From: Avi Kivity <avi@redhat.com>
To: Gleb Natapov <gleb@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>,
kvm@vger.kernel.org, Jan Kiszka <jan.kiszka@web.de>
Subject: Re: [RFC PATCH 0/2] irq destination caching prototype
Date: Mon, 13 Aug 2012 13:21:33 +0300 [thread overview]
Message-ID: <5028D52D.9050104@redhat.com> (raw)
In-Reply-To: <20120813101608.GS3341@redhat.com>
On 08/13/2012 01:16 PM, Gleb Natapov wrote:
> On Mon, Aug 13, 2012 at 01:12:46PM +0300, Michael S. Tsirkin wrote:
>> On Mon, Aug 13, 2012 at 12:36:41PM +0300, Avi Kivity wrote:
>> > On 08/13/2012 12:16 PM, Gleb Natapov wrote:
>> > > Here is a quick prototype of what we discussed yesterday. This one
>> > > caches only MSI interrupts for now. The obvious problem is that not
>> > > all interrupts (namely IPIs and MSIs using KVM_CAP_SIGNAL_MSI) use irq
>> > > routing table, so they cannot be cached.
>> >
>> > We can have a small rcu-managed hash table to look those up.
>>
>> Yes but how small? We probably need at least one entry
>> per vcpu, no?
>>
> One entry? We will spend more time managing it than injecting interrupts
> :) ideally we need entry for each IPI sent and for each potential MSI
> from userspace. What happens when hash table is full?
Drop the entire cache.
> We stop caching or
> invalidate old entries? If later then cache can go valid->invalid which
> may complicate the code.
>
We can drop the entire cache via rcu freeing. In fact we can have a
closed hash allocated as a single blob, easy to manage.
--
error compiling committee.c: too many arguments to function
next prev parent reply other threads:[~2012-08-13 10:21 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-08-13 9:16 [RFC PATCH 0/2] irq destination caching prototype Gleb Natapov
2012-08-13 9:16 ` [RFC PATCH 1/2] Call irq_rt callback under rcu_read_lock() Gleb Natapov
2012-08-13 9:16 ` [RFC PATCH 2/2] Cache msi irq destination Gleb Natapov
2012-08-13 9:32 ` Avi Kivity
2012-08-13 9:34 ` Gleb Natapov
2012-08-13 9:34 ` [RFC PATCH 0/2] irq destination caching prototype Michael S. Tsirkin
2012-08-13 9:36 ` Gleb Natapov
2012-08-13 9:46 ` Michael S. Tsirkin
2012-08-13 9:48 ` Gleb Natapov
2012-08-13 9:36 ` Avi Kivity
2012-08-13 10:12 ` Michael S. Tsirkin
2012-08-13 10:16 ` Gleb Natapov
2012-08-13 10:21 ` Avi Kivity [this message]
2012-08-13 10:24 ` Gleb Natapov
2012-08-13 10:31 ` Avi Kivity
2012-08-13 10:35 ` Gleb Natapov
2012-08-13 10:38 ` Michael S. Tsirkin
2012-08-13 10:58 ` Avi Kivity
2012-08-13 11:01 ` Gleb Natapov
2012-08-13 11:03 ` Avi Kivity
2012-08-13 11:12 ` Gleb Natapov
2012-08-13 11:22 ` Michael S. Tsirkin
2012-08-13 11:29 ` Gleb Natapov
2012-08-13 11:43 ` Gleb Natapov
2012-08-13 12:14 ` Avi Kivity
2012-08-13 11:30 ` Avi Kivity
2012-08-13 11:41 ` Gleb Natapov
2012-08-13 12:13 ` Avi Kivity
2012-08-13 12:59 ` Michael S. Tsirkin
2012-08-13 11:19 ` Michael S. Tsirkin
2012-08-13 9:43 ` Avi Kivity
2012-08-13 9:51 ` Michael S. Tsirkin
2012-08-13 9:53 ` Gleb Natapov
2012-08-13 10:33 ` Gleb Natapov
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=5028D52D.9050104@redhat.com \
--to=avi@redhat.com \
--cc=gleb@redhat.com \
--cc=jan.kiszka@web.de \
--cc=kvm@vger.kernel.org \
--cc=mst@redhat.com \
/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;
as well as URLs for NNTP newsgroup(s).