summaryrefslogtreecommitdiffstats
path: root/examples/vm_power_manager
diff options
context:
space:
mode:
authorLuca Boccassi <luca.boccassi@gmail.com>2018-08-14 18:52:30 +0100
committerLuca Boccassi <luca.boccassi@gmail.com>2018-08-14 18:53:17 +0100
commitb63264c8342e6a1b6971c79550d2af2024b6a4de (patch)
tree83114aac64286fe616506c0b3dfaec2ab86ef835 /examples/vm_power_manager
parentca33590b6af032bff57d9cc70455660466a654b2 (diff)
New upstream version 18.08upstream/18.08
Change-Id: I32fdf5e5016556d9c0a6d88ddaf1fc468961790a Signed-off-by: Luca Boccassi <luca.boccassi@gmail.com>
Diffstat (limited to 'examples/vm_power_manager')
-rw-r--r--examples/vm_power_manager/Makefile7
-rw-r--r--examples/vm_power_manager/channel_monitor.c28
-rw-r--r--examples/vm_power_manager/guest_cli/Makefile2
-rw-r--r--examples/vm_power_manager/guest_cli/main.c151
-rw-r--r--examples/vm_power_manager/guest_cli/parse.c82
-rw-r--r--examples/vm_power_manager/guest_cli/parse.h19
-rw-r--r--examples/vm_power_manager/guest_cli/vm_power_cli_guest.c113
-rw-r--r--examples/vm_power_manager/guest_cli/vm_power_cli_guest.h6
-rw-r--r--examples/vm_power_manager/main.c177
-rw-r--r--examples/vm_power_manager/meson.build10
-rw-r--r--examples/vm_power_manager/oob_monitor.h68
-rw-r--r--examples/vm_power_manager/oob_monitor_nop.c38
-rw-r--r--examples/vm_power_manager/oob_monitor_x86.c258
-rw-r--r--examples/vm_power_manager/parse.c81
-rw-r--r--examples/vm_power_manager/parse.h20
-rw-r--r--examples/vm_power_manager/power_manager.c139
-rw-r--r--examples/vm_power_manager/power_manager.h23
17 files changed, 1060 insertions, 162 deletions
diff --git a/examples/vm_power_manager/Makefile b/examples/vm_power_manager/Makefile
index ef2a9f95..13a5205b 100644
--- a/examples/vm_power_manager/Makefile
+++ b/examples/vm_power_manager/Makefile
@@ -19,7 +19,12 @@ APP = vm_power_mgr
# all source are stored in SRCS-y
SRCS-y := main.c vm_power_cli.c power_manager.c channel_manager.c
-SRCS-y += channel_monitor.c
+SRCS-y += channel_monitor.c parse.c
+ifeq ($(CONFIG_RTE_ARCH_X86_64),y)
+SRCS-y += oob_monitor_x86.c
+else
+SRCS-y += oob_monitor_nop.c
+endif
CFLAGS += -O3 -I$(RTE_SDK)/lib/librte_power/
CFLAGS += $(WERROR_FLAGS)
diff --git a/examples/vm_power_manager/channel_monitor.c b/examples/vm_power_manager/channel_monitor.c
index 1c7b6eb2..7fa47ba9 100644
--- a/examples/vm_power_manager/channel_monitor.c
+++ b/examples/vm_power_manager/channel_monitor.c
@@ -27,6 +27,7 @@
#include "channel_commands.h"
#include "channel_manager.h"
#include "power_manager.h"
+#include "oob_monitor.h"
#define RTE_LOGTYPE_CHANNEL_MONITOR RTE_LOGTYPE_USER1
@@ -92,6 +93,10 @@ get_pcpu_to_control(struct policy *pol)
struct vm_info info;
int pcpu, count;
uint64_t mask_u64b;
+ struct core_info *ci;
+ int ret;
+
+ ci = get_core_info();
RTE_LOG(INFO, CHANNEL_MONITOR, "Looking for pcpu for %s\n",
pol->pkt.vm_name);
@@ -100,8 +105,22 @@ get_pcpu_to_control(struct policy *pol)
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;
+ if ((mask_u64b >> pcpu) & 1) {
+ if (pol->pkt.policy_to_use == BRANCH_RATIO) {
+ ci->cd[pcpu].oob_enabled = 1;
+ ret = add_core_to_monitor(pcpu);
+ if (ret == 0)
+ printf("Monitoring pcpu %d via Branch Ratio\n",
+ pcpu);
+ else
+ printf("Failed to start OOB Monitoring pcpu %d\n",
+ pcpu);
+
+ } else {
+ pol->core_share[count].pcpu = pcpu;
+ printf("Monitoring pcpu %d\n", pcpu);
+ }
+ }
}
}
}
@@ -110,12 +129,11 @@ static int
get_pfid(struct policy *pol)
{
- int i, x, ret = 0, nb_ports;
+ int i, x, ret = 0;
- nb_ports = rte_eth_dev_count();
for (i = 0; i < pol->pkt.nb_mac_to_monitor; i++) {
- for (x = 0; x < nb_ports; x++) {
+ RTE_ETH_FOREACH_DEV(x) {
ret = rte_pmd_i40e_query_vfid_by_mac(x,
(struct ether_addr *)&(pol->pkt.vfid[i]));
if (ret != -EINVAL) {
diff --git a/examples/vm_power_manager/guest_cli/Makefile b/examples/vm_power_manager/guest_cli/Makefile
index d710e22d..8b1db861 100644
--- a/examples/vm_power_manager/guest_cli/Makefile
+++ b/examples/vm_power_manager/guest_cli/Makefile
@@ -14,7 +14,7 @@ include $(RTE_SDK)/mk/rte.vars.mk
APP = guest_vm_power_mgr
# all source are stored in SRCS-y
-SRCS-y := main.c vm_power_cli_guest.c
+SRCS-y := main.c vm_power_cli_guest.c parse.c
CFLAGS += -O3 -I$(RTE_SDK)/lib/librte_power/
CFLAGS += $(WERROR_FLAGS)
diff --git a/examples/vm_power_manager/guest_cli/main.c b/examples/vm_power_manager/guest_cli/main.c
index b17936d6..36365b12 100644
--- a/examples/vm_power_manager/guest_cli/main.c
+++ b/examples/vm_power_manager/guest_cli/main.c
@@ -2,23 +2,20 @@
* Copyright(c) 2010-2014 Intel Corporation
*/
-/*
#include <stdio.h>
