summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorjohn stultz <johnstul@us.ibm.com>2009-10-02 16:17:53 -0700
committerIngo Molnar <mingo@elte.hu>2009-10-05 13:51:48 +0200
commita092ff0f90cae22b2ac8028ecd2c6f6c1a9e4601 (patch)
tree79ec451d0bcdf6c08e0bc210b4beed694fbbf4a9
parent8a0382f6fceaf0c6479e582e1054f36333ea3d24 (diff)
time: Implement logarithmic time accumulation
Accumulating one tick at a time works well unless we're using NOHZ. Then it can be an issue, since we may have to run through the loop a few thousand times, which can increase timer interrupt caused latency. The current solution was to accumulate in half-second intervals with NOHZ. This kept the number of loops down, however it did slightly change how we make NTP adjustments. While not an issue with NTPd users, as NTPd makes adjustments over a longer period of time, other adjtimex() users have noticed the half-second granularity with which we can apply frequency changes to the clock. For instance, if a application tries to apply a 100ppm frequency correction for 20ms to correct a 2us offset, with NOHZ they either get no correction, or a 50us correction. Now, there will always be some granularity error for applying frequency corrections. However with users sensitive to this error have seen a 50-500x increase with NOHZ compared to running without NOHZ. So I figured I'd try another approach then just simply increasing the interval. My approach is to consume the time interval logarithmically. This reduces the number of times through the loop needed keeping latency down, while still preserving the original granularity error for adjtimex() changes. Further, this change allows us to remove the xtime_cache code (patch to follow), as xtime is always within one tick of the current time, instead of the half-second updates it saw before. An earlier version of this patch has been shipping to x86 users in the RedHat MRG releases for awhile without issue, but I've reworked this version to be even more careful about avoiding possible overflows if the shift value gets too large. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1254525473.7741.88.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
-rw-r--r--include/linux/timex.h4
-rw-r--r--kernel/time/timekeeping.c85
2 files changed, 60 insertions, 29 deletions
diff --git a/include/linux/timex.h b/include/linux/timex.h
index e6967d10d9e5..0c0ef7d4db7c 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -261,11 +261,7 @@ static inline int ntp_synced(void)
#define NTP_SCALE_SHIFT 32
-#ifdef CONFIG_NO_HZ
-#define NTP_INTERVAL_FREQ (2)
-#else
#define NTP_INTERVAL_FREQ (HZ)
-#endif
#define NTP_INTERVAL_LENGTH (NSEC_PER_SEC/NTP_INTERVAL_FREQ)
/* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index fb0f46fa1ecd..5fdd78e0858a 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -721,6 +721,51 @@ static void timekeeping_adjust(s64 offset)
timekeeper.ntp_error_shift;
}
+
+/**
+ * logarithmic_accumulation - shifted accumulation of cycles
+ *
+ * This functions accumulates a shifted interval of cycles into
+ * into a shifted interval nanoseconds. Allows for O(log) accumulation
+ * loop.
+ *
+ * Returns the unconsumed cycles.
+ */
+static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
+{
+ u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
+
+ /* If the offset is smaller then a shifted interval, do nothing */
+ if (offset < timekeeper.cycle_interval<<shift)
+ return offset;
+
+ /* Accumulate one shifted interval */
+ offset -= timekeeper.cycle_interval << shift;
+ timekeeper.clock->cycle_last += timekeeper.cycle_interval << shift;
+
+ timekeeper.xtime_nsec += timekeeper.xtime_interval << shift;
+ while (timekeeper.xtime_nsec >= nsecps) {
+ timekeeper.xtime_nsec -= nsecps;
+ xtime.tv_sec++;
+ second_overflow();
+ }
+
+ /* Accumulate into raw time */
+ raw_time.tv_nsec += timekeeper.raw_interval << shift;;
+ while (raw_time.tv_nsec >= NSEC_PER_SEC) {
+ raw_time.tv_nsec -= NSEC_PER_SEC;
+ raw_time.tv_sec++;
+ }
+
+ /* Accumulate error between NTP and clock interval */
+ timekeeper.ntp_error += tick_length << shift;
+ timekeeper.ntp_error -= timekeeper.xtime_interval <<
+ (timekeeper.ntp_error_shift + shift);
+
+ return offset;
+}
+
+
/**
* update_wall_time - Uses the current clocksource to increment the wall time
*
@@ -731,6 +776,7 @@ void update_wall_time(void)
struct clocksource *clock;
cycle_t offset;
u64 nsecs;
+ int shift = 0, maxshift;
/* Make sure we're fully resumed: */
if (unlikely(timekeeping_suspended))
@@ -744,33 +790,22 @@ void update_wall_time(void)
#endif
timekeeper.xtime_nsec = (s64)xtime.tv_nsec << timekeeper.shift;
- /* normally this loop will run just once, however in the
- * case of lost or late ticks, it will accumulate correctly.
+ /*
+ * With NO_HZ we may have to accumulate many cycle_intervals
+ * (think "ticks") worth of time at once. To do this efficiently,
+ * we calculate the largest doubling multiple of cycle_intervals
+ * that is smaller then the offset. We then accumulate that
+ * chunk in one go, and then try to consume the next smaller
+ * doubled multiple.
*/
+ shift = ilog2(offset) - ilog2(timekeeper.cycle_interval);
+ shift = max(0, shift);
+ /* Bound shift to one less then what overflows tick_length */
+ maxshift = (8*sizeof(tick_length) - (ilog2(tick_length)+1)) - 1;
+ shift = min(shift, maxshift);
while (offset >= timekeeper.cycle_interval) {
- u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift;
-
- /* accumulate one interval */
- offset -= timekeeper.cycle_interval;
- clock->cycle_last += timekeeper.cycle_interval;
-
- timekeeper.xtime_nsec += timekeeper.xtime_interval;
- if (timekeeper.xtime_nsec >= nsecps) {
- timekeeper.xtime_nsec -= nsecps;
- xtime.tv_sec++;
- second_overflow();
- }
-
- raw_time.tv_nsec += timekeeper.raw_interval;
- if (raw_time.tv_nsec >= NSEC_PER_SEC) {
- raw_time.tv_nsec -= NSEC_PER_SEC;
- raw_time.tv_sec++;
- }
-
- /* accumulate error between NTP and clock interval */
- timekeeper.ntp_error += tick_length;
- timekeeper.ntp_error -= timekeeper.xtime_interval <<
- timekeeper.ntp_error_shift;
+ offset = logarithmic_accumulation(offset, shift);
+ shift--;
}
/* correct the clock when NTP error is too big */