[dpdk-dev] [PATCH v2 5/8] examples/vm_power_mgr: add policy to channels

David Hunt david.hunt at intel.com
Mon Sep 25 14:27:06 CEST 2017


From: "Sexton, Rory" <rory.sexton at intel.com>

Signed-off-by: Nemanja Marjanovic <nemanja.marjanovic at intel.com>
Signed-off-by: Rory Sexton <rory.sexton at intel.com>
Signed-off-by: David Hunt <david.hunt at intel.com>
---
 examples/vm_power_manager/channel_monitor.c | 331 +++++++++++++++++++++++++++-
 examples/vm_power_manager/channel_monitor.h |  20 ++
 2 files changed, 345 insertions(+), 6 deletions(-)

diff --git a/examples/vm_power_manager/channel_monitor.c b/examples/vm_power_manager/channel_monitor.c
index ac40dac..3c8f72d 100644
--- a/examples/vm_power_manager/channel_monitor.c
+++ b/examples/vm_power_manager/channel_monitor.c
@@ -41,13 +41,20 @@
 #include <sys/types.h>
 #include <sys/epoll.h>
 #include <sys/queue.h>
+#include <sys/time.h>
 
 #include <rte_log.h>
 #include <rte_memory.h>
 #include <rte_malloc.h>
 #include <rte_atomic.h>
+#include <rte_cycles.h>
+#include <rte_ethdev.h>
 
+#ifdef RTE_LIBRTE_I40E_PMD
+#include <rte_pmd_i40e.h>
+#endif
 
+#include <libvirt/libvirt.h>
 #include "channel_monitor.h"
 #include "channel_commands.h"
 #include "channel_manager.h"
@@ -57,10 +64,17 @@
 
 #define MAX_EVENTS 256
 
+#ifdef RTE_LIBRTE_I40E_PMD
+uint64_t vsi_pkt_count_prev[384];
+uint64_t rdtsc_prev[384];
+#endif
 
+double time_period_s = 1;
 static volatile unsigned run_loop = 1;
 static int global_event_fd;
+static unsigned int policy_is_set;
 static struct epoll_event *global_events_list;
+static struct policy policies[MAX_VMS];
 
 void channel_monitor_exit(void)
 {
@@ -68,6 +82,293 @@ void channel_monitor_exit(void)
 	rte_free(global_events_list);
 }
 
