[ovs-dev] [PATCH v2 1/1] DPDK: Remove support for vhost-user zero-copy.

Ian Stokes ian.stokes at intel.com
Thu Sep 10 17:30:59 UTC 2020


Support for vhost-user dequeue zero-copy was deprecated in OVS 2.14 with
the aim of removing it for OVS 2.15.

OVS only supports zero copy for vhost client mode, as such it will cease
to function due to DPDK commit [1]

Also DPDK is set to remove zero-copy functionality in DPDK 20.11 as
referenced by commit [2]

As such remove support from OVS.

[1] 715070ea10e6 ("vhost: prevent zero-copy with incompatible client mode")
[2] d21003c9dafa ("doc: announce removal of vhost zero-copy dequeue")

Signed-off-by: Ian Stokes <ian.stokes at intel.com>

---
v1 -> v2
* Remove reference to zero copy in vhost post copy documentation.
* Add DPDK commits that have influenced OVS decision to remove support
  for zero-copy.
* Correct NEWS to reference removal rather than deprecation of zc.
---
 Documentation/topics/dpdk/vhost-user.rst | 76 --------------------------------
 NEWS                                     |  2 +
 lib/netdev-dpdk.c                        | 25 -----------
 vswitchd/vswitch.xml                     | 11 -----
 4 files changed, 2 insertions(+), 112 deletions(-)

diff --git a/Documentation/topics/dpdk/vhost-user.rst b/Documentation/topics/dpdk/vhost-user.rst
index 4af738d11..3be8f8b5e 100644
--- a/Documentation/topics/dpdk/vhost-user.rst
+++ b/Documentation/topics/dpdk/vhost-user.rst
@@ -339,10 +339,6 @@ The default value is ``false``.
     migration recovery was fixed for post-copy in 3.0 and few additional bug
     fixes (like userfaulfd leak) was released in 3.0.1.
 
-    DPDK Post-copy feature requires avoiding to populate the guest memory
-    (application must not call mlock* syscall). So enabling mlockall and
-    dequeue zero-copy features is mis-compatible with post-copy feature.
-
     Note that during migration of vhost-user device, PMD threads hang for the
     time of faulted pages download from source host. Transferring 1GB hugepage
     across a 10Gbps link possibly unacceptably slow. So recommended hugepage
@@ -553,78 +549,6 @@ shown with::
 
   $ ovs-vsctl get Interface dpdkvhostclient0 statistics:ovs_tx_retries
 
-vhost-user Dequeue Zero Copy (experimental)
--------------------------------------------
-
-.. warning::
-
-   vhost-user Dequeue Zero Copy is deprecated in OVS and will be removed in
-   the next release.
-
-Normally when dequeuing a packet from a vHost User device, a memcpy operation
-must be used to copy that packet from guest address space to host address
-space. This memcpy can be removed by enabling dequeue zero-copy like so::
-
-    $ ovs-vsctl add-port br0 dpdkvhostuserclient0 -- set Interface \
-        dpdkvhostuserclient0 type=dpdkvhostuserclient \
-        options:vhost-server-path=/tmp/dpdkvhostclient0 \
-        options:dq-zero-copy=true
-
-With this feature enabled, a reference (pointer) to the packet is passed to
-the host, instead of a copy of the packet. Removing this memcpy can give a
-performance improvement for some use cases, for example switching large packets
-between different VMs. However additional packet loss may be observed.
-
-Note that the feature is disabled by default and must be explicitly enabled
-by setting the ``dq-zero-copy`` option to ``true`` while specifying the
-``vhost-server-path`` option as above. If you wish to split out the command
-into multiple commands as below, ensure ``dq-zero-copy`` is set before
-``vhost-server-path``::
-
-    $ ovs-vsctl set Interface dpdkvhostuserclient0 options:dq-zero-copy=true
-    $ ovs-vsctl set Interface dpdkvhostuserclient0 \
-        options:vhost-server-path=/tmp/dpdkvhostclient0
-
-The feature is only available to ``dpdkvhostuserclient`` port types.
-
-A limitation exists whereby if packets from a vHost port with
-``dq-zero-copy=true`` are destined for a ``dpdk`` type port, the number of tx
-descriptors (``n_txq_desc``) for that port must be reduced to a smaller number,
-128 being the recommended value. This can be achieved by issuing the following
-command::
-
-    $ ovs-vsctl set Interface dpdkport options:n_txq_desc=128
-
-Note: The sum of the tx descriptors of all ``dpdk`` ports the VM will send to
-should not exceed 128. For example, in case of a bond over two physical ports
-in balance-tcp mode, one must divide 128 by the number of links in the bond.
-
-Refer to :ref:`dpdk-queues-sizes` for more information.
-
-The reason for this limitation is due to how the zero copy functionality is
-implemented. The vHost device's 'tx used vring', a virtio structure used for
-tracking used ie. sent descriptors, will only be updated when the NIC frees
-the corresponding mbuf. If we don't free the mbufs frequently enough, that
-vring will be starved and packets will no longer be processed. One way to
-ensure we don't encounter this scenario, is to configure ``n_txq_desc`` to a
-small enough number such that the 'mbuf free threshold' for the NIC will be hit
-more often and thus free mbufs more frequently. The value of 128 is suggested,
-but values of 64 and 256 have been tested and verified to work too, with
-differing performance characteristics. A value of 512 can be used too, if the
-virtio queue size in the guest is increased to 1024 (available to configure in
-QEMU versions v2.10 and greater). This value can be set like so::
-
-    $ qemu-system-x86_64 ... -chardev socket,id=char1,path=<sockpath>,server
-      -netdev type=vhost-user,id=mynet1,chardev=char1,vhostforce
-      -device virtio-net-pci,mac=00:00:00:00:00:01,netdev=mynet1,
-      tx_queue_size=1024
-
-Because of this limitation, this feature is considered 'experimental'.
-
-.. note::
-
-   Post-copy Live Migration is not compatible with dequeue zero copy.
-
 Further information can be found in the
 `DPDK documentation
 <https://doc.dpdk.org/guides-19.11/prog_guide/vhost_lib.html>`__
diff --git a/NEWS b/NEWS
index 2f67d5047..b2ff619c6 100644
--- a/NEWS
+++ b/NEWS
@@ -1,5 +1,7 @@
 Post-v2.14.0
 ---------------------
+   - DPDK:
+     * Removed support for vhost-user dequeue zero-copy.
 
