[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <4444ffc8-9e7b-5bd2-20da-af422fe834cc@redhat.com>
Date: Thu, 22 Jun 2017 13:51:14 +0200
From: Paolo Bonzini <pbonzini@...hat.com>
To: root <yang.zhang.wz@...il.com>, tglx@...utronix.de,
mingo@...hat.com, hpa@...or.com
Cc: x86@...nel.org, corbet@....net, tony.luck@...el.com, bp@...en8.de,
peterz@...radead.org, mchehab@...nel.org,
akpm@...ux-foundation.org, krzk@...nel.org, jpoimboe@...hat.com,
luto@...nel.org, borntraeger@...ibm.com, thgarnie@...gle.com,
rgerst@...il.com, minipli@...glemail.com,
douly.fnst@...fujitsu.com, nicstange@...il.com, fweisbec@...il.com,
dvlasenk@...hat.com, bristot@...hat.com,
yamada.masahiro@...ionext.com, mika.westerberg@...ux.intel.com,
yu.c.chen@...el.com, aaron.lu@...el.com, rostedt@...dmis.org,
me@...ehuey.com, len.brown@...el.com, prarit@...hat.com,
hidehiro.kawai.ez@...achi.com, fengtiantian@...wei.com,
pmladek@...e.com, jeyu@...hat.com, Larry.Finger@...inger.net,
zijun_hu@....com, luisbg@....samsung.com, johannes.berg@...el.com,
niklas.soderlund+renesas@...natech.se, zlpnobody@...il.com,
adobriyan@...il.com, fgao@...ai8.com, ebiederm@...ssion.com,
subashab@...eaurora.org, arnd@...db.de, matt@...eblueprint.co.uk,
mgorman@...hsingularity.net, linux-kernel@...r.kernel.org,
linux-doc@...r.kernel.org, linux-edac@...r.kernel.org,
kvm@...r.kernel.org
Subject: Re: [PATCH 2/2] x86/idle: use dynamic halt poll
On 22/06/2017 13:22, root wrote:
> ==============================================================
>
> +poll_grow: (X86 only)
> +
> +This parameter is multiplied in the grow_poll_ns() to increase the poll time.
> +By default, the values is 2.
> +
> +==============================================================
> +poll_shrink: (X86 only)
> +
> +This parameter is divided in the shrink_poll_ns() to reduce the poll time.
> +By default, the values is 2.
Even before starting the debate on whether this is a good idea or a bad
idea, KVM reduces the polling value to the minimum (10 us) by default
when polling fails. Also, it shouldn't be bound to
CONFIG_HYPERVISOR_GUEST, since there's nothing specific to virtual
machines here.
Regarding the good/bad idea part, KVM's polling is made much more
acceptable by single_task_running(). At least you need to integrate it
with paravirtualization. If the VM is scheduled out, you shrink the
polling period. There is already vcpu_is_preempted for this, it is used
by mutexes.
Paolo
Powered by blists - more mailing lists