+static void
+core_share(int pNo, int z, int x, int t)
+{
+	if (policies[pNo].core_share[z].pcpu == lvm_info[x].pcpus[t]) {
+		if (strcmp(policies[pNo].pkt.vm_name,
+				lvm_info[x].vm_name) != 0) {
+			policies[pNo].core_share[z].status = 1;
+			power_manager_scale_core_max(
+					policies[pNo].core_share[z].pcpu);
+		}
+	}
+}
+
+static void
+core_share_status(int pNo) {
+
+	int noVms, noVcpus, z, x, t;
+
+	get_all_vm(&noVms, &noVcpus);
+
+	/* Reset Core Share Status. */
+	for (z = 0; z < noVcpus; z++)
+		policies[pNo].core_share[z].status = 0;
+
+	/* Foreach vcpu in a policy. */
+	for (z = 0; z < policies[pNo].pkt.num_vcpu; z++) {
+		/* Foreach VM on the platform. */
+		for (x = 0; x < noVms; x++) {
+			/* Foreach vcpu of VMs on platform. */
+			for (t = 0; t < lvm_info[x].num_cpus; t++)
+				core_share(pNo, z, x, t);
+		}
+	}
+}
+
+static void
+get_pcpu_to_control(struct policy *pol) {
+
+	/* Convert vcpu to pcpu. */
+	struct vm_info info;
+	int pcpu, count;
+	uint64_t mask_u64b;
+
+	RTE_LOG(INFO, CHANNEL_MONITOR, "Looking for pcpu for %s\n",
+			pol->pkt.vm_name);
+	get_info_vm(pol->pkt.vm_name, &info);
+
+	for (count = 0; count < pol->pkt.num_vcpu; count++) {
+		mask_u64b = info.pcpu_mask[pol->pkt.vcpu_to_control[count]];
+		for (pcpu = 0; mask_u64b; mask_u64b &= ~(1ULL << pcpu++)) {
+			if ((mask_u64b >> pcpu) & 1)
+				pol->core_share[count].pcpu = pcpu;
+		}
+	}
+}
+
+#ifdef RTE_LIBRTE_I40E_PMD
+static int
+get_pfid(struct policy *pol) {
+
+	int i, x, ret = 0, nb_ports;
+
+	nb_ports = rte_eth_dev_count();
+	for (i = 0; i < pol->pkt.nb_mac_to_monitor; i++) {
+
+		for (x = 0; x < nb_ports; x++) {
+			ret = rte_pmd_i40e_query_vfid_by_mac(x,
+					pol->pkt.vfid[i]);
+			if (ret != -EINVAL) {
+				pol->port[i] = x;
+				break;
+			}
+		}
+		if (ret == -EINVAL) {
+			RTE_LOG(INFO, CHANNEL_MONITOR,
+				"Error with Policy. MAC not found on "
+				"attached ports ");
+			pol->enabled = 0;
+			return ret;
+		}
+		pol->pfid[i] = ret;
+	}
+	return 1;
+}
+#endif
+
+static int
+update_policy(struct channel_packet *pkt) {
+
+	unsigned int updated = 0;
+
+	for (int i = 0; i < MAX_VMS; i++) {
+		if (strcmp(policies[i].pkt.vm_name, pkt->vm_name) == 0) {
+			policies[i].pkt = *pkt;
+			get_pcpu_to_control(&policies[i]);
+#ifdef RTE_LIBRTE_I40E_PMD
+			if (get_pfid(&policies[i]) == -1) {
+				updated = 1;
+				break;
+			}
+#endif
+			core_share_status(i);
+			policies[i].enabled = 1;
+			updated = 1;
+		}
+	}
+	if (!updated) {
+		for (int i = 0; i < MAX_VMS; i++) {
+			if (policies[i].enabled == 0) {
+				policies[i].pkt = *pkt;
+				get_pcpu_to_control(&policies[i]);
+#ifdef RTE_LIBRTE_I40E_PMD
+				if (get_pfid(&policies[i]) == -1)
+					break;
+#endif
+				core_share_status(i);
+				policies[i].enabled = 1;
+				break;
+			}
+		}
+	}
+	return 0;
+}
+
+#ifdef RTE_LIBRTE_I40E_PMD
+static uint64_t
+get_pkt_diff(struct policy *pol) {
+
+	uint64_t vsi_pkt_count,
+		vsi_pkt_total = 0,
+		vsi_pkt_count_prev_total = 0;
+	double rdtsc_curr, rdtsc_diff, diff;
+	int x;
+	struct rte_eth_stats vf_stats;
+
+	for (x = 0; x < pol->pkt.nb_mac_to_monitor; x++) {
+
+		/*Read vsi stats*/
+		if (rte_pmd_i40e_get_vf_stats(x, pol->pfid[x], &vf_stats) == 0)
+			vsi_pkt_count = vf_stats.ipackets;
+		else
+			vsi_pkt_count = -1;
+
+		vsi_pkt_total += vsi_pkt_count;
+
+		vsi_pkt_count_prev_total += vsi_pkt_count_prev[pol->pfid[x]];
+		vsi_pkt_count_prev[pol->pfid[x]] = vsi_pkt_count;
+	}
+
+	rdtsc_curr = rte_rdtsc_precise();
+	rdtsc_diff = rdtsc_curr - rdtsc_prev[pol->pfid[x-1]];
+	rdtsc_prev[pol->pfid[x-1]] = rdtsc_curr;
+
+	diff = (vsi_pkt_total - vsi_pkt_count_prev_total) *
+			((double)rte_get_tsc_hz() / rdtsc_diff);
+
+	return diff;
+}
+
