1ac09ef2c6
Revise the gccgo version of memory/block/mutex profiling to reduce runtime overhead. The main change is to collect raw stack traces while the profile is on line, then post-process the stacks just prior to the point where we are ready to use the final product. Memory profiling (at a very low sampling rate) is enabled by default, and the overhead of the symbolization / DWARF-reading from backtrace_full was slowing things down relative to the main Go runtime. Reviewed-on: https://go-review.googlesource.com/c/gofrontend/+/171497 From-SVN: r271172 |
||
---|---|---|
.. | ||
aeshash.c | ||
arch.h | ||
array.h | ||
defs.h | ||
env_posix.c | ||
getncpu-aix.c | ||
getncpu-bsd.c | ||
getncpu-hurd.c | ||
getncpu-irix.c | ||
getncpu-linux.c | ||
getncpu-none.c | ||
getncpu-solaris.c | ||
go-assert.c | ||
go-assert.h | ||
go-caller.c | ||
go-callers.c | ||
go-cdiv.c | ||
go-cgo.c | ||
go-construct-map.c | ||
go-ffi.c | ||
go-fieldtrack.c | ||
go-libmain.c | ||
go-main.c | ||
go-matherr.c | ||
go-memclr.c | ||
go-memcmp.c | ||
go-memequal.c | ||
go-nanotime.c | ||
go-nosys.c | ||
go-now.c | ||
go-reflect-call.c | ||
go-runtime-error.c | ||
go-setenv.c | ||
go-signal.c | ||
go-string.h | ||
go-strslice.c | ||
go-type.h | ||
go-typedesc-equal.c | ||
go-unsafe-pointer.c | ||
go-unsetenv.c | ||
go-unwind.c | ||
go-varargs.c | ||
panic.c | ||
print.c | ||
proc.c | ||
rtems-task-variable-add.c | ||
runtime_c.c | ||
runtime.h | ||
stack.c | ||
yield.c |