mir/openvswitch
2
0
Fork 0
mirror of https://github.com/openvswitch/ovs synced 2025-10-13 14:07:02 +00:00
Code Issues Releases Wiki Activity

dpif-netdev: Only poll enabled vhost queues.

Browse Source 
We currently poll all available queues based on the max queue count
exchanged with the vhost peer and rely on the vhost library in DPDK to
check the vring status beneath.
This can lead to some overhead when we have a lot of unused queues.

To enhance the situation, we can skip the disabled queues.
On rxq notifications, we make use of the netdev's change_seq number so
that the pmd thread main loop can cache the queue state periodically.

$ ovs-appctl dpif-netdev/pmd-rxq-show
pmd thread numa_id 0 core_id 1:
  isolated : true
  port: dpdk0             queue-id:  0 (enabled)   pmd usage:  0 %
pmd thread numa_id 0 core_id 2:
  isolated : true
  port: vhost1            queue-id:  0 (enabled)   pmd usage:  0 %
  port: vhost3            queue-id:  0 (enabled)   pmd usage:  0 %
pmd thread numa_id 0 core_id 15:
  isolated : true
  port: dpdk1             queue-id:  0 (enabled)   pmd usage:  0 %
pmd thread numa_id 0 core_id 16:
  isolated : true
  port: vhost0            queue-id:  0 (enabled)   pmd usage:  0 %
  port: vhost2            queue-id:  0 (enabled)   pmd usage:  0 %

$ while true; do
  ovs-appctl dpif-netdev/pmd-rxq-show |awk '
  /port: / {
    tot++;
    if ($5 == "(enabled)") {
      en++;
    }
  }
  END {
    print "total: " tot ", enabled: " en
  }'
  sleep 1
done

total: 6, enabled: 2
total: 6, enabled: 2
...

 # Started vm, virtio devices are bound to kernel driver which enables
 # F_MQ + all queue pairs
total: 6, enabled: 2
total: 66, enabled: 66
...

 # Unbound vhost0 and vhost1 from the kernel driver
total: 66, enabled: 66
total: 66, enabled: 34
...

 # Configured kernel bound devices to use only 1 queue pair
total: 66, enabled: 34
total: 66, enabled: 19
total: 66, enabled: 4
...

 # While rebooting the vm
total: 66, enabled: 4
total: 66, enabled: 2
...
total: 66, enabled: 66
...

 # After shutting down the vm
total: 66, enabled: 66
total: 66, enabled: 2

Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Ilya Maximets <i.maximets@samsung.com>
Signed-off-by: Ian Stokes <ian.stokes@intel.com>
This commit is contained in:
David Marchand
2019-04-25 17:22:08 +02:00
committed by Ian Stokes
parent 934a85a877
commit 35c91567c8
6 changed files with 115 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
lib/dpif-netdev.c
View File

@@ -592,6 +592,8 @@ struct polled_queue {
struct dp_netdev_rxq *rxq;
odp_port_t port_no;
bool emc_enabled;
bool rxq_enabled;
uint64_t change_seq;
};
/* Contained by struct dp_netdev_pmd_thread's 'poll_list' member. */
@@ -1164,6 +1166,8 @@ pmd_info_show_rxq(struct ds *reply, struct dp_netdev_pmd_thread *pmd)
}
ds_put_format(reply, " port: %-16s queue-id: %2d", name,
netdev_rxq_get_queue_id(list[i].rxq->rx));
ds_put_format(reply, " %s", netdev_rxq_enabled(list[i].rxq->rx)
? "(enabled) " : "(disabled)");
ds_put_format(reply, " pmd usage: ");
if (total_cycles) {
ds_put_format(reply, "%2"PRIu64"",
@@ -5202,6 +5206,11 @@ dpif_netdev_run(struct dpif *dpif)
}
for (i = 0; i < port->n_rxq; i++) {
if (!netdev_rxq_enabled(port->rxqs[i].rx)) {
continue;
}
if (dp_netdev_process_rxq_port(non_pmd,
&port->rxqs[i],
port->port_no)) {
@@ -5375,6 +5384,9 @@ pmd_load_queues_and_ports(struct dp_netdev_pmd_thread *pmd,
poll_list[i].rxq = poll->rxq;
poll_list[i].port_no = poll->rxq->port->port_no;
poll_list[i].emc_enabled = poll->rxq->port->emc_enabled;
poll_list[i].rxq_enabled = netdev_rxq_enabled(poll->rxq->rx);
poll_list[i].change_seq =
netdev_get_change_seq(poll->rxq->port->netdev);
i++;
}
@@ -5440,6 +5452,10 @@ reload:
for (i = 0; i < poll_cnt; i++) {
if (!poll_list[i].rxq_enabled) {
continue;
}
if (poll_list[i].emc_enabled) {
atomic_read_relaxed(&pmd->dp->emc_insert_min,
&pmd->ctx.emc_insert_min);
@@ -5476,6 +5492,16 @@ reload:
if (reload) {
break;
}
for (i = 0; i < poll_cnt; i++) {
uint64_t current_seq =
netdev_get_change_seq(poll_list[i].rxq->port->netdev);
if (poll_list[i].change_seq != current_seq) {
poll_list[i].change_seq = current_seq;
poll_list[i].rxq_enabled =
netdev_rxq_enabled(poll_list[i].rxq->rx);
}
}
}
pmd_perf_end_iteration(s, rx_packets, tx_packets,
pmd_perf_metrics_enabled(pmd));