-#include <string.h>
-#include <stdint.h>
-#include <sys/epoll.h>
-#include <fcntl.h>
-#include <unistd.h>
#include <stdlib.h>
-#include <errno.h>
-*/
#include <signal.h>
+#include <getopt.h>
+#include <string.h>
#include <rte_lcore.h>
#include <rte_power.h>
#include <rte_debug.h>
+#include <rte_eal.h>
+#include <rte_log.h>
#include "vm_power_cli_guest.h"
+#include "parse.h"
static void
sig_handler(int signo)
@@ -32,6 +29,136 @@ sig_handler(int signo)
}
+#define MAX_HOURS 24
+
+/* Parse the argument given in the command line of the application */
+static int
+parse_args(int argc, char **argv)
+{
+ int opt, ret;
+ char **argvopt;
+ int option_index;
+ char *prgname = argv[0];
+ const struct option lgopts[] = {
+ { "vm-name", required_argument, 0, 'n'},
+ { "busy-hours", required_argument, 0, 'b'},
+ { "quiet-hours", required_argument, 0, 'q'},
+ { "port-list", required_argument, 0, 'p'},
+ { "vcpu-list", required_argument, 0, 'l'},
+ { "policy", required_argument, 0, 'o'},
+ {NULL, 0, 0, 0}
+ };
+ struct channel_packet *policy;
+ unsigned short int hours[MAX_HOURS];
+ unsigned short int cores[MAX_VCPU_PER_VM];
+ unsigned short int ports[MAX_VCPU_PER_VM];
+ int i, cnt, idx;
+
+ policy = get_policy();
+ set_policy_defaults(policy);
+
+ argvopt = argv;
+
+ while ((opt = getopt_long(argc, argvopt, "n:b:q:p:",
+ lgopts, &option_index)) != EOF) {
+
+ switch (opt) {
+ /* portmask */
+ case 'n':
+ strcpy(policy->vm_name, optarg);
+ printf("Setting VM Name to [%s]\n", policy->vm_name);
+ break;
+ case 'b':
+ case 'q':
+ //printf("***Processing set using [%s]\n", optarg);
+ cnt = parse_set(optarg, hours, MAX_HOURS);
+ if (cnt < 0) {
+ printf("Invalid value passed to quiet/busy hours - [%s]\n",
+ optarg);
+ break;
+ }
+ idx = 0;
+ for (i = 0; i < MAX_HOURS; i++) {
+ if (hours[i]) {
+ if (opt == 'b') {
+ printf("***Busy Hour %d\n", i);
+ policy->timer_policy.busy_hours
+ [idx++] = i;
+ } else {
+ printf("***Quiet Hour %d\n", i);
+ policy->timer_policy.quiet_hours
+ [idx++] = i;
+ }
+ }
+ }
+ break;
+ case 'l':
+ cnt = parse_set(optarg, cores, MAX_VCPU_PER_VM);
+ if (cnt < 0) {
+ printf("Invalid value passed to vcpu-list - [%s]\n",
+ optarg);
+ break;
+ }
+ idx = 0;
+ for (i = 0; i < MAX_VCPU_PER_VM; i++) {
+ if (cores[i]) {
+ printf("***Using core %d\n", i);
+ policy->vcpu_to_control[idx++] = i;
+ }
+ }
+ policy->num_vcpu = idx;
+ printf("Total cores: %d\n", idx);
+ break;
+ case 'p':
+ cnt = parse_set(optarg, ports, MAX_VCPU_PER_VM);
+ if (cnt < 0) {
+ printf("Invalid value passed to port-list - [%s]\n",
+ optarg);
+ break;
+ }
+ idx = 0;
+ for (i = 0; i < MAX_VCPU_PER_VM; i++) {
+ if (ports[i]) {
+ printf("***Using port %d\n", i);
+ set_policy_mac(i, idx++);
+ }
+ }
+ policy->nb_mac_to_monitor = idx;
+ printf("Total Ports: %d\n", idx);
+ break;
+ case 'o':
+ if (!strcmp(optarg, "TRAFFIC"))
+ policy->policy_to_use = TRAFFIC;
+ else if (!strcmp(optarg, "TIME"))
+ policy->policy_to_use = TIME;
+ else if (!strcmp(optarg, "WORKLOAD"))
+ policy->policy_to_use = WORKLOAD;
+ else if (!strcmp(optarg, "BRANCH_RATIO"))
+ policy->policy_to_use = BRANCH_RATIO;
+ else {
+ printf("Invalid policy specified: %s\n",
+ optarg);
+ return -1;
+ }
+ break;
+ /* long options */
+
+ case 0:
+ break;
+
+ default:
+ return -1;
+ }
+ }
+
+ if (optind >= 0)
+ argv[optind-1] = prgname;
+
+ ret = optind-1;
+ optind = 0; /* reset getopt lib */
+ return ret;
+}
+
int
main(int argc, char **argv)
{
@@ -45,6 +172,14 @@ main(int argc, char **argv)
signal(SIGINT, sig_handler);
signal(SIGTERM, sig_handler);
+ argc -= ret;
+ argv += ret;
+
+ /* parse application arguments (after the EAL ones) */
+ ret = parse_args(argc, argv);
+ if (ret < 0)
+ rte_exit(EXIT_FAILURE, "Invalid arguments\n");
+
rte_power_set_env(PM_ENV_KVM_VM);
RTE_LCORE_FOREACH(lcore_id) {
rte_power_init(lcore_id);
diff --git a/examples/vm_power_manager/guest_cli/parse.c b/examples/vm_power_manager/guest_cli/parse.c
new file mode 100644
index 00000000..528df6d6
--- /dev/null
+++ b/examples/vm_power_manager/guest_cli/parse.c
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2014 Intel Corporation.
+ * Copyright(c) 2014 6WIND S.A.
+ */
+
+#include <stdlib.h>
+#include <string.h>
+#include <rte_log.h>
+#include "parse.h"
+
+/*
+ * Parse elem, the elem could be single number/range or group
+ * 1) A single number elem, it's just a simple digit. e.g. 9
+ * 2) A single range elem, two digits with a '-' between. e.g. 2-6
+ * 3) A group elem, combines multiple 1) or 2) e.g 0,2-4,6
+ * Within group, '-' used for a range separator;
+ * ',' used for a single number.
