From d38e83c715270cc2e137bbf6f25206c8c023896b Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 13 Aug 2014 21:19:56 +0200 Subject: sched: s/do_each_thread/for_each_process_thread/ in debug.c Change kernel/sched/debug.c to use for_each_process_thread(). Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Hidetoshi Seto Cc: Frank Mayhar Cc: Frederic Weisbecker Cc: Andrew Morton Cc: Sanjay Rao Cc: Larry Woodman Cc: Rik van Riel Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20140813191956.GA19324@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/debug.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 627b3c34b821..c7fe1ea0e8ab 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -160,14 +160,12 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) "----------------------------------------------------\n"); read_lock_irqsave(&tasklist_lock, flags); - - do_each_thread(g, p) { + for_each_process_thread(g, p) { if (task_cpu(p) != rq_cpu) continue; print_task(m, rq, p); - } while_each_thread(g, p); - + } read_unlock_irqrestore(&tasklist_lock, flags); } -- cgit v1.2.3 From 5bd96ab6fef66ec6b9f54134364e618fd0f8f2f3 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sun, 21 Sep 2014 21:33:41 +0200 Subject: sched: print_rq(): Don't use tasklist_lock read_lock_irqsave(tasklist_lock) in print_rq() looks strange. We do not need to disable irqs, and they are already disabled by the caller. And afaics this lock buys nothing, we can rely on rcu_read_lock(). In this case it makes sense to also move rcu_read_lock/unlock from the caller to print_rq(). Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Cc: Kirill Tkhai Cc: Mike Galbraith Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20140921193341.GA28628@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/debug.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index c7fe1ea0e8ab..ce33780d8f20 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -150,7 +150,6 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) { struct task_struct *g, *p; - unsigned long flags; SEQ_printf(m, "\nrunnable tasks:\n" @@ -159,14 +158,14 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) "------------------------------------------------------" "----------------------------------------------------\n"); - read_lock_irqsave(&tasklist_lock, flags); + rcu_read_lock(); for_each_process_thread(g, p) { if (task_cpu(p) != rq_cpu) continue; print_task(m, rq, p); } - read_unlock_irqrestore(&tasklist_lock, flags); + rcu_read_unlock(); } void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) @@ -331,9 +330,7 @@ do { \ print_cfs_stats(m, cpu); print_rt_stats(m, cpu); - rcu_read_lock(); print_rq(m, rq, cpu); - rcu_read_unlock(); spin_unlock_irqrestore(&sched_debug_lock, flags); SEQ_printf(m, "\n"); } -- cgit v1.2.3 From acb32132ec0433c03bed750f3e9508dc29db0328 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Fri, 31 Oct 2014 06:39:33 +0800 Subject: sched/deadline: Add deadline rq status print This patch add deadline rq status print. Signed-off-by: Wanpeng Li Signed-off-by: Peter Zijlstra (Intel) Cc: Juri Lelli Cc: Kirill Tkhai Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1414708776-124078-3-git-send-email-wanpeng.li@linux.intel.com Signed-off-by: Ingo Molnar --- kernel/sched/deadline.c | 9 +++++++++ kernel/sched/debug.c | 7 +++++++ kernel/sched/sched.h | 1 + 3 files changed, 17 insertions(+) (limited to 'kernel/sched/debug.c') diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index c047a94de273..8867a67b8f0a 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1747,3 +1747,12 @@ const struct sched_class dl_sched_class = { .switched_from = switched_from_dl, .switched_to = switched_to_dl, }; + +#ifdef CONFIG_SCHED_DEBUG +extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq); + +void print_dl_stats(struct seq_file *m, int cpu) +{ + print_dl_rq(m, cpu, &cpu_rq(cpu)->dl); +} +#endif /* CONFIG_SCHED_DEBUG */ diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index ce33780d8f20..eeb6046d60c7 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -261,6 +261,12 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) #undef P } +void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq) +{ + SEQ_printf(m, "\ndl_rq[%d]:\n", cpu); + SEQ_printf(m, " .