From cd64647f043e3fd3569bcf068f47f030198ff93a Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Mon, 23 Sep 2013 16:43:58 +0800 Subject: hung_task: Change sysctl_hung_task_check_count to 'int' As 'sysctl_hung_task_check_count' is 'unsigned long' when this value is assigned to max_count in check_hung_uninterruptible_tasks(), it's truncated to 'int' type. This causes a minor artifact: if we write 2^32 to sysctl.hung_task_check_count, hung task detection will be effectively disabled. With this fix, it will still truncate the user input to 32 bits, but reading sysctl.hung_task_check_count reflects the actual truncated value. Signed-off-by: Li Zefan Acked-by: Ingo Molnar Link: http://lkml.kernel.org/r/523FFF4E.9050401@huawei.com Signed-off-by: Ingo Molnar --- kernel/sysctl.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b2f06f3c6a3..b24ed7f87a1 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -962,9 +962,10 @@ static struct ctl_table kern_table[] = { { .procname = "hung_task_check_count", .data = &sysctl_hung_task_check_count, - .maxlen = sizeof(unsigned long), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_doulongvec_minmax, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, }, { .procname = "hung_task_timeout_secs", -- cgit v1.2.3-70-g09d2 From 723478c8a471403c53cf144999701f6e0c4bbd11 Mon Sep 17 00:00:00 2001 From: Knut Petersen Date: Wed, 25 Sep 2013 14:29:37 +0200 Subject: perf: Enforce 1 as lower limit for perf_event_max_sample_rate /proc/sys/kernel/perf_event_max_sample_rate will accept negative values as well as 0. Negative values are unreasonable, and 0 causes a divide by zero exception in perf_proc_update_handler. This patch enforces a lower limit of 1. Signed-off-by: Knut Petersen Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/5242DB0C.4070005@t-online.de Signed-off-by: Ingo Molnar --- kernel/events/core.c | 2 +- kernel/sysctl.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/events/core.c b/kernel/events/core.c index d49a9d29334..b25d65ce710 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -193,7 +193,7 @@ int perf_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret = proc_dointvec(table, write, buffer, lenp, ppos); + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret || !write) return ret; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b2f06f3c6a3..2a9db916c3f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1049,6 +1049,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(sysctl_perf_event_sample_rate), .mode = 0644, .proc_handler = perf_proc_update_handler, + .extra1 = &one, }, { .procname = "perf_cpu_time_max_percent", -- cgit v1.2.3-70-g09d2 From 3a7053b3224f4a8b0e8184166190076593621617 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 7 Oct 2013 11:29:00 +0100 Subject: sched/numa: Favour moving tasks towards the preferred node This patch favours moving tasks towards NUMA node that recorded a higher number of NUMA faults during active load balancing. Ideally this is self-reinforcing as the longer the task runs on that node, the more faults it should incur causing task_numa_placement to keep the task running on that node. In reality a big weakness is that the nodes CPUs can be overloaded and it would be more efficient to queue tasks on an idle node and migrate to the new node. This would require additional smarts in the balancer so for now the balancer will simply prefer to place the task on the preferred node for a PTE scans which is controlled by the numa_balancing_settle_count sysctl. Once the settle_count number of scans has complete the schedule is free to place the task on an alternative node if the load is imbalanced. [srikar@linux.vnet.ibm.com: Fixed statistics] Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Cc: Andrea Arcangeli Cc: Johannes Weiner Cc: Srikar Dronamraju [ Tunable and use higher faults instead of preferred. ] Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1381141781-10992-23-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar --- Documentation/sysctl/kernel.txt | 8 +++++- include/linux/sched.h | 1 + kernel/sched/core.c | 3 +- kernel/sched/fair.c | 63 ++++++++++++++++++++++++++++++++++++++--- kernel/sched/features.h | 7 +++++ kernel/sysctl.c | 7 +++++ 6 files changed, 83 insertions(+), 6 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 8cd7e5fc79d..d48bca45b6f 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -375,7 +375,8 @@ feature should be disabled. Otherwise, if the system overhead from the feature is too high then the rate the kernel samples for NUMA hinting faults may be controlled by the numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms, numa_balancing_scan_period_reset, -numa_balancing_scan_period_max_ms