diff options
author | Waiman Long <longman@redhat.com> | 2017-02-08 10:44:14 +1100 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2017-02-09 17:01:39 +1100 |
commit | b4d623f67460595ba2c37eefceec33a3cea97422 (patch) | |
tree | 5e6f41eb9621b4a18fdd320f1af83d7a41085f12 | |
parent | 9ef13af6296977af2e8443c1b5b304dd1b50a1e4 (diff) |
debugobjects: track number of kmem_cache_alloc/kmem_cache_free done
Patch series "debugobjects: Reduce global pool_lock contention", v2.
This patchset aims to reduce contention of the global pool_lock while
improving performance at the same time. It is done to resolve the
following soft lockup problem with a debug kernel in some of the large SMP
systems:
NMI watchdog: BUG: soft lockup - CPU#35 stuck for 22s! [rcuos/1:21]
...
RIP: 0010:[<ffffffff817c216b>] [<ffffffff817c216b>]
_raw_spin_unlock_irqrestore+0x3b/0x60
...
Call Trace:
[<ffffffff813f40d1>] free_object+0x81/0xb0
[<ffffffff813f4f33>] debug_check_no_obj_freed+0x193/0x220
[<ffffffff81101a59>] ? trace_hardirqs_on_caller+0xf9/0x1c0
[<ffffffff81284996>] ? file_free_rcu+0x36/0x60
[<ffffffff81251712>] kmem_cache_free+0xd2/0x380
[<ffffffff81284960>] ? fput+0x90/0x90
[<ffffffff81284996>] file_free_rcu+0x36/0x60
[<ffffffff81124c23>] rcu_nocb_kthread+0x1b3/0x550
[<ffffffff81124b71>] ? rcu_nocb_kthread+0x101/0x550
[<ffffffff81124a70>] ? sync_exp_work_done.constprop.63+0x50/0x50
[<ffffffff810c59d1>] kthread+0x101/0x120
[<ffffffff81101a59>] ? trace_hardirqs_on_caller+0xf9/0x1c0
[<ffffffff817c2d32>] ret_from_fork+0x22/0x50
On a 8-socket IvyBridge-EX system (120 cores, 240 threads), the elapsed
time of a 4.9-rc7 kernel parallel build (make -j 240) was reduced from
7m57s to 7m19s with a patched 4.9-rc7 kernel. There was also about a 10X
reduction in the number of debug objects being allocated from or freed to
the kmemcache during the kernel build.
This patch (of 3):
New debugfs stat counters are added to track the numbers of
kmem_cache_alloc() and kmem_cache_free() function calls to get a sense of
how the internal debug objects cache management is performing.
Link: http://lkml.kernel.org/r/1483647425-4135-2-git-send-email-longman@redhat.com
Signed-off-by: Waiman Long <longman@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "Du Changbin" <changbin.du@intel.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Jan Stancek <jstancek@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-rw-r--r-- | lib/debugobjects.c | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 04c1ef717fe0..d78673e7dc56 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -55,6 +55,12 @@ static int debug_objects_enabled __read_mostly static struct debug_obj_descr *descr_test __read_mostly; +/* + * Track numbers of kmem_cache_alloc and kmem_cache_free done. + */ +static int debug_objects_alloc; +static int debug_objects_freed; + static void free_obj_work(struct work_struct *work); static DECLARE_WORK(debug_obj_work, free_obj_work); @@ -102,6 +108,7 @@ static void fill_pool(void) raw_spin_lock_irqsave(&pool_lock, flags); hlist_add_head(&new->node, &obj_pool); + debug_objects_alloc++; obj_pool_free++; raw_spin_unlock_irqrestore(&pool_lock, flags); } @@ -173,6 +180,7 @@ static void free_obj_work(struct work_struct *work) obj = hlist_entry(obj_pool.first, typeof(*obj), node); hlist_del(&obj->node); obj_pool_free--; + debug_objects_freed++; /* * We release pool_lock across kmem_cache_free() to * avoid contention on pool_lock. @@ -758,6 +766,8 @@ static int debug_stats_show(struct seq_file *m, void *v) seq_printf(m, "pool_min_free :%d\n", obj_pool_min_free); seq_printf(m, "pool_used :%d\n", obj_pool_used); seq_printf(m, "pool_max_used :%d\n", obj_pool_max_used); + seq_printf(m, "objects_alloc :%d\n", debug_objects_alloc); + seq_printf(m, "objects_freed :%d\n", debug_objects_freed); return 0; } |