From 52bf84aa206cd2c2516dfa3e03b578edf8a3242f Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 27 Jan 2014 17:03:40 -0500 Subject: sched/numa, mm: Remove p->numa_migrate_deferred Excessive migration of pages can hurt the performance of workloads that span multiple NUMA nodes. However, it turns out that the p->numa_migrate_deferred knob is a really big hammer, which does reduce migration rates, but does not actually help performance. Now that the second stage of the automatic numa balancing code has stabilized, it is time to replace the simplistic migration deferral code with something smarter. Signed-off-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Peter Zijlstra Cc: Chegu Vinod Link: http://lkml.kernel.org/r/1390860228-21539-2-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar --- kernel/sysctl.c | 7 ------- 1 file changed, 7 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c8da99f905c..b41d61d95c1 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -384,13 +384,6 @@ 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 */ { -- cgit v1.2.3-70-g09d2 From 89f8b33ca1ea881d1d84542282cb85d07d02e78d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 13 Mar 2014 09:38:42 -0600 Subject: block: remove old blk_iopoll_enabled variable This was a debugging measure to toggle enabled/disabled when testing. But for real production setups, it's not safe to toggle this setting without either reloading drivers of quiescing IO first. Neither of which the toggle enforces. Additionally, it makes drivers deal with the conditional state. Remove it completely. It's up to the driver whether iopoll is enabled or not. Signed-off-by: Jens Axboe --- block/blk-iopoll.c | 3 - drivers/scsi/be2iscsi/be_main.c | 206 ++++++++++++---------------------------- drivers/scsi/ipr.c | 15 +-- include/linux/blk-iopoll.h | 2 - kernel/sysctl.c | 12 --- 5 files changed, 68 insertions(+), 170 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/block/blk-iopoll.c b/block/blk-iopoll.c index 1855bf51edb..c11d24e379e 100644 --- a/block/blk-iopoll.c +++ b/block/blk-iopoll.c @@ -14,9 +14,6 @@ #include "blk.h" -int blk_iopoll_enabled = 1; -EXPORT_SYMBOL(blk_iopoll_enabled); - static unsigned int blk_iopoll_budget __read_mostly = 256; static DEFINE_PER_CPU(struct list_head, blk_cpu_iopoll); diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c index 1f375051483..a929c3c9aed 100644 --- a/drivers/scsi/be2iscsi/be_main.c +++ b/drivers/scsi/be2iscsi/be_main.c @@ -873,7 +873,6 @@ static irqreturn_t be_isr_msix(int irq, void *dev_id) struct be_queue_info *cq; unsigned int num_eq_processed; struct be_eq_obj *pbe_eq; - unsigned long flags; pbe_eq = dev_id; eq = &pbe_eq->q; @@ -882,31 +881,15 @@ static irqreturn_t be_isr_msix(int irq, void *dev_id) phba = pbe_eq->phba; num_eq_processed = 0; - if (blk_iopoll_enabled) { - while (eqe->dw[offsetof(struct amap_eq_entry, valid) / 32] - & EQE_VALID_MASK) { - if (!blk_iopoll_sched_prep(&pbe_eq->iopoll)) - blk_iopoll_sched(&pbe_eq->iopoll); - - AMAP_SET_BITS(struct amap_eq_entry, valid, eqe, 0); - queue_tail_inc(eq); - eqe = queue_tail_node(eq); - num_eq_processed++; - } - } else { - while (eqe->dw[offsetof(struct amap_eq_entry, valid) / 32] - & EQE_VALID_MASK) { - spin_lock_irqsave(&phba->isr_lock, flags); - pbe_eq->todo_cq = true; - spin_unlock_irqrestore(&phba->isr_lock, flags); - AMAP_SET_BITS(struct amap_eq_entry, valid, eqe, 0); - queue_tail_inc(eq); - eqe = queue_tail_node(eq); - num_eq_processed++; - } + while (eqe->dw[offsetof(struct amap_eq_entry, valid) / 32] + & EQE_VALID_MASK) { + if (!blk_iopoll_sched_prep(&pbe_eq->iopoll)) + blk_iopoll_sched(&pbe_eq->iopoll); - if (pbe_eq->todo_cq) - queue_work(phba->wq, &pbe_eq->work_cqs); + AMAP_SET_BITS(struct amap_eq_entry, valid, eqe, 0); + queue_tail_inc(eq); + eqe = queue_tail_node(eq); + num_eq_processed++; } if (num_eq_processed) @@ -927,7 +910,6 @@ static irqreturn_t be_isr(int irq, void *dev_id) struct hwi_context_memory *phwi_context; struct be_eq_entry *eqe = NULL; struct be_queue_info *eq; - struct be_queue_info *cq; struct be_queue_info *mcc; unsigned long flags, index; unsigned int num_mcceq_processed, num_ioeq_processed; @@ -953,72 +935,40 @@ static irqreturn_t be_isr(int irq, void *dev_id) num_ioeq_processed = 0; num_mcceq_processed = 0; - if (blk_iopoll_enabled) { - while (eqe->dw[offsetof(struct amap_eq_entry, valid) / 32] - & EQE_VALID_MASK) { - if (((eqe->dw[offsetof(struct amap_eq_entry, - resource_id) / 32] & - EQE_RESID_MASK) >> 16) == mcc->id) { - spin_lock_irqsave(&phba->isr_lock, flags); - pbe_eq->todo_mcc_cq = true; - spin_unlock_irqrestore(&phba->isr_lock, flags); - num_mcceq_processed++; - } else { - if (!blk_iopoll_sched_prep(&pbe_eq->iopoll)) - blk_iopoll_sched(&pbe_eq->iopoll); - num_ioeq_processed++; - } - AMAP_SET_BITS(struct amap_eq_entry, valid, eqe, 0); - queue_tail_inc(eq); - eqe = queue_tail_node(eq); - } - if (num_ioeq_processed || num_mcceq_processed) { - if (pbe_eq->todo_mcc_cq) - queue_work(phba->wq, &pbe_eq->work_cqs); - - if ((num_mcceq_processed) && (!num_ioeq_processed)) - hwi_ring_eq_db(phba, eq->id, 0, - (num_ioeq_processed + - num_mcceq_processed) , 1, 1); - else - hwi_ring_eq_db(phba, eq->id, 0, - (num_ioeq_processed + - num_mcceq_processed), 0, 1); - - return IRQ_HANDLED; - } else - return IRQ_NONE; - } else { - cq = &phwi_context->be_cq[0]; - while (eqe->dw[offsetof(struct amap_eq_entry, valid) / 32] - & EQE_VALID_MASK) { - - if (((eqe->dw[offsetof(struct amap_eq_entry, - resource_id) / 32] & - EQE_RESID_MASK) >> 16) != cq->id) { - spin_lock_irqsave(&phba->isr_lock, flags); - pbe_eq->todo_mcc_cq = true; - spin_unlock_irqrestore(&phba->isr_lock, flags); - } else { - spin_lock_irqsave(&phba->isr_lock, flags); - pbe_eq->todo_cq = true; - spin_unlock_irqrestore(&phba->isr_lock, flags); - } - AMAP_SET_BITS(struct amap_eq_entry, valid, eqe, 0); - queue_tail_inc(eq); - eqe = queue_tail_node(eq); + while (eqe->dw[offsetof(struct amap_eq_entry, valid) / 32] + & EQE_VALID_MASK) { + if (((eqe->dw[offsetof(struct amap_eq_entry, + resource_id) / 32] & + EQE_RESID_MASK) >> 16) == mcc->id) { + spin_lock_irqsave(&phba->isr_lock, flags); + pbe_eq->todo_mcc_cq = true; + spin_unlock_irqrestore(&phba->isr_lock, flags); + num_mcceq_processed++; + } else { + if (!blk_iopoll_sched_prep(&pbe_eq->iopoll)) + blk_iopoll_sched(&pbe_eq->iopoll); num_ioeq_processed++; } - if (pbe_eq->todo_cq || pbe_eq->todo_mcc_cq) + AMAP_SET_BITS(struct amap_eq_entry, valid, eqe, 0); + queue_tail_inc(eq); + eqe = queue_tail_node(eq); + } + if (num_ioeq_processed || num_mcceq_processed) { + if (pbe_eq->todo_mcc_cq) queue_work(phba->wq, &pbe_eq->work_cqs); - if (num_ioeq_processed) { + if ((num_mcceq_processed) && (!num_ioeq_processed)) hwi_ring_eq_db(phba, eq->id, 0, - num_ioeq_processed, 1, 1); - return IRQ_HANDLED; - } else - return IRQ_NONE; - } + (num_ioeq_processed + + num_mcceq_processed) , 1, 1); + else + hwi_ring_eq_db(phba, eq->id, 0, + (num_ioeq_processed + + num_mcceq_processed), 0, 1); + + return IRQ_HANDLED; + } else + return IRQ_NONE; } static int beiscsi_init_irqs(struct beiscsi_hba *phba) @@ -5216,11 +5166,10 @@ static void beiscsi_quiesce(struct