kni: allow configuring thread granularity

The Kni kthreads seem to be re-scheduled at a granularity of roughly 1 millisecond right now, which seems to be insufficient for performing tests involving a lot of control plane traffic. Even if KNI_KTHREAD_RESCHEDULE_INTERVAL is set to 5 microseconds, it seems that the existing code cannot reschedule at the desired granularily, due to precision constraints of schedule_timeout_interruptible(). In our use case, we leverage the Linux Kernel for control plane, and it is not uncommon to have 60K - 100K pps for some signaling protocols. Since we are not in atomic context, the usleep_range() function seems to be more appropriate for being able to introduce smaller controlled delays, in the range of 5-10 microseconds. Upon reading the existing code, it would seem that this was the original intent. Adding sub-millisecond delays, seems unfeasible with a call to schedule_timeout_interruptible(). KNI_KTHREAD_RESCHEDULE_INTERVAL 5 /* us */ schedule_timeout_interruptible( usecs_to_jiffies(KNI_KTHREAD_RESCHEDULE_INTERVAL)); Below, we attempted a brief comparison between the existing implementation, which uses schedule_timeout_interruptible() and usleep_range(). We attempt to measure the CPU usage, and RTT between two Kni interfaces, which are created on top of vmxnet3 adapters, connected by a vSwitch. insmod rte_kni.ko kthread_mode=single carrier=on schedule_timeout_interruptible(usecs_to_jiffies(5)) kni_single CPU Usage: 2-4 % [root@localhost ~]# ping 1.1.1.2 -I eth1 PING 1.1.1.2 (1.1.1.2) from 1.1.1.1 eth1: 56(84) bytes of data. 64 bytes from 1.1.1.2: icmp_seq=1 ttl=64 time=2.70 ms 64 bytes from 1.1.1.2: icmp_seq=2 ttl=64 time=1.00 ms 64 bytes from 1.1.1.2: icmp_seq=3 ttl=64 time=1.99 ms 64 bytes from 1.1.1.2: icmp_seq=4 ttl=64 time=0.985 ms 64 bytes from 1.1.1.2: icmp_seq=5 ttl=64 time=1.00 ms usleep_range(5, 10) kni_single CPU usage: 50% 64 bytes from 1.1.1.2: icmp_seq=1 ttl=64 time=0.338 ms 64 bytes from 1.1.1.2: icmp_seq=2 ttl=64 time=0.150 ms 64 bytes from 1.1.1.2: icmp_seq=3 ttl=64 time=0.123 ms 64 bytes from 1.1.1.2: icmp_seq=4 ttl=64 time=0.139 ms 64 bytes from 1.1.1.2: icmp_seq=5 ttl=64 time=0.159 ms usleep_range(20, 50) kni_single CPU usage: 24% 64 bytes from 1.1.1.2: icmp_seq=1 ttl=64 time=0.202 ms 64 bytes from 1.1.1.2: icmp_seq=2 ttl=64 time=0.170 ms 64 bytes from 1.1.1.2: icmp_seq=3 ttl=64 time=0.171 ms 64 bytes from 1.1.1.2: icmp_seq=4 ttl=64 time=0.248 ms 64 bytes from 1.1.1.2: icmp_seq=5 ttl=64 time=0.185 ms usleep_range(50, 100) kni_single CPU usage: 13% 64 bytes from 1.1.1.2: icmp_seq=1 ttl=64 time=0.537 ms 64 bytes from 1.1.1.2: icmp_seq=2 ttl=64 time=0.257 ms 64 bytes from 1.1.1.2: icmp_seq=3 ttl=64 time=0.231 ms 64 bytes from 1.1.1.2: icmp_seq=4 ttl=64 time=0.143 ms 64 bytes from 1.1.1.2: icmp_seq=5 ttl=64 time=0.200 ms usleep_range(100, 200) kni_single CPU usage: 7% 64 bytes from 1.1.1.2: icmp_seq=1 ttl=64 time=0.716 ms 64 bytes from 1.1.1.2: icmp_seq=2 ttl=64 time=0.167 ms 64 bytes from 1.1.1.2: icmp_seq=3 ttl=64 time=0.459 ms 64 bytes from 1.1.1.2: icmp_seq=4 ttl=64 time=0.455 ms 64 bytes from 1.1.1.2: icmp_seq=5 ttl=64 time=0.252 ms usleep_range(1000, 1100) kni_single CPU usage: 2% 64 bytes from 1.1.1.2: icmp_seq=1 ttl=64 time=2.22 ms 64 bytes from 1.1.1.2: icmp_seq=2 ttl=64 time=1.17 ms 64 bytes from 1.1.1.2: icmp_seq=3 ttl=64 time=1.17 ms 64 bytes from 1.1.1.2: icmp_seq=4 ttl=64 time=1.17 ms 64 bytes from 1.1.1.2: icmp_seq=5 ttl=64 time=1.15 ms Upon testing, usleep_range(1000, 1100) seems roughly equivalent in latency and cpu usage to the variant with schedule_timeout_interruptible(), while usleep_range(100, 200) seems to give a decent tradeoff between latency and cpu usage, while allowing users to tweak the limits for improved precision if they have such use cases. Disabling RTE_KNI_PREEMPT_DEFAULT, interestingly seems to lead to a softlockup on my kernel. Kernel panic - not syncing: softlockup: hung tasks CPU: 0 PID: 1226 Comm: kni_single Tainted: G W O 3.10 #1 <IRQ> [<ffffffff814f84de>] dump_stack+0x19/0x1b [<ffffffff814f7891>] panic+0xcd/0x1e0 [<ffffffff810993b0>] watchdog_timer_fn+0x160/0x160 [<ffffffff810644b2>] __run_hrtimer.isra.4+0x42/0xd0 [<ffffffff81064b57>] hrtimer_interrupt+0xe7/0x1f0 [<ffffffff8102cd57>] smp_apic_timer_interrupt+0x67/0xa0 [<ffffffff8150321d>] apic_timer_interrupt+0x6d/0x80 This patch also attempts to remove this option. References: [1] https://www.kernel.org/doc/Documentation/timers/timers-howto.txt Signed-off-by: Tudor Cornea <tudor.cornea@gmail.com> Acked-by: Padraig Connolly <Padraig.J.Connolly@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
spdk · Feb 2, 2022 · 5569dd7 · 5569dd7
1 parent e16b972
commit 5569dd7
Show file tree

