Change the rebuilding of worker thread clone datastructures
to run in parallel on the workers, instead of serially
on main.
Change-Id: Ib76bcfbef1e51f2399972090f4057be7aaa84e08
Signed-off-by: Colin Tregenza Dancer <ctd@metaswitch.com>
An external (to VPP) process can register (over the VPP binary API) to
receive control plane packets over a UNIX domain socket. The packets are
prepended with a packet descriptor containing meta-data (if_index of
interface, etc).
Currently only UDP is supported.
The socket supports sending of packets/frames as well.
The sent packet is prepended with a descriptor, telling VPP to
route the packet (via ip4-lookup, ip6-lookup) or as an pre-formed
Ethernet frame that is sent directly to interface-output.
The intended use case for this is for an external DHCP client or
a RIP implementation.
New configuration option:
punt { socket <socket path> }
To register use the punt_socket API message.
TODO:
- Add support for pre-routing. I.e send L3 packet to given
TX interface, but do ARP/ND (ip[46]-rewrite)
- Add test scripts
- Support for abstract names (starting with \0)
- Add rate limiting (COP)
- Support for other protocols, e.g. IPv6 ND
Change-Id: I4a0afc8020deebb3d9d74686dde694ee5bcb8d0f
Signed-off-by: Ole Troan <ot@cisco.com>
1. Limit MAC entry update per l2-learn call to reduce update burst
when wall clock advance to the the next minute so all MAC time
stamps are behind current time needing update.
2. Optimize l2-learn node fast path code sequence.
3. Invalidate cache_key when update MAC entry.
4. Change L2 learn hit counter to L2 learn hit-update counter.
5. Increase L2FIB table memory size to 512MB to fit 4M entries
6. Set MAC learn limit at 4M entries
Change-Id: I3075ee8fb59645a56850126bac2e3e6d341cef4d
Signed-off-by: John Lo <loj@cisco.com>
vpp_uses_dpdk is set to "no" in build-data/platforms/vpp.mk causing the
build to fail.
This patch addresses that issue.
Change-Id: Icc1aaa508e730c9b8715119e1259e4c82f974048
Signed-off-by: Marco Varlese <marco.varlese@suse.com>
Simply call pool_init_fixed(...) before using the pool. Note that
fixed, preallocated pools live in individually-mmap'ed address
segments, except for the free element bitmap. A large fixed pool can
exceed 4gb.
Fix tcp buffer allocator leak, remove broken assert
Change-Id: I4421082e12a77c41c6e20f7747f3150dcd01fc26
Signed-off-by: Dave Barach <dave@barachs.net>
According to the spec, supporting interrupt mode from the driver is optional,
not a must. When interrupt mode is configured on the interface, we should
check to make sure that the driver didn't opt out for the kickfd support and
reject the configuration if it did.
Change-Id: I7d3dbaddde65458e1a6a802754a3768ae8685a0e
Signed-off-by: Steven <sluong@cisco.com>
Adding new dependency is not right solution to this problem.
This reverts commit e58c93b2764eb306d286531a2b920c6de080cb77.
Change-Id: I08f2af5cf9c26c4302b0dbaccebbb52f0614f80f
Signed-off-by: Damjan Marion <damarion@cisco.com>
Setting the bucket-level LRU cache size to zero removes the
bucket-level LRU cache code.
Change-Id: Idf2e63d0d508675e957366515863766f79a3479c
Signed-off-by: Dave Barach <dbarach@cisco.com>
replace $(echo "..." | bc) by `echo ... | bc` as they do not seem to
behave the same way.
Change-Id: Ib8f13f0c8213aaae89d65559427e01bc40f4e8d1
Signed-off-by: Gabriel Ganne <gabriel.ganne@enea.com>
First attempt to make internal buffer manager thread safe was not
succesfull, so trying again. This time with more testing.
Change-Id: I01b8385a9c26d233934a3339255ea4bd31c865ac
Signed-off-by: Damjan Marion <damarion@cisco.com>
In the data path, we grab qsz from vhost_user_vring_t to compute
qsz_mask and store it in a stack variable to use on many occasions.
We never use qsz for any meaningful purpose. It is more useful to
cache qsz_mask in vhost_user_vring_t to avoid the needless computation
in the data path.
Change-Id: Idf4d94a9754d5c75c899f1f4f59602275b9904a6
Signed-off-by: Steven <sluong@cisco.com>
Upon hash collision, the flow start time was not reset.
The hash computation techniques (crc32 or xxhash) also both
had bugs which are now fixed.
Change-Id: I94d72997f34018d1699324264f7dded2a5cbd776
Signed-off-by: Pierre Pfister <ppfister@cisco.com>
create/delete/modify vhost_user APIs no longer support the operation mode
(polling/interrupt/adaptive). They are now done via the generic interface.
Change-Id: I9e9bd503f9b56c953ecd2b271b3e2007da20c72a
Signed-off-by: Steven <sluong@cisco.com>
JIRA: VPP-498
Changes to build to help with downstream distro builds
for Fedora, Centos and RHEL distros.
Add nasm, automake, libtool, byacc, bison and flex.
Remove libconfuse and dependencies.
Remove epel-release rpm and dependencies.
Add conditionals to work around Python 2 packaging
inconsistency in Fed 25.
Add numactl to rpm requirements.
Change-Id: Ia39f8b931dc87e42df56414d38662eb33c7a4ca7
Signed-off-by: Thomas F Herbert <therbert@redhat.com>
added debug version commands to Readme files for example tests
Change-Id: Icc5d5cdd33efb6d7c7512c7a78e22d9dc3d31fdc
Signed-off-by: Matej Perina <mperina@cisco.com>
- Remove frame handoff support machinery. We haven't used it in a long
time.
- Configuration support for the local endpoints bihash table
- Drop lookup failure packets in tcp46_syn_sent
Change-Id: Icd51e6785f74661c741e76fac23d21c4cc998d17
Signed-off-by: Dave Barach <dave@barachs.net>
Separating test discovery code to it's own script file has the
advantage of easily doing e.g. listing of all existing tests.
Change-Id: I80dc280263cc7e33e7e13cb0d48b39bf08ece24d
Signed-off-by: Klement Sekera <ksekera@cisco.com>
The fix for VPP-935 missed the case that hash_acl_add() and hash_acl_delete() may be called
during the replacement of the existing applied ACL, as a result the "applied" logic needs
to be replicated for the hash acls separately, since it is a lower layer.
Change-Id: I7dcb2b120fcbdceb5e59acb5029f9eb77bd0f240
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
(cherry picked from commit ce9714032d36d18abe72981552219dff871ff392)
- set session state as closed on session manager delete
- enable retransmit as opposed to persist timer after persist timer completes
- properly discard buffer chain bytes when new data overlaps ooo
segments
- don't use rxt bytes in snd space estimate used on tx path
Change-Id: Id9cab686e532e5fe70c775d5440260e8eb890a9f
Signed-off-by: Florin Coras <fcoras@cisco.com>
test can be run with:
make test TEST=test_jvpp
memory_shared.c:
declaring and assigning variable in if statement
makes it usage outside statement impossible. Looks like memory
space assigned to variable declared in statement is freed when
statement ends
svm.c:
- fixed case when root path can have a "/" at beggining
- added option for test to operate over shared memory space
with /vpe-api name and not create new one with name consisting of
root path and region name which would require root permisions
Change-Id: Iff1170dc6a5c1be134c152f2757c7ab9b919a8ed
Signed-off-by: Matej Perina <mperina@cisco.com>