+static void
+apply_traffic_profile(struct policy *pol) {
+
+	int count;
+	uint64_t diff = 0;
+
+	diff = get_pkt_diff(pol);
+
+	RTE_LOG(INFO, CHANNEL_MONITOR, "Applying traffic profile\n");
+
+	if (diff >= (pol->pkt.traffic_policy.max_max_packet_thresh)) {
+		for (count = 0; count < pol->pkt.num_vcpu; count++) {
+			if (pol->core_share[count].status != 1)
+				power_manager_scale_core_max(
+						pol->core_share[count].pcpu);
+		}
+	} else if (diff >= (pol->pkt.traffic_policy.avg_max_packet_thresh)) {
+		for (count = 0; count < pol->pkt.num_vcpu; count++) {
+			if (pol->core_share[count].status != 1)
+				power_manager_scale_core_med(
+						pol->core_share[count].pcpu);
+		}
+	} else if (diff < (pol->pkt.traffic_policy.avg_max_packet_thresh)) {
+		for (count = 0; count < pol->pkt.num_vcpu; count++) {
+			if (pol->core_share[count].status != 1)
+				power_manager_scale_core_min(
+						pol->core_share[count].pcpu);
+		}
+	}
+}
+#endif
+
+static void
+apply_time_profile(struct policy *pol) {
+
+	int count, x;
+	struct timeval tv;
+	struct tm *ptm;
+	char time_string[40];
+
+	/* Obtain the time of day, and convert it to a tm struct. */
+	gettimeofday(&tv, NULL);
+	ptm = localtime(&tv.tv_sec);
+	/* Format the date and time, down to a single second. */
+	strftime(time_string, sizeof(time_string), "%Y-%m-%d %H:%M:%S", ptm);
+
+	for (x = 0; x < HOURS; x++) {
+
+		if (ptm->tm_hour == pol->pkt.timer_policy.busy_hours[x]) {
+			for (count = 0; count < pol->pkt.num_vcpu; count++) {
+				if (pol->core_share[count].status != 1) {
+					power_manager_scale_core_max(
+						pol->core_share[count].pcpu);
+				RTE_LOG(INFO, CHANNEL_MONITOR,
+					"Scaling up core %d to max\n",
+					pol->core_share[count].pcpu);
+				}
+			}
+			break;
+		} else if (ptm->tm_hour ==
+				pol->pkt.timer_policy.quiet_hours[x]) {
+			for (count = 0; count < pol->pkt.num_vcpu; count++) {
+				if (pol->core_share[count].status != 1) {
+					power_manager_scale_core_min(
+						pol->core_share[count].pcpu);
+				RTE_LOG(INFO, CHANNEL_MONITOR,
+					"Scaling down core %d to min\n",
+					pol->core_share[count].pcpu);
+			}
+		}
+			break;
+#ifdef RTE_LIBRTE_I40E_PMD
+		} else if (ptm->tm_hour ==
+			pol->pkt.timer_policy.hours_to_use_traffic_profile[x]) {
+			apply_traffic_profile(pol);
+			break;
+		}
+#else
+	}
+#endif
+	}
+}
+
+static void
+apply_workload_profile(struct policy *pol) {
+
+	int count;
+
+	if (pol->pkt.workload == HIGH) {
+		for (count = 0; count < pol->pkt.num_vcpu; count++) {
+			if (pol->core_share[count].status != 1)
+				power_manager_scale_core_max(
+						pol->core_share[count].pcpu);
+		}
+	} else if (pol->pkt.workload == MEDIUM) {
+		for (count = 0; count < pol->pkt.num_vcpu; count++) {
+			if (pol->core_share[count].status != 1)
+				power_manager_scale_core_med(
+						pol->core_share[count].pcpu);
+		}
+	} else if (pol->pkt.workload == LOW) {
+		for (count = 0; count < pol->pkt.num_vcpu; count++) {
+			if (pol->core_share[count].status != 1)
+				power_manager_scale_core_min(
+						pol->core_share[count].pcpu);
+		}
+	}
+}
+
+static void
+apply_policy(struct policy *pol) {
+
+	struct channel_packet *pkt = &pol->pkt;
+
+	/*Check policy to use*/
+#ifdef RTE_LIBRTE_I40E_PMD
+	if (pkt->policy_to_use == TRAFFIC)
+		apply_traffic_profile(pol);
+	else if (pkt->policy_to_use == TIME)
+#else
+	if (pkt->policy_to_use == TIME)
+#endif
+		apply_time_profile(pol);
+	else if (pkt->policy_to_use == WORKLOAD)
+		apply_workload_profile(pol);
+}
+
+
 static int
 process_request(struct channel_packet *pkt, struct channel_info *chan_info)
 {
@@ -140,6 +441,13 @@ process_request(struct channel_packet *pkt, struct channel_info *chan_info)
 