58
lib/netdev-dpdk.c
View File

@@ -423,6 +423,9 @@ struct netdev_dpdk {
OVSRCU_TYPE(struct ingress_policer *) ingress_policer;
uint32_t policer_rate;
uint32_t policer_burst;
/* Array of vhost rxq states, see vring_state_changed. */
bool *vhost_rxq_enabled;
);
PADDED_MEMBERS(CACHE_LINE_SIZE,
@@ -1234,8 +1237,14 @@ vhost_common_construct(struct netdev *netdev)
int socket_id = rte_lcore_to_socket_id(rte_get_master_lcore());
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
dev->vhost_rxq_enabled = dpdk_rte_mzalloc(OVS_VHOST_MAX_QUEUE_NUM *
sizeof *dev->vhost_rxq_enabled);
if (!dev->vhost_rxq_enabled) {
return ENOMEM;
}
dev->tx_q = netdev_dpdk_alloc_txq(OVS_VHOST_MAX_QUEUE_NUM);
if (!dev->tx_q) {
rte_free(dev->vhost_rxq_enabled);
return ENOMEM;
}
@@ -1448,6 +1457,7 @@ netdev_dpdk_vhost_destruct(struct netdev *netdev)
vhost_id = dev->vhost_id;
dev->vhost_id = NULL;
rte_free(dev->vhost_rxq_enabled);
common_destruct(dev);
@@ -2202,6 +2212,14 @@ netdev_dpdk_vhost_rxq_recv(struct netdev_rxq *rxq,
return 0;
}
static bool
netdev_dpdk_vhost_rxq_enabled(struct netdev_rxq *rxq)
{
struct netdev_dpdk *dev = netdev_dpdk_cast(rxq->netdev);
return dev->vhost_rxq_enabled[rxq->queue_id];
}
static int
netdev_dpdk_rxq_recv(struct netdev_rxq *rxq, struct dp_packet_batch *batch,
int *qfill)
@@ -3565,6 +3583,8 @@ destroy_device(int vid)
ovs_mutex_lock(&dev->mutex);
dev->vhost_reconfigured = false;
ovsrcu_index_set(&dev->vid, -1);
memset(dev->vhost_rxq_enabled, 0,
dev->up.n_rxq * sizeof *dev->vhost_rxq_enabled);
netdev_dpdk_txq_map_clear(dev);
netdev_change_seq_changed(&dev->up);
@@ -3599,24 +3619,30 @@ vring_state_changed(int vid, uint16_t queue_id, int enable)
struct netdev_dpdk *dev;
bool exists = false;
int qid = queue_id / VIRTIO_QNUM;
bool is_rx = (queue_id % VIRTIO_QNUM) == VIRTIO_TXQ;
char ifname[IF_NAME_SZ];
rte_vhost_get_ifname(vid, ifname, sizeof ifname);
if (queue_id % VIRTIO_QNUM == VIRTIO_TXQ) {
return 0;
}
ovs_mutex_lock(&dpdk_mutex);
LIST_FOR_EACH (dev, list_node, &dpdk_list) {
ovs_mutex_lock(&dev->mutex);
if (nullable_string_is_equal(ifname, dev->vhost_id)) {
if (enable) {
dev->tx_q[qid].map = qid;
if (is_rx) {
bool old_state = dev->vhost_rxq_enabled[qid];
dev->vhost_rxq_enabled[qid] = enable != 0;
if (old_state != dev->vhost_rxq_enabled[qid]) {
netdev_change_seq_changed(&dev->up);
}
} else {
dev->tx_q[qid].map = OVS_VHOST_QUEUE_DISABLED;
if (enable) {
dev->tx_q[qid].map = qid;
} else {
dev->tx_q[qid].map = OVS_VHOST_QUEUE_DISABLED;
}
netdev_dpdk_remap_txqs(dev);
}
netdev_dpdk_remap_txqs(dev);
exists = true;
ovs_mutex_unlock(&dev->mutex);
break;
@@ -3626,9 +3652,9 @@ vring_state_changed(int vid, uint16_t queue_id, int enable)
ovs_mutex_unlock(&dpdk_mutex);
if (exists) {
VLOG_INFO("State of queue %d ( tx_qid %d ) of vhost device '%s' "
"changed to \'%s\'", queue_id, qid, ifname,
(enable == 1) ? "enabled" : "disabled");
VLOG_INFO("State of queue %d ( %s_qid %d ) of vhost device '%s' "
"changed to \'%s\'", queue_id, is_rx == true ? "rx" : "tx",
qid, ifname, (enable == 1) ? "enabled" : "disabled");
} else {
VLOG_INFO("vHost Device '%s' not found", ifname);
return -1;
@@ -4087,6 +4113,10 @@ dpdk_vhost_reconfigure_helper(struct netdev_dpdk *dev)
dev->up.n_rxq = dev->requested_n_rxq;
int err;
/* Always keep RX queue 0 enabled for implementations that won't
* report vring states. */
dev->vhost_rxq_enabled[0] = true;
/* Enable TX queue 0 by default if it wasn't disabled. */
if (dev->tx_q[0].map == OVS_VHOST_QUEUE_MAP_UNKNOWN) {
dev->tx_q[0].map = 0;
@@ -4324,7 +4354,8 @@ static const struct netdev_class dpdk_vhost_class = {
.get_stats = netdev_dpdk_vhost_get_stats,
.get_status = netdev_dpdk_vhost_user_get_status,
.reconfigure = netdev_dpdk_vhost_reconfigure,
.rxq_recv = netdev_dpdk_vhost_rxq_recv
.rxq_recv = netdev_dpdk_vhost_rxq_recv,
.rxq_enabled = netdev_dpdk_vhost_rxq_enabled,
};
static const struct netdev_class dpdk_vhost_client_class = {
@@ -4338,7 +4369,8 @@ static const struct netdev_class dpdk_vhost_client_class = {
.get_stats = netdev_dpdk_vhost_get_stats,
.get_status = netdev_dpdk_vhost_user_get_status,
.reconfigure = netdev_dpdk_vhost_client_reconfigure,
.rxq_recv = netdev_dpdk_vhost_rxq_recv
.rxq_recv = netdev_dpdk_vhost_rxq_recv,
.rxq_enabled = netdev_dpdk_vhost_rxq_enabled,
};
void

