On Saturday 21 April 2007 22:12, Willy Tarreau wrote:Looks like this code does it: +int sysctl_sched_privileged_nice_level __read_mostly = -19; allows anything that sets sched_privileged_task one way or another gets nice -19, and this is enabled by default. --- linux-cfs-2.6.20.7.q.orig/arch/i386/kernel/ioport.c +++ linux-cfs-2.6.20.7.q/arch/i386/kernel/ioport.c + if (turn_on) { + if (!capable(CAP_SYS_RAWIO)) + return -EPERM; + /* + * Task will be accessing hardware IO ports, + * mark it as special with the scheduler too: + */ + sched_privileged_task(current); + } presumably that selects out X as a privileged task... and sets it to nice -19 by default. -- -ck -
| Pardo | Re: pthread_create() slow for many threads; also time to revisit 64b context switc... |
| Paul Jackson | Inquiry: Should we remove "isolcpus= kernel boot option? (may have realtime uses) |
| Srivatsa Vaddagiri | Re: [PATCH, RFC] reimplement flush_workqueue() |
| Peter Zijlstra | Re: Btrfs v0.16 released |
git: | |
| Giuseppe Bilotta | Re: gitweb and remote branches |
| Miklos Vajna | [rfc] git submodules howto |
| JD Guzman | C# Git Implementation |
| Junio C Hamano | Re: [PATCH] fix parallel make problem |
| Richard Stallman | Real men don't attack straw men |
| Steve B | SSH brute force attacks no longer being caught by PF rule |
| GVG GVG | ssh_exchange_identification: Connection closed by remote host |
| Marius ROMAN | 1440x900 resolution problem |
| Tomasz Grobelny | [PATCH 0/5] [DCCP]: Queuing policies |
| Dushan Tcholich | Re: ksoftirqd high cpu load on kernels 2.6.24 to 2.6.27-rc1-mm1 |
| John Heffner | Re: A Linux TCP SACK Question |
| Denys Fedoryshchenko | Re: Could you make vconfig less stupid? |
