tracing: Shrink max latency ringbuffer if unnecessary
Documentation/trace/ftrace.txt says
buffer_size_kb:
This sets or displays the number of kilobytes each CPU
buffer can hold. The tracer buffers are the same size
for each CPU. The displayed number is the size of the
CPU buffer and not total size of all buffers. The
trace buffers are allocated in pages (blocks of memory
that the kernel uses for allocation, usually 4 KB in size).
If the last page allocated has room for more bytes
than requested, the rest of the page will be used,
making the actual allocation bigger than requested.
( Note, the size may not be a multiple of the page size
due to buffer management overhead. )
This can only be updated when the current_tracer
is set to "nop".
But it's incorrect. currently total memory consumption is
'buffer_size_kb x CPUs x 2'.
Why two times difference is there? because ftrace implicitly allocate
the buffer for max latency too.
That makes sad result when admin want to use large buffer. (If admin
want full logging and makes detail analysis). example, If admin
have 24 CPUs machine and write 200MB to buffer_size_kb, the system
consume ~10GB memory (200MB x 24 x 2). umm.. 5GB memory waste is
usually unacceptable.
Fortunatelly, almost all users don't use max latency feature.
The max latency buffer can be disabled easily.
This patch shrink buffer size of the max latency buffer if
unnecessary.
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
LKML-Reference: <20100701104554.DA2D.A69D9226@jp.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index af90429..f7488f4 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -660,6 +660,10 @@
return;
WARN_ON_ONCE(!irqs_disabled());
+ if (!current_trace->use_max_tr) {
+ WARN_ON_ONCE(1);
+ return;
+ }
arch_spin_lock(&ftrace_max_lock);
tr->buffer = max_tr.buffer;
@@ -686,6 +690,11 @@
return;
WARN_ON_ONCE(!irqs_disabled());
+ if (!current_trace->use_max_tr) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+
arch_spin_lock(&ftrace_max_lock);
ftrace_disable_cpu();
@@ -2801,6 +2810,9 @@
if (ret < 0)
return ret;
+ if (!current_trace->use_max_tr)
+ goto out;
+
ret = ring_buffer_resize(max_tr.buffer, size);
if (ret < 0) {
int r;
@@ -2828,11 +2840,14 @@
return ret;
}
+ max_tr.entries = size;
+ out:
global_trace.entries = size;
return ret;
}
+
/**
* tracing_update_buffers - used by tracing facility to expand ring buffers
*
@@ -2893,12 +2908,26 @@
trace_branch_disable();
if (current_trace && current_trace->reset)
current_trace->reset(tr);
-
+ if (current_trace && current_trace->use_max_tr) {
+ /*
+ * We don't free the ring buffer. instead, resize it because
+ * The max_tr ring buffer has some state (e.g. ring->clock) and
+ * we want preserve it.
+ */
+ ring_buffer_resize(max_tr.buffer, 1);
+ max_tr.entries = 1;
+ }
destroy_trace_option_files(topts);
current_trace = t;
topts = create_trace_option_files(current_trace);
+ if (current_trace->use_max_tr) {
+ ret = ring_buffer_resize(max_tr.buffer, global_trace.entries);
+ if (ret < 0)
+ goto out;
+ max_tr.entries = global_trace.entries;
+ }
if (t->init) {
ret = tracer_init(t, tr);
@@ -3480,7 +3509,6 @@
}
tracing_start();
- max_tr.entries = global_trace.entries;
mutex_unlock(&trace_types_lock);
return cnt;
@@ -4578,16 +4606,14 @@
#ifdef CONFIG_TRACER_MAX_TRACE
- max_tr.buffer = ring_buffer_alloc(ring_buf_size,
- TRACE_BUFFER_FLAGS);
+ max_tr.buffer = ring_buffer_alloc(1, TRACE_BUFFER_FLAGS);
if (!max_tr.buffer) {
printk(KERN_ERR "tracer: failed to allocate max ring buffer!\n");
WARN_ON(1);
ring_buffer_free(global_trace.buffer);
goto out_free_cpumask;
}
- max_tr.entries = ring_buffer_size(max_tr.buffer);
- WARN_ON(max_tr.entries != global_trace.entries);
+ max_tr.entries = 1;
#endif
/* Allocate the first page for all buffers */