+ */
+int
+parse_set(const char *input, uint16_t set[], unsigned int num)
+{
+ unsigned int idx;
+ const char *str = input;
+ char *end = NULL;
+ unsigned int min, max;
+
+ memset(set, 0, num * sizeof(uint16_t));
+
+ while (isblank(*str))
+ str++;
+
+ /* only digit or left bracket is qualify for start point */
+ if (!isdigit(*str) || *str == '\0')
+ return -1;
+
+ while (isblank(*str))
+ str++;
+ if (*str == '\0')
+ return -1;
+
+ min = num;
+ do {
+
+ /* go ahead to the first digit */
+ while (isblank(*str))
+ str++;
+ if (!isdigit(*str))
+ return -1;
+
+ /* get the digit value */
+ errno = 0;
+ idx = strtoul(str, &end, 10);
+ if (errno || end == NULL || idx >= num)
+ return -1;
+
+ /* go ahead to separator '-' and ',' */
+ while (isblank(*end))
+ end++;
+ if (*end == '-') {
+ if (min == num)
+ min = idx;
+ else /* avoid continuous '-' */
+ return -1;
+ } else if ((*end == ',') || (*end == '\0')) {
+ max = idx;
+
+ if (min == num)
+ min = idx;
+
+ for (idx = RTE_MIN(min, max);
+ idx <= RTE_MAX(min, max); idx++) {
+ set[idx] = 1;
+ }
+ min = num;
+ } else
+ return -1;
+
+ str = end + 1;
+ } while (*end != '\0');
+
+ return str - input;
+}
diff --git a/examples/vm_power_manager/guest_cli/parse.h b/examples/vm_power_manager/guest_cli/parse.h
new file mode 100644
index 00000000..c8aa0ea5
--- /dev/null
+++ b/examples/vm_power_manager/guest_cli/parse.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Intel Corporation
+ */
+
+#ifndef PARSE_H_
+#define PARSE_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+int
+parse_set(const char *, uint16_t [], unsigned int);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* PARSE_H_ */
diff --git a/examples/vm_power_manager/guest_cli/vm_power_cli_guest.c b/examples/vm_power_manager/guest_cli/vm_power_cli_guest.c
index 43bdeace..0db1b804 100644
--- a/examples/vm_power_manager/guest_cli/vm_power_cli_guest.c
+++ b/examples/vm_power_manager/guest_cli/vm_power_cli_guest.c
@@ -33,6 +33,71 @@ struct cmd_quit_result {
cmdline_fixed_string_t quit;
};
+union PFID {
+ struct ether_addr addr;
+ uint64_t pfid;
+};
+
+static struct channel_packet policy;
+
+struct channel_packet *
+get_policy(void)
+{
+ return &policy;
+}
+
+int
+set_policy_mac(int port, int idx)
+{
+ struct channel_packet *policy;
+ union PFID pfid;
+
+ /* Use port MAC address as the vfid */
+ rte_eth_macaddr_get(port, &pfid.addr);
+
+ printf("Port %u MAC: %02" PRIx8 ":%02" PRIx8 ":%02" PRIx8 ":"
+ "%02" PRIx8 ":%02" PRIx8 ":%02" PRIx8 "\n",
+ port,
+ pfid.addr.addr_bytes[0], pfid.addr.addr_bytes[1],
+ pfid.addr.addr_bytes[2], pfid.addr.addr_bytes[3],
+ pfid.addr.addr_bytes[4], pfid.addr.addr_bytes[5]);
+ policy = get_policy();
+ policy->vfid[idx] = pfid.pfid;
+ return 0;
+}
+
+void
+set_policy_defaults(struct channel_packet *pkt)
+{
+ set_policy_mac(0, 0);
+ pkt->nb_mac_to_monitor = 1;
+
+ pkt->t_boost_status.tbEnabled = false;
+
+ pkt->vcpu_to_control[0] = 0;
+ pkt->vcpu_to_control[1] = 1;
+ pkt->num_vcpu = 2;
+ /* Dummy Population. */
+ pkt->traffic_policy.min_packet_thresh = 96000;
+ pkt->traffic_policy.avg_max_packet_thresh = 1800000;
+ pkt->traffic_policy.max_max_packet_thresh = 2000000;
+
+ pkt->timer_policy.busy_hours[0] = 3;
+ pkt->timer_policy.busy_hours[1] = 4;
+ pkt->timer_policy.busy_hours[2] = 5;
+ pkt->timer_policy.quiet_hours[0] = 11;
+ pkt->timer_policy.quiet_hours[1] = 12;
+ pkt->timer_policy.quiet_hours[2] = 13;
+
+ pkt->timer_policy.hours_to_use_traffic_profile[0] = 8;
+ pkt->timer_policy.hours_to_use_traffic_profile[1] = 10;
+
+ pkt->workload = LOW;
+ pkt->policy_to_use = TIME;
+ pkt->command = PKT_POLICY;
+ strcpy(pkt->vm_name, "ubuntu2");
+}
+
static void cmd_quit_parsed(__attribute__((unused)) void *parsed_result,
__attribute__((unused)) struct cmdline *cl,
__attribute__((unused)) void *data)
@@ -118,54 +183,12 @@ struct cmd_send_policy_result {
cmdline_fixed_string_t cmd;
};
-union PFID {
- struct ether_addr addr;
- uint64_t pfid;
-};
-
static inline int
-send_policy(void)
+send_policy(struct channel_packet *pkt)
{
- struct channel_packet pkt;
int ret;
- union PFID pfid;
- /* Use port MAC address as the vfid */
- rte_eth_macaddr_get(0, &pfid.addr);
- printf("Port %u MAC: %02" PRIx8 ":%02" PRIx8 ":%02" PRIx8 ":"
- "%02" PRIx8 ":%02" PRIx8 ":%02" PRIx8 "\n",
- 1,
- pfid.addr.addr_bytes[0], pfid.addr.addr_bytes[1],
- pfid.addr.addr_bytes[2], pfid.addr.addr_bytes[3],
- pfid.addr.addr_bytes[4], pfid.addr.addr_bytes[5]);
- pkt.vfid[0] = pfid.pfid;
-
- pkt.nb_mac_to_monitor = 1;
- pkt.t_boost_status.tbEnabled = false;
-
- pkt.vcpu_to_control[0] = 0;
- pkt.vcpu_to_control[1] = 1;
- pkt.num_vcpu = 2;
- /* Dummy Population. */
- pkt.traffic_policy.min_packet_thresh = 96000;
- pkt.traffic_policy.avg_max_packet_thresh = 1800000;
- pkt.traffic_policy.max_max_packet_thresh = 2000000;
-
- pkt.timer_policy.busy_hours[0] = 3;
- pkt.timer_policy.busy_hours[1] = 4;
- pkt.timer_policy.busy_hours[2] = 5;
- pkt.timer_policy.quiet_hours[0] = 11;
- pkt.timer_policy.quiet_hours[1] = 12;
- pkt.timer_policy.quiet_hours[2] = 13;
-
- pkt.timer_policy.hours_to_use_traffic_profile[0] = 8;
- pkt.timer_policy.hours_to_use_traffic_profile[1] = 10;
-
- pkt.workload = LOW;
- pkt.policy_to_use = TIME;
