提交 0ec9fab3 编写于 作者: M Mike Galbraith 提交者: Ingo Molnar

sched: Improve latencies and throughput

Make the idle balancer more agressive, to improve a
x264 encoding workload provided by Jason Garrett-Glaser:

 NEXT_BUDDY NO_LB_BIAS
 encoded 600 frames, 252.82 fps, 22096.60 kb/s
 encoded 600 frames, 250.69 fps, 22096.60 kb/s
 encoded 600 frames, 245.76 fps, 22096.60 kb/s

 NO_NEXT_BUDDY LB_BIAS
 encoded 600 frames, 344.44 fps, 22096.60 kb/s
 encoded 600 frames, 346.66 fps, 22096.60 kb/s
 encoded 600 frames, 352.59 fps, 22096.60 kb/s

 NO_NEXT_BUDDY NO_LB_BIAS
 encoded 600 frames, 425.75 fps, 22096.60 kb/s
 encoded 600 frames, 425.45 fps, 22096.60 kb/s
 encoded 600 frames, 422.49 fps, 22096.60 kb/s

Peter pointed out that this is better done via newidle_idx,
not via LB_BIAS, newidle balancing should look for where
there is load _now_, not where there was load 2 ticks ago.

Worst-case latencies are improved as well as no buddies
means less vruntime spread. (as per prior lkml discussions)

This change improves kbuild-peak parallelism as well.
Reported-by: NJason Garrett-Glaser <darkshikari@gmail.com>
Signed-off-by: NMike Galbraith <efault@gmx.de>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1253011667.9128.16.camel@marge.simson.net>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
上级 6bd7821f
......@@ -61,7 +61,7 @@ void build_cpu_to_node_map(void);
.cache_nice_tries = 2, \
.busy_idx = 2, \
.idle_idx = 1, \
.newidle_idx = 2, \
.newidle_idx = 0, \
.wake_idx = 0, \
.forkexec_idx = 1, \
.flags = SD_LOAD_BALANCE \
......@@ -87,10 +87,11 @@ void build_cpu_to_node_map(void);
.cache_nice_tries = 2, \
.busy_idx = 3, \
.idle_idx = 2, \
.newidle_idx = 2, \
.newidle_idx = 0, \
.wake_idx = 0, \
.forkexec_idx = 1, \
.flags = SD_LOAD_BALANCE \
| SD_BALANCE_NEWIDLE \
| SD_BALANCE_EXEC \
| SD_BALANCE_FORK \
| SD_BALANCE_WAKE \
......
......@@ -57,7 +57,7 @@ static inline int pcibus_to_node(struct pci_bus *bus)
.cache_nice_tries = 1, \
.busy_idx = 3, \
.idle_idx = 1, \
.newidle_idx = 2, \
.newidle_idx = 0, \
.wake_idx = 0, \
.flags = SD_LOAD_BALANCE \
| SD_BALANCE_EXEC \
......
......@@ -15,13 +15,14 @@
.cache_nice_tries = 2, \
.busy_idx = 3, \
.idle_idx = 2, \
.newidle_idx = 2, \
.newidle_idx = 0, \
.wake_idx = 0, \
.forkexec_idx = 1, \
.flags = SD_LOAD_BALANCE \
| SD_BALANCE_FORK \
| SD_BALANCE_EXEC \
| SD_BALANCE_WAKE \
| SD_BALANCE_NEWIDLE \
| SD_SERIALIZE, \
.last_balance = jiffies, \
.balance_interval = 1, \
......
......@@ -116,14 +116,12 @@ extern unsigned long node_remap_size[];
# define SD_CACHE_NICE_TRIES 1
# define SD_IDLE_IDX 1
# define SD_NEWIDLE_IDX 2
# define SD_FORKEXEC_IDX 0
#else
# define SD_CACHE_NICE_TRIES 2
# define SD_IDLE_IDX 2
# define SD_NEWIDLE_IDX 2
# define SD_FORKEXEC_IDX 1
#endif
......@@ -137,7 +135,7 @@ extern unsigned long node_remap_size[];
.cache_nice_tries = SD_CACHE_NICE_TRIES, \
.busy_idx = 3, \
.idle_idx = SD_IDLE_IDX, \
.newidle_idx = SD_NEWIDLE_IDX, \
.newidle_idx = 0, \
.wake_idx = 0, \
.forkexec_idx = SD_FORKEXEC_IDX, \
\
......
......@@ -151,7 +151,7 @@ int arch_update_cpu_topology(void);
.cache_nice_tries = 1, \
.busy_idx = 2, \
.idle_idx = 1, \
.newidle_idx = 2, \
.newidle_idx = 0, \
.wake_idx = 0, \
.forkexec_idx = 1, \
\
......
......@@ -67,7 +67,7 @@ SCHED_FEAT(AFFINE_WAKEUPS, 1)
* wakeup-preemption), since its likely going to consume data we
* touched, increases cache locality.
*/
SCHED_FEAT(NEXT_BUDDY, 1)
SCHED_FEAT(NEXT_BUDDY, 0)
/*
* Prefer to schedule the task that ran last (when we did
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册