[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH v2 0/6] aio: Support epoll by introducing qemu_p
From: |
Paolo Bonzini |
Subject: |
Re: [Qemu-devel] [PATCH v2 0/6] aio: Support epoll by introducing qemu_poll abstraction |
Date: |
Thu, 08 Jan 2015 14:00:04 +0100 |
User-agent: |
Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.3.0 |
On 08/01/2015 03:53, Fam Zheng wrote:
>>> > > 1) Remove 1ns PR_SET_TIMERSLACK in timerfd+epoll, this doesn't make
>>> > > qemu_poll
>>> > > faster than the old qemu_poll_ns, but may have other positive effects
>>> > > that
>>> > > compensate the cost.
>> >
>> > Sounds like a random hack. What is the reasoning for messing with timer
>> > slack?
> In a test this doesn't work. The reason is that timer slack affects poll
> sys calls' timeout, therefore they are correlated. Anyway, I've left this.
1ns is definitely too much, it's just accuracy theater (and I am
responsible for it). We don't care about 3 clock cycles when a context
switch is at least 500.
We probably could change it to 100 ns (0.1 us) with no practical
effects; the default is 50 us.
Paolo