7
lib/netdev-provider.h
View File

@@ -774,6 +774,13 @@ struct netdev_class {
void (*rxq_destruct)(struct netdev_rxq *);
void (*rxq_dealloc)(struct netdev_rxq *);
/* Retrieves the current state of rx queue. 'false' means that queue won't
* get traffic in a short term and could be not polled.
*
* This function may be set to null if it would always return 'true'
* anyhow. */
bool (*rxq_enabled)(struct netdev_rxq *);
/* Attempts to receive a batch of packets from 'rx'. In 'batch', the
* caller supplies 'packets' as the pointer to the beginning of an array
* of NETDEV_MAX_BURST pointers to dp_packet. If successful, the

10
lib/netdev.c
View File

@@ -686,6 +686,16 @@ netdev_rxq_close(struct netdev_rxq *rx)
}
}
bool netdev_rxq_enabled(struct netdev_rxq *rx)
{
bool enabled = true;
if (rx->netdev->netdev_class->rxq_enabled) {
enabled = rx->netdev->netdev_class->rxq_enabled(rx);
}
return enabled;
}
/* Attempts to receive a batch of packets from 'rx'. 'batch' should point to
* the beginning of an array of NETDEV_MAX_BURST pointers to dp_packet. If
* successful, this function stores pointers to up to NETDEV_MAX_BURST

1
lib/netdev.h
View File

@@ -183,6 +183,7 @@ enum netdev_pt_mode netdev_get_pt_mode(const struct netdev *);
/* Packet reception. */
int netdev_rxq_open(struct netdev *, struct netdev_rxq **, int id);
void netdev_rxq_close(struct netdev_rxq *);
bool netdev_rxq_enabled(struct netdev_rxq *);
const char *netdev_rxq_get_name(const struct netdev_rxq *);
int netdev_rxq_get_queue_id(const struct netdev_rxq *);

