Age | Commit message (Collapse) | Author | Files | Lines |
|
When vhost and another interface, say tap, are configured for interrupt
mode, performance number may be very low from vhost.
Further analysis discovers that when vhost posts an interrupt to the
RX infra, there is a 10 msec delay in waking up its input routine.
The delay is due to vhost posts the interrupt from the main thread
which tries to wake up the worker thread.
The fix is for vhost to move the posting interrupt call to the
corresponding input worker thread by calling
vnet_hw_if_set_rx_queue_file_index() to set it up.
While at it, streamline the function vhost_user_kickfd_read_ready()
since it will be called from the worker thread.
Type: fix
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: I9beedcd33e1558c8335da4ee7fadc51c29ee4589
|
|
Type: fix
Change-Id: I433fe3799975fe3ba00fa30226f6e8dae34e88fc
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Type: improvement
Some tests i.e. ipsec see performance regression when offload flags
are moved to 2nd cacheline. This patch moves them back to 1st cacheline.
Change-Id: I6ead45ff6d2c467b0d248f409e27c2ba31758741
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Type: improvement
Change-Id: I4ac6b1a6553e26a5c26b6761fa3c4cc5d4925486
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Type: fix
virtio/tap interfaces set the empty buffers in the input node
for receiving data. Backend uses those buffers, fills them with
data and notifies the virtio/tap driver. But virtio/tap driver
gets into stall state if interface is created and configured
through exec script on VPP startup.conf and put the interface in
interrupt mode while VPP is only configured with main thread.
This patch fixes the problem by prefilling buffers during the
interface creation.
Change-Id: Ibc4d0e70e127ccc4b7cf8b2b18406ae4b02c73b4
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
trajectory trace has been broken for a while because we used to save the
buffer trajectory in a vector pointed to in opaque2. This does not work
well when opaque2 is copied (eg. because of a clone) as 2 buffers end up
sharing the same vector.
This dedicates a full cacheline in the buffer metadata instead when
trajectory is compiled in. No dynamic allocation, no sharing, no tears.
Type: refactor
Change-Id: I6a028ca1b48d38f393a36979e5e452c2dd48ad3f
Signed-off-by: Benoît Ganne <bganne@cisco.com>
|
|
The /sys filesystem is not always accurate when switching network
namespaces. Using netlink should work in more situations.
Type: improvement
Change-Id: I71611f14319820469ea7794eec5b7c6c70e2be6d
Signed-off-by: Aloys Augustin <aloaugus@cisco.com>
|
|
Patch 24601 introduced description into template. In vhost_user_process,
template is reused inside the while loop to call clib_file_add. But
description is allocated outside of the loop only once. As a result, the
same storage for description is being referenced by all instances of call
to clib_file_add. As long as we don't call clib_file_del, we may be
good with multiple fds sharing the same storage for the description. When
one of the fds disconnects and frees the description, the other fds is
holding onto the free memory pointer. Bad news eventually happens when
another fd disconnects and frees the description that was already free
previously.
The fix is to move the allocation of description inside the loop to avoid
sharing.
Type: fix
Fixes: gerrit.fd.io/r/c/vpp/+/24601
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: Ie670931acdc2c7b851982d98fd0d837284a19036
|
|
Type: improvement
Change-Id: I56dadb852f63da0597ddf4db395a22afdf2d9cc0
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Type: improvement
This patch adds flags to represent the modern NICs capabilities.
Change-Id: I96d38d9ab7eac55974d72795cd100d8337168e1e
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Type: feature
This feautre only applies to ESP not AH SAs.
As well as the gobal switch for ayncs mode, allow individual SAs to be
async.
If global async is on, all SAs are async. If global async mode is off,
then if then an SA can be individually set to async. This preserves the
global switch behaviour.
the stratergy in the esp encrypt.decrypt nodes is to separate the frame
into, 1) sync buffers, 2) async buffers and 3) no-op buffers.
Sync buffer will undergo a cyrpto/ath operation, no-op will not, they
are dropped or handed-off.
Signed-off-by: Neale Ranns <neale@graphiant.com>
Change-Id: Ifc15b10b870b19413ad030ce7f92ed56275d6791
|
|
Type: improvement
Change-Id: I8322bca1a9aa75c97c0fe2ff24b2f65fc43242ce
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Make the ipsec[46]-tun-input nodes siblings of device-input so that
input features can be enabled on them. Register ipsec-tun for feature
updates. When a feature is enabled on the device-input arc and the
ifindex is an IPSec tunnel, change the end node of the arc for that
ifindex to be the appropriate ESP decrypt node. Set a flag on the
tunnel to indicate that the feature arc should be started for packets
input on the tunnel.