- pkt.command = PKT_POLICY;
- strcpy(pkt.vm_name, "ubuntu2");
- ret = rte_power_guest_channel_send_msg(&pkt, 1);
+ ret = rte_power_guest_channel_send_msg(pkt, 1);
if (ret == 0)
return 1;
RTE_LOG(DEBUG, POWER, "Error sending message: %s\n",
@@ -182,7 +205,7 @@ cmd_send_policy_parsed(void *parsed_result, struct cmdline *cl,
if (!strcmp(res->cmd, "now")) {
printf("Sending Policy down now!\n");
- ret = send_policy();
+ ret = send_policy(&policy);
}
if (ret != 1)
cmdline_printf(cl, "Error sending message: %s\n",
diff --git a/examples/vm_power_manager/guest_cli/vm_power_cli_guest.h b/examples/vm_power_manager/guest_cli/vm_power_cli_guest.h
index 75a26296..fd77f6a6 100644
--- a/examples/vm_power_manager/guest_cli/vm_power_cli_guest.h
+++ b/examples/vm_power_manager/guest_cli/vm_power_cli_guest.h
@@ -11,6 +11,12 @@ extern "C" {
#include "channel_commands.h"
+struct channel_packet *get_policy(void);
+
+int set_policy_mac(int port, int idx);
+
+void set_policy_defaults(struct channel_packet *pkt);
+
void run_cli(__attribute__((unused)) void *arg);
#ifdef __cplusplus
diff --git a/examples/vm_power_manager/main.c b/examples/vm_power_manager/main.c
index 8a1e95bd..58c5fa45 100644
--- a/examples/vm_power_manager/main.c
+++ b/examples/vm_power_manager/main.c
@@ -29,6 +29,8 @@
#include "channel_monitor.h"
#include "power_manager.h"
#include "vm_power_cli.h"
+#include "oob_monitor.h"
+#include "parse.h"
#include <rte_pmd_ixgbe.h>
#include <rte_pmd_i40e.h>
#include <rte_pmd_bnxt.h>
@@ -47,7 +49,6 @@ static volatile bool force_quit;
static const struct rte_eth_conf port_conf_default = {
.rxmode = {
.max_rx_pkt_len = ETHER_MAX_LEN,
- .ignore_offload_bitfield = 1,
},
};
@@ -61,7 +62,7 @@ port_init(uint16_t port, struct rte_mempool *mbuf_pool)
struct rte_eth_dev_info dev_info;
struct rte_eth_txconf txq_conf;
- if (port >= rte_eth_dev_count())
+ if (!rte_eth_dev_is_valid_port(port))
return -1;
rte_eth_dev_info_get(port, &dev_info);
@@ -83,7 +84,6 @@ port_init(uint16_t port, struct rte_mempool *mbuf_pool)
}
txq_conf = dev_info.default_txconf;
- txq_conf.txq_flags = ETH_TXQ_FLAGS_IGNORE;
txq_conf.offloads = port_conf.txmode.offloads;
/* Allocate and set up 1 TX queue per Ethernet port. */
for (q = 0; q < tx_rings; q++) {
@@ -135,18 +135,25 @@ parse_portmask(const char *portmask)
static int
parse_args(int argc, char **argv)
{
- int opt, ret;
+ int opt, ret, cnt, i;
char **argvopt;
+ uint16_t *oob_enable;
int option_index;
char *prgname = argv[0];
+ struct core_info *ci;
+ float branch_ratio;
static struct option lgopts[] = {
{ "mac-updating", no_argument, 0, 1},
{ "no-mac-updating", no_argument, 0, 0},
+ { "core-list", optional_argument, 0, 'l'},
+ { "port-list", optional_argument, 0, 'p'},
+ { "branch-ratio", optional_argument, 0, 'b'},
{NULL, 0, 0, 0}
};
argvopt = argv;
+ ci = get_core_info();
- while ((opt = getopt_long(argc, argvopt, "p:q:T:",
+ while ((opt = getopt_long(argc, argvopt, "l:p:q:T:b:",
lgopts, &option_index)) != EOF) {
switch (opt) {
@@ -158,6 +165,39 @@ parse_args(int argc, char **argv)
return -1;
}
break;
+ case 'l':
+ oob_enable = malloc(ci->core_count * sizeof(uint16_t));
+ if (oob_enable == NULL) {
+ printf("Error - Unable to allocate memory\n");
+ return -1;
+ }
+ cnt = parse_set(optarg, oob_enable, ci->core_count);
+ if (cnt < 0) {
+ printf("Invalid core-list - [%s]\n",
+ optarg);
+ break;
+ }
+ for (i = 0; i < ci->core_count; i++) {
+ if (oob_enable[i]) {
+ printf("***Using core %d\n", i);
+ ci->cd[i].oob_enabled = 1;
+ ci->cd[i].global_enabled_cpus = 1;
+ }
+ }
+ free(oob_enable);
+ break;
+ case 'b':
+ branch_ratio = 0.0;
+ if (strlen(optarg))
+ branch_ratio = atof(optarg);
+ if (branch_ratio <= 0.0) {
+ printf("invalid branch ratio specified\n");
+ return -1;
+ }
+ ci->branch_ratio_threshold = branch_ratio;
+ printf("***Setting branch ratio to %f\n",
+ branch_ratio);
+ break;
/* long options */
case 0:
break;
@@ -176,7 +216,7 @@ parse_args(int argc, char **argv)
}
static void
-check_all_ports_link_status(uint16_t port_num, uint32_t port_mask)
+check_all_ports_link_status(uint32_t port_mask)
{
#define CHECK_INTERVAL 100 /* 100ms */
#define MAX_CHECK_TIME 90 /* 9s (90 * 100ms) in total */
@@ -189,7 +229,7 @@ check_all_ports_link_status(uint16_t port_num, uint32_t port_mask)
if (force_quit)
return;
all_ports_up = 1;
- for (portid = 0; portid < port_num; portid++) {
+ RTE_ETH_FOREACH_DEV(portid) {
if (force_quit)
return;
if ((port_mask & (1 << portid)) == 0)
@@ -243,6 +283,17 @@ run_monitor(__attribute__((unused)) void *arg)
return 0;
}
+static int
+run_core_monitor(__attribute__((unused)) void *arg)
+{
+ if (branch_monitor_init() < 0) {
+ printf("Unable to initialize core monitor\n");
+ return -1;
+ }
+ run_branch_monitor();
+ return 0;
+}
+
static void
sig_handler(int signo)
{
@@ -261,7 +312,14 @@ main(int argc, char **argv)
unsigned int nb_ports;
struct rte_mempool *mbuf_pool;
uint16_t portid;
+ struct core_info *ci;
+
+
+ ret = core_info_init();
+ if (ret < 0)
+ rte_panic("Cannot allocate core info\n");
+ ci = get_core_info();
ret = rte_eal_init(argc, argv);
if (ret < 0)
@@ -278,53 +336,58 @@ main(int argc, char **argv)
if (ret < 0)
rte_exit(EXIT_FAILURE, "Invalid arguments\n");