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running); +} + extern __read_mostly int sched_clock_running; static void print_cpu(struct seq_file *m, int cpu) @@ -329,6 +335,7 @@ do { \ spin_lock_irqsave(&sched_debug_lock, flags); print_cfs_stats(m, cpu); print_rt_stats(m, cpu); + print_dl_stats(m, cpu); print_rq(m, rq, cpu); spin_unlock_irqrestore(&sched_debug_lock, flags); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 49b941fe2cc2..7e5c1eebc110 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1537,6 +1537,7 @@ extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq); extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq); extern void print_cfs_stats(struct seq_file *m, int cpu); extern void print_rt_stats(struct seq_file *m, int cpu); +extern void print_dl_stats(struct seq_file *m, int cpu); extern void init_cfs_rq(struct cfs_rq *cfs_rq); extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq); -- cgit v1.2.3 From 44dba3d5d6a10685fb15bd1954e62016334825e0 Mon Sep 17 00:00:00 2001 From: Iulia Manda Date: Fri, 31 Oct 2014 02:13:31 +0200 Subject: sched: Refactor task_struct to use numa_faults instead of numa_* pointers This patch simplifies task_struct by removing the four numa_* pointers in the same array and replacing them with the array pointer. By doing this, on x86_64, the size of task_struct is reduced by 3 ulong pointers (24 bytes on x86_64). A new parameter is added to the task_faults_idx function so that it can return an index to the correct offset, corresponding with the old precalculated pointers. All of the code in sched/ that depended on task_faults_idx and numa_* was changed in order to match the new logic. Signed-off-by: Iulia Manda Signed-off-by: Peter Zijlstra (Intel) Cc: mgorman@suse.de Cc: dave@stgolabs.net Cc: riel@redhat.com Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20141031001331.GA30662@winterfell Signed-off-by: Ingo Molnar --- include/linux/sched.h | 31 ++++++-------- kernel/sched/core.c | 3 +- kernel/sched/debug.c | 4 +- kernel/sched/fair.c | 110 ++++++++++++++++++++++++++------------------------ kernel/sched/sched.h | 7 ++++ 5 files changed, 80 insertions(+), 75 deletions(-) (limited to 'kernel/sched/debug.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4400ddc2fe73..bd7c14ba86c4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1597,27 +1597,22 @@ struct task_struct { struct numa_group *numa_group; /* - * Exponential decaying average of faults on a per-node basis. - * Scheduling placement decisions are made based on the these counts. - * The values remain static for the duration of a PTE scan + * numa_faults is an array split into four regions: + * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer + * in this precise order. + * + * faults_memory: Exponential decaying average of faults on a per-node + * basis. Scheduling placement decisions are made based on these + * counts. The values remain static for the duration of a PTE scan. + * faults_cpu: Track the nodes the process was running on when a NUMA + * hinting fault was incurred. + * faults_memory_buffer and faults_cpu_buffer: Record faults per node + * during the current scan window. When the scan completes, the counts + * in faults_memory and faults_cpu decay and these values are copied. */ - unsigned long *numa_faults_memory; + unsigned long *numa_faults; unsigned long total_numa_faults; - /* - * numa_faults_buffer records faults per node during the current - * scan window. When the scan completes, the counts in - * numa_faults_memory decay and these values are copied. - */ - unsigned long *numa_faults_buffer_memory; - - /* - * Track the nodes the process was running on when a NUMA hinting - * fault was incurred. - */ - unsigned long *numa_faults_cpu; - unsigned long *numa_faults_buffer_cpu; - /* * numa_faults_locality tracks if faults recorded during the last * scan window were remote/local. The task scan period is adapted diff --git a/kernel/sched/core.c b/kernel/sched/core.c index df0569ebec0f..72d9d926a034 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1857,8 +1857,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0; p->numa_scan_period = sysctl_numa_balancing_scan_delay; p->numa_work.next = &p->numa_work; - p->numa_faults_memory = NULL; - p->numa_faults_buffer_memory = NULL; + p->numa_faults = NULL; p->last_task_numa_placement = 0; p->last_sum_exec_runtime = 0; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index eeb6046d60c7..92cc52001e74 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -535,8 +535,8 @@ static void sched_show_numa(struct task_struct *p, struct seq_file *m) unsigned long nr_faults = -1; int cpu_current, home_node; - if (p->numa_faults_memory) - nr_faults = p->numa_faults_memory[2*node + i]; + if (p->numa_faults) + nr_faults = p->numa_faults[2*node + i]; cpu_current = !i ? (task_node(p) == node) : (pol && node_isset(node, pol->v.nodes)); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index