 
 v2.14.0 - 17 Aug 2020
diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c
index 18c4adcc7..515ad612e 100644
--- a/lib/netdev-dpdk.c
+++ b/lib/netdev-dpdk.c
@@ -2032,12 +2032,6 @@ netdev_dpdk_vhost_client_set_config(struct netdev *netdev,
         if (!nullable_string_is_equal(path, dev->vhost_id)) {
             free(dev->vhost_id);
             dev->vhost_id = nullable_xstrdup(path);
-            /* check zero copy configuration */
-            if (smap_get_bool(args, "dq-zero-copy", false)) {
-                dev->vhost_driver_flags |= RTE_VHOST_USER_DEQUEUE_ZERO_COPY;
-            } else {
-                dev->vhost_driver_flags &= ~RTE_VHOST_USER_DEQUEUE_ZERO_COPY;
-            }
             netdev_request_reconfigure(netdev);
         }
     }
@@ -5028,7 +5022,6 @@ netdev_dpdk_vhost_client_reconfigure(struct netdev *netdev)
     int err;
     uint64_t vhost_flags = 0;
     uint64_t vhost_unsup_flags;
-    bool zc_enabled;
 
     ovs_mutex_lock(&dev->mutex);
 
@@ -5054,19 +5047,6 @@ netdev_dpdk_vhost_client_reconfigure(struct netdev *netdev)
             vhost_flags |= RTE_VHOST_USER_POSTCOPY_SUPPORT;
         }
 
-        zc_enabled = dev->vhost_driver_flags
-                     & RTE_VHOST_USER_DEQUEUE_ZERO_COPY;
-        /* Enable zero copy flag, if requested */
-        if (zc_enabled) {
-            vhost_flags |= RTE_VHOST_USER_DEQUEUE_ZERO_COPY;
-            /* DPDK vHost library doesn't allow zero-copy with linear buffers.
-             * Hence disable Linear buffer.
-             */
-            vhost_flags &= ~RTE_VHOST_USER_LINEARBUF_SUPPORT;
-            VLOG_WARN("Zero copy enabled, disabling linear buffer"
-                      " check for vHost port %s", dev->up.name);
-        }
-
         /* Enable External Buffers if TCP Segmentation Offload is enabled. */
         if (userspace_tso_enabled()) {
             vhost_flags |= RTE_VHOST_USER_EXTBUF_SUPPORT;
@@ -5083,11 +5063,6 @@ netdev_dpdk_vhost_client_reconfigure(struct netdev *netdev)
             VLOG_INFO("vHost User device '%s' created in 'client' mode, "
                       "using client socket '%s'",
                       dev->up.name, dev->vhost_id);
-            if (zc_enabled) {
-                VLOG_INFO("Zero copy enabled for vHost port %s", dev->up.name);
-                VLOG_WARN("Zero copy support is deprecated and will be "
-                          "removed in the next OVS release.");
-            }
         }
 
         err = rte_vhost_driver_callback_register(dev->vhost_id,
diff --git a/vswitchd/vswitch.xml b/vswitchd/vswitch.xml
index 81c84927f..07da2ee8c 100644
--- a/vswitchd/vswitch.xml
+++ b/vswitchd/vswitch.xml
@@ -3236,17 +3236,6 @@ ovs-vsctl add-port br0 p0 -- set Interface p0 type=patch options:peer=p1 \
         </p>
       </column>
 
-      <column name="options" key="dq-zero-copy"
-              type='{"type": "boolean"}'>
-        <p>
-          The value specifies whether or not to enable dequeue zero copy on
-          the given interface.
-          Must be set before vhost-server-path is specified.
-          Only supported by dpdkvhostuserclient interfaces.
-          The feature is considered experimental.
-        </p>
-      </column>
-
       <column name="options" key="tx-retries-max"
               type='{"type": "integer", "minInteger": 0, "maxInteger": 32}'>
         <p>
-- 
2.13.6



More information about the dev mailing list