Hi Peter,
FYI, there are new compile warnings show up in
tree: git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git master
head: 2ef756a2e79149dc84c88f7ccc42ec38cbb7722e
commit: 4ae834f767c59b42cdf2a5077a18388525ba78b2 [27/35] sched/numa: Implement NUMA home-node selection code
config: avr32-atngw100_defconfig
All warnings:
kernel/sched/fair.c:791: warning: 'task_h_load' declared 'static' but never defined
kernel/sched/fair.c:909: warning: 'account_offnode_enqueue' defined but not used
vim +791 kernel/sched/fair.c
305e6835 kernel/sched_fair.c (Venkatesh Pallipadi 2010-10-04 775) se->exec_start = rq_of(cfs_rq)->clock_task;
bf0f6f24 kernel/sched_fair.c (Ingo Molnar 2007-07-09 776) }
bf0f6f24 kernel/sched_fair.c (Ingo Molnar 2007-07-09 777)
bf0f6f24 kernel/sched_fair.c (Ingo Molnar 2007-07-09 778) /**************************************************
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 779) * Scheduling class numa methods.
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 780) *
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 781) * The purpose of the NUMA bits are to maintain compute (task) and data
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 782) * (memory) locality. We try and achieve this by making tasks stick to
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 783) * a particular node (their home node) but if fairness mandates they run
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 784) * elsewhere for long enough, we let the memory follow them.
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 785) *
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 786) * Tasks start out with their home-node unset (-1) this effectively means
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 787) * they act !NUMA until we've established the task is busy enough to bother
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 788) * with placement.
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 789) */
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 790)
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 @791) static unsigned long task_h_load(struct task_struct *p);
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 792)
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 793) #ifdef CONFIG_SCHED_NUMA
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 794) static void account_offnode_enqueue(struct rq *rq, struct task_struct *p)
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 795) {
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 796) p->numa_contrib = task_h_load(p);
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 797) rq->offnode_weight += p->numa_contrib;
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 798) rq->offnode_running++;
4ae834f7 kernel/sched/fair.c (Peter Zijlstra 2012-07-16 799) }
---
0-DAY kernel build testing backend Open Source Technology Centre
Fengguang Wu, Yuanhan Liu Intel Corporation
--
To unsubscribe from this list: send the line "unsubscribe kernel-janitors" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