d03d76de7aff..826fdf326683 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -896,18 +896,24 @@ pid_t task_numa_group_id(struct task_struct *p) return p->numa_group ? p->numa_group->gid : 0; } -static inline int task_faults_idx(int nid, int priv) +/* + * The averaged statistics, shared & private, memory & cpu, + * occupy the first half of the array. The second half of the + * array is for current counters, which are averaged into the + * first set by task_numa_placement. + */ +static inline int task_faults_idx(enum numa_faults_stats s, int nid, int priv) { - return NR_NUMA_HINT_FAULT_TYPES * nid + priv; + return NR_NUMA_HINT_FAULT_TYPES * (s * nr_node_ids + nid) + priv; } static inline unsigned long task_faults(struct task_struct *p, int nid) { - if (!p->numa_faults_memory) + if (!p->numa_faults) return 0; - return p->numa_faults_memory[task_faults_idx(nid, 0)] + - p->numa_faults_memory[task_faults_idx(nid, 1)]; + return p->numa_faults[task_faults_idx(NUMA_MEM, nid, 0)] + + p->numa_faults[task_faults_idx(NUMA_MEM, nid, 1)]; } static inline unsigned long group_faults(struct task_struct *p, int nid) @@ -915,14 +921,14 @@ static inline unsigned long group_faults(struct task_struct *p, int nid) if (!p->numa_group) return 0; - return p->numa_group->faults[task_faults_idx(nid, 0)] + - p->numa_group->faults[task_faults_idx(nid, 1)]; + return p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 0)] + + p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)]; } static inline unsigned long group_faults_cpu(struct numa_group *group, int nid) { - return group->faults_cpu[task_faults_idx(nid, 0)] + - group->faults_cpu[task_faults_idx(nid, 1)]; + return group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 0)] + + group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)]; } /* Handle placement on systems where not all nodes are directly connected. */ @@ -1001,7 +1007,7 @@ static inline unsigned long task_weight(struct task_struct *p, int nid, { unsigned long faults, total_faults; - if (!p->numa_faults_memory) + if (!p->numa_faults) return 0; total_faults = p->total_numa_faults; @@ -1517,7 +1523,7 @@ static void numa_migrate_preferred(struct task_struct *p) unsigned long interval = HZ; /* This task has no NUMA fault statistics yet */ - if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults_memory)) + if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults)) return; /* Periodically retry migrating the task to the preferred node */ @@ -1779,18 +1785,23 @@ static void task_numa_placement(struct task_struct *p) /* Find the node with the highest number of faults */ for_each_online_node(nid) { + /* Keep track of the offsets in numa_faults array */ + int mem_idx, membuf_idx, cpu_idx, cpubuf_idx; unsigned long faults = 0, group_faults = 0; - int priv, i; + int priv; for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) { long diff, f_diff, f_weight; - i = task_faults_idx(nid, priv); + mem_idx = task_faults_idx(NUMA_MEM, nid, priv); + membuf_idx = task_faults_idx(NUMA_MEMBUF, nid, priv); + cpu_idx = task_faults_idx(NUMA_CPU, nid, priv); + cpubuf_idx = task_faults_idx(NUMA_CPUBUF, nid, priv); /* Decay existing window, copy faults since last scan */ - diff = p->numa_faults_buffer_memory[i] - p->numa_faults_memory[i] / 2; - fault_types[priv] += p->numa_faults_buffer_memory[i]; - p->numa_faults_buffer_memory[i] = 0; + diff = p->numa_faults[membuf_idx] - p->numa_faults[mem_idx] / 2; + fault_types[priv] += p->numa_faults[membuf_idx]; + p->numa_faults[membuf_idx] = 0; /* * Normalize the faults_from, so all tasks in a group @@ -1800,21 +1811,27 @@ static void task_numa_placement(struct task_struct *p) * faults are less important. */ f_weight = div64_u64(runtime << 16, period + 1); - f_weight = (f_weight * p->numa_faults_buffer_cpu[i]) / + f_weight = (f_weight * p->numa_faults[cpubuf_idx]) / (total_faults + 1); - f_diff = f_weight - p->numa_faults_cpu[i] / 2; - p->numa_faults_buffer_cpu[i] = 0; + f_diff = f_weight - p->numa_faults[cpu_idx] / 2; + p->numa_faults[cpubuf_idx] = 0; - p->numa_faults_memory[i] += diff; - p->numa_faults_cpu[i] += f_diff; - faults += p->numa_faults_memory[i]; + p->numa_faults[mem_idx] += diff; + p->numa_faults[cpu_idx] += f_diff; + faults += p->numa_faults[mem_idx]; p->total_numa_faults += diff; if (p->numa_group) { - /* safe because we can only change our own group */ - p->numa_group->faults[i] += diff; - p->numa_group->faults_cpu[i] += f_diff; + /* + * safe because we can only change our own group + * + * mem_idx represents the offset for a given + * nid and priv in a specific