Hide file tree

Showing 4 changed files with 58 additions and 12 deletions.
diff --git a/config/rte_config.h b/config/rte_config.h
@@ -95,9 +95,6 @@
 #define RTE_SCHED_PORT_N_GRINDERS 8
 #undef RTE_SCHED_VECTOR
 
-/* KNI defines */
-#define RTE_KNI_PREEMPT_DEFAULT 1
-
 /* rte_graph defines */
 #define RTE_GRAPH_BURST_SIZE 256
 #define RTE_LIBRTE_GRAPH_STATS 1

diff --git a/doc/guides/prog_guide/kernel_nic_interface.rst b/doc/guides/prog_guide/kernel_nic_interface.rst
@@ -61,6 +61,10 @@ can be specified when the module is loaded to control its behavior:
                     userspace callback and supporting async requests (default=off):
                     on    Enable request processing support for bifurcated drivers.
                      (charp)
+    parm:           min_scheduling_interval: KNI thread min scheduling interval (default=100 microseconds)
+                     (long)
+    parm:           max_scheduling_interval: KNI thread max scheduling interval (default=200 microseconds)
+                     (long)
 
 
 Loading the ``rte_kni`` kernel module without any optional parameters is
@@ -202,6 +206,35 @@ Enabling bifurcated device support releases ``rtnl`` lock before calling
 callback and locks it back after callback. Also enables asynchronous request to
 support callbacks that requires rtnl lock to work (interface down).
 