beiscsi_hba *phba, } pci_disable_msix(phba->pcidev); - if (blk_iopoll_enabled) - for (i = 0; i < phba->num_cpus; i++) { - pbe_eq = &phwi_context->be_eq[i]; - blk_iopoll_disable(&pbe_eq->iopoll); - } + for (i = 0; i < phba->num_cpus; i++) { + pbe_eq = &phwi_context->be_eq[i]; + blk_iopoll_disable(&pbe_eq->iopoll); + } if (unload_state == BEISCSI_CLEAN_UNLOAD) { destroy_workqueue(phba->wq); @@ -5429,32 +5378,18 @@ static void beiscsi_eeh_resume(struct pci_dev *pdev) phwi_ctrlr = phba->phwi_ctrlr; phwi_context = phwi_ctrlr->phwi_ctxt; - if (blk_iopoll_enabled) { - for (i = 0; i < phba->num_cpus; i++) { - pbe_eq = &phwi_context->be_eq[i]; - blk_iopoll_init(&pbe_eq->iopoll, be_iopoll_budget, - be_iopoll); - blk_iopoll_enable(&pbe_eq->iopoll); - } - - i = (phba->msix_enabled) ? i : 0; - /* Work item for MCC handling */ + for (i = 0; i < phba->num_cpus; i++) { pbe_eq = &phwi_context->be_eq[i]; - INIT_WORK(&pbe_eq->work_cqs, beiscsi_process_all_cqs); - } else { - if (phba->msix_enabled) { - for (i = 0; i <= phba->num_cpus; i++) { - pbe_eq = &phwi_context->be_eq[i]; - INIT_WORK(&pbe_eq->work_cqs, - beiscsi_process_all_cqs); - } - } else { - pbe_eq = &phwi_context->be_eq[0]; - INIT_WORK(&pbe_eq->work_cqs, - beiscsi_process_all_cqs); - } + blk_iopoll_init(&pbe_eq->iopoll, be_iopoll_budget, + be_iopoll); + blk_iopoll_enable(&pbe_eq->iopoll); } + i = (phba->msix_enabled) ? i : 0; + /* Work item for MCC handling */ + pbe_eq = &phwi_context->be_eq[i]; + INIT_WORK(&pbe_eq->work_cqs, beiscsi_process_all_cqs); + ret = beiscsi_init_irqs(phba); if (ret < 0) { beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT, @@ -5614,32 +5549,18 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev, phwi_ctrlr = phba->phwi_ctrlr; phwi_context = phwi_ctrlr->phwi_ctxt; - if (blk_iopoll_enabled) { - for (i = 0; i < phba->num_cpus; i++) { - pbe_eq = &phwi_context->be_eq[i]; - blk_iopoll_init(&pbe_eq->iopoll, be_iopoll_budget, - be_iopoll); - blk_iopoll_enable(&pbe_eq->iopoll); - } - - i = (phba->msix_enabled) ? i : 0; - /* Work item for MCC handling */ + for (i = 0; i < phba->num_cpus; i++) { pbe_eq = &phwi_context->be_eq[i]; - INIT_WORK(&pbe_eq->work_cqs, beiscsi_process_all_cqs); - } else { - if (phba->msix_enabled) { - for (i = 0; i <= phba->num_cpus; i++) { - pbe_eq = &phwi_context->be_eq[i]; - INIT_WORK(&pbe_eq->work_cqs, - beiscsi_process_all_cqs); - } - } else { - pbe_eq = &phwi_context->be_eq[0]; - INIT_WORK(&pbe_eq->work_cqs, - beiscsi_process_all_cqs); - } + blk_iopoll_init(&pbe_eq->iopoll, be_iopoll_budget, + be_iopoll); + blk_iopoll_enable(&pbe_eq->iopoll); } + i = (phba->msix_enabled) ? i : 0; + /* Work item for MCC handling */ + pbe_eq = &phwi_context->be_eq[i]; + INIT_WORK(&pbe_eq->work_cqs, beiscsi_process_all_cqs); + ret = beiscsi_init_irqs(phba); if (ret < 0) { beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT, @@ -5668,11 +5589,10 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev, free_blkenbld: destroy_workqueue(phba->wq); - if (blk_iopoll_enabled) - for (i = 0; i < phba->num_cpus; i++) { - pbe_eq = &phwi_context->be_eq[i]; - blk_iopoll_disable(&pbe_eq->iopoll); - } + for (i = 0; i < phba->num_cpus; i++) { + pbe_eq = &phwi_context->be_eq[i]; + blk_iopoll_disable(&pbe_eq->iopoll); + } free_twq: beiscsi_clean_port(phba); beiscsi_free_mem(phba); diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 3f5b56a9989..69470f5c0ac 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -3630,16 +3630,14 @@ static ssize_t ipr_store_iopoll_weight(struct device *dev, return strlen(buf); } - if (blk_iopoll_enabled && ioa_cfg->iopoll_weight && - ioa_cfg->sis64 && ioa_cfg->nvectors > 1) { + if (ioa_cfg->iopoll_weight && ioa_cfg->sis64 && ioa_cfg->nvectors > 1) { for (i = 1; i < ioa_cfg->hrrq_num; i++) blk_iopoll_disable(&ioa_cfg->hrrq[i].iopoll); } spin_lock_irqsave(shost->host_lock, lock_flags); ioa_cfg->iopoll_weight = user_iopoll_weight; - if (blk_iopoll_enabled && ioa_cfg->iopoll_weight && - ioa_cfg->sis64 && ioa_cfg->nvectors > 1) { + if (ioa_cfg->iopoll_weight && ioa_cfg->sis64 && ioa_cfg->nvectors > 1) { for (i = 1; i < ioa_cfg->hrrq_num; i++) { blk_iopoll_init(&ioa_cfg->hrrq[i].iopoll, ioa_cfg->iopoll_weight, ipr_iopoll); @@ -5484,8 +5482,7 @@ static irqreturn_t ipr_isr_mhrrq(int irq, void *devp) return IRQ_NONE; } - if (blk_iopoll_enabled && ioa_cfg->iopoll_weight && - ioa_cfg->sis64 && ioa_cfg->nvectors > 1) { + if (ioa_cfg->iopoll_weight && ioa_cfg->sis64 && ioa_cfg->nvectors > 1) { if ((be32_to_cpu(*hrrq->hrrq_curr) & IPR_HRRQ_TOGGLE_BIT) == hrrq->toggle_bit) { if (!blk_iopoll_sched_prep(&hrrq->iopoll)) @@ -9859,8 +9856,7 @@ static int ipr_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id) ioa_cfg->host->max_channel = IPR_VSET_BUS; ioa_cfg->iopoll_weight = ioa_cfg->chip_cfg->iopoll_weight; - if (blk_iopoll_enabled && ioa_cfg->iopoll_weight && - ioa_cfg->sis64 && ioa_cfg->nvectors > 1) { + if (ioa_cfg->iopoll_weight && ioa_cfg->sis64 && ioa_cfg->nvectors > 1) { for (i = 1; i < ioa_cfg->hrrq_num; i++) { blk_iopoll_init(&ioa_cfg->hrrq[i].iopoll, ioa_cfg->iopoll_weight, ipr_iopoll); @@ -9889,8 +9885,7 @@ static void ipr_shutdown(struct pci_dev *pdev) int i; spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); - if (blk_iopoll_enabled && ioa_cfg->iopoll_weight && - ioa_cfg->sis64 && ioa_cfg->nvectors > 1) { + if (ioa_cfg->iopoll_weight && ioa_cfg->sis64 && ioa_cfg->nvectors > 1) { ioa_cfg->iopoll_weight = 0; for (i = 1; i < ioa_cfg->hrrq_num; i++) blk_iopoll_disable(&ioa_cfg->hrrq[i].iopoll); diff --git a/include/linux/blk-iopoll.h b/include/linux/blk-iopoll.h index 308734d3d4a..77ae77c0b70 100644 --- a/include/linux/blk-iopoll.h +++ b/include/linux/blk-iopoll.h @@ -43,6 +43,4 @@ extern void __blk_iopoll_complete(struct blk_iopoll *); extern void blk_iopoll_enable(struct blk_iopoll *); extern void blk_iopoll_disable(struct blk_iopoll *); -extern int blk_iopoll_enabled; - #endif diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 49e13e1f8fe..ef0bf04e864 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -112,9 +112,6 @@ extern int sysctl_nr_open_min, sysctl_nr_open_max; #ifndef CONFIG_MMU extern int sysctl_nr_trim_pages; #endif -#ifdef CONFIG_BLOCK -extern int blk_iopoll_enabled; -#endif /* Constants used for minimum and maximum */ #ifdef CONFIG_LOCKUP_DETECTOR @@ -1093,15 +1090,6 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, -#endif -#ifdef CONFIG_BLOCK - { - .procname = "blk_iopoll", - .data = &blk_iopoll_enabled, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, #endif { } }; -- cgit v1.2.3-70-g09d2 From 5509a5d27b971a90b940e148ca9ca53312e4fa7a Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Thu, 3 Apr 2014 14:48:19 -0700 Subject: drop_caches: add some documentation and info message There is plenty of anecdotal evidence and a load of blog posts suggesting that using "drop_caches" periodically keeps your system running in "tip top shape". Perhaps adding some kernel documentation will increase the amount of accurate data on its use. If we are not shrinking caches effectively, then we have real bugs. Using drop_caches will simply mask the bugs and make them harder to find, but certainly