With memcg v2 enabled, memcg->memory.usage is a very hot member for
the workloads doing memcg charging on multiple CPUs concurrently.
Particularly the network intensive workloads. In addition, there is a
false cache sharing between memory.usage and memory.high on the charge
path. This patch moves the usage into a separate cacheline and move all
the read most fields into separate cacheline.
To evaluate the impact of this optimization, on a 72 CPUs machine, we
ran the following workload in a three level of cgroup hierarchy with top
level having min and low setup appropriately. More specifically
memory.min equal to size of netperf binary and memory.low double of
that.
$ netserver -6
# 36 instances of netperf with following params
$ netperf -6 -H ::1 -l 60 -t TCP_SENDFILE -- -m 10K
Results (average throughput of netperf):
Without (6.0-rc1) 10482.7 Mbps
With patch 12413.7 Mbps (18.4% improvement)
With the patch, the throughput improved by 18.4%.
One side-effect of this patch is the increase in the size of struct
mem_cgroup. However for the performance improvement, this additional
size is worth it. In addition there are opportunities to reduce the size
of struct mem_cgroup like deprecation of kmem and tcpmem page counters
and better packing.
Signed-off-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
Reported-by: kernel test robot <oliver.sang@xxxxxxxxx>
---
include/linux/page_counter.h | 34 +++++++++++++++++++++++-----------
1 file changed, 23 insertions(+), 11 deletions(-)
diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
index 679591301994..8ce99bde645f 100644
--- a/include/linux/page_counter.h
+++ b/include/linux/page_counter.h
@@ -3,15 +3,27 @@
#define _LINUX_PAGE_COUNTER_H
#include <linux/atomic.h>
+#include <linux/cache.h>
#include <linux/kernel.h>
#include <asm/page.h>
+#if defined(CONFIG_SMP)
+struct pc_padding {
+ char x[0];
+} ____cacheline_internodealigned_in_smp;
+#define PC_PADDING(name) struct pc_padding name
+#else
+#define PC_PADDING(name)
+#endif
+
struct page_counter {
+ /*
+ * Make sure 'usage' does not share cacheline with any other field. The
+ * memcg->memory.usage is a hot member of struct mem_cgroup.
+ */
+ PC_PADDING(_pad1_);
atomic_long_t usage;
- unsigned long min;
- unsigned long low;
- unsigned long high;
- unsigned long max;
+ PC_PADDING(_pad2_);
/* effective memory.min and memory.min usage tracking */
unsigned long emin;
@@ -23,16 +35,16 @@ struct page_counter {
atomic_long_t low_usage;
atomic_long_t children_low_usage;
- /* legacy */
unsigned long watermark;
unsigned long failcnt;
- /*
- * 'parent' is placed here to be far from 'usage' to reduce
- * cache false sharing, as 'usage' is written mostly while
- * parent is frequently read for cgroup's hierarchical
- * counting nature.
- */
+ /* Keep all the read most fields in a separete cacheline. */
+ PC_PADDING(_pad3_);
+
+ unsigned long min;
+ unsigned long low;
+ unsigned long high;
+ unsigned long max;
struct page_counter *parent;
};
--
2.37.1.595.g718a3a8f04-goog