and numa_balancing_scan_size_mb sysctls. +numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb and +numa_balancing_settle_count sysctls. ============================================================== @@ -420,6 +421,11 @@ scanned for a given scan. numa_balancing_scan_period_reset is a blunt instrument that controls how often a tasks scan delay is reset to detect sudden changes in task behaviour. +numa_balancing_settle_count is how many scan periods must complete before +the schedule balancer stops pushing the task towards a preferred node. This +gives the scheduler a chance to place the task on an alternative node if the +preferred node is overloaded. + ============================================================== osrelease, ostype & version: diff --git a/include/linux/sched.h b/include/linux/sched.h index a463bc3ad43..aecdc5a1877 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -777,6 +777,7 @@ enum cpu_idle_type { #define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */ #define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */ #define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */ +#define SD_NUMA 0x4000 /* cross-node balancing */ extern int __weak arch_sd_sibiling_asym_packing(void); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 064a0af4454..b7e6b6f9c5f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1631,7 +1631,7 @@ static void __sched_fork(struct task_struct *p) p->node_stamp = 0ULL; p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0; - p->numa_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 0; + p->numa_migrate_seq = 0; p->numa_scan_period = sysctl_numa_balancing_scan_delay; p->numa_preferred_nid = -1; p->numa_work.next = &p->numa_work; @@ -5656,6 +5656,7 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu) | 0*SD_SHARE_PKG_RESOURCES | 1*SD_SERIALIZE | 0*SD_PREFER_SIBLING + | 1*SD_NUMA | sd_local_flags(level) , .last_balance = jiffies, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 3abc651bc38..6ffddca687f 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -877,6 +877,15 @@ static unsigned int task_scan_max(struct task_struct *p) return max(smin, smax); } +/* + * Once a preferred node is selected the scheduler balancer will prefer moving + * a task to that node for sysctl_numa_balancing_settle_count number of PTE + * scans. This will give the process the chance to accumulate more faults on + * the preferred node but still allow the scheduler to move the task again if + * the nodes CPUs are overloaded. + */ +unsigned int sysctl_numa_balancing_settle_count __read_mostly = 3; + static void task_numa_placement(struct task_struct *p) { int seq, nid, max_nid = -1; @@ -888,6 +897,7 @@ static void task_numa_placement(struct task_struct *p) if (p->numa_scan_seq == seq) return; p->numa_scan_seq = seq; + p->numa_migrate_seq++; p->numa_scan_period_max = task_scan_max(p); /* Find the node with the highest number of faults */ @@ -907,8 +917,10 @@ static void task_numa_placement(struct task_struct *p) } /* Update the tasks preferred node if necessary */ - if (max_faults && max_nid != p->numa_preferred_nid) + if (max_faults && max_nid != p->numa_preferred_nid) { p->numa_preferred_nid = max_nid; + p->numa_migrate_seq = 0; + } } /* @@ -4071,6 +4083,38 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) return delta < (s64)sysctl_sched_migration_cost; } +#ifdef CONFIG_NUMA_BALANCING +/* Returns true if the destination node has incurred more faults */ +static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env) +{ + int src_nid, dst_nid; + + if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults || + !(env->sd->flags & SD_NUMA)) { + return false; + } + + src_nid = cpu_to_node(env->src_cpu); + dst_nid = cpu_to_node(env->dst_cpu); + + if (src_nid == dst_nid || + p->numa_migrate_seq >= sysctl_numa_balancing_settle_count) + return false; + + if (dst_nid == p->numa_preferred_nid || + p->numa_faults[dst_nid] > p->numa_faults[src_nid]) + return true; + + return false; +} +#else +static inline bool migrate_improves_locality(struct task_struct *p, + struct lb_env *env) +{ + return false; +} +#endif + /* * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? */ @@ -4128,11 +4172,22 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) /* * Aggressive migration if: - * 1) task is cache cold, or - * 2) too many balance attempts have failed. + * 1) destination numa is preferred + * 2) task is cache cold, or + * 3) too many balance attempts have failed. */ - tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd); + + if (migrate_improves_locality(p, env)) { +#ifdef CONFIG_SCHEDSTATS + if (tsk_cache_hot) { + schedstat_inc(env->sd, lb_hot_gained[env->idle]); + schedstat_inc(p, se.statistics.nr_forced_migrations); + } +#endif + return 1; + } + if (!tsk_cache_hot || env->sd->nr_balance_failed > env->sd->cache_nice_tries) { diff --git a/kernel/sched/features.h b/kernel/sched/features.h index cba5c616a15..d9278ce2c4b 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -67,4 +67,11 @@ SCHED_FEAT(LB_MIN, false) */ #ifdef CONFIG_NUMA_BALANCING SCHED_FEAT(NUMA, false) + +/* + * NUMA_FAVOUR_HIGHER will favor moving tasks towards nodes where a + * higher number of hinting faults are recorded during active load + * balancing. + */ +SCHED_FEAT(NUMA_FAVOUR_HIGHER, true) #endif diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b2f06f3c6a3..42f616a74f4 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -391,6 +391,13 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "numa_balancing_settle_count", + .data = &sysctl_numa_balancing_settle_count, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_SCHED_DEBUG */ { -- cgit v1.2.3-70-g09d2 From 930aa174fcc8b0efaad102fd80f677b92f35eaa2 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 7 Oct 2013 11:29:37 +0100 Subject: sched/numa: Remove the numa_balancing_scan_period_reset sysctl With scan rate adaptions based on whether the workload has properly converged or not there should be no need for the scan period reset hammer. Get rid of it. Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Cc: Andrea Arcangeli Cc: Johannes Weiner Cc: Srikar Dronamraju Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1381141781-10992-60-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar --- Documentation/sysctl/kernel.txt | 11 +++-------- include/linux/mm_types.h | 3 --- include/linux/sched/sysctl.h | 1 - kernel/sched/core.c | 1 - kernel/sched/fair.c | 18 +----------------- kernel/sysctl.c | 7 ------- 6 files changed, 4 insertions(+), 37 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index d48bca45b6f..84f17800f8b 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -374,15 +374,13 @@ guarantee. If the target workload is already bound to NUMA nodes then this feature should be disabled. Otherwise, if the system overhead from the feature is too high then the rate the kernel samples for NUMA hinting faults may be controlled by the numa_balancing_scan_period_min_ms, -numa_balancing_scan_delay_ms, numa_balancing_scan_period_reset, -numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb and -numa_balancing_settle_count sysctls. +numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, +numa_balancing_scan_size_mb and numa_balancing_settle_count sysctls. ============================================================== numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms, -numa_balancing_scan_period_max_ms, numa_balancing_scan_period_reset, -numa_balancing_scan_size_mb +numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb Automatic NUMA balancing scans tasks address space and unmaps pages to detect if pages are properly placed or if the data should be migrated to a @@ -418,9 +416,6 @@ rate for each task. numa_balancing_scan_size_mb is how many megabytes worth of pages are scanned for a given scan. -numa_balancing_scan_period_reset is a blunt instrument that controls how -often a tasks scan delay is reset to detect sudden changes in task behaviour. - numa_balancing_settle_count is how many scan periods must complete before the schedule balancer stops pushing the task towards a preferred node. This gives the scheduler a chance to place the task on an alternative node if the diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index a30f9ca6655..a3198e5aaf4 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -420,9 +420,6 @@ struct mm_struct { */ unsigned long numa_next_scan; - /* numa_next_reset is when the PTE scanner period will be reset */ - unsigned long numa_next_reset; - /* Restart point for scanning and setting pte_numa */ unsigned long numa_scan_offset; diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index bf8086b2506..10d16c4fbe8 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -47,7 +47,6 @@ extern enum sched_tunable_scaling sysctl_sched_tunable_scaling; extern unsigned int sysctl_numa_balancing_scan_delay; extern unsigned int sysctl_numa_balancing_scan_period_min; extern unsigned int sysctl_numa_balancing_scan_period_max; -extern unsigned int sysctl_numa_balancing_scan_period_reset; extern unsigned int sysctl_numa_balancing_scan_size; extern unsigned int sysctl_numa_balancing_settle_count; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8cfd51f6224..89c5ae836f6 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1721,7 +1721,6 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) #ifdef