- nb_ports = rte_eth_dev_count();
+ nb_ports = rte_eth_dev_count_avail();
- mbuf_pool = rte_pktmbuf_pool_create("MBUF_POOL", NUM_MBUFS * nb_ports,
- MBUF_CACHE_SIZE, 0, RTE_MBUF_DEFAULT_BUF_SIZE, rte_socket_id());
+ if (nb_ports > 0) {
+ mbuf_pool = rte_pktmbuf_pool_create("MBUF_POOL",
+ NUM_MBUFS * nb_ports, MBUF_CACHE_SIZE, 0,
+ RTE_MBUF_DEFAULT_BUF_SIZE, rte_socket_id());
- if (mbuf_pool == NULL)
- rte_exit(EXIT_FAILURE, "Cannot create mbuf pool\n");
+ if (mbuf_pool == NULL)
+ rte_exit(EXIT_FAILURE, "Cannot create mbuf pool\n");
- /* Initialize ports. */
- for (portid = 0; portid < nb_ports; portid++) {
- struct ether_addr eth;
- int w, j;
- int ret;
+ /* Initialize ports. */
+ RTE_ETH_FOREACH_DEV(portid) {
+ struct ether_addr eth;
+ int w, j;
+ int ret;
- if ((enabled_port_mask & (1 << portid)) == 0)
- continue;
+ if ((enabled_port_mask & (1 << portid)) == 0)
+ continue;
- eth.addr_bytes[0] = 0xe0;
- eth.addr_bytes[1] = 0xe0;
- eth.addr_bytes[2] = 0xe0;
- eth.addr_bytes[3] = 0xe0;
- eth.addr_bytes[4] = portid + 0xf0;
+ eth.addr_bytes[0] = 0xe0;
+ eth.addr_bytes[1] = 0xe0;
+ eth.addr_bytes[2] = 0xe0;
+ eth.addr_bytes[3] = 0xe0;
+ eth.addr_bytes[4] = portid + 0xf0;
- if (port_init(portid, mbuf_pool) != 0)
- rte_exit(EXIT_FAILURE, "Cannot init port %"PRIu8 "\n",
+ if (port_init(portid, mbuf_pool) != 0)
+ rte_exit(EXIT_FAILURE,
+ "Cannot init port %"PRIu8 "\n",
portid);
- for (w = 0; w < MAX_VFS; w++) {
- eth.addr_bytes[5] = w + 0xf0;
-
- ret = rte_pmd_ixgbe_set_vf_mac_addr(portid,
- w, &eth);
- if (ret == -ENOTSUP)
- ret = rte_pmd_i40e_set_vf_mac_addr(portid,
- w, &eth);
- if (ret == -ENOTSUP)
- ret = rte_pmd_bnxt_set_vf_mac_addr(portid,
- w, &eth);
-
- switch (ret) {
- case 0:
- printf("Port %d VF %d MAC: ",
- portid, w);
- for (j = 0; j < 6; j++) {
- printf("%02x", eth.addr_bytes[j]);
- if (j < 5)
- printf(":");
+ for (w = 0; w < MAX_VFS; w++) {
+ eth.addr_bytes[5] = w + 0xf0;
+
+ ret = rte_pmd_ixgbe_set_vf_mac_addr(portid,
+ w, &eth);
+ if (ret == -ENOTSUP)
+ ret = rte_pmd_i40e_set_vf_mac_addr(
+ portid, w, &eth);
+ if (ret == -ENOTSUP)
+ ret = rte_pmd_bnxt_set_vf_mac_addr(
+ portid, w, &eth);
+
+ switch (ret) {
+ case 0:
+ printf("Port %d VF %d MAC: ",
+ portid, w);
+ for (j = 0; j < 5; j++) {
+ printf("%02x:",
+ eth.addr_bytes[j]);
+ }
+ printf("%02x\n", eth.addr_bytes[5]);
+ break;
}
printf("\n");
break;
@@ -332,16 +395,23 @@ main(int argc, char **argv)
}
}
+ check_all_ports_link_status(enabled_port_mask);
+
lcore_id = rte_get_next_lcore(-1, 1, 0);
if (lcore_id == RTE_MAX_LCORE) {
- RTE_LOG(ERR, EAL, "A minimum of two cores are required to run "
+ RTE_LOG(ERR, EAL, "A minimum of three cores are required to run "
"application\n");
return 0;
}
-
- check_all_ports_link_status(nb_ports, enabled_port_mask);
+ printf("Running channel monitor on lcore id %d\n", lcore_id);
rte_eal_remote_launch(run_monitor, NULL, lcore_id);
+ lcore_id = rte_get_next_lcore(lcore_id, 1, 0);
+ if (lcore_id == RTE_MAX_LCORE) {
+ RTE_LOG(ERR, EAL, "A minimum of three cores are required to run "
+ "application\n");
+ return 0;
+ }
if (power_manager_init() < 0) {
printf("Unable to initialize power manager\n");
return -1;
@@ -350,8 +420,17 @@ main(int argc, char **argv)
printf("Unable to initialize channel manager\n");
return -1;
}
+
+ printf("Running core monitor on lcore id %d\n", lcore_id);
+ rte_eal_remote_launch(run_core_monitor, NULL, lcore_id);
+
run_cli(NULL);
+ branch_monitor_exit();
+
rte_eal_mp_wait_lcore();
+
+ free(ci->cd);
+
return 0;
}
diff --git a/examples/vm_power_manager/meson.build b/examples/vm_power_manager/meson.build
new file mode 100644
index 00000000..c370d747
--- /dev/null
+++ b/examples/vm_power_manager/meson.build
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2018 Intel Corporation
+
+# meson file, for building this example as part of a main DPDK build.
+#
+# To build this example as a standalone application with an already-installed
+# DPDK instance, use 'make'
+
+# Example app currently unsupported by meson build
+build = false
diff --git a/examples/vm_power_manager/oob_monitor.h b/examples/vm_power_manager/oob_monitor.h
new file mode 100644
index 00000000..b96e08df
--- /dev/null
+++ b/examples/vm_power_manager/oob_monitor.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Intel Corporation
+ */
+
+#ifndef OOB_MONITOR_H_
+#define OOB_MONITOR_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/**
+ * Setup the Branch Monitor resources required to initialize epoll.
+ * Must be called first before calling other functions.
+ *
+ * @return
+ * - 0 on success.
+ * - Negative on error.
+ */
+int branch_monitor_init(void);
+
+/**
+ * Run the OOB branch monitor, loops forever on on epoll_wait.
+ *
+ *
+ * @return
+ * None
+ */
+void run_branch_monitor(void);
+
+/**
+ * Exit the OOB Branch Monitor.
+ *
+ * @return
+ * None
+ */
+void branch_monitor_exit(void);
+
+/**
+ * Add a core to the list of cores to monitor.
+ *
+ * @param core
+ * Core Number
+ *
+ * @return
+ * - 0 on success.
+ * - Negative on error.
+ */
+int add_core_to_monitor(int core);
+
+/**
+ * Remove a previously added core from core list.
+ *
+ * @param core
+ * Core Number
+ *
+ * @return
+ * - 0 on success.
+ * - Negative on error.
