thousands of CPUs. It also scales down nicely to
smaller systems.
-config PREEMPT_RCU
- bool "Preemptible RCU"
+config TREE_PREEMPT_RCU
+ bool "Preemptable tree-based hierarchical RCU"
depends on PREEMPT
help
- This option reduces the latency of the kernel by making certain
- RCU sections preemptible. Normally RCU code is non-preemptible, if
- this option is selected then read-only RCU sections become
- preemptible. This helps latency, but may expose bugs due to
- now-naive assumptions about each RCU read-side critical section
- remaining on a given CPU through its execution.
+ This option selects the RCU implementation that is
+ designed for very large SMP systems with hundreds or
+ thousands of CPUs, but for which real-time response
+ is also required.
endchoice
config RCU_TRACE
bool "Enable tracing for RCU"
- depends on TREE_RCU || PREEMPT_RCU
+ depends on TREE_RCU || TREE_PREEMPT_RCU
help
This option provides tracing in RCU which presents stats
in debugfs for debugging RCU implementation.
int "Tree-based hierarchical RCU fanout value"
range 2 64 if 64BIT
range 2 32 if !64BIT
- depends on TREE_RCU
+ depends on TREE_RCU || TREE_PREEMPT_RCU
default 64 if 64BIT
default 32 if !64BIT
help
config RCU_FANOUT_EXACT
bool "Disable tree-based hierarchical RCU auto-balancing"
- depends on TREE_RCU
+ depends on TREE_RCU || TREE_PREEMPT_RCU
default n
help
This option forces use of the exact RCU_FANOUT value specified,
Say N if unsure.
config TREE_RCU_TRACE
- def_bool RCU_TRACE && TREE_RCU
- select DEBUG_FS
- help
- This option provides tracing for the TREE_RCU implementation,
- permitting Makefile to trivially select kernel/rcutree_trace.c.
-
-config PREEMPT_RCU_TRACE
- def_bool RCU_TRACE && PREEMPT_RCU
+ def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU )
select DEBUG_FS
help
- This option provides tracing for the PREEMPT_RCU implementation,
- permitting Makefile to trivially select kernel/rcupreempt_trace.c.
+ This option provides tracing for the TREE_RCU and
+ TREE_PREEMPT_RCU implementations, permitting Makefile to
+ trivially select kernel/rcutree_trace.c.
endmenu # "RCU Subsystem"
config PERF_COUNTERS
bool "Kernel Performance Counters"
+ default y if PROFILING
depends on HAVE_PERF_COUNTERS
select ANON_INODES
help
Say Y if unsure.
config EVENT_PROFILE
- bool "Tracepoint profile sources"
- depends on PERF_COUNTERS && EVENT_TRACER
+ bool "Tracepoint profiling sources"
+ depends on PERF_COUNTERS && EVENT_TRACING
default y
+ help
+ Allow the use of tracepoints as software performance counters.
+
+ When this is enabled, you can create perf counters based on
+ tracepoints using PERF_TYPE_TRACEPOINT and the tracepoint ID
+ found in debugfs://tracing/events/*/*/id. (The -e/--events
+ option to the perf tool can parse and interpret symbolic
+ tracepoints, in the subsystem:tracepoint_name format.)
endmenu