| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1588922717-63697-4-git-send-email-feng.tang@intel.com>
Date: Fri, 8 May 2020 15:25:17 +0800
From: Feng Tang <feng.tang@...el.com>
To: Andrew Morton <akpm@...ux-foundation.org>,
Michal Hocko <mhocko@...e.com>,
Johannes Weiner <hannes@...xchg.org>,
Matthew Wilcox <willy@...radead.org>,
Mel Gorman <mgorman@...e.de>,
Kees Cook <keescook@...omium.org>,
Luis Chamberlain <mcgrof@...nel.org>,
Iurii Zaikin <yzaikin@...gle.com>, andi.kleen@...el.com,
tim.c.chen@...el.com, dave.hansen@...el.com, ying.huang@...el.com,
linux-mm@...ck.org, linux-kernel@...r.kernel.org
Cc: Feng Tang <feng.tang@...el.com>
Subject: [PATCH 3/3] mm: adjust vm_committed_as_batch according to vm overcommit policy
When checking a performance change for will-it-scale scalability
mmap test [1], we found very high lock contention for spinlock of
percpu counter 'vm_committed_as':
94.14% 0.35% [kernel.kallsyms] [k] _raw_spin_lock_irqsave
48.21% _raw_spin_lock_irqsave;percpu_counter_add_batch;__vm_enough_memory;mmap_region;do_mmap;
45.91% _raw_spin_lock_irqsave;percpu_counter_add_batch;__do_munmap;
Actually this heavy lock contention is not always necessary. The
'vm_committed_as' needs to be very precise when the strict
OVERCOMMIT_NEVER policy is set, which requires a rather small batch
number for the percpu counter.
So lift the batch number to 16X for OVERCOMMIT_ALWAYS and
OVERCOMMIT_GUESS policies, and add a sysctl handler to adjust it
when the policy is reconfigured.
Benchmark with the same testcase in [1] shows 53% improvement on a
8C/16T desktop, and 2097%(20X) on a 4S/72C/144T server. And no change
for some platforms, due to the test mmap size of the case is bigger
than the batch number computed, though the patch will help mmap/munmap
generally.
[1] https://lkml.org/lkml/2020/3/5/57
Signed-off-by: Feng Tang <feng.tang@...el.com>
---
include/linux/mm.h | 2 ++
include/linux/mman.h | 4 ++++
kernel/sysctl.c | 2 +-
mm/mm_init.c | 19 +++++++++++++++----
mm/util.c | 13 +++++++++++++
5 files changed, 35 insertions(+), 5 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5a32342..bc3722f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -205,6 +205,8 @@ extern int overcommit_ratio_handler(struct ctl_table *, int, void __user *,
size_t *, loff_t *);
extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *,
size_t *, loff_t *);
+extern int overcommit_policy_handler(struct ctl_table *, int, void __user *,
+ size_t *, loff_t *);
#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
diff --git a/include/linux/mman.h b/include/linux/mman.h
index 4b08e9c..91c93c1 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -57,8 +57,12 @@ extern struct percpu_counter vm_committed_as;
#ifdef CONFIG_SMP
extern s32 vm_committed_as_batch;
+extern void mm_compute_batch(void);
#else
#define vm_committed_as_batch 0
+static inline void mm_compute_batch(void)
+{
+}
#endif
unsigned long vm_memory_committed(void);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 8a176d8..6fa552d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1278,7 +1278,7 @@ static struct ctl_table vm_table[] = {
.data = &sysctl_overcommit_memory,
.maxlen = sizeof(sysctl_overcommit_memory),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = overcommit_policy_handler,
.extra1 = SYSCTL_ZERO,
.extra2 = &two,
},
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 7da6991..1654358 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -13,6 +13,7 @@
#include <linux/memory.h>
#include <linux/notifier.h>
#include <linux/sched.h>
+#include <linux/mman.h>
#include "internal.h"
#ifdef CONFIG_DEBUG_MEMORY_INIT
@@ -140,16 +141,26 @@ EXPORT_SYMBOL_GPL(mm_kobj);
#ifdef CONFIG_SMP
s32 vm_committed_as_batch = 32;
-static void __meminit mm_compute_batch(void)
+void mm_compute_batch(void)
{
u64 memsized_batch;
s32 nr = num_present_cpus();
s32 batch = max_t(s32, nr*2, 32);
-
- /* batch size set to 0.4% of (total memory/#cpus), or max int32 */
- memsized_batch = min_t(u64, (totalram_pages()/nr)/256, 0x7fffffff);
+ unsigned long ram_pages = totalram_pages();
+
+ /*
+ * For policy of OVERCOMMIT_NEVER, set batch size to 0.4%
+ * of (total memory/#cpus), and lift it to 6.25% for other
+ * policies to easy the possible lock contention for percpu_counter
+ * vm_committed_as, while the max limit is INT_MAX
+ */
+ if (sysctl_overcommit_memory == OVERCOMMIT_NEVER)
+ memsized_batch = min_t(u64, ram_pages/nr/256, INT_MAX);
+ else
+ memsized_batch = min_t(u64, ram_pages/nr/16, INT_MAX);
vm_committed_as_batch = max_t(s32, memsized_batch, batch);
+ printk("vm_committed_as_batch = %d\n", vm_committed_as_batch);
}
static int __meminit mm_compute_batch_notifier(struct notifier_block *self,
diff --git a/mm/util.c b/mm/util.c
index 3de78e9..99936d3 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -729,6 +729,19 @@ int overcommit_ratio_handler(struct ctl_table *table, int write,
return ret;
}
+int overcommit_policy_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret;
+
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ if (ret == 0 && write)
+ mm_compute_batch();
+
+ return ret;
+}
+
int overcommit_kbytes_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
--
2.7.4
Powered by blists - more mailing lists