I've been working on the scheduler issues for the last two days. http://leaf.dragonflybsd.org/~dillon/sched02.patch The work is intended to solve jerkiness / other scheduler issues related to mixed batch / interactive loads. I fixed a number of low level issues that were causing the scheduler to make bad choices in regards to what to schedule, even in the face of properly working statistical measurements. I also added a long-term interactivity measurement which so far appears to do a good job discerning between, say, a buildworld and X/mozilla. I'm not so sure how will it will do with, e.g. audio and video playback... probably not so well with video in the face of other batch ops. It does degrade pipe throughput slightly (mainly because the hacks I had added to the existing scheduler to make pipe throughput better screwed up other things so I backed them out in this patch). In anycase, I'm looking for people to test the stability and value of the changes verses what we had before, especially on MP systems. It is entirely untested on MP systems. -Matt Matthew Dillon <dillon@backplane.com>
| Andrew Morton | Re: Linux 2.6.21-rc4 |
| Len Brown | [PATCH 01/85] ACPI: Add missing acpi.debug_layer Documentation hunk from Thomas Re... |
| David | sdhci: Ricoh Co Ltd R5C822 SD/SDIO/MMC/MS/MSPro Host Adapter - disabling IRQ |
| Olaf van der Spek | Unix sockets via TCP on localhost: is TCP slower? |
git: | |
| Andy Parkins | svn:externals using git submodules |
| Peter Karlsson | CRLF problems with Git on Win32 |
| Denis Bueno | Git clone error |
| Michael S. Tsirkin | git-kill: rewrite history removing a commit |
| Martín Coco | Hardware recommendation for firewalls (more than 4 NICs) |
| C. Soragan Ong | OpenBSD 4.4 amd64 bsd.mp can't detect 4GB memory |
| Richard Stallman | Real men don't attack straw men |
| Chris | OpenBSD 4.4 installation error: write failed; file system full |
| Jarek Poplawski | Re: [PATCH] pkt_sched: Destroy gen estimators under rtnl_lock(). |
| Wenji Wu | A Linux TCP SACK Question |
| Dushan Tcholich | Re: ksoftirqd high cpu load on kernels 2.6.24 to 2.6.27-rc1-mm1 |
| Hannes Eder | [PATCH 19/27] drivers/net/usb: fix sparse warnings: make symbols static |
