On Fri, 25 Jul 2014 20:18:18 +0530 Chintan Pandya <cpandya@xxxxxxxxxxxxxx> wrote:
> 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
>
> ...
>
> --- a/Documentation/vm/ksm.txt
> +++ b/Documentation/vm/ksm.txt
> @@ -87,6 +87,13 @@ pages_sharing - how many more sites are sharing them i.e. how much saved
> 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.)
Text indenting is odd.
>
> ...
>
> +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);
Unhandled error.
> + if (enable == 0 || enable == 1)
> + use_deferrable_timer = enable;
> +
> + return count;
Should return -EINVAL if `enable' is invalid.
--- a/Documentation/vm/ksm.txt~ksm-provide-support-to-use-deferrable-timers-for-scanner-thread-fix
+++ a/Documentation/vm/ksm.txt
@@ -88,12 +88,12 @@ pages_unshared - how many pages unique
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.)
+ 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.
--- a/mm/ksm.c~ksm-provide-support-to-use-deferrable-timers-for-scanner-thread-fix
+++ a/mm/ksm.c
@@ -2202,10 +2202,11 @@ static ssize_t deferrable_timer_store(st
int err;
err = kstrtoul(buf, 10, &enable);
-
- if (enable == 0 || enable == 1)
- use_deferrable_timer = enable;
-
+ if (err < 0)
+ return err;
+ if (enable >= 1)
+ return -EINVAL;
+ use_deferrable_timer = enable;
return count;
}
KSM_ATTR(deferrable_timer);
_
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>