region because it + * is at the beginning of the numa_faults array. + */ + p->numa_group->faults[mem_idx] += diff; + p->numa_group->faults_cpu[mem_idx] += f_diff; p->numa_group->total_faults += diff; - group_faults += p->numa_group->faults[i]; + group_faults += p->numa_group->faults[mem_idx]; } } @@ -1886,7 +1903,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, node_set(task_node(current), grp->active_nodes); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) - grp->faults[i] = p->numa_faults_memory[i]; + grp->faults[i] = p->numa_faults[i]; grp->total_faults = p->total_numa_faults; @@ -1945,8 +1962,8 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, double_lock_irq(&my_grp->lock, &grp->lock); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) { - my_grp->faults[i] -= p->numa_faults_memory[i]; - grp->faults[i] += p->numa_faults_memory[i]; + my_grp->faults[i] -= p->numa_faults[i]; + grp->faults[i] += p->numa_faults[i]; } my_grp->total_faults -= p->total_numa_faults; grp->total_faults += p->total_numa_faults; @@ -1971,14 +1988,14 @@ no_join: void task_numa_free(struct task_struct *p) { struct numa_group *grp = p->numa_group; - void *numa_faults = p->numa_faults_memory; + void *numa_faults = p->numa_faults; unsigned long flags; int i; if (grp) { spin_lock_irqsave(&grp->lock, flags); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) - grp->faults[i] -= p->numa_faults_memory[i]; + grp->faults[i] -= p->numa_faults[i]; grp->total_faults -= p->total_numa_faults; list_del(&p->numa_entry); @@ -1988,10 +2005,7 @@ void task_numa_free(struct task_struct *p) put_numa_group(grp); } - p->numa_faults_memory = NULL; - p->numa_faults_buffer_memory = NULL; - p->numa_faults_cpu= NULL; - p->numa_faults_buffer_cpu = NULL; + p->numa_faults = NULL; kfree(numa_faults); } @@ -2014,24 +2028,14 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) return; /* Allocate buffer to track faults on a per-node basis */ - if (unlikely(!p->numa_faults_memory)) { - int size = sizeof(*p->numa_faults_memory) * + if (unlikely(!p->numa_faults)) { + int size = sizeof(*p->numa_faults) * NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids; - p->numa_faults_memory = kzalloc(size, GFP_KERNEL|__GFP_NOWARN); - if (!p->numa_faults_memory) + p->numa_faults = kzalloc(size, GFP_KERNEL|__GFP_NOWARN); + if (!p->numa_faults) return; - BUG_ON(p->numa_faults_buffer_memory); - /* - * The averaged statistics, shared & private, memory & cpu, - * occupy the first half of the array. The second half of the - * array is for current counters, which are averaged into the - * first set by task_numa_placement. - */ - p->numa_faults_cpu = p->numa_faults_memory + (2 * nr_node_ids); - p->numa_faults_buffer_memory = p->numa_faults_memory + (4 * nr_node_ids); - p->numa_faults_buffer_cpu = p->numa_faults_memory + (6 * nr_node_ids); p->total_numa_faults = 0; memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality)); } @@ -2071,8 +2075,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) if (migrated) p->numa_pages_migrated += pages; - p->numa_faults_buffer_memory[task_faults_idx(mem_node, priv)] += pages; - p->numa_faults_buffer_cpu[task_faults_idx(cpu_node, priv)] += pages; + p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages; + p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages; p->numa_faults_locality[local] += pages; } @@ -5361,7 +5365,7 @@ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env) struct numa_group *numa_group = rcu_dereference(p->numa_group); int src_nid, dst_nid; - if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults_memory || + if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults || !(env->sd->flags & SD_NUMA)) { return false; } @@ -5400,7 +5404,7 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env) if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER)) return false; - if (!p->numa_faults_memory || !(env->sd->flags & SD_NUMA)) + if (!p->numa_faults || !(env->sd->flags & SD_NUMA)) return false; src_nid = cpu_to_node(env->src_cpu); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 7e5c1eebc110..31f1e4d2996a 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -709,6 +709,13 @@ extern bool find_numa_distance(int distance); #endif #ifdef CONFIG_NUMA_BALANCING +/* The regions in numa_faults array from task_struct */ +enum numa_faults_stats { + NUMA_MEM = 0, + NUMA_CPU, + NUMA_MEMBUF, + NUMA_CPUBUF +}; extern void sched_setnuma(struct task_struct *p, int node); extern int migrate_task_to(struct task_struct *p, int cpu); extern int migrate_swap(struct task_struct *, struct task_struct *); -- cgit v1.2.3