+ */
+int remove_core_from_monitor(int core);
+
+#ifdef __cplusplus
+}
+#endif
+
+
+#endif /* OOB_MONITOR_H_ */
diff --git a/examples/vm_power_manager/oob_monitor_nop.c b/examples/vm_power_manager/oob_monitor_nop.c
new file mode 100644
index 00000000..7e7b8bc1
--- /dev/null
+++ b/examples/vm_power_manager/oob_monitor_nop.c
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2014 Intel Corporation
+ */
+
+#include "oob_monitor.h"
+
+void branch_monitor_exit(void)
+{
+}
+
+__attribute__((unused)) static float
+apply_policy(__attribute__((unused)) int core)
+{
+ return 0.0;
+}
+
+int
+add_core_to_monitor(__attribute__((unused)) int core)
+{
+ return 0;
+}
+
+int
+remove_core_from_monitor(__attribute__((unused)) int core)
+{
+ return 0;
+}
+
+int
+branch_monitor_init(void)
+{
+ return 0;
+}
+
+void
+run_branch_monitor(void)
+{
+}
diff --git a/examples/vm_power_manager/oob_monitor_x86.c b/examples/vm_power_manager/oob_monitor_x86.c
new file mode 100644
index 00000000..589c604e
--- /dev/null
+++ b/examples/vm_power_manager/oob_monitor_x86.c
@@ -0,0 +1,258 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Intel Corporation
+ */
+
+#include <unistd.h>
+#include <fcntl.h>
+#include <rte_log.h>
+
+#include "oob_monitor.h"
+#include "power_manager.h"
+#include "channel_manager.h"
+
+static volatile unsigned run_loop = 1;
+static uint64_t g_branches, g_branch_misses;
+static int g_active;
+
+void branch_monitor_exit(void)
+{
+ run_loop = 0;
+}
+
+/* Number of microseconds between each poll */
+#define INTERVAL 100
+#define PRINT_LOOP_COUNT (1000000/INTERVAL)
+#define IA32_PERFEVTSEL0 0x186
+#define IA32_PERFEVTSEL1 0x187
+#define IA32_PERFCTR0 0xc1
+#define IA32_PERFCTR1 0xc2
+#define IA32_PERFEVT_BRANCH_HITS 0x05300c4
+#define IA32_PERFEVT_BRANCH_MISS 0x05300c5
+
+static float
+apply_policy(int core)
+{
+ struct core_info *ci;
+ uint64_t counter;
+ uint64_t branches, branch_misses;
+ uint32_t last_branches, last_branch_misses;
+ int hits_diff, miss_diff;
+ float ratio;
+ int ret;
+
+ g_active = 0;
+ ci = get_core_info();
+
+ last_branches = ci->cd[core].last_branches;
+ last_branch_misses = ci->cd[core].last_branch_misses;
+
+ ret = pread(ci->cd[core].msr_fd, &counter,
+ sizeof(counter), IA32_PERFCTR0);
+ if (ret < 0)
+ RTE_LOG(ERR, POWER_MANAGER,
+ "unable to read counter for core %u\n",
+ core);
+ branches = counter;
+
+ ret = pread(ci->cd[core].msr_fd, &counter,
+ sizeof(counter), IA32_PERFCTR1);
+ if (ret < 0)
+ RTE_LOG(ERR, POWER_MANAGER,
+ "unable to read counter for core %u\n",
+ core);
+ branch_misses = counter;
+
+
+ ci->cd[core].last_branches = branches;
+ ci->cd[core].last_branch_misses = branch_misses;
+
+ hits_diff = (int)branches - (int)last_branches;
+ if (hits_diff <= 0) {
+ /* Likely a counter overflow condition, skip this round */
+ return -1.0;
+ }
+
+ miss_diff = (int)branch_misses - (int)last_branch_misses;
+ if (miss_diff <= 0) {
+ /* Likely a counter overflow condition, skip this round */
+ return -1.0;
+ }
+
+ g_branches = hits_diff;
+ g_branch_misses = miss_diff;
+
+ if (hits_diff < (INTERVAL*100)) {
+ /* Likely no workload running on this core. Skip. */
+ return -1.0;
+ }
+
+ ratio = (float)miss_diff * (float)100 / (float)hits_diff;
+
+ if (ratio < ci->branch_ratio_threshold)
+ power_manager_scale_core_min(core);
+ else
+ power_manager_scale_core_max(core);
+
+ g_active = 1;
+ return ratio;
+}
+
+int
+add_core_to_monitor(int core)
+{
+ struct core_info *ci;
+ char proc_file[UNIX_PATH_MAX];
+ int ret;
+
+ ci = get_core_info();
+
+ if (core < ci->core_count) {
+ long setup;
+
+ snprintf(proc_file, UNIX_PATH_MAX, "/dev/cpu/%d/msr", core);
+ ci->cd[core].msr_fd = open(proc_file, O_RDWR | O_SYNC);
+ if (ci->cd[core].msr_fd < 0) {
+ RTE_LOG(ERR, POWER_MANAGER,
+ "Error opening MSR file for core %d "
+ "(is msr kernel module loaded?)\n",
+ core);
+ return -1;
+ }
+ /*
+ * Set up branch counters
+ */
+ setup = IA32_PERFEVT_BRANCH_HITS;
+ ret = pwrite(ci->cd[core].msr_fd, &setup,
+ sizeof(setup), IA32_PERFEVTSEL0);
+ if (ret < 0) {
+ RTE_LOG(ERR, POWER_MANAGER,
+ "unable to set counter for core %u\n",
+ core);
+ return ret;
+ }
+ setup = IA32_PERFEVT_BRANCH_MISS;
+ ret = pwrite(ci->cd[core].msr_fd, &setup,
+ sizeof(setup), IA32_PERFEVTSEL1);
+ if (ret < 0) {
+ RTE_LOG(ERR, POWER_MANAGER,
+ "unable to set counter for core %u\n",
+ core);
+ return ret;
+ }
+ /*
+ * Close the file and re-open as read only so
+ * as not to hog the resource
+ */
+ close(ci->cd[core].msr_fd);
+ ci->cd[core].msr_fd = open(proc_file, O_RDONLY);
+ if (ci->cd[core].msr_fd < 0) {
+ RTE_LOG(ERR, POWER_MANAGER,
+ "Error opening MSR file for core %d "
+ "(is msr kernel module loaded?)\n",
+ core);
+ return -1;
+ }
+ ci->cd[core].oob_enabled = 1;
+ }
+ return 0;
+}
+
+int
+remove_core_from_monitor(int core)
+{
+ struct core_info *ci;
+ char proc_file[UNIX_PATH_MAX];
+ int ret;
+
+ ci = get_core_info();
+
+ if (ci->cd[core].oob_enabled) {
+ long setup;
+
+ /*
+ * close the msr file, then reopen rw so we can
+ * disable the counters
+ */
+ if (ci->cd[core].msr_fd != 0)
+ close(ci->cd[core].msr_fd);
+ snprintf(proc_file, UNIX_PATH_MAX, "/dev/cpu/%d/msr", core);
+ ci->cd[core].msr_fd = open(proc_file, O_RDWR | O_SYNC);
+ if (ci->cd[core].msr_fd < 0) {
+ RTE_LOG(ERR, POWER_MANAGER,
+ "Error opening MSR file for core %d "
+ "(is msr kernel module loaded?)\n",
+ core);
+ return -1;
+ }
+ setup = 0x0; /* clear event */
+ ret = pwrite(ci->cd[core].msr_fd, &setup,
+ sizeof(setup), IA32_PERFEVTSEL0);
+ if (ret < 0) {
+ RTE_LOG(ERR, POWER_MANAGER,
+ "unable to set counter for core %u\n",
+ core);
+ return ret;
+ }
+ setup = 0x0; /* clear event */
+ ret = pwrite(ci->cd[core].msr_fd, &setup,
+ sizeof(setup), IA32_PERFEVTSEL1);
+ if (ret < 0) {
+ RTE_LOG(ERR, POWER_MANAGER,
+ "unable to set counter for core %u\n",
+ core);
+ return ret;
+ }
+
+ close(ci->cd[core].msr_fd);
+ ci->cd[core].msr_fd = 0;
+ ci->cd[core].oob_enabled = 0;
+ }
+ return 0;
+}
+
+int
+branch_monitor_init(void)
+{
+ return 0;
+}
+
+void
+run_branch_monitor(void)
+{
+ struct core_info *ci;
+ int print = 0;
+ float ratio;
+ int printed;
+ int reads = 0;
+
+ ci = get_core_info();
+
+ while (run_loop) {
+
+ if (!run_loop)
+ break;
+ usleep(INTERVAL);
+ int j;
+ print++;
+ printed = 0;
+ for (j = 0; j < ci->core_count; j++) {
+ if (ci->cd[j].oob_enabled) {
+ ratio = apply_policy(j);
+ if ((print > PRINT_LOOP_COUNT) && (g_active)) {
+ printf(" %d: %.4f {%lu} {%d}", j,
+ ratio, g_branches,
+ reads);
+ printed = 1;
+ reads = 0;
+ } else {
+ reads++;
+ }
+ }
+ }
+ if (print > PRINT_LOOP_COUNT) {
+ if (printed)
+ printf("\n");
+ print = 0;
+ }
+ }
+}
diff --git a/examples/vm_power_manager/parse.c b/examples/vm_power_manager/parse.c
new file mode 100644
index 00000000..8231533b
--- /dev/null
+++ b/examples/vm_power_manager/parse.c
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2014 Intel Corporation.
