ple_window grow/shrink Radim Krčmář
2014-08-19 20:35 ` [PATCH 7/9] KVM: VMX: abstract ple_window modifiers Radim Krčmář
2014-08-20 7:02 ` Paolo Bonzini
2014-08-20 12:25 ` Radim Krčmář
2014-08-19 20:35 ` [PATCH 8/9] KVM: VMX: runtime knobs for dynamic PLE window Radim Krčmář
2014-08-19 20:35 ` [PATCH 9/9] KVM: VMX: automatic PLE window maximum Radim Krčmář
2014-08-20 7:16 ` Paolo Bonzini
2014-08-20 7:18 ` Paolo Bonzini
2014-08-20 12:41 ` Radim Krčmář
2014-08-20 13:15 ` Paolo Bonzini
2014-08-20 15:31 ` Radim Krčmář
2014-08-20 15:34 ` Paolo Bonzini
2014-08-20 16:01 ` Radim Krčmář
2014-08-20 16:03 ` Paolo Bonzini
2014-08-20 16:26 ` Radim Krčmář
2014-08-21 6:48 ` [PATCH 0/9] Dynamic Pause Loop Exiting window Zhao, Hui-Zhi (Steven, HPservers-Core-OE-PSC)
2014-08-21 6:48 ` Zhao, Hui-Zhi (Steven, HPservers-Core-OE-PSC)
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=1408480536-8240-1-git-send-email-rkrcmar@redhat.com \
--to=rkrcmar@redhat.com \
--cc=chegu_vinod@hp.com \
--cc=gleb@kernel.org \
--cc=hui-zhi.zhao@hp.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=raghavendra.kt@linux.vnet.ibm.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 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.