From: Alex Kogan <alex.kogan@oracle.com>
To: linux@armlinux.org.uk, peterz@infradead.org, mingo@redhat.com,
will.deacon@arm.com, arnd@arndb.de, longman@redhat.com,
linux-arch@vger.kernel.org, linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org, tglx@linutronix.de, bp@alien8.de,
hpa@zytor.com, x86@kernel.org, guohanjun@huawei.com,
jglauber@marvell.com
Cc: alex.kogan@oracle.com, dave.dice@oracle.com,
steven.sistare@oracle.com, daniel.m.jordan@oracle.com
Subject: [PATCH v9 4/5] locking/qspinlock: Introduce starvation avoidance into CNA
Date: Tue, 14 Jan 2020 22:59:19 -0500 [thread overview]
Message-ID: <20200115035920.54451-5-alex.kogan@oracle.com> (raw)
In-Reply-To: <20200115035920.54451-1-alex.kogan@oracle.com>
Keep track of the number of intra-node lock handoffs, and force
inter-node handoff once this number reaches a preset threshold.
The default value for the threshold can be overridden with
the new kernel boot command-line option "numa_spinlock_threshold".
Signed-off-by: Alex Kogan <alex.kogan@oracle.com>
Reviewed-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Waiman Long <longman@redhat.com>
---
.../admin-guide/kernel-parameters.txt | 8 ++++
kernel/locking/qspinlock.c | 3 ++
kernel/locking/qspinlock_cna.h | 41 ++++++++++++++++++-
3 files changed, 51 insertions(+), 1 deletion(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index b68cb80e477f..30d79819a3b0 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3200,6 +3200,14 @@
Not specifying this option is equivalent to
numa_spinlock=auto.
+ numa_spinlock_threshold= [NUMA, PV_OPS]
+ Set the threshold for the number of intra-node
+ lock hand-offs before the NUMA-aware spinlock
+ is forced to be passed to a thread on another NUMA node.
+ Valid values are in the [0..31] range. Smaller values
+ result in a more fair, but less performant spinlock, and
+ vice versa. The default value is 16.
+
cpu0_hotplug [X86] Turn on CPU0 hotplug feature when
CONFIG_BOOTPARAM_HOTPLUG_CPU0 is off.
Some features depend on CPU0. Known dependencies are:
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 609980a53841..e382d8946ccc 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -597,6 +597,9 @@ EXPORT_SYMBOL(queued_spin_lock_slowpath);
#if !defined(_GEN_CNA_LOCK_SLOWPATH) && defined(CONFIG_NUMA_AWARE_SPINLOCKS)
#define _GEN_CNA_LOCK_SLOWPATH
+#undef pv_init_node
+#define pv_init_node cna_init_node
+
#undef pv_wait_head_or_lock
#define pv_wait_head_or_lock cna_pre_scan
diff --git a/kernel/locking/qspinlock_cna.h b/kernel/locking/qspinlock_cna.h
index 8000231f3d51..a2b65f87e6f8 100644
--- a/kernel/locking/qspinlock_cna.h
+++ b/kernel/locking/qspinlock_cna.h
@@ -51,13 +51,25 @@ struct cna_node {
int numa_node;
u32 encoded_tail;
u32 pre_scan_result; /* encoded tail or enum val */
+ u32 intra_count;
};
enum {
LOCAL_WAITER_FOUND = 2, /* 0 and 1 are reserved for @locked */
+ FLUSH_SECONDARY_QUEUE = 3,
MIN_ENCODED_TAIL
};
+/*
+ * Controls the threshold for the number of intra-node lock hand-offs before
+ * the NUMA-aware variant of spinlock is forced to be passed to a thread on
+ * another NUMA node. By default, the chosen value provides reasonable
+ * long-term fairness without sacrificing performance compared to a lock
+ * that does not have any fairness guarantees. The default setting can
+ * be changed with the "numa_spinlock_threshold" boot option.
+ */
+unsigned int intra_node_handoff_threshold __ro_after_init = 1 << 16;
+
static void __init cna_init_nodes_per_cpu(unsigned int cpu)
{
struct mcs_spinlock *base = per_cpu_ptr(&qnodes[0].mcs, cpu);
@@ -97,6 +109,11 @@ static int __init cna_init_nodes(void)
}
early_initcall(cna_init_nodes);
+static __always_inline void cna_init_node(struct mcs_spinlock *node)
+{
+ ((struct cna_node *)node)->intra_count = 0;
+}
+
/* this function is called only when the primary queue is empty */
static inline bool cna_try_change_tail(struct qspinlock *lock, u32 val,
struct mcs_spinlock *node)
@@ -232,7 +249,9 @@ __always_inline u32 cna_pre_scan(struct qspinlock *lock,
{
struct cna_node *cn = (struct cna_node *)node;
- cn->pre_scan_result = cna_scan_main_queue(node, node);
+ cn->pre_scan_result =
+ cn->intra_count == intra_node_handoff_threshold ?
