summaryrefslogtreecommitdiff
path: root/kernel/locking
diff options
context:
space:
mode:
authorByungchul Park <byungchul.park@lge.com>2017-10-25 17:56:00 +0900
committerIngo Molnar <mingo@kernel.org>2017-10-25 12:19:01 +0200
commitd141babe4244945f1d001118578e0eb3ce12729d (patch)
tree2a8e33099749737decdd4cb0e4b8438c66ee3bec /kernel/locking
parent24208435e343679b21502fb90786084dfaf15369 (diff)
locking/lockdep: Add a boot parameter allowing unwind in cross-release and disable it by default
Johan Hovold reported a heavy performance regression caused by lockdep cross-release: > Boot time (from "Linux version" to login prompt) had in fact doubled > since 4.13 where it took 17 seconds (with my current config) compared to > the 35 seconds I now see with 4.14-rc4. > > I quick bisect pointed to lockdep and specifically the following commit: > > 28a903f63ec0 ("locking/lockdep: Handle non(or multi)-acquisition > of a crosslock") > > which I've verified is the commit which doubled the boot time (compared > to 28a903f63ec0^) (added by lockdep crossrelease series [1]). Currently cross-release performs unwind on every acquisition, but that is very expensive. This patch makes unwind optional and disables it by default and only records acquire_ip. Full stack traces are sometimes required for full analysis, in which case a boot paramter, crossrelease_fullstack, can be specified. On my qemu Ubuntu machine (x86_64, 4 cores, 512M), the regression was fixed. We measure boot times with 'perf stat --null --repeat 10 $QEMU', where $QEMU launches a kernel with init=/bin/true: 1. No lockdep enabled: Performance counter stats for 'qemu_booting_time.sh bzImage' (10 runs): 2.756558155 seconds time elapsed ( +- 0.09% ) 2. Lockdep enabled: Performance counter stats for 'qemu_booting_time.sh bzImage' (10 runs): 2.968710420 seconds time elapsed ( +- 0.12% ) 3. Lockdep enabled + cross-release enabled: Performance counter stats for 'qemu_booting_time.sh bzImage' (10 runs): 3.153839636 seconds time elapsed ( +- 0.31% ) 4. Lockdep enabled + cross-release enabled + this patch applied: Performance counter stats for 'qemu_booting_time.sh bzImage' (10 runs): 2.963669551 seconds time elapsed ( +- 0.11% ) I.e. lockdep cross-release performance is now indistinguishable from vanilla lockdep. Bisected-by: Johan Hovold <johan@kernel.org> Analyzed-by: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Thomas Gleixner <tglx@linutronix.de> Reported-by: Johan Hovold <johan@kernel.org> Signed-off-by: Byungchul Park <byungchul.park@lge.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: amir73il@gmail.com Cc: axboe@kernel.dk Cc: darrick.wong@oracle.com Cc: david@fromorbit.com Cc: hch@infradead.org Cc: idryomov@gmail.com Cc: johannes.berg@intel.com Cc: kernel-team@lge.com Cc: linux-block@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org Cc: linux-mm@kvack.org Cc: linux-xfs@vger.kernel.org Cc: oleg@redhat.com Cc: tj@kernel.org Link: http://lkml.kernel.org/r/1508921765-15396-5-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/locking')
-rw-r--r--kernel/locking/lockdep.c19
1 files changed, 17 insertions, 2 deletions
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index e36e652d996f..160b5d6df7cb 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -76,6 +76,15 @@ module_param(lock_stat, int, 0644);
#define lock_stat 0
#endif
+static int crossrelease_fullstack;
+static int __init allow_crossrelease_fullstack(char *str)
+{
+ crossrelease_fullstack = 1;
+ return 0;
+}
+
+early_param("crossrelease_fullstack", allow_crossrelease_fullstack);
+
/*
* lockdep_lock: protects the lockdep graph, the hashes and the
* class/list/hash allocators.
@@ -4863,8 +4872,14 @@ static void add_xhlock(struct held_lock *hlock)
xhlock->trace.nr_entries = 0;
xhlock->trace.max_entries = MAX_XHLOCK_TRACE_ENTRIES;
xhlock->trace.entries = xhlock->trace_entries;
- xhlock->trace.skip = 3;
- save_stack_trace(&xhlock->trace);
+
+ if (crossrelease_fullstack) {
+ xhlock->trace.skip = 3;
+ save_stack_trace(&xhlock->trace);
+ } else {
+ xhlock->trace.nr_entries = 1;
+ xhlock->trace.entries[0] = hlock->acquire_ip;
+ }
}
static inline int same_context_xhlock(struct hist_lock *xhlock)