does not fix them, nor is it an appropriate "workaround" to limit the size of the caches. On the contrary, there have been bug reports on issues that turned out to be misguided use of cache dropping. Dropping caches is a very drastic and disruptive operation that is good for debugging and running tests, but if it creates bug reports from production use, kernel developers should be aware of its use. Add a bit more documentation about it, a syslog message to track down abusers, and vmstat drop counters to help analyze problem reports. [akpm@linux-foundation.org: checkpatch fixes] [hannes@cmpxchg.org: add runtime suppression control] Signed-off-by: Dave Hansen Signed-off-by: Michal Hocko Acked-by: KOSAKI Motohiro Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 33 +++++++++++++++++++++++++++------ fs/drop_caches.c | 16 ++++++++++++++-- include/linux/vm_event_item.h | 1 + kernel/sysctl.c | 4 ++-- mm/vmstat.c | 3 +++ 5 files changed, 47 insertions(+), 10 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index d614a9b6a28..dd9d0e33b44 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -175,18 +175,39 @@ Setting this to zero disables periodic writeback altogether. drop_caches -Writing to this will cause the kernel to drop clean caches, dentries and -inodes from memory, causing that memory to become free. +Writing to this will cause the kernel to drop clean caches, as well as +reclaimable slab objects like dentries and inodes. Once dropped, their +memory becomes free. To free pagecache: echo 1 > /proc/sys/vm/drop_caches -To free dentries and inodes: +To free reclaimable slab objects (includes dentries and inodes): echo 2 > /proc/sys/vm/drop_caches -To free pagecache, dentries and inodes: +To free slab objects and pagecache: echo 3 > /proc/sys/vm/drop_caches -As this is a non-destructive operation and dirty objects are not freeable, the -user should run `sync' first. +This is a non-destructive operation and will not free any dirty objects. +To increase the number of objects freed by this operation, the user may run +`sync' prior to writing to /proc/sys/vm/drop_caches. This will minimize the +number of dirty objects on the system and create more candidates to be +dropped. + +This file is not a means to control the growth of the various kernel caches +(inodes, dentries, pagecache, etc...) These objects are automatically +reclaimed by the kernel when memory is needed elsewhere on the system. + +Use of this file can cause performance problems. Since it discards cached +objects, it may cost a significant amount of I/O and CPU to recreate the +dropped objects, especially if they were under heavy use. Because of this, +use outside of a testing or debugging environment is not recommended. + +You may see informational messages in your kernel log when this file is +used: + + cat (1234): drop_caches: 3 + +These are informational only. They do not mean that anything is wrong +with your system. To disable them, echo 4 (bit 3) into drop_caches. ============================================================== diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 9fd702f5bfb..9280202e488 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -59,10 +59,22 @@ int drop_caches_sysctl_handler(ctl_table *table, int write, if (ret) return ret; if (write) { - if (sysctl_drop_caches & 1) + static int stfu; + + if (sysctl_drop_caches & 1) { iterate_supers(drop_pagecache_sb, NULL); - if (sysctl_drop_caches & 2) + count_vm_event(DROP_PAGECACHE); + } + if (sysctl_drop_caches & 2) { drop_slab(); + count_vm_event(DROP_SLAB); + } + if (!stfu) { + pr_info("%s (%d): drop_caches: %d\n", + current->comm, task_pid_nr(current), + sysctl_drop_caches); + } + stfu |= sysctl_drop_caches & 4; } return 0; } diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 3a712e2e7d7..486c3972c0b 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -37,6 +37,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL, KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY, PAGEOUTRUN, ALLOCSTALL, PGROTATED, + DROP_PAGECACHE, DROP_SLAB, #ifdef CONFIG_NUMA_BALANCING NUMA_PTE_UPDATES, NUMA_HUGE_PTE_UPDATES, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 09d2e241360..5c14b547882 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -123,7 +123,7 @@ static int __maybe_unused neg_one = -1; static int zero; static int __maybe_unused one = 1; static int __maybe_unused two = 2; -static int __maybe_unused three = 3; +static int __maybe_unused four = 4; static unsigned long one_ul = 1; static int one_hundred = 100; #ifdef CONFIG_PRINTK @@ -1264,7 +1264,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = drop_caches_sysctl_handler, .extra1 = &one, - .extra2 = &three, + .extra2 = &four, }, #ifdef CONFIG_COMPACTION { diff --git a/mm/vmstat.c b/mm/vmstat.c index f3155d51acf..197b4c4a958 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -813,6 +813,9 @@ const char * const vmstat_text[] = { "pgrotated", + "drop_pagecache", + "drop_slab", + #ifdef CONFIG_NUMA_BALANCING "numa_pte_updates", "numa_huge_pte_updates", -- cgit v1.2.3-70-g09d2 From 80df28476505ed4e6701c3448c63c9229a50c655 Mon Sep 17 00:00:00 2001 From: Liu Hua Date: Mon, 7 Apr 2014 15:38:57 -0700 Subject: hung_task: check the value of "sysctl_hung_task_timeout_sec" As sysctl_hung_task_timeout_sec is unsigned long, when this value is larger then LONG_MAX/HZ, the function schedule_timeout_interruptible in watchdog will return immediately without sleep and with print : schedule_timeout: wrong timeout value ffffffffffffff83 and then the funtion watchdog will call schedule_timeout_interruptible again and again. The screen will be filled with "schedule_timeout: wrong timeout value ffffffffffffff83" This patch does some check and correction in sysctl, to let the function schedule_timeout_interruptible allways get the valid parameter. Signed-off-by: Liu Hua Tested-by: Satoru Takeuchi Cc: [3.4+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/kernel.txt | 1 + kernel/sysctl.c | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'kernel/sysctl.c') diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 271a09db662..9886c3d57fc 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -317,6 +317,7 @@ for more than this value report a warning. This file shows up if CONFIG_DETECT_HUNG_TASK is enabled. 0: means infinite timeout - no checking done. +Possible values to set are in range {0..LONG_MAX/HZ}. ============================================================== diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 5c14b547882..74f5b580fe3 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -141,6 +141,11 @@ static int min_percpu_pagelist_fract = 8; static int ngroups_max = NGROUPS_MAX; static const int cap_last_cap = CAP_LAST_CAP; +/*this is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs */ +#ifdef CONFIG_DETECT_HUNG_TASK +static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); +#endif + #ifdef CONFIG_INOTIFY_USER #include #endif @@ -985,6 +990,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_dohung_task_timeout_secs, + .extra2 = &hung_task_timeout_max, }, { .procname = "hung_task_warnings", -- cgit v1.2.3-70-g09d2