+ FLUSH_SECONDARY_QUEUE : cna_scan_main_queue(node, node);
return 0;
}
@@ -262,6 +281,9 @@ static inline void cna_pass_lock(struct mcs_spinlock *node,
* if we acquired the MCS lock when its queue was empty
*/
val = node->locked ? node->locked : 1;
+ /* inc @intra_count if the secondary queue is not empty */
+ ((struct cna_node *)next_holder)->intra_count =
+ cn->intra_count + (node->locked > 1);
} else if (node->locked > 1) { /* if secondary queue is not empty */
/* next holder will be the first node in the secondary queue */
tail_2nd = decode_tail(node->locked);
@@ -316,3 +338,20 @@ void __init cna_configure_spin_lock_slowpath(void)
pr_info("Enabling CNA spinlock\n");
}
}
+
+static int __init numa_spinlock_threshold_setup(char *str)
+{
+ int new_threshold_param;
+
+ if (get_option(&str, &new_threshold_param)) {
+ /* valid value is between 0 and 31 */
+ if (new_threshold_param < 0 || new_threshold_param > 31)
+ return 0;
+
+ intra_node_handoff_threshold = 1 << new_threshold_param;
+ return 1;
+ }
+
+ return 0;
+}
+__setup("numa_spinlock_threshold=", numa_spinlock_threshold_setup);
--
2.21.0 (Apple Git-122.2)
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2020-01-15 4:15 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-01-15 3:59 [PATCH v9 0/5] Add NUMA-awareness to qspinlock Alex Kogan
2020-01-15 3:59 ` [PATCH v9 1/5] locking/qspinlock: Rename mcs lock/unlock macros and make them more generic Alex Kogan
2020-01-15 3:59 ` [PATCH v9 2/5] locking/qspinlock: Refactor the qspinlock slow path Alex Kogan
2020-01-15 3:59 ` [PATCH v9 3/5] locking/qspinlock: Introduce CNA into the slow path of qspinlock Alex Kogan
2020-01-23 9:26 ` Peter Zijlstra
2020-01-23 10:06 ` Peter Zijlstra
2020-01-23 10:16 ` Peter Zijlstra
2020-01-23 11:22 ` Will Deacon
2020-01-23 13:17 ` Peter Zijlstra
2020-01-23 14:15 ` Waiman Long
2020-01-23 15:29 ` Peter Zijlstra
2020-01-15 3:59 ` Alex Kogan [this message]
2020-01-23 19:55 ` [PATCH v9 4/5] locking/qspinlock: Introduce starvation avoidance into CNA Waiman Long
2020-01-23 20:39 ` Waiman Long
2020-01-23 23:39 ` Alex Kogan
2020-01-15 3:59 ` [PATCH v9 5/5] locking/qspinlock: Introduce the shuffle reduction optimization " Alex Kogan
2020-01-22 11:45 ` [PATCH v9 0/5] Add NUMA-awareness to qspinlock Lihao Liang
2020-01-22 17:24 ` Waiman Long
2020-01-23 11:35 ` Will Deacon
2020-01-23 15:25 ` Waiman Long
2020-01-23 19:08 ` Waiman Long
2020-01-22 19:29 ` Alex Kogan
2020-01-26 0:32 ` Lihao Liang
2020-01-26 1:58 ` Lihao Liang
2020-01-27 16:01 ` Alex Kogan
2020-01-29 1:39 ` Lihao Liang
2020-01-27 6:16 ` Alex Kogan
2020-01-24 22:24 ` Paul E. McKenney
[not found] ` <6AAE7FC6-F5DE-4067-8BC4-77F27948CD09@oracle.com>
2020-01-25 0:57 ` Paul E. McKenney
2020-01-25 1:59 ` Waiman Long
[not found] ` <adb4fb09-f374-4d64-096b-ba9ad8b35fd5@redhat.com>
2020-01-25 4:58 ` Paul E. McKenney
2020-01-25 19:41 ` Waiman Long
2020-01-26 15:35 ` Paul E. McKenney
2020-01-26 22:42 ` Paul E. McKenney
2020-01-26 23:32 ` Paul E. McKenney
2020-01-27 6:04 ` Alex Kogan
2020-01-27 14:11 ` Waiman Long
2020-01-27 15:09 ` Paul E. McKenney
[not found] ` <9b3a3f16-5405-b6d1-d023-b85f4aab46dd@redhat.com>
2020-01-27 17:17 ` Waiman Long
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200115035920.54451-5-alex.kogan@oracle.com \
--to=alex.kogan@oracle.com \
--cc=arnd@arndb.de \
--cc=bp@alien8.de \
--cc=daniel.m.jordan@oracle.com \
--cc=dave.dice@oracle.com \
--cc=guohanjun@huawei.com \
--cc=hpa@zytor.com \
--cc=jglauber@marvell.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@armlinux.org.uk \
--cc=longman@redhat.com \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=steven.sistare@oracle.com \
--cc=tglx@linutronix.de \
--cc=will.deacon@arm.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).