52
tests/pmd.at
View File

@@ -14,7 +14,7 @@ parse_pmd_rxq_show () {
# of the core on one line
# 'port:' port_name 'queue_id:' rxq_id rxq_id rxq_id rxq_id
parse_pmd_rxq_show_group () {
awk '/port:/ {print $1, $2, $3, $4, $12, $20, $28}'
awk '/port:/ {print $1, $2, $3, $4, $13, $22, $31}'
}
# Given the output of `ovs-appctl dpctl/dump-flows`, prints a list of flows
@@ -72,7 +72,7 @@ CHECK_PMD_THREADS_CREATED()
AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | sed SED_NUMA_CORE_PATTERN], [0], [dnl
pmd thread numa_id <cleared> core_id <cleared>:
isolated : false
port: p0 queue-id: 0 pmd usage: NOT AVAIL
port: p0 queue-id: 0 (enabled) pmd usage: NOT AVAIL
])
AT_CHECK([ovs-appctl dpif/show | sed 's/\(tx_queues=\)[[0-9]]*/\1<cleared>/g'], [0], [dnl
@@ -103,14 +103,14 @@ dummy@ovs-dummy: hit:0 missed:0
AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | sed SED_NUMA_CORE_PATTERN], [0], [dnl
pmd thread numa_id <cleared> core_id <cleared>:
isolated : false
port: p0 queue-id: 0 pmd usage: NOT AVAIL
port: p0 queue-id: 1 pmd usage: NOT AVAIL
port: p0 queue-id: 2 pmd usage: NOT AVAIL
port: p0 queue-id: 3 pmd usage: NOT AVAIL
port: p0 queue-id: 4 pmd usage: NOT AVAIL
port: p0 queue-id: 5 pmd usage: NOT AVAIL
port: p0 queue-id: 6 pmd usage: NOT AVAIL
port: p0 queue-id: 7 pmd usage: NOT AVAIL
port: p0 queue-id: 0 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 1 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 2 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 3 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 4 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 5 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 6 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 7 (enabled) pmd usage: NOT AVAIL
])
OVS_VSWITCHD_STOP
@@ -134,14 +134,14 @@ dummy@ovs-dummy: hit:0 missed:0
AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | sed SED_NUMA_CORE_PATTERN], [0], [dnl
pmd thread numa_id <cleared> core_id <cleared>:
isolated : false
port: p0 queue-id: 0 pmd usage: NOT AVAIL
port: p0 queue-id: 1 pmd usage: NOT AVAIL
port: p0 queue-id: 2 pmd usage: NOT AVAIL
port: p0 queue-id: 3 pmd usage: NOT AVAIL
port: p0 queue-id: 4 pmd usage: NOT AVAIL
port: p0 queue-id: 5 pmd usage: NOT AVAIL
port: p0 queue-id: 6 pmd usage: NOT AVAIL
port: p0 queue-id: 7 pmd usage: NOT AVAIL
port: p0 queue-id: 0 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 1 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 2 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 3 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 4 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 5 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 6 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 7 (enabled) pmd usage: NOT AVAIL
])
AT_CHECK([ovs-vsctl set Open_vSwitch . other_config:pmd-rxq-assign=cycles])
@@ -167,14 +167,14 @@ CHECK_PMD_THREADS_CREATED([1], [], [+$TMP])
AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | sed SED_NUMA_CORE_PATTERN], [0], [dnl
pmd thread numa_id <cleared> core_id <cleared>:
isolated : false
port: p0 queue-id: 0 pmd usage: NOT AVAIL
port: p0 queue-id: 1 pmd usage: NOT AVAIL
port: p0 queue-id: 2 pmd usage: NOT AVAIL
port: p0 queue-id: 3 pmd usage: NOT AVAIL
port: p0 queue-id: 4 pmd usage: NOT AVAIL
port: p0 queue-id: 5 pmd usage: NOT AVAIL
port: p0 queue-id: 6 pmd usage: NOT AVAIL
port: p0 queue-id: 7 pmd usage: NOT AVAIL
port: p0 queue-id: 0 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 1 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 2 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 3 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 4 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 5 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 6 (enabled) pmd usage: NOT AVAIL
port: p0 queue-id: 7 (enabled) pmd usage: NOT AVAIL
])
OVS_VSWITCHD_STOP