Ciara Loftus <ciara.lof...@intel.com> writes:
> A new other_config DB option has been added called 'vhost_driver_mode'.
> By default this is set to 'server' which is the mode of operation OVS
> with DPDK has used up until this point - whereby OVS creates and manages
> vHost user sockets.
>
> If set to 'client', OVS will act as the vHost client and connect to
> sockets created and managed by QEMU which acts as the server. This mode
> allows for reconnect capability, which allows vHost ports to resume
> normal connectivity in event of switch reset.
>
> QEMU v2.7.0+ is required when using OVS in client mode and QEMU in
> server mode.
>
> Signed-off-by: Ciara Loftus <ciara.lof...@intel.com>
> ---
> INSTALL.DPDK-ADVANCED.md | 27 +++++++++++++++++++++++++++
> NEWS | 1 +
> lib/netdev-dpdk.c | 37 ++++++++++++++++++++++++++-----------
> vswitchd/vswitch.xml | 13 +++++++++++++
> 4 files changed, 67 insertions(+), 11 deletions(-)
>
> diff --git a/INSTALL.DPDK-ADVANCED.md b/INSTALL.DPDK-ADVANCED.md
> index ec1de29..ad3e59e 100644
> --- a/INSTALL.DPDK-ADVANCED.md
> +++ b/INSTALL.DPDK-ADVANCED.md
> @@ -489,6 +489,33 @@ DPDK 16.07 supports two types of vhost:
> where `-L`: Changes the numbers of channels of the specified network
> device
> and `combined`: Changes the number of multi-purpose channels.
>
> + 4. Enable OVS vHost client-mode & vHost reconnect (OPTIONAL)
> +
> + By default, OVS DPDK acts as the vHost socket server and QEMU the
> + client. In QEMU v2.7 the option is available for QEMU to act as the
> + server. In order for this to work, OVS DPDK must be switched to
> 'client'
> + mode. This is possible by setting the 'vhost_driver_mode' DB entry to
> + 'client' like so:
> +
> + ```
> + ovs-vsctl set Open_vSwitch . other_config:vhost_driver_mode="client"
> + ```
> +
> + This must be done before the switch is launched. It cannot sucessfully
> + be changed after switch has launched.
> +
> + One must also append ',server' to the 'chardev' arguments on the QEMU
> + command line, to instruct QEMU to use vHost server mode, like so:
> +
> + ````
> + -chardev
> socket,id=char0,path=/usr/local/var/run/openvswitch/vhost0,server
> + ````
> +
> + One benefit of using this mode is the ability for vHost ports to
> + 'reconnect' in event of the switch crashing or being brought down.
> Once
> + it is brought back up, the vHost ports will reconnect automatically
> and
> + normal service will resume.
> +
> - VM Configuration with libvirt
>
> * change the user/group, access control policty and restart libvirtd.
> diff --git a/NEWS b/NEWS
> index f50b05e..08bac37 100644
> --- a/NEWS
> +++ b/NEWS
> @@ -53,6 +53,7 @@ Post-v2.5.0
> * PMD threads servicing vHost User ports can now come from the NUMA
> node that device memory is located on if CONFIG_RTE_LIBRTE_VHOST_NUMA
> is enabled in DPDK.
> + * OVS client mode for vHost and vHost reconnect (Requires QEMU 2.7)
> - ovs-benchmark: This utility has been removed due to lack of use and
> bitrot.