+ * Copyright(c) 2014 6WIND S.A.
+ */
+
+#include <string.h>
+#include <rte_log.h>
+#include "parse.h"
+
+/*
+ * Parse elem, the elem could be single number/range or group
+ * 1) A single number elem, it's just a simple digit. e.g. 9
+ * 2) A single range elem, two digits with a '-' between. e.g. 2-6
+ * 3) A group elem, combines multiple 1) or 2) e.g 0,2-4,6
+ * Within group, '-' used for a range separator;
+ * ',' used for a single number.
+ */
+int
+parse_set(const char *input, uint16_t set[], unsigned int num)
+{
+ unsigned int idx;
+ const char *str = input;
+ char *end = NULL;
+ unsigned int min, max;
+
+ memset(set, 0, num * sizeof(uint16_t));
+
+ while (isblank(*str))
+ str++;
+
+ /* only digit or left bracket is qualify for start point */
+ if (!isdigit(*str) || *str == '\0')
+ return -1;
+
+ while (isblank(*str))
+ str++;
+ if (*str == '\0')
+ return -1;
+
+ min = num;
+ do {
+
+ /* go ahead to the first digit */
+ while (isblank(*str))
+ str++;
+ if (!isdigit(*str))
+ return -1;
+
+ /* get the digit value */
+ errno = 0;
+ idx = strtoul(str, &end, 10);
+ if (errno || end == NULL || idx >= num)
+ return -1;
+
+ /* go ahead to separator '-' and ',' */
+ while (isblank(*end))
+ end++;
+ if (*end == '-') {
+ if (min == num)
+ min = idx;
+ else /* avoid continuous '-' */
+ return -1;
+ } else if ((*end == ',') || (*end == '\0')) {
+ max = idx;
+
+ if (min == num)
+ min = idx;
+
+ for (idx = RTE_MIN(min, max);
+ idx <= RTE_MAX(min, max); idx++) {
+ set[idx] = 1;
+ }
+ min = num;
+ } else
+ return -1;
+
+ str = end + 1;
+ } while (*end != '\0');
+
+ return str - input;
+}
diff --git a/examples/vm_power_manager/parse.h b/examples/vm_power_manager/parse.h
new file mode 100644
index 00000000..a5971e9a
--- /dev/null
+++ b/examples/vm_power_manager/parse.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Intel Corporation
+ */
+
+#ifndef PARSE_H_
+#define PARSE_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+int
+parse_set(const char *, uint16_t [], unsigned int);
+
+#ifdef __cplusplus
+}
+#endif
+
+
+#endif /* PARSE_H_ */
diff --git a/examples/vm_power_manager/power_manager.c b/examples/vm_power_manager/power_manager.c
index 35db2559..b7769c3c 100644
--- a/examples/vm_power_manager/power_manager.c
+++ b/examples/vm_power_manager/power_manager.c
@@ -12,20 +12,21 @@
#include <dirent.h>
#include <errno.h>
+#include <sys/sysinfo.h>
#include <sys/types.h>
#include <rte_log.h>
#include <rte_power.h>
#include <rte_spinlock.h>
+#include "channel_manager.h"
#include "power_manager.h"
-
-#define RTE_LOGTYPE_POWER_MANAGER RTE_LOGTYPE_USER1
+#include "oob_monitor.h"
#define POWER_SCALE_CORE(DIRECTION, core_num , ret) do { \
- if (core_num >= POWER_MGR_MAX_CPUS) \
+ if (core_num >= ci.core_count) \
return -1; \
- if (!(global_enabled_cpus & (1ULL << core_num))) \
+ if (!(ci.cd[core_num].global_enabled_cpus)) \
return -1; \
rte_spinlock_lock(&global_core_freq_info[core_num].power_sl); \
ret = rte_power_freq_##DIRECTION(core_num); \
@@ -36,7 +37,7 @@
int i; \
for (i = 0; core_mask; core_mask &= ~(1 << i++)) { \
if ((core_mask >> i) & 1) { \
- if (!(global_enabled_cpus & (1ULL << i))) \
+ if (!(ci.cd[i].global_enabled_cpus)) \
continue; \
rte_spinlock_lock(&global_core_freq_info[i].power_sl); \
if (rte_power_freq_##DIRECTION(i) != 1) \
@@ -54,63 +55,82 @@ struct freq_info {
static struct freq_info global_core_freq_info[POWER_MGR_MAX_CPUS];
-static uint64_t global_enabled_cpus;
+struct core_info ci;
#define SYSFS_CPU_PATH "/sys/devices/system/cpu/cpu%u/topology/core_id"
-static unsigned
-set_host_cpus_mask(void)
+struct core_info *
+get_core_info(void)
{
- char path[PATH_MAX];
- unsigned i;
- unsigned num_cpus = 0;
-
- for (i = 0; i < POWER_MGR_MAX_CPUS; i++) {
- snprintf(path, sizeof(path), SYSFS_CPU_PATH, i);
- if (access(path, F_OK) == 0) {
- global_enabled_cpus |= 1ULL << i;
- num_cpus++;
- } else
- return num_cpus;
+ return &ci;
+}
+
+int
+core_info_init(void)
+{
+ struct core_info *ci;
+ int i;
+
+ ci = get_core_info();
+
+ ci->core_count = get_nprocs_conf();
+ ci->branch_ratio_threshold = BRANCH_RATIO_THRESHOLD;
+ ci->cd = malloc(ci->core_count * sizeof(struct core_details));
+ if (!ci->cd) {
+ RTE_LOG(ERR, POWER_MANAGER, "Failed to allocate memory for core info.");
+ return -1;
}
- return num_cpus;
+ for (i = 0; i < ci->core_count; i++) {
+ ci->cd[i].global_enabled_cpus = 1;