 		}
 	}
+
+	if (pkt->command == PKT_POLICY) {
+		RTE_LOG(INFO, CHANNEL_MONITOR, "\nProcessing Policy request from Guest\n");
+		update_policy(pkt);
+		policy_is_set = 1;
+	}
+
 	/* Return is not checked as channel status may have been set to DISABLED
 	 * from management thread
 	 */
@@ -209,9 +517,10 @@ run_channel_monitor(void)
 			struct channel_info *chan_info = (struct channel_info *)
 					global_events_list[i].data.ptr;
 			if ((global_events_list[i].events & EPOLLERR) ||
-					(global_events_list[i].events & EPOLLHUP)) {
+				(global_events_list[i].events & EPOLLHUP)) {
 				RTE_LOG(DEBUG, CHANNEL_MONITOR, "Remote closed connection for "
-						"channel '%s'\n", chan_info->channel_path);
+						"channel '%s'\n",
+						chan_info->channel_path);
 				remove_channel(&chan_info);
 				continue;
 			}
@@ -223,14 +532,17 @@ run_channel_monitor(void)
 				int buffer_len = sizeof(pkt);
 
 				while (buffer_len > 0) {
-					n_bytes = read(chan_info->fd, buffer, buffer_len);
+					n_bytes = read(chan_info->fd,
+							buffer, buffer_len);
 					if (n_bytes == buffer_len)
 						break;
 					if (n_bytes == -1) {
 						err = errno;
-						RTE_LOG(DEBUG, CHANNEL_MONITOR, "Received error on "
-								"channel '%s' read: %s\n",
-								chan_info->channel_path, strerror(err));
+						RTE_LOG(DEBUG, CHANNEL_MONITOR,
+							"Received error on "
+							"channel '%s' read: %s\n",
+							chan_info->channel_path,
+							strerror(err));
 						remove_channel(&chan_info);
 						break;
 					}
@@ -241,5 +553,12 @@ run_channel_monitor(void)
 					process_request(&pkt, chan_info);
 			}
 		}
+		rte_delay_us(time_period_s*1000000);
+		if (policy_is_set) {
+			for (int j = 0; j < MAX_VMS; j++) {
+				if (policies[j].enabled == 1)
+					apply_policy(&policies[j]);
+			}
+		}
 	}
 }
diff --git a/examples/vm_power_manager/channel_monitor.h b/examples/vm_power_manager/channel_monitor.h
index c138607..11f5f75 100644
--- a/examples/vm_power_manager/channel_monitor.h
+++ b/examples/vm_power_manager/channel_monitor.h
@@ -35,6 +35,26 @@
 #define CHANNEL_MONITOR_H_
 
 #include "channel_manager.h"
+#include "channel_commands.h"
+
+struct core_share {
+	unsigned int pcpu;
+	/*
+	 * 1 CORE SHARE
+	 * 0 NOT SHARED
+	 */
+	int status;
+};
+
+struct policy {
+	struct channel_packet pkt;
+#ifdef RTE_LIBRTE_I40E_PMD
+	uint32_t pfid[MAX_VFS];
+	uint32_t port[MAX_VFS];
+#endif
+	unsigned int enabled;
+	struct core_share core_share[MAX_VCPU_PER_VM];
+};
 
 #ifdef __cplusplus
 extern "C" {
-- 
2.7.4



More information about the dev mailing list