From: Vitaly Kuznetsov <vkuznets@redhat.com>
To: Sean Christopherson <seanjc@google.com>
Cc: kvm@vger.kernel.org, Paolo Bonzini <pbonzini@redhat.com>,
Wanpeng Li <wanpengli@tencent.com>,
Jim Mattson <jmattson@google.com>
Subject: Re: [PATCH RFC 0/4] KVM: x86: Drastically raise KVM_USER_MEM_SLOTS limit
Date: Fri, 15 Jan 2021 17:23:32 +0100 [thread overview]
Message-ID: <87zh1a5fuj.fsf@vitty.brq.redhat.com> (raw)
In-Reply-To: <YAG8t9ww/dgFaFht@google.com>
Sean Christopherson <seanjc@google.com> writes:
> On Fri, Jan 15, 2021, Vitaly Kuznetsov wrote:
>> TL;DR: any particular reason why KVM_USER_MEM_SLOTS is so low?
>
> Because memslots were allocated statically up until fairly recently (v5.7), and
> IIRC consumed ~92kb. Doubling that for every VM would be quite painful.
>
I should've added 'now' to the question). So the main reason is gone,
thanks for the confirmation!
>> Longer version:
>>
>> Current KVM_USER_MEM_SLOTS limit (509) can be a limiting factor for some
>> configurations. In particular, when QEMU tries to start a Windows guest
>> with Hyper-V SynIC enabled and e.g. 256 vCPUs the limit is hit as SynIC
>> requires two pages per vCPU and the guest is free to pick any GFN for
>> each of them, this fragments memslots as QEMU wants to have a separate
>> memslot for each of these pages (which are supposed to act as 'overlay'
>> pages).
>
> What exactly does QEMU do on the backend? I poked around the code a bit, but
> didn't see anything relevant.
>
In QEMU's terms it registers memory sub-regions for these two pages (see
synic_update() in hw/hyperv/hyperv.c). Memory for these page-sized
sub-regions is allocated separately so in KVM terms they become
page-sized slots and previously continuous 'system memory' slot breaks
into several slots.
--
Vitaly
next prev parent reply other threads:[~2021-01-15 16:25 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-15 13:18 [PATCH RFC 0/4] KVM: x86: Drastically raise KVM_USER_MEM_SLOTS limit Vitaly Kuznetsov
2021-01-15 13:18 ` [PATCH RFC 1/4] KVM: x86: Drop redundant KVM_MEM_SLOTS_NUM definition Vitaly Kuznetsov
2021-01-15 16:47 ` Sean Christopherson
2021-01-15 13:18 ` [PATCH RFC 2/4] KVM: mips: Drop KVM_PRIVATE_MEM_SLOTS definition Vitaly Kuznetsov
2021-01-15 13:18 ` [PATCH RFC 3/4] KVM: Define KVM_USER_MEM_SLOTS in arch-neutral include/linux/kvm_host.h Vitaly Kuznetsov
2021-01-15 17:05 ` Sean Christopherson
2021-01-18 9:52 ` Vitaly Kuznetsov
2021-01-19 17:20 ` Sean Christopherson
2021-01-20 11:34 ` Igor Mammedov
2021-01-20 12:02 ` Vitaly Kuznetsov
2021-01-20 17:25 ` Sean Christopherson
2021-01-15 13:18 ` [PATCH RFC 4/4] KVM: x86: Stop limiting KVM_USER_MEM_SLOTS Vitaly Kuznetsov
2021-01-15 16:03 ` [PATCH RFC 0/4] KVM: x86: Drastically raise KVM_USER_MEM_SLOTS limit Sean Christopherson
2021-01-15 16:23 ` Vitaly Kuznetsov [this message]
2021-01-15 16:45 ` Sean Christopherson
2021-01-15 18:47 ` Maciej S. Szmigiero
2021-01-27 17:55 ` Vitaly Kuznetsov
2021-01-27 22:26 ` Maciej S. Szmigiero
2021-01-28 8:47 ` Vitaly Kuznetsov
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=87zh1a5fuj.fsf@vitty.brq.redhat.com \
--to=vkuznets@redhat.com \
--cc=jmattson@google.com \
--cc=kvm@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=seanjc@google.com \
--cc=wanpengli@tencent.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).