From df858fa8276f85106f2f5c3cd49c1fa524058070 Mon Sep 17 00:00:00 2001 From: Christian Ehrhardt Date: Tue, 31 Jul 2012 16:41:46 -0700 Subject: documentation: update how page-cluster affects swap I/O Fix of the documentation of /proc/sys/vm/page-cluster to match the behavior of the code and add some comments about what the tunable will change in that behavior. Signed-off-by: Christian Ehrhardt Acked-by: Jens Axboe Reviewed-by: Minchan Kim Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'Documentation/sysctl/vm.txt') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 96f0ee825bed..84eb25cd69aa 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -574,16 +574,24 @@ of physical RAM. See above. page-cluster -page-cluster controls the number of pages which are written to swap in -a single attempt. The swap I/O size. +page-cluster controls the number of pages up to which consecutive pages +are read in from swap in a single attempt. This is the swap counterpart +to page cache readahead. +The mentioned consecutivity is not in terms of virtual/physical addresses, +but consecutive on swap space - that means they were swapped out together. It is a logarithmic value - setting it to zero means "1 page", setting it to 1 means "2 pages", setting it to 2 means "4 pages", etc. +Zero disables swap readahead completely. The default value is three (eight pages at a time). There may be some small benefits in tuning this to a different value if your workload is swap-intensive. +Lower values mean lower latencies for initial faults, but at the same time +extra faults and I/O delays for following faults if they would have been part of +that consecutive pages readahead would have brought in. + ============================================================= panic_on_oom -- cgit v1.2.3 From 3965c9ae47d64aadf6f13b6fcd37767b83c0689a Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Tue, 31 Jul 2012 16:41:52 -0700 Subject: mm: prepare for removal of obsolete /proc/sys/vm/nr_pdflush_threads Since per-BDI flusher threads were introduced in 2.6, the pdflush mechanism is not used any more. But the old interface exported through /proc/sys/vm/nr_pdflush_threads still exists and is obviously useless. For back-compatibility, printk warning information and return 2 to notify the users that the interface is removed. Signed-off-by: Wanpeng Li Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .../ABI/obsolete/proc-sys-vm-nr_pdflush_threads | 5 +++++ Documentation/feature-removal-schedule.txt | 8 ++++++++ Documentation/sysctl/vm.txt | 11 ----------- fs/fs-writeback.c | 5 ----- include/linux/backing-dev.h | 3 +++ include/linux/writeback.h | 5 ----- kernel/sysctl.c | 8 +++----- kernel/sysctl_binary.c | 2 +- mm/backing-dev.c | 20 ++++++++++++++++++++ 9 files changed, 40 insertions(+), 27 deletions(-) create mode 100644 Documentation/ABI/obsolete/proc-sys-vm-nr_pdflush_threads (limited to 'Documentation/sysctl/vm.txt') diff --git a/Documentation/ABI/obsolete/proc-sys-vm-nr_pdflush_threads b/Documentation/ABI/obsolete/proc-sys-vm-nr_pdflush_threads new file mode 100644 index 000000000000..b0b0eeb20fe3 --- /dev/null +++ b/Documentation/ABI/obsolete/proc-sys-vm-nr_pdflush_threads @@ -0,0 +1,5 @@ +What: /proc/sys/vm/nr_pdflush_threads +Date: June 2012 +Contact: Wanpeng Li +Description: Since pdflush is replaced by per-BDI flusher, the interface of old pdflush + exported in /proc/sys/vm/ should be removed. diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index e9237fb71950..88f2fa48bb63 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -13,6 +13,14 @@ Who: Jim Cromie , Jason Baron --------------------------- +What: /proc/sys/vm/nr_pdflush_threads +When: 2012 +Why: Since pdflush is deprecated, the interface exported in /proc/sys/vm/ + should be removed. +Who: Wanpeng Li + +--------------------------- + What: CONFIG_APM_CPU_IDLE, and its ability to call APM BIOS in idle When: 2012 Why: This optional sub-feature of APM is of dubious reliability, diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 84eb25cd69aa..06d662b1c5d5 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -42,7 +42,6 @@ Currently, these files are in /proc/sys/vm: - mmap_min_addr - nr_hugepages - nr_overcommit_hugepages -- nr_pdflush_threads - nr_trim_pages (only if CONFIG_MMU=n) - numa_zonelist_order - oom_dump_tasks @@ -426,16 +425,6 @@ See Documentation/vm/hugetlbpage.txt ============================================================== -nr_pdflush_threads - -The current number of pdflush threads. This value is read-only. -The value changes according to the number of dirty pages in the system. - -When necessary, additional pdflush threads are created, one per second, up to -nr_pdflush_threads_max. - -============================================================== - nr_trim_pages This is available only on NOMMU kernels. diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 50d0b78130a1..be3efc4f64f4 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -52,11 +52,6 @@ struct wb_writeback_work { struct completion *done; /* set if the caller waits */ }; -/* - * We don't actually have pdflush, but this one is exported though /proc... - */ -int nr_pdflush_threads; - /** * writeback_in_progress - determine whether there is writeback in progress * @bdi: the device's backing_dev_info structure. diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 489de625cd25..c97c6b9cd38e 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -17,6 +17,7 @@ #include #include #include +#include struct page; struct device; @@ -304,6 +305,8 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int sync); void set_bdi_congested(struct backing_dev_info *bdi, int sync); long congestion_wait(int sync, long timeout); long wait_iff_congested(struct zone *zone, int sync, long timeout); +int pdflush_proc_obsolete(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi) { diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 6d0a0fcd80e7..c66fe3332d83 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -189,9 +189,4 @@ void tag_pages_for_writeback(struct address_space *mapping, void account_page_redirty(struct page *page); -/* pdflush.c */ -extern int nr_pdflush_threads; /* Global so it can be exported to sysctl - read-only. */ - - #endif /* WRITEBACK_H */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 97186b99b0e4..6502d35a25ba 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1101,11 +1101,9 @@ static struct ctl_table vm_table[] = { .extra1 = &zero, }, { - .procname = "nr_pdflush_threads", - .data = &nr_pdflush_threads, - .maxlen = sizeof nr_pdflush_threads, - .mode = 0444 /* read-only*/, - .proc_handler = proc_dointvec, + .procname = "nr_pdflush_threads", + .mode = 0444 /* read-only */, + .proc_handler = pdflush_proc_obsolete, }, { .procname = "swappiness", diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index a650694883a1..65bdcf198d4e 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -147,7 +147,7 @@ static const struct bin_table bin_vm_table[] = { { CTL_INT, VM_DIRTY_RATIO, "dirty_ratio" }, /* VM_DIRTY_WB_CS "dirty_writeback_centisecs" no longer used */ /* VM_DIRTY_EXPIRE_CS "dirty_expire_centisecs" no longer used */ - { CTL_INT, VM_NR_PDFLUSH_THREADS, "nr_pdflush_threads" }, + /* VM_NR_PDFLUSH_THREADS "nr_pdflush_threads" no longer used */ { CTL_INT, VM_OVERCOMMIT_RATIO, "overcommit_ratio" }, /* VM_PAGEBUF unused */ /* VM_HUGETLB_PAGES "nr_hugepages" no longer used */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 3387aea11209..6b4718e2ee34 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -886,3 +886,23 @@ out: return ret; } EXPORT_SYMBOL(wait_iff_congested); + +int pdflush_proc_obsolete(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + char kbuf[] = "0\n"; + + if (*ppos) { + *lenp = 0; + return 0; + } + + if (copy_to_user(buffer, kbuf, sizeof(kbuf))) + return -EFAULT; + printk_once(KERN_WARNING "%s exported in /proc is scheduled for removal\n", + table->procname); + + *lenp = 2; + *ppos += *lenp; + return 2; +} -- cgit v1.2.3 From de34d965a80d0f61a354bdefa0b15a88bcff2028 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 31 Jul 2012 16:42:56 -0700 Subject: mm, oom: replace some information in tasklist dump The number of ptes and swap entries are used in the oom killer's badness heuristic, so they should be shown in the tasklist dump. This patch adds those fields and replaces cpu and oom_adj values that are currently emitted. Cpu isn't interesting and oom_adj is deprecated and will be removed later this year, the same information is already displayed as oom_score_adj which is used internally. At the same time, make the documentation a little more clear to state this information is helpful to determine why the oom killer chose the task it did to kill. Signed-off-by: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 7 ++++--- mm/oom_kill.c | 11 ++++++----- 2 files changed, 10 insertions(+), 8 deletions(-) (limited to 'Documentation/sysctl/vm.txt') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 06d662b1c5d5..dcc2a94ae34e 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -491,9 +491,10 @@ oom_dump_tasks Enables a system-wide task dump (excluding kernel threads) to be produced when the kernel performs an OOM-killing and includes such -information as pid, uid, tgid, vm size, rss, cpu, oom_adj score, and -name. This is helpful to determine why the OOM killer was invoked -and to identify the rogue task that caused it. +information as pid, uid, tgid, vm size, rss, nr_ptes, swapents, +oom_score_adj score, and name. This is helpful to determine why the +OOM killer was invoked, to identify the rogue task that caused it, +and to determine why the OOM killer chose the task it did to kill. If this is set to zero, this information is suppressed. On very large systems with thousands of tasks it may not be feasible to dump diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 50e74373e855..c82ede69bf3f 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -371,8 +371,8 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, * Dumps the current memory state of all eligible tasks. Tasks not in the same * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes * are not shown. - * State information includes task's pid, uid, tgid, vm size, rss, cpu, oom_adj - * value, oom_score_adj value, and name. + * State information includes task's pid, uid, tgid, vm size, rss, nr_ptes, + * swapents, oom_score_adj value, and name. * * Call with tasklist_lock read-locked. */ @@ -381,7 +381,7 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas struct task_struct *p; struct task_struct *task; - pr_info("[ pid ] uid tgid total_vm rss cpu oom_adj oom_score_adj name\n"); + pr_info("[ pid ] uid tgid total_vm rss nr_ptes swapents oom_score_adj name\n"); for_each_process(p) { if (oom_unkillable_task(p, memcg, nodemask)) continue; @@ -396,10 +396,11 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas continue; } - pr_info("[%5d] %5d %5d %8lu %8lu %3u %3d %5d %s\n", + pr_info("[%5d] %5d %5d %8lu %8lu %7lu %8lu %5d %s\n", task->pid, from_kuid(&init_user_ns, task_uid(task)), task->tgid, task->mm->total_vm, get_mm_rss(task->mm), - task_cpu(task), task->signal->oom_adj, + task->mm->nr_ptes, + get_mm_counter(task->mm, MM_SWAPENTS), task->signal->oom_score_adj, task->comm); task_unlock(task); } -- cgit v1.2.3