From: Nick Piggin <nickpiggin@yahoo.com.au>
These are some values I just found from thin-air that should hopefully make
ia64 work after the latest sched patches.
Though it did look like there may have been some problems with the old
values, which I tried to fix up too:
- SD_ALLNODES_INIT had .balance_interval set a specific way - this field
is internal to the scheduler and will end up sitting between min_interval
and max_interval and not do what was intended, so tweak max_interval
instead.
- SD_ALLNODES_INIT had SD_BALANCE_EXEC set. The scheduler doesn't cope
_really_ well with doing balance-on-exec over the top level of a
multi-level NUMA setup like this. It will tend to fill up the first CPUs
in each high level group (cluster of 6 nodes) rather than spreading the
load on a per-node basis. This could be improved if we really need it,
but for now remove the flag from the top level.
- Increase SD_NODES_PER_DOMAIN in the low level NUMA domain so we still
push tasks out a reasonable distance. Set SD_BALANCE_FORK in this domain
too.
Signed-off-by: Andrew Morton <akpm@osdl.org>
---
25-akpm/arch/ia64/kernel/domain.c | 2 -
25-akpm/include/asm-ia64/topology.h | 62 +++++++++++++++++++++++++++---------
2 files changed, 49 insertions(+), 15 deletions(-)
diff -puN arch/ia64/kernel/domain.c~random-ia64-sched-domains-values arch/ia64/kernel/domain.c
--- 25/arch/ia64/kernel/domain.c~random-ia64-sched-domains-values 2005-02-25 00:30:26.000000000 -0800
+++ 25-akpm/arch/ia64/kernel/domain.c 2005-02-25 00:30:26.000000000 -0800
@@ -14,7 +14,7 @@
#include <linux/topology.h>
#include <linux/nodemask.h>
-#define SD_NODES_PER_DOMAIN 6
+#define SD_NODES_PER_DOMAIN 16
#ifdef CONFIG_NUMA
/**
diff -puN include/asm-ia64/topology.h~random-ia64-sched-domains-values include/asm-ia64/topology.h
--- 25/include/asm-ia64/topology.h~random-ia64-sched-domains-values 2005-02-25 00:30:26.000000000 -0800
+++ 25-akpm/include/asm-ia64/topology.h 2005-02-25 00:30:26.000000000 -0800
@@ -42,25 +42,55 @@
void build_cpu_to_node_map(void);
+#define SD_CPU_INIT (struct sched_domain) { \
+ .span = CPU_MASK_NONE, \
+ .parent = NULL, \
+ .groups = NULL, \
+ .min_interval = 1, \
+ .max_interval = 4, \
+ .busy_factor = 64, \
+ .imbalance_pct = 125, \
+ .cache_hot_time = (10*1000000), \
+ .cache_nice_tries = 2, \
+ .per_cpu_gain = 100, \
+ .cache_nice_tries = 2, \
+ .busy_idx = 2, \
+ .idle_idx = 1, \
+ .newidle_idx = 2, \
+ .wake_idx = 1, \
+ .forkexec_idx = 1, \
+ .flags = SD_LOAD_BALANCE \
+ | SD_BALANCE_NEWIDLE \
+ | SD_BALANCE_EXEC \
+ | SD_WAKE_AFFINE, \
+ .last_balance = jiffies, \
+ .balance_interval = 1, \
+ .nr_balance_failed = 0, \
+}
+
/* sched_domains SD_NODE_INIT for IA64 NUMA machines */
#define SD_NODE_INIT (struct sched_domain) { \
.span = CPU_MASK_NONE, \
.parent = NULL, \
.groups = NULL, \
- .min_interval = 80, \
- .max_interval = 320, \
- .busy_factor = 320, \
+ .min_interval = 8, \
+ .max_interval = 8*(min(num_online_cpus(), 32)), \
+ .busy_factor = 64, \
.imbalance_pct = 125, \
.cache_hot_time = (10*1000000), \
- .cache_nice_tries = 1, \
+ .cache_nice_tries = 2, \
+ .busy_idx = 3, \
+ .idle_idx = 2, \
+ .newidle_idx = 0, /* unused */ \
+ .wake_idx = 1, \
+ .forkexec_idx = 1, \
.per_cpu_gain = 100, \
.flags = SD_LOAD_BALANCE \
| SD_BALANCE_EXEC \
- | SD_BALANCE_NEWIDLE \
- | SD_WAKE_IDLE \
+ | SD_BALANCE_FORK \
| SD_WAKE_BALANCE, \
.last_balance = jiffies, \
- .balance_interval = 1, \
+ .balance_interval = 64, \
.nr_balance_failed = 0, \
}
@@ -69,17 +99,21 @@ void build_cpu_to_node_map(void);
.span = CPU_MASK_NONE, \
.parent = NULL, \
.groups = NULL, \
- .min_interval = 80, \
- .max_interval = 320, \
- .busy_factor = 320, \
- .imbalance_pct = 125, \
+ .min_interval = 64, \
+ .max_interval = 64*num_online_cpus(), \
+ .busy_factor = 128, \
+ .imbalance_pct = 133, \
.cache_hot_time = (10*1000000), \
.cache_nice_tries = 1, \
+ .busy_idx = 3, \
+ .idle_idx = 3, \
+ .newidle_idx = 0, /* unused */ \
+ .wake_idx = 0, /* unused */ \
+ .forkexec_idx = 0, /* unused */ \
.per_cpu_gain = 100, \
- .flags = SD_LOAD_BALANCE \
- | SD_BALANCE_EXEC, \
+ .flags = SD_LOAD_BALANCE, \
.last_balance = jiffies, \
- .balance_interval = 100*(63+num_online_cpus())/64, \
+ .balance_interval = 64, \
.nr_balance_failed = 0, \
}
_