On Tue, 25 Mar 2008, Thomas Meyer wrote:Ok, so it didn't use to be at the 4GB mark. This seems to be a PCI and resource alloc issue. It would be really interesting to see where the 4GB allocation started. Ie ignore anything else (warnings, driver loadings etc), and _just_ look at lspci -vv output for where the memory got allocated. Did you already bisect that and I just missed it? Linus --
| David Miller | [GIT]: Networking |
| Fred . | Please add ZFS support (from GPL sources) |
| Pavel Roskin | [PATCH 2.6.25] module: allow ndiswrapper to use GPL-only symbols |
| David Howells | [PATCH 02/52] CRED: Give in_group_p() a cred pointer |
git: | |
| Dmitry Torokhov | Garbage in .git directories??? |
| Dan Farina | backup or mirror a repository |
| Sergei Organov | Newbie: report of first experience with git-rebase. |
| Richard Quirk | git-cherry-pick no longer detecting moved files in 1.5.3.4 |
| Kevin | uvm_mapent_alloc: out of static map entries on 4.3 i386 |
| GVG GVG | ssh_exchange_identification: Connection closed by remote host |
| Douglas A. Tutty | how get colour mutt when ssh from OBSD? |
| Brandon Lee | DELL PERC 5iR slow performance |
| Hubert Feyrer | Compressed vnd handling tested successfully |
| Jaromir Dolecek | Arch-specific maxproc limit? |
| YAMAMOTO Takashi | scheduler_wait_hook |
| David Laight | Re: Integrating securelevel and kauth(9) |
