The patch titled Subject: ksm: provide support to use deferrable timers for scanner thread has been removed from the -mm tree. Its filename was ksm-provide-support-to-use-deferrable-timers-for-scanner-thread.patch This patch was dropped because an updated version will be merged ------------------------------------------------------ From: Chintan Pandya <cpandya@xxxxxxxxxxxxxx> Subject: ksm: provide support to use deferrable timers for scanner thread KSM thread to scan pages is scheduled on definite timeout. That wakes up CPU from idle state and hence may affect the power consumption. Provide an optional support to use deferrable timer which suites low-power use-cases. Typically, on our setup we observed, 10% less power consumption with some use-cases in which CPU goes to power collapse frequently. For example, playing audio while typically CPU remains idle. To enable deferrable timers, $ echo 1 > /sys/kernel/mm/ksm/deferrable_timer Signed-off-by: Chintan Pandya <cpandya@xxxxxxxxxxxxxx> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx> Cc: John Stultz <john.stultz@xxxxxxxxxx> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> Cc: Ingo Molnar <mingo@xxxxxxxxxx> Cc: Hugh Dickins <hughd@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- Documentation/vm/ksm.txt | 7 ++++++ mm/ksm.c | 40 +++++++++++++++++++++++++++++++++++-- 2 files changed, 45 insertions(+), 2 deletions(-) diff -puN Documentation/vm/ksm.txt~ksm-provide-support-to-use-deferrable-timers-for-scanner-thread Documentation/vm/ksm.txt --- a/Documentation/vm/ksm.txt~ksm-provide-support-to-use-deferrable-timers-for-scanner-thread +++ a/Documentation/vm/ksm.txt @@ -87,6 +87,13 @@ pages_sharing - how many more sites a pages_unshared - how many pages unique but repeatedly checked for merging pages_volatile - how many pages changing too fast to be placed in a tree full_scans - how many times all mergeable areas have been scanned +deferrable_timer - whether to use deferrable timers or not + e.g. "echo 1 > /sys/kernel/mm/ksm/deferrable_timer" + Default: 0 (means, we are not using deferrable timers. Users + might want to set deferrable_timer option if they donot want + ksm thread to wakeup CPU to carryout ksm activities thus + gaining on battery while compromising slightly on memory + that could have been saved.) A high ratio of pages_sharing to pages_shared indicates good sharing, but a high ratio of pages_unshared to pages_sharing indicates wasted effort. diff -puN mm/ksm.c~ksm-provide-support-to-use-deferrable-timers-for-scanner-thread mm/ksm.c --- a/mm/ksm.c~ksm-provide-support-to-use-deferrable-timers-for-scanner-thread +++ a/mm/ksm.c @@ -223,6 +223,9 @@ static unsigned int ksm_thread_pages_to_ /* Milliseconds ksmd should sleep between batches */ static unsigned int ksm_thread_sleep_millisecs = 20; +/* Boolean to indicate whether to use deferrable timer or not */ +static bool use_deferrable_timer; + #ifdef CONFIG_NUMA /* Zeroed when merging across nodes is not allowed */ static unsigned int ksm_merge_across_nodes = 1; @@ -1705,6 +1708,11 @@ static void ksm_do_scan(unsigned int sca } } +static void process_timeout(unsigned long __data) +{ + wake_up_process((struct task_struct *)__data); +} + static int ksmd_should_run(void) { return (ksm_run & KSM_RUN_MERGE) && !list_empty(&ksm_mm_head.mm_list); @@ -1712,6 +1720,8 @@ static int ksmd_should_run(void) static int ksm_scan_thread(void *nothing) { + signed long to; + set_freezable(); set_user_nice(current, 5); @@ -1725,8 +1735,11 @@ static int ksm_scan_thread(void *nothing try_to_freeze(); if (ksmd_should_run()) { - schedule_timeout_interruptible( - msecs_to_jiffies(ksm_thread_sleep_millisecs)); + timeout = msecs_to_jiffies(ksm_thread_sleep_millisecs); + if (use_deferrable_timer) + schedule_timeout_deferrable_interruptible(to); + else + schedule_timeout_interruptible(to); } else { wait_event_freezable(ksm_thread_wait, ksmd_should_run() || kthread_should_stop()); @@ -2175,6 +2188,28 @@ static ssize_t run_store(struct kobject } KSM_ATTR(run); +static ssize_t deferrable_timer_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return snprintf(buf, 8, "%d\n", use_deferrable_timer); +} + +static ssize_t deferrable_timer_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long enable; + int err; + + err = kstrtoul(buf, 10, &enable); + + if (enable == 0 || enable == 1) + use_deferrable_timer = enable; + + return count; +} +KSM_ATTR(deferrable_timer); + #ifdef CONFIG_NUMA static ssize_t merge_across_nodes_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -2287,6 +2322,7 @@ static struct attribute *ksm_attrs[] = { &pages_unshared_attr.attr, &pages_volatile_attr.attr, &full_scans_attr.attr, + &deferrable_timer_attr.attr, #ifdef CONFIG_NUMA &merge_across_nodes_attr.attr, #endif _ Patches currently in -mm which might be from cpandya@xxxxxxxxxxxxxx are origin.patch ksm-provide-support-to-use-deferrable-timers-for-scanner-thread-fix.patch ksm-provide-support-to-use-deferrable-timers-for-scanner-thread-fix-fix-2.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html