Test input policing on ESP IPSec tunnels.
Type: improvement
Signed-off-by: Brian Russell <brian@graphiant.com>
Change-Id: I3b9f047e5e737f3ea4c58fc82cd3c15700b6f9f7
|
|
Type: improvement
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
Change-Id: Ic25ffe9c8e37826733cfb9e62cefb491bb3322bc
|
|
Type: refactor
This patch refactors the offload flags in vlib_buffer_t.
There are two main reasons behind this refactoring.
First, offload flags are insufficient to represent outer
and inner headers offloads. Second, room for these flags
in first cacheline of vlib_buffer_t is also limited.
This patch introduces a generic offload flag in first
cacheline. And detailed offload flags in 2nd cacheline
of the structure for performance optimization.
Change-Id: Icc363a142fb9208ec7113ab5bbfc8230181f6004
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Type: improvement
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
Change-Id: Ib3cefe5d27286c4853eb0c0e1803a94787a62c97
|
|
Type: fix
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
Change-Id: I41faa2ca249ff75e564a732af896e6b5d76bf665
|
|
Type: fix
Set the GSO flag when buffer length exceeds the
linux mtu. Don't listen for mtu changes on linux
side for now.
This also fixes a TX issue, as we only search for
valid frames on tx to the extent of n_left, we might
stay stuck.
Change-Id: Idf0bdd88990254a614962c2f7bc3e0292ccfd61a
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
|
|
Type: fix
Interrupt are suppressed from kernel on tx path.
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
Change-Id: I9f39f343b7e16bad09910766adf0b09654721f67
|
|
The check args->hwaddr is always true and it always copies the
mac address from args->hwaddr even though none was set.
Check args->use_custom_mac instead.
Type: fix
Fixes: gerrit 29970
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: I0c51bf1ea79b02c4fbdc3c52e694f186bdd96600
|
|
Change-Id: I85a463b4ca15baf11e3eb70189f5190ba2585170
Type: refactor
Signed-off-by: Mohammed Hawari <mohammed@hawari.fr>
|
|
Change-Id: If8077280cef501599f810ad9255efa2a5a451ced
Signed-off-by: Mohammed Hawari <mohammed@hawari.fr>
Type: improvement
|
|
Type: improvement
Change-Id: I4008cadfd5141f921afbdc09a3ebcd1dcf88eb29
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
VPP only supports a poor man's approach for interrupt notification to the
driver. It uses a simple binary flag for "interrupt needed" or "interrupt
not needed". Most drivers support more sophisticated event index already.
This feature is to add the long due missing feature and make it configurable,
off by default.
Type: feature
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: I68dab7dd07045cafb49af97b7f70db9b8131ae03
|
|
Type: fix
Fixes: 587f9130424fd451e4ba823240d02f655fb197d1
Change-Id: Ia1739fad6a36fa658aece157d7adea8bbaa751d2
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Add descriptions to clib_file_t template structures so that
sockets can be identified via the 'show unix file' cli command.
Type: fix
Change-Id: Ibf82d55aa6c7b1126bd252b76d0dc8b7076f5046
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
|
|
Current vhost multi-queues support has a hard limit of 8 queue pairs
due to static vring array. This limit was raised in qemu. VPP should
support more than 8 queue pairs also.
Change static vring allocation to dynamic. When the interface is
created, we allocate 8 queue pairs to begin with. We also keep track
of how many queue pairs that the interface actually uses.
We reply VHOST_USER_GET_QUEUE_NUM with 128 as our maximum number of
support queue pair. When qemu starts initializing queue pair greater
than 8, we expand the vrings as needed on demand.
