On Fri, 4 Apr 2008, Jeremy Fitzhardinge wrote:Note that you could use 4k page size chunks for the memmap if its virtualized (CONFIG_SPARSEMEM_VMEMMAP). Instead of a single PMD pointing to a 2MB block you would have the PMD point to a block of ptes that would in turn point to the discontiguous series of 4k pages. The memory is virtually contiguous so all the logic stays the same. What would be needed is some enhancements to the way the memmap is populated. --
| Ingo Molnar | Re: 2.6.24-rc6-mm1 |
| David Woodhouse | Re: [GIT *] Allow request_firmware() to be satisfied from in-kernel, use it in mor... |
| Eric W. Biederman | [PATCH] ipv4/ipvs: Convert to kthread API |
| Karl Meyer | PROBLEM: 2.6.23-rc "NETDEV WATCHDOG: eth0: transmit timed out" |
git: | |
| Shawn O. Pearce | libgit2 - a true git library |
| Martin Langhoff | Re: pack operation is thrashing my server |
| Andreas Ericsson | git to libgit2 code relicensing |
| Eric Hanchrow | Re: how to backup git |
| rezidue | Speed Problems |
| GVG GVG | ssh_exchange_identification: Connection closed by remote host |
| Henning Brauer | Re: About Xen: maybe a reiterative question but .. |
| Richard Stallman | Real men don't attack straw men |
| Hannes Eder | [PATCH 00/27] drivers/net: fix sparse warnings |
| David Miller | Re: [PATCH] pkt_sched: Destroy gen estimators under rtnl_lock(). |
| Herbert Xu | Re: incorrect cksum with tcp/udp on lo with 2.6.20/2.6.21/2.6.22 |
| Simon Horman | Re: [PATCH RFC 00/24] IPVS: Add first IPv6 support to IPVS |