> - ovs-appctl:
> diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c
> index 9cf0b0c..6763039 100644
> --- a/lib/netdev-dpdk.c
> +++ b/lib/netdev-dpdk.c
> @@ -138,9 +138,11 @@ BUILD_ASSERT_DECL((MAX_NB_MBUF /
> ROUND_DOWN_POW2(MAX_NB_MBUF/MIN_NB_MBUF))
> * yet mapped to another queue. */
>
> #ifdef VHOST_CUSE
> -static char *cuse_dev_name = NULL; /* Character device cuse_dev_name. */
> +static char *cuse_dev_name = NULL; /* Character device cuse_dev_name. */
> +#else
> +static char *vhost_sock_dir = NULL; /* Location of vhost-user sockets */
> +static uint64_t vhost_driver_flags = 0; /* Denote whether client/server mode
> */
> #endif
> -static char *vhost_sock_dir = NULL; /* Location of vhost-user sockets */
>
> #define VHOST_ENQ_RETRY_NUM 8
>
> @@ -845,7 +847,6 @@ netdev_dpdk_vhost_user_construct(struct netdev *netdev)
> struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
> const char *name = netdev->name;
> int err;
> - uint64_t flags = 0;
>
> /* 'name' is appended to 'vhost_sock_dir' and used to create a socket in
> * the file system. '/' or '\' would traverse directories, so they're not
> @@ -868,14 +869,17 @@ netdev_dpdk_vhost_user_construct(struct netdev *netdev)
> snprintf(dev->vhost_id, sizeof(dev->vhost_id), "%s/%s",
> vhost_sock_dir, name);
>
> - err = rte_vhost_driver_register(dev->vhost_id, flags);
> + err = rte_vhost_driver_register(dev->vhost_id, vhost_driver_flags);
> if (err) {
> VLOG_ERR("vhost-user socket device setup failure for socket %s\n",
> dev->vhost_id);
> } else {
> - fatal_signal_add_file_to_unlink(dev->vhost_id);
> - VLOG_INFO("Socket %s created for vhost-user port %s\n",
> - dev->vhost_id, name);
> + if (!(vhost_driver_flags & RTE_VHOST_USER_CLIENT)) {
> + /* OVS server mode - OVS may delete the socket */
> + fatal_signal_add_file_to_unlink(dev->vhost_id);
> + VLOG_INFO("Socket %s created for vhost-user port %s\n",
> + dev->vhost_id, name);
> + }
> err = vhost_construct_helper(netdev);
> }
>
> @@ -945,7 +949,8 @@ netdev_dpdk_vhost_destruct(struct netdev *netdev)
>
> if (rte_vhost_driver_unregister(dev->vhost_id)) {
> VLOG_ERR("Unable to remove vhost-user socket %s", dev->vhost_id);
> - } else {
> + } else if (!(vhost_driver_flags & RTE_VHOST_USER_CLIENT)) {
> + /* OVS server mode - OVS may delete the socket */
> fatal_signal_remove_file_to_unlink(dev->vhost_id);
> }
>
> @@ -3208,6 +3213,7 @@ dpdk_init__(const struct smap *ovs_other_config)
> cpu_set_t cpuset;
> #ifndef VHOST_CUSE
> char *sock_dir_subcomponent;
> + const char *val;
> #endif
>
> if (!smap_get_bool(ovs_other_config, "dpdk-init", false)) {
> @@ -3218,8 +3224,8 @@ dpdk_init__(const struct smap *ovs_other_config)
> VLOG_INFO("DPDK Enabled, initializing");
>
> #ifdef VHOST_CUSE
> - if (process_vhost_flags("cuse-dev-name", xstrdup("vhost-net"),
> - PATH_MAX, ovs_other_config, &cuse_dev_name)) {
> + process_vhost_flags("cuse-dev-name", xstrdup("vhost-net"),
> + PATH_MAX, ovs_other_config, &cuse_dev_name);
> #else
> if (process_vhost_flags("vhost-sock-dir", xstrdup(ovs_rundir()),
> NAME_MAX, ovs_other_config,
> @@ -3243,8 +3249,17 @@ dpdk_init__(const struct smap *ovs_other_config)
> free(sock_dir_subcomponent);
> } else {
> vhost_sock_dir = sock_dir_subcomponent;
> -#endif
> }
> + val = smap_get(ovs_other_config, "vhost_driver_mode");
> + if (val != NULL && strncmp(val, "client", strlen(val)) == 0) {
> + vhost_driver_flags |= RTE_VHOST_USER_CLIENT;
> + VLOG_INFO("OVS client mode (QEMU server mode) selected for vHost");
> + } else {
> + /* default case */
> + vhost_driver_flags &= ~RTE_VHOST_USER_CLIENT;
> + VLOG_INFO("OVS server mode (QEMU client mode) selected for vHost");
> + }
Is it possible to just use the process_vhost_flags call for this section
instead? Do you think it would make sense for consistency?
> +#endif
>
> argv = grow_argv(&argv, 0, 1);
> argc = 1;
> diff --git a/vswitchd/vswitch.xml b/vswitchd/vswitch.xml
> index fed6f56..66007e5 100644
> --- a/vswitchd/vswitch.xml
> +++ b/vswitchd/vswitch.xml
> @@ -311,6 +311,19 @@
> </p>
> </column>
>
> + <column name="other_config" key="vhost_driver_mode"
> + type='{"type": "string", "enum": ["set", ["server",
> "client"]]}'>
> + <p>
> + Specifies which mode OVS will use for vHost. In 'server' mode, OVS
> + creates and destroys the vHost User sockets. In 'client' mode, OVS
> + attaches to sockets created by QEMU.
> + </p>
> + <p>
> + Defaults to 'server' mode. Changing this value requires restarting
> + the daemon.
> + </p>
> + </column>
> +
> <column name="other_config" key="n-handler-threads"
> type='{"type": "integer", "minInteger": 1}'>
> <p>
_______________________________________________
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
