Date: Fri, 23 Aug 2013 12:29:42 +0200 From: Ivan Voras <ivoras@freebsd.org> To: freebsd-virtualization@freebsd.org Subject: Re: CFT: nested page table integration with amd64/pmap Message-ID: <kv7dig$id5$1@ger.gmane.org> In-Reply-To: <CAFgRE9H2n63%2B3GFwWNwE-Zu3gHPBcWhD4g6frB_ksXz=HAXp5w@mail.gmail.com> References: <CAFgRE9H2n63%2B3GFwWNwE-Zu3gHPBcWhD4g6frB_ksXz=HAXp5w@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
[-- Attachment #1 --] On 23/08/2013 00:55, Neel Natu wrote: > Hi, > > The projects/bhyve_npt_pmap branch modifies the amd64/pmap to be able to > deal with Intel EPT mappings in addition to the regular x86 page tables. > > This provides bhyve with the following features: > > 1. Memory overcommit > Guest memory is now pageable and therefore virtual machines can allocate > more memory than is physically available on the host. I always wondered about virtualization environments which have pageable guest memory - how does the guest kernel handle situations where it really needs non-pageable memory? Does is simply "not care" because for it the memory access looks just like it isn't paged but is simply very, very slow? What about time-sensitive situations (like the originally mentioned PCI-passthrough)? [-- Attachment #2 --] -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.19 (FreeBSD) Comment: Using GnuPG with Thunderbird - http://www.enigmail.net/ iEYEARECAAYFAlIXOZgACgkQ/QjVBj3/HSyYgACfWA9NPNFPLYXIN6ijqvyFaZxe QHQAoI0xT/PjHIGqddUrZ4HMZU+MJgcy =ptsi -----END PGP SIGNATURE-----
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?kv7dig$id5$1>