38. Vhost Library
The vhost library implements a user space virtio net server allowing the user to manipulate the virtio ring directly. In another words, it allows the user to fetch/put packets from/to the VM virtio net device. To achieve this, a vhost library should be able to:
Access the guest memory:
For QEMU, this is done by using the
-object memory-backend-file,share=on,...option. Which means QEMU will create a file to serve as the guest RAM. The
share=onoption allows another process to map that file, which means it can access the guest RAM.
Know all the necessary information about the vring:
Information such as where the available ring is stored. Vhost defines some messages (passed through a Unix domain socket file) to tell the backend all the information it needs to know how to manipulate the vring.
38.1. Vhost API Overview
The following is an overview of some key Vhost API functions:
This function registers a vhost driver into the system.
pathspecifies the Unix domain socket file path.
Currently supported flags are:
DPDK vhost-user will act as the client when this flag is given. See below for an explanation.
When DPDK vhost-user acts as the client it will keep trying to reconnect to the server (QEMU) until it succeeds. This is useful in two cases:
- When QEMU is not started yet.
- When QEMU restarts (for example due to a guest OS reboot).
This reconnect option is enabled by default. However, it can be turned off by setting this flag.
Dequeue zero copy will be enabled when this flag is set. It is disabled by default.
There are some truths (including limitations) you might want to know while setting this flag:
zero copy is not good for small packets (typically for packet size below 512).
zero copy is really good for VM2VM case. For iperf between two VMs, the boost could be above 70% (when TSO is enableld).
for VM2NIC case, the
nb_tx_deschas to be small enough: <= 64 if virtio indirect feature is not enabled and <= 128 if it is enabled.
This is because when dequeue zero copy is enabled, guest Tx used vring will be updated only when corresponding mbuf is freed. Thus, the nb_tx_desc has to be small enough so that the PMD driver will run out of available Tx descriptors and free mbufs timely. Otherwise, guest Tx vring would be starved.
Guest memory should be backended with huge pages to achieve better performance. Using 1G page size is the best.
When dequeue zero copy is enabled, the guest phys address and host phys address mapping has to be established. Using non-huge pages means far more page segments. To make it simple, DPDK vhost does a linear search of those segments, thus the fewer the segments, the quicker we will get the mapping. NOTE: we may speed it by using tree searching in future.
IOMMU support will be enabled when this flag is set. It is disabled by default.
Enabling this flag makes possible to use guest vIOMMU to protect vhost from accessing memory the virtio device isn’t allowed to, when the feature is negotiated and an IOMMU device is declared.
However, this feature enables vhost-user’s reply-ack protocol feature, which implementation is buggy in Qemu v2.7.0-v2.9.0 when doing multiqueue. Enabling this flag with these Qemu version results in Qemu being blocked when multiple queue pairs are declared.
This function sets the feature bits the vhost-user driver supports. The vhost-user driver could be vhost-user net, yet it could be something else, say, vhost-user SCSI.
This function registers a set of callbacks, to let DPDK applications take the appropriate action when some events happen. The following events are currently supported:
This callback is invoked when a virtio device becomes ready.
vidis the vhost device ID.
This callback is invoked when a virtio device is paused or shut down.
vring_state_changed(int vid, uint16_t queue_id, int enable)
This callback is invoked when a specific queue’s state is changed, for example to enabled or disabled.
features_changed(int vid, uint64_t features)
This callback is invoked when the features is changed. For example,
VHOST_F_LOG_ALLwill be set/cleared at the start/end of live migration, respectively.
This callback is invoked on new vhost-user socket connection. If DPDK acts as the server the device should not be deleted before
destroy_connectioncallback is received.
This callback is invoked when vhost-user socket connection is closed. It indicates that device with id
vidis no longer in use and can be safely deleted.
This function disables/enables some features. For example, it can be used to disable mergeable buffers and TSO features, which both are enabled by default.
This function triggers the vhost-user negotiation. It should be invoked at the end of initializing a vhost-user driver.
rte_vhost_enqueue_burst(vid, queue_id, pkts, count)
countpackets from host to guest.
rte_vhost_dequeue_burst(vid, queue_id, mbuf_pool, pkts, count)
countpackets from guest, and stored them at
38.2. Vhost-user Implementations
Vhost-user uses Unix domain sockets for passing messages. This means the DPDK vhost-user implementation has two options:
DPDK vhost-user acts as the server.
DPDK will create a Unix domain socket server file and listen for connections from the frontend.
Note, this is the default mode, and the only mode before DPDK v16.07.
DPDK vhost-user acts as the client.
Unlike the server mode, this mode doesn’t create the socket file; it just tries to connect to the server (which responses to create the file instead).
When the DPDK vhost-user application restarts, DPDK vhost-user will try to connect to the server again. This is how the “reconnect” feature works.
- The “reconnect” feature requires QEMU v2.7 (or above).
- The vhost supported features must be exactly the same before and after the restart. For example, if TSO is disabled and then enabled, nothing will work and issues undefined might happen.
No matter which mode is used, once a connection is established, DPDK vhost-user will start receiving and processing vhost messages from QEMU.
For messages with a file descriptor, the file descriptor can be used directly in the vhost process as it is already installed by the Unix domain socket.
The supported vhost messages are:
VHOST_SET_MEM_TABLE message, QEMU will send information for each
memory region and its file descriptor in the ancillary data of the message.
The file descriptor is used to map that region.
VHOST_SET_VRING_KICK is used as the signal to put the vhost device into
the data plane, and
VHOST_GET_VRING_BASE is used as the signal to remove
the vhost device from the data plane.
When the socket connection is closed, vhost will destroy the device.
38.3. Vhost supported vSwitch reference
For more vhost details and how to support vhost in vSwitch, please refer to the vhost example in the DPDK Sample Applications Guide.