Type: improvement
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: I4a02d987d52d1bbe601b00e71f650fe6ebfcc0d7
|
|
Type: refactor
Change-Id: Ie67dc579e88132ddb1ee4a34cb69f96920101772
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
- reduces number of instructions generated 4 times compared to old code
- adds pool_foreach2 which is more friendly to clang-format
Type: improvement
Change-Id: I51e9c7fb09655c60d883987dadf5b2666c12b3f7
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Type: fix
Change-Id: I7ca955882c0e263a9ace4b14021e51488564e411
Signed-off-by: Benoît Ganne <bganne@cisco.com>
|
|
Type: fix
Change-Id: I2cc1cfd519e5b3502c59cf72e95e454f9122b8e5
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Type: fix
Change-Id: I8ce1df5c97941fb645b33476db9cfc74f1395b15
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Type: fix
Change-Id: I1f1f0b6e8c5ef8bc9f2aca4bdc78e89fa951b841
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Type: fix
Fixes: 2e6f624f1f82ae0351dd05ad5d930d6876105519
Change-Id: Ib41c82ea1e8430afc920250fb0d054a2fb2d08c9
Signed-off-by: Benoît Ganne <bganne@cisco.com>
|
|
Type: feature
Change-Id: I12703371541298efa029903d6762b1cd1f7322ca
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Type: refactor
Change-Id: I3f561818bc7c221f676477a52c7c7781624c185a
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Type: fix
Fixes: 587f9130424fd451e4ba823240d02f655fb197d1
Change-Id: I230993a54c84e22e324de2a8defeda83c517d733
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
When using classifier to filter traces, not all packets will be traced.
In that case, we should only count traced packets.
Type: fix
Change-Id: I87d1e217b580ebff8c6ade7860eb43950420ae78
Signed-off-by: Benoît Ganne <bganne@cisco.com>
|
|
A plugin can set the speed on a host interface making it possible for
host applications to be aware of the actual interface speed, not the
one that the driver reports by default.
With this change, add a function to set speed on a host interface.
Type: feature
Signed-off-by: Alexander Chernavin <achernavin@netgate.com>
Change-Id: I259a52b736022bdd805e8d92dcd1bfd5c58f6f96
|
|
Type: feature
Add a function to adjust the link state of the host side of a tap
interface. If an application (e.g. route protocol daemons) running on
the host uses netlink to monitor interface state, a plugin
could use this function to communicate a loss of connectivity
to the application by making the interface appear to go down.
Requires a somewhat recent kernel. E.g. it does not have any effect
on CentOS 7 but it works on CentOS 8.
Change-Id: I677ee7889d2eb142e2395bea98f0b4d7e7e7f810
Signed-off-by: Matthew Smith <mgsmith@netgate.com>
|
|
Type: improvement
Change-Id: Iaf98a60e37dd28828feca365b8fdc5d2f7ae6935
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Improves compile time....
Type: improvement
Change-Id: I310a2e55e5e488a953d65fd065f7795a43d2e9a7
Signed-off-by: Damjan Marion <damarion@cisco.com>
|
|
Type: fix
Change-Id: I53cb96950f8658d7159fb0bd8ecfa50b6977e5af
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Type: refactor
Signed-off-by: Neale Ranns <neale.ranns@cisco.com>
Change-Id: Id1801519638a9b97175847d7ed58824fb83433d6
|
|
Type: fix
Fixes: 2e6f624f1f82ae0351dd05ad5d930d6876105519
Change-Id: I24a9822d1968a134c7e41221f48296cc8a67dd91
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Type: improvement
packet buffering is common code to tun/tap/virtio.
Change-Id: I59a339f268a28a0c32756e52d10d1ed6b207db42
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Type: improvement
GRO is common to tap/tun/virtio devices. Hence move to
common place.
Change-Id: Ibb099f3a80f493ddb934df6bb7640f7c9c370fd5
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
When GSO is enabled, vhost clears the checksum field prior to transmitting
the packet. Some newer kernel version does not like that and complains
about checksum error. This was seen with ip6 traffic.
Type: fix
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: I7c6f2a6148f4a30107bfa8b078f5990e64300cf1
|
|
Type: fix
Fixes: 03b76a20c569b8275beb8783691300a7d66b54a4
Change-Id: Ife788974cb7b2c35f40a017dd195dc2f7ee797b4
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|
|
Type: improvement
virtio interfaces support packet coalescing and buffering which
depends on timer expiry to flush the stored packets periodically.
virtio input node checks timer expiry and schedules tx queue
accordingly. In poll mode, timer expiry is handled naturally,
as input node runs periodically. In interrupt mode, virtio
input node depends on the interrupts send from backend.
Stored packets could starve, if there would not be interrupts
to input node.
This patch implements a process node which periodically
sends interrupt to virtio input node given coalescing or buffering
feature is enabled on an interface.
Change-Id: Ic38f749f74b001073d4d0579dca149d0a4cea039
Signed-off-by: Mohsin Kazmi <sykazmi@cisco.com>
|