CONFIG_NUMA_BALANCING if (p->mm && atomic_read(&p->mm->mm_users) == 1) { p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); - p->mm->numa_next_reset = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset); p->mm->numa_scan_seq = 0; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 66237ff8b01..da6fa22be00 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -826,7 +826,6 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) */ unsigned int sysctl_numa_balancing_scan_period_min = 1000; unsigned int sysctl_numa_balancing_scan_period_max = 60000; -unsigned int sysctl_numa_balancing_scan_period_reset = 60000; /* Portion of address space to scan in MB */ unsigned int sysctl_numa_balancing_scan_size = 256; @@ -1685,24 +1684,9 @@ void task_numa_work(struct callback_head *work) if (p->flags & PF_EXITING) return; - if (!mm->numa_next_reset || !mm->numa_next_scan) { + if (!mm->numa_next_scan) { mm->numa_next_scan = now + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); - mm->numa_next_reset = now + - msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset); - } - - /* - * Reset the scan period if enough time has gone by. Objective is that - * scanning will be reduced if pages are properly placed. As tasks - * can enter different phases this needs to be re-examined. Lacking - * proper tracking of reference behaviour, this blunt hammer is used. - */ - migrate = mm->numa_next_reset; - if (time_after(now, migrate)) { - p->numa_scan_period = task_scan_min(p); - next_scan = now + msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset); - xchg(&mm->numa_next_reset, next_scan); } /* diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 42f616a74f4..e509b90a800 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -370,13 +370,6 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "numa_balancing_scan_period_reset", - .data = &sysctl_numa_balancing_scan_period_reset, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { .procname = "numa_balancing_scan_period_max_ms", .data = &sysctl_numa_balancing_scan_period_max, -- cgit v1.2.3-70-g09d2 From de1c9ce6f07fec0381a39a9d0b379ea35aa1167f Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 7 Oct 2013 11:29:39 +0100 Subject: sched/numa: Skip some page migrations after a shared fault Shared faults can lead to lots of unnecessary page migrations, slowing down the system, and causing private faults to hit the per-pgdat migration ratelimit. This patch adds sysctl numa_balancing_migrate_deferred, which specifies how many shared page migrations to skip unconditionally, after each page migration that is skipped because it is a shared fault. This reduces the number of page migrations back and forth in shared fault situations. It also gives a strong preference to the tasks that are already running where most of the memory is, and to moving the other tasks to near the memory. Testing this with a much higher scan rate than the default still seems to result in fewer page migrations than before. Memory seems to be somewhat better consolidated than previously, with multi-instance specjbb runs on a 4 node system. Signed-off-by: Rik van Riel Signed-off-by: Mel Gorman Cc: Andrea Arcangeli Cc: Johannes Weiner Cc: Srikar Dronamraju Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1381141781-10992-62-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar --- Documentation/sysctl/kernel.txt | 10 ++++++++- include/linux/sched.h | 5 ++++- kernel/sched/fair.c | 8 +++++++ kernel/sysctl.c | 7 ++++++ mm/mempolicy.c | 48 ++++++++++++++++++++++++++++++++++++++++- 5 files changed, 75 insertions(+), 3 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 84f17800f8b..4273b2d71a2 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -375,7 +375,8 @@ feature should be disabled. Otherwise, if the system overhead from the feature is too high then the rate the kernel samples for NUMA hinting faults may be controlled by the numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, -numa_balancing_scan_size_mb and numa_balancing_settle_count sysctls. +numa_balancing_scan_size_mb, numa_balancing_settle_count sysctls and +numa_balancing_migrate_deferred. ============================================================== @@ -421,6 +422,13 @@ the schedule balancer stops pushing the task towards a preferred node. This gives the scheduler a chance to place the task on an alternative node if the preferred node is overloaded. +numa_balancing_migrate_deferred is how many page migrations get skipped +unconditionally, after a page migration is skipped because a page is shared +with other tasks. This reduces page migration overhead, and determines +how much stronger the "move task near its