+KNI Kthread Scheduling
+~~~~~~~~~~~~~~~~~~~~~~
+
+The ``min_scheduling_interval`` and ``max_scheduling_interval`` parameters
+control the rescheduling interval of the KNI kthreads.
+
+This might be useful if we have use cases in which we require improved
+latency or performance for control plane traffic.
+
+The implementation is backed by Linux High Precision Timers, and uses ``usleep_range``.
+Hence, it will have the same granularity constraints as this Linux subsystem.
+
+For Linux High Precision Timers, you can check the following resource: `Kernel Timers <http://www.kernel.org/doc/Documentation/timers/timers-howto.txt>`_
+
+To set the ``min_scheduling_interval`` to a value of 100 microseconds:
+
+.. code-block:: console
+
+    # insmod <build_dir>/kernel/linux/kni/rte_kni.ko min_scheduling_interval=100
+
+To set the ``max_scheduling_interval`` to a value of 200 microseconds:
+
+.. code-block:: console
+
+    # insmod <build_dir>/kernel/linux/kni/rte_kni.ko max_scheduling_interval=200
+
+If the ``min_scheduling_interval`` and ``max_scheduling_interval`` parameters are
+not specified, the default interval limits will be set to *100* and *200* respectively.
+
 KNI Creation and Deletion
 -------------------------
 

diff --git a/kernel/linux/kni/kni_dev.h b/kernel/linux/kni/kni_dev.h
@@ -27,7 +27,7 @@
 #include <linux/list.h>
 
 #include <rte_kni_common.h>
-#define KNI_KTHREAD_RESCHEDULE_INTERVAL 5 /* us */
+#define KNI_KTHREAD_MAX_RESCHEDULE_INTERVAL 1000000 /* us */
 
 #define MBUF_BURST_SZ 32
 

diff --git a/kernel/linux/kni/kni_misc.c b/kernel/linux/kni/kni_misc.c
@@ -45,6 +45,10 @@ uint32_t kni_dflt_carrier;
 static char *enable_bifurcated;
 uint32_t bifurcated_support;
 
+/* KNI thread scheduling interval */
+static long min_scheduling_interval = 100; /* us */
+static long max_scheduling_interval = 200; /* us */
+
 #define KNI_DEV_IN_USE_BIT_NUM 0 /* Bit number for device in use */
 
 static int kni_net_id;
@@ -132,11 +136,8 @@ kni_thread_single(void *data)
 			}
 		}
 		up_read(&knet->kni_list_lock);
-#ifdef RTE_KNI_PREEMPT_DEFAULT
 		/* reschedule out for a while */
-		schedule_timeout_interruptible(
-			usecs_to_jiffies(KNI_KTHREAD_RESCHEDULE_INTERVAL));
-#endif
+		usleep_range(min_scheduling_interval, max_scheduling_interval);
 	}
 
 	return 0;
@@ -153,10 +154,7 @@ kni_thread_multiple(void *param)
 			kni_net_rx(dev);
 			kni_net_poll_resp(dev);
 		}
-#ifdef RTE_KNI_PREEMPT_DEFAULT
-		schedule_timeout_interruptible(
-			usecs_to_jiffies(KNI_KTHREAD_RESCHEDULE_INTERVAL));
-#endif
+		usleep_range(min_scheduling_interval, max_scheduling_interval);
 	}
 
 	return 0;
@@ -617,6 +615,14 @@ kni_init(void)
 	if (bifurcated_support == 1)
 		pr_debug("bifurcated support is enabled.\n");
 
+	if (min_scheduling_interval < 0 || max_scheduling_interval < 0 ||
+		min_scheduling_interval > KNI_KTHREAD_MAX_RESCHEDULE_INTERVAL ||
+		max_scheduling_interval > KNI_KTHREAD_MAX_RESCHEDULE_INTERVAL ||
+		min_scheduling_interval >= max_scheduling_interval) {
+		pr_err("Invalid parameters for scheduling interval\n");
+		return -EINVAL;
+	}
+
 #ifdef HAVE_SIMPLIFIED_PERNET_OPERATIONS
 	rc = register_pernet_subsys(&kni_net_ops);
 #else
@@ -692,3 +698,13 @@ MODULE_PARM_DESC(enable_bifurcated,
 "\t\ton    Enable request processing support for bifurcated drivers.\n"
 "\t\t"
 );
+
+module_param(min_scheduling_interval, long, 0644);
+MODULE_PARM_DESC(min_scheduling_interval,
+"KNI thread min scheduling interval (default=100 microseconds)"
+);
+
+module_param(max_scheduling_interval, long, 0644);
+MODULE_PARM_DESC(max_scheduling_interval,
+"KNI thread max scheduling interval (default=200 microseconds)"
+);