- To: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
- Subject: Re: [PATCH RFC V6 0/11] Paravirtualized ticketlocks
- From: Srivatsa Vaddagiri <vatsa@xxxxxxxxxxxxxxxxxx>
- Date: Sat, 31 Mar 2012 09:39:15 +0530
- Cc: the arch/x86 maintainers <x86@xxxxxxxxxx>, KVM <kvm@xxxxxxxxxxxxxxx>, Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>, Peter Zijlstra <peterz@xxxxxxxxxxxxx>, Stefano Stabellini <stefano.stabellini@xxxxxxxxxxxxx>, Raghavendra K T <raghavendra.kt@xxxxxxxxxxxxxxxxxx>, LKML <linux-kernel@xxxxxxxxxxxxxxx>, Andi Kleen <andi@xxxxxxxxxxxxxx>, Avi Kivity <avi@xxxxxxxxxx>, Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx>, "H. Peter Anvin" <hpa@xxxxxxxxx>, Attilio Rao <attilio.rao@xxxxxxxxxx>, Ingo Molnar <mingo@xxxxxxx>, Virtualization <virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx>, Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>, Xen Devel <xen-devel@xxxxxxxxxxxxxxxxxxx>, Stephan Diestelhorst <stephan.diestelhorst@xxxxxxx>
- Delivered-to: virtualization@xxxxxxxxxxxxxxxxxxxxxxxx
- In-reply-to: <20120331040745.GC14030@linux.vnet.ibm.com>
- Reply-to: Srivatsa Vaddagiri <vatsa@xxxxxxxxxxxxxxxxxx>
- User-agent: Mutt/1.5.21 (2010-09-15)
* Srivatsa Vaddagiri <vatsa@xxxxxxxxxxxxxxxxxx> [2012-03-31 09:37:45]:
> The issue is with ticketlocks though. VCPUs could go into a spin w/o
> a lock being held by anybody. Say VCPUs 1-99 try to grab a lock in
> that order (on a host with one cpu). VCPU1 wins (after VCPU0 releases it)
> and releases the lock. VCPU1 is next eligible to take the lock. If
Sorry I meant to say "VCPU2 is next eligible ..."
> that is not scheduled early enough by host, then remaining vcpus would keep
> spinning (even though lock is technically not held by anybody) w/o making
> forward progress.
> In that situation, what we really need is for the guest to hint to host
> scheduler to schedule VCPU1 early (via yield_to or something similar).
Virtualization mailing list
[Linux for Hams]
[Find Someone Nice]
[Video 4 Linux]