memory" policy scheduler becomes, +versus the "move memory near its task" memory management policy, for workloads +with shared memory. + ============================================================== osrelease, ostype & version: diff --git a/include/linux/sched.h b/include/linux/sched.h index d24f70ffdde..833eed55cf4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1342,6 +1342,8 @@ struct task_struct { int numa_scan_seq; unsigned int numa_scan_period; unsigned int numa_scan_period_max; + int numa_preferred_nid; + int numa_migrate_deferred; unsigned long numa_migrate_retry; u64 node_stamp; /* migration stamp */ struct callback_head numa_work; @@ -1372,7 +1374,6 @@ struct task_struct { */ unsigned long numa_faults_locality[2]; - int numa_preferred_nid; unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ @@ -1469,6 +1470,8 @@ extern void task_numa_fault(int last_node, int node, int pages, int flags); extern pid_t task_numa_group_id(struct task_struct *p); extern void set_numabalancing_state(bool enabled); extern void task_numa_free(struct task_struct *p); + +extern unsigned int sysctl_numa_balancing_migrate_deferred; #else static inline void task_numa_fault(int last_node, int node, int pages, int flags) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 8454c38b1b1..e7884dc3416 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -833,6 +833,14 @@ unsigned int sysctl_numa_balancing_scan_size = 256; /* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */ unsigned int sysctl_numa_balancing_scan_delay = 1000; +/* + * After skipping a page migration on a shared page, skip N more numa page + * migrations unconditionally. This reduces the number of NUMA migrations + * in shared memory workloads, and has the effect of pulling tasks towards + * where their memory lives, over pulling the memory towards the task. + */ +unsigned int sysctl_numa_balancing_migrate_deferred = 16; + static unsigned int task_nr_scan_windows(struct task_struct *p) { unsigned long rss = 0; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index e509b90a800..a159e1fd201 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -391,6 +391,13 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "numa_balancing_migrate_deferred", + .data = &sysctl_numa_balancing_migrate_deferred, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_SCHED_DEBUG */ { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 2929c24c22b..71cb253368c 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2301,6 +2301,35 @@ static void sp_free(struct sp_node *n) kmem_cache_free(sn_cache, n); } +#ifdef CONFIG_NUMA_BALANCING +static bool numa_migrate_deferred(struct task_struct *p, int last_cpupid) +{ + /* Never defer a private fault */ + if (cpupid_match_pid(p, last_cpupid)) + return false; + + if (p->numa_migrate_deferred) { + p->numa_migrate_deferred--; + return true; + } + return false; +} + +static inline void defer_numa_migrate(struct task_struct *p) +{ + p->numa_migrate_deferred = sysctl_numa_balancing_migrate_deferred; +} +#else +static inline bool numa_migrate_deferred(struct task_struct *p, int last_cpupid) +{ + return false; +} + +static inline void defer_numa_migrate(struct task_struct *p) +{ +} +#endif /* CONFIG_NUMA_BALANCING */ + /** * mpol_misplaced - check whether current page node is valid in policy * @@ -2402,7 +2431,24 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long * relation. */ last_cpupid = page_cpupid_xchg_last(page, this_cpupid); - if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid) + if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != thisnid) { + + /* See sysctl_numa_balancing_migrate_deferred comment */ + if (!cpupid_match_pid(current, last_cpupid)) + defer_numa_migrate(current); + + goto out; + } + + /* + * The quadratic filter above reduces extraneous migration + * of shared pages somewhat. This code reduces it even more, + * reducing the overhead of page migrations of shared pages. + * This makes workloads with shared pages rely more on + * "move task near its memory", and less on "move memory + * towards its task", which is exactly what we want. + */ + if (numa_migrate_deferred(current, last_cpupid)) goto out; } -- cgit v1.2.3-70-g09d2 From 8eaede49dfdc1ff1d727f9c913665b8009945191 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 7 Oct 2013 01:05:46 +0100 Subject: sysrq: Allow magic SysRq key functions to be disabled through Kconfig Turn the initial value of sysctl kernel.sysrq (SYSRQ_DEFAULT_ENABLE) into a Kconfig variable. Original version by Bastian Blank . Signed-off-by: Ben Hutchings Signed-off-by: Greg Kroah-Hartman --- Documentation/sysrq.txt | 13 ++++++------- drivers/tty/sysrq.c | 2 +- include/linux/sysrq.h | 3 --- kernel/sysctl.c | 2 +- lib/Kconfig.debug | 9 +++++++++ 5 files changed, 17 insertions(+), 12 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt index 1c0471dc70f..0e307c94809 100644 --- a/Documentation/sysrq.txt +++ b/Documentation/sysrq.txt @@ -11,11 +11,9 @@ regardless of whatever else it is doing, unless it is completely locked up. You need to say "yes" to 'Magic SysRq key (CONFIG_MAGIC_SYSRQ)' when configuring the kernel. When running a kernel with SysRq compiled in, /proc/sys/kernel/sysrq controls the functions allowed to be invoked via -the SysRq key. By default the file contains 1 which means that every -possible SysRq request is allowed (in older versions SysRq was disabled -by default, and you were required to specifically enable it at run-time -but this is not the case any more). Here is the list of possible values -in /proc/sys/kernel/sysrq: +the SysRq key. The default value in this file is set by the +CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE config symbol, which itself defaults +to 1. Here is the list of possible values in /proc/sys/kernel/sysrq: 0 - disable sysrq completely 1 - enable all functions of sysrq >1 - bitmask of allowed sysrq functions (see below for detailed function @@ -32,8 +30,9 @@ in /proc/sys/kernel/sysrq: You can set the value in the file by the following command: echo "number" >/proc/sys/kernel/sysrq -The number may be written either as decimal or as hexadecimal with the -0x prefix. +The number may be written here either as decimal or as hexadecimal +with the 0x prefix. CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE must always be +written in hexadecimal. Note that the value of /proc/sys/kernel/sysrq influences only the invocation via a keyboard. Invocation of any operation via /proc/sysrq-trigger is always diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index 40a9fe9d3b1..ce396ecdf41 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -51,7 +51,7 @@ #include /* Whether we react on sysrq keys or just ignore them */ -static int __read_mostly sysrq_enabled = SYSRQ_DEFAULT_ENABLE; +static int __read_mostly sysrq_enabled = CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE; static bool __read_mostly sysrq_always_enabled; unsigned short platform_sysrq_reset_seq[] __weak = { KEY_RESERVED }; diff --git a/include/linux/sysrq.h b/include/linux/sysrq.h index 7faf933cced..387fa7d05c9 100644 --- a/include/linux/sysrq.h +++ b/include/linux/sysrq.h @@ -17,9 +17,6 @@ #include #include -/* Enable/disable SYSRQ support by default (0==no, 1==yes). */ -#define SYSRQ_DEFAULT_ENABLE 1 - /* Possible values of bitmask for enabling sysrq functions */ /* 0x0001 is reserved for enable everything */ #define SYSRQ_ENABLE_LOG 0x0002 diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b2f06f3c6a3..8b80f1bae21 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -190,7 +190,7 @@ static int proc_dostring_coredump(struct ctl_table *table, int write, #ifdef CONFIG_MAGIC_SYSRQ /* Note: sysrq code uses it's own private copy */ -static int __sysrq_enabled = SYSRQ_DEFAULT_ENABLE; +static int __sysrq_enabled = CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE; static int sysrq_sysctl_handler(ctl_table *table, int write, void __user *buffer, size_t *lenp, diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 06344d986eb..29329374ff0 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -312,6 +312,15 @@ config MAGIC_SYSRQ keys are documented in . Don't say Y unless you really know what this hack does. +config MAGIC_SYSRQ_DEFAULT_ENABLE + hex "Enable magic SysRq key functions by default" + depends on MAGIC_SYSRQ + default 0x1 + help + Specifies which SysRq key functions are enabled by default. + This may be set to 1 or 0 to enable or disable them all, or + to a bitmask as described in Documentation/sysrq.txt. + config DEBUG_KERNEL bool "Kernel debugging" help -- cgit v1.2.3-70-g09d2 From 7833819d2e5b2a0189f6e9d445ba03f4d7ba2656 Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Tue, 12 Nov 2013 15:11:21 -0800 Subject: kernel/sysctl.c: check return value after call proc_put_char() in __do_proc_doulongvec_minmax() Need to check the return value of proc_put_char(), as was done in __do_proc_doulongvec_minmax(). Signed-off-by: Chen Gang Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 36547dddcdb..d37d9dd8f46 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2222,8 +2222,11 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int *i = val; } else { val = convdiv * (*i) / convmul; - if (!first) + if (!first) { err = proc_put_char(&buffer, &left, '\t'); + if (err) + break; + } err = proc_put_long(&buffer, &left, val, false); if (err) break; -- cgit v1.2.3-70-g09d2