+ ci->cd[i].oob_enabled = 0;
+ ci->cd[i].msr_fd = 0;
+ }
+ printf("%d cores in system\n", ci->core_count);
+ return 0;
}
int
power_manager_init(void)
{
- unsigned int i, num_cpus, num_freqs;
- uint64_t cpu_mask;
+ unsigned int i, num_cpus = 0, num_freqs = 0;
int ret = 0;
+ struct core_info *ci;
+
+ rte_power_set_env(PM_ENV_ACPI_CPUFREQ);
- num_cpus = set_host_cpus_mask();
- if (num_cpus == 0) {
- RTE_LOG(ERR, POWER_MANAGER, "Unable to detected host CPUs, please "
- "ensure that sufficient privileges exist to inspect sysfs\n");
+ ci = get_core_info();
+ if (!ci) {
+ RTE_LOG(ERR, POWER_MANAGER,
+ "Failed to get core info!\n");
return -1;
}
- rte_power_set_env(PM_ENV_ACPI_CPUFREQ);
- cpu_mask = global_enabled_cpus;
- for (i = 0; cpu_mask; cpu_mask &= ~(1 << i++)) {
- if (rte_power_init(i) < 0)
- RTE_LOG(ERR, POWER_MANAGER,
- "Unable to initialize power manager "
- "for core %u\n", i);
- num_freqs = rte_power_freqs(i, global_core_freq_info[i].freqs,
+
+ for (i = 0; i < ci->core_count; i++) {
+ if (ci->cd[i].global_enabled_cpus) {
+ if (rte_power_init(i) < 0)
+ RTE_LOG(ERR, POWER_MANAGER,
+ "Unable to initialize power manager "
+ "for core %u\n", i);
+ num_cpus++;
+ num_freqs = rte_power_freqs(i,
+ global_core_freq_info[i].freqs,
RTE_MAX_LCORE_FREQS);
- if (num_freqs == 0) {
- RTE_LOG(ERR, POWER_MANAGER,
- "Unable to get frequency list for core %u\n",
- i);
- global_enabled_cpus &= ~(1 << i);
- num_cpus--;
- ret = -1;
+ if (num_freqs == 0) {
+ RTE_LOG(ERR, POWER_MANAGER,
+ "Unable to get frequency list for core %u\n",
+ i);
+ ci->cd[i].oob_enabled = 0;
+ ret = -1;
+ }
+ global_core_freq_info[i].num_freqs = num_freqs;
+
+ rte_spinlock_init(&global_core_freq_info[i].power_sl);
}
- global_core_freq_info[i].num_freqs = num_freqs;
- rte_spinlock_init(&global_core_freq_info[i].power_sl);
+ if (ci->cd[i].oob_enabled)
+ add_core_to_monitor(i);
}
- RTE_LOG(INFO, POWER_MANAGER, "Detected %u host CPUs , enabled core mask:"
- " 0x%"PRIx64"\n", num_cpus, global_enabled_cpus);
+ RTE_LOG(INFO, POWER_MANAGER, "Managing %u cores out of %u available host cores\n",
+ num_cpus, ci->core_count);
return ret;
}
@@ -125,7 +145,7 @@ power_manager_get_current_frequency(unsigned core_num)
core_num, POWER_MGR_MAX_CPUS-1);
return -1;
}
- if (!(global_enabled_cpus & (1ULL << core_num)))
+ if (!(ci.cd[core_num].global_enabled_cpus))
return 0;
rte_spinlock_lock(&global_core_freq_info[core_num].power_sl);
@@ -144,15 +164,26 @@ power_manager_exit(void)
{
unsigned int i;
int ret = 0;
+ struct core_info *ci;
+
+ ci = get_core_info();
+ if (!ci) {
+ RTE_LOG(ERR, POWER_MANAGER,
+ "Failed to get core info!\n");
+ return -1;
+ }
- for (i = 0; global_enabled_cpus; global_enabled_cpus &= ~(1 << i++)) {
- if (rte_power_exit(i) < 0) {
- RTE_LOG(ERR, POWER_MANAGER, "Unable to shutdown power manager "
- "for core %u\n", i);
- ret = -1;
+ for (i = 0; i < ci->core_count; i++) {
+ if (ci->cd[i].global_enabled_cpus) {
+ if (rte_power_exit(i) < 0) {
+ RTE_LOG(ERR, POWER_MANAGER, "Unable to shutdown power manager "
+ "for core %u\n", i);
+ ret = -1;
+ }
+ ci->cd[i].global_enabled_cpus = 0;
}
+ remove_core_from_monitor(i);
}
- global_enabled_cpus = 0;
return ret;
}
@@ -268,10 +299,12 @@ int
power_manager_scale_core_med(unsigned int core_num)
{
int ret = 0;
+ struct core_info *ci;
+ ci = get_core_info();
if (core_num >= POWER_MGR_MAX_CPUS)
return -1;
- if (!(global_enabled_cpus & (1ULL << core_num)))
+ if (!(ci->cd[core_num].global_enabled_cpus))
return -1;
rte_spinlock_lock(&global_core_freq_info[core_num].power_sl);
ret = rte_power_set_freq(core_num,
diff --git a/examples/vm_power_manager/power_manager.h b/examples/vm_power_manager/power_manager.h
index 8a8a84aa..605b3c8f 100644
--- a/examples/vm_power_manager/power_manager.h
+++ b/examples/vm_power_manager/power_manager.h
@@ -8,6 +8,29 @@
#ifdef __cplusplus
extern "C" {
#endif
+struct core_details {
+ uint64_t last_branches;
+ uint64_t last_branch_misses;
+ uint16_t global_enabled_cpus;
+ uint16_t oob_enabled;
+ int msr_fd;
+};
+
+struct core_info {
+ uint16_t core_count;
+ struct core_details *cd;
+ float branch_ratio_threshold;
+};
+
+#define BRANCH_RATIO_THRESHOLD 0.1
+
+struct core_info *
+get_core_info(void);
+
+int
+core_info_init(void);
+
+#define RTE_LOGTYPE_POWER_MANAGER RTE_LOGTYPE_USER1
/* Maximum number of CPUS to manage */
#define POWER_MGR_MAX_CPUS 64