From: Wanpeng Li <wanpeng.li@hotmail.com>
To: "Theodore Y. Ts'o" <tytso@mit.edu>
Cc: "ksummit-discuss@lists.linuxfoundation.org"
<ksummit-discuss@lists.linuxfoundation.org>
Subject: Re: [Ksummit-discuss] [TECH TOPIC] Torwards a more scalable KVM hypervisor
Date: Wed, 12 Sep 2018 11:49:05 +0000 [thread overview]
Message-ID: <SG2PR02MB131211303EF0FD3F95FF7FC1801B0@SG2PR02MB1312.apcprd02.prod.outlook.com> (raw)
In-Reply-To: <20180912031213.GB8476@thunk.org>
[-- Attachment #1: Type: text/plain, Size: 1649 bytes --]
Hi Ted,
>On Wed, Sep 12, 2018 at 12:39:26AM +0000, Wanpeng Li wrote:
>> The kvm hypervisor is at the core of cloud computing, Virtual
>> Machine based approaches to workload consolidation, as seen in IaaS
>> cloud as well as data center platforms, have long had to contend
>> with performance degradation caused by synchronization primitives
>> inside the guest environments. These primitives can be affected by
>> virtual CPU preemptions by the host scheduler that can introduce
>> delays that are orders of magnitude longer than those primitives
>> were designed for. In this presentation, Wanpeng Li will introduce
>> current progress to mitigate TLB Shootdown Preemption. In addition,
>> Wanpeng Li will also introduce Exitless IPIs to scale large VMs.
>
>It looks like you are proposing an English language version of this
>talk from LinuxCon China:
>
>https://lc32018.sched.com/event/ER9W/torwards-a-more-scalable-kvm-hypervisor-wanpeng-li-tencent-cloud
>
>
>LinuxCon + ContainerCon + CloudOpen China 2018: Torwards a more Scalable KVM Hypervisor...
>lc32018.sched.com
>View more about this event at LinuxCon + ContainerCon + CloudOpen China 2018
>
>
>Is that correct? I wasn't able to find slides from the LinuxCon China
>presentations. Are they available?
>
Yeah, in attachment. In addition, I hope to replace the contents w/ my TLB Shootdown Preemption
Mitigation(Paravirtual TLB Shootdown) which can benefit overcommit in the Clouds and Exit-less IPIs
(https://lkml.org/lkml/2018/7/23/108) which can scale large VMs. These features have already been
merged in upstream this year.
Regards,
Wanpeng Li
[-- Attachment #2: Torwards a more Scalable KVM Hypervisor.pdf --]
[-- Type: application/pdf, Size: 344864 bytes --]
prev parent reply other threads:[~2018-09-12 11:49 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-09-12 0:39 Wanpeng Li
2018-09-12 3:12 ` Theodore Y. Ts'o
2018-09-12 11:49 ` Wanpeng Li [this message]
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=SG2PR02MB131211303EF0FD3F95FF7FC1801B0@SG2PR02MB1312.apcprd02.prod.outlook.com \
--to=wanpeng.li@hotmail.com \
--cc=ksummit-discuss@lists.linuxfoundation.org \
--cc=tytso@mit.edu \
/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