lkml.org 
[lkml]   [2022]   [Jun]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: Commit 282d8998e997 (srcu: Prevent expedited GPs and blocking readers from consuming CPU) cause qemu boot slow
On Sun, Jun 12, 2022 at 07:47:10PM +0200, Paolo Bonzini wrote:
> On 6/12/22 19:29, Paolo Bonzini wrote:
> > On 6/12/22 18:40, Paul E. McKenney wrote:
> > > > Do these reserved memory regions really need to be allocated separately?
> > > > (For example, are they really all non-contiguous?  If not, that is, if
> > > > there are a lot of contiguous memory regions, could you sort the IORT
> > > > by address and do one ioctl() for each set of contiguous memory
> > > > regions?)
> > > >
> > > > Are all of these reserved memory regions set up before init is spawned?
> > > >
> > > > Are all of these reserved memory regions set up while there is only a
> > > > single vCPU up and running?
> > > >
> > > > Is the SRCU grace period really needed in this case?  (I freely confess
> > > > to not being all that familiar with KVM.)
> > >
> > > Oh, and there was a similar many-requests problem with networking many
> > > years ago.  This was solved by adding a new syscall/ioctl()/whatever
> > > that permitted many requests to be presented to the kernel with a single
> > > system call.
> > >
> > > Could a new ioctl() be introduced that requested a large number
> > > of these memory regions in one go so as to make each call to
> > > synchronize_rcu_expedited() cover a useful fraction of your 9000+
> > > requests?  Adding a few of the KVM guys on CC for their thoughts.
>
> Another question: how much can call_srcu() callbacks pile up these days?
> I've always been a bit wary of letting userspace do an arbitrary number of
> allocations that can only be freed after a grace period, but perhaps there's
> a way to query SRCU and apply some backpressure?

They can pile up as much as ever, especially if you have long-duration
sleeping readers.

But you could do the occasional srcu_barrier() to wait for all the
preceding ones to get done. Maybe every 1000th call_srcu() or similar?

Thanx, Paul

\
 
 \ /
  Last update: 2022-06-12 20:52    [W:0.664 / U:0.036 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site