format_vl_api_address_union() is used by vnet, creating a linkage
dependency from vnet to vpp.
Type: fix
Change-Id: I298a90d521e51b7527ef140d66130062824e1d16
Signed-off-by: Benoît Ganne <bganne@cisco.com>
Type: feature
If 'main-core' is not specified, the main thread is pinned
by default to the cpu it is running on during initialization.
This change does not impact manual core-pinning, which
requires the 'main-core' argument
e.g. 'cpu {main-core x corelist-workers n}.
Change-Id: I874034591bf0acf4d71b231dfbbb0f6de8fe6060
Signed-off-by: hsandid <halsandi@cisco.com>
Add a unix method for getting the current executable name. This is
implemented to match the readlink api for existing calls.
Type: improvement
Change-Id: Id06a55892d09d0b305a56b55a424f53ffb685a72
Signed-off-by: Tom Jones <thj@freebsd.org>
Signed-off-by: Damjan Marion <damarion@cisco.com>
vl_api_prefix_t.len is 1 byte only, but unformat %d writes 4 bytes
add helper functions unformat_u(8|16) which don't write more than
appropriate amount of bytes
fix other similar errors in vpp/api/types.c
Type: fix
Change-Id: I74a61a377147c373f8c25ed083052b2287763c39
Signed-off-by: Klement Sekera <klement.sekera@gmail.com>
Change I58e1ae1c91f4a62e80eaf4e16e9932d8bab17c74 has introduced a reference to config.h,
which is not there in a case of building a static standalone vppctl.
Solution: add a variable STATIC_VPPCTL which, when defined, avoids including
the missing include file. Thanks a lot to Damjan for the suggestion.
Type: fix
Change-Id: I133235ba07e5c2e0d5669be9c2292cab0fdf436f
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
set asan default options in vppctl and vpp_get_stats
Type: improvement
Signed-off-by: Dmitry Valter <d-valter@yandex-team.com>
Change-Id: I58e1ae1c91f4a62e80eaf4e16e9932d8bab17c74
In case of both stdin and non-interactive inputs are there
vppctl parses them all, causing mixed corrupted output:
$ echo foo | vppctl sh bar
show: unknown input `bar'
unknown input `foo'
This is not desired, stdin should be ignored if there's a command
but still allow stdin commands - following cases are still equal:
$ vppctl foo
$ echo foo | vppctl
Type: fix
Signed-off-by: Vladislav Grishenko <themiron@yandex-team.ru>
Change-Id: I98667391627150c98a57d49ae544e48ef3351f34
FreeBSD doesn't offer epoll, but an implementation which uses kqueue is
available as an external library. On FreeBSD in subsystems which require
epoll have cmake look for libepoll-shim.
Type: improvement
Change-Id: Iafd5406a9e2ebaa53fd94034489ffbbf87a7d040
Signed-off-by: Tom Jones <thj@freebsd.org>
* Refactor the existing prometheus exporter to function print_metric_v1()
* Add a 'v2' flag which instead uses metric names with labels, example:
nodes_clocks{node="ip4-lookup",index="0",thread="4"} 30198798628761
nodes_vectors{node="ip4-lookup",index="0",thread="4"} 298176625181
nodes_calls{node="ip4-lookup",index="0",thread="4"} 119789874274
nodes_suspends{node="ip4-lookup",index="0",thread="4"} 0
interfaces_rx_packets{interface="tap0",index="0",thread="1"} 79582338270
interfaces_rx_bytes{interface="tap0",index="0",thread="1"} 16265349667188
* For stat names that we don't know, print their v1 equivalent, which
keeps backwards compatibility.
Details in https://ipng.ch/s/articles/2023/04/09/vpp-stats.html
Type: improvement
Signed-off-by: pim@ipng.nl
Change-Id: I53ed3ede8cc7853eb46c354834d89eb788ece3b1
There are cases where default port for prometheus exporter is not
available e.g. when multiple vpp are running on single node.
Type: improvement
Change-Id: I39701486f9dfaf4dc9f08aab56e88126687b507a
Signed-off-by: Fahad Khan <fahadnaeemkhan@gmail.com>
Several api messages were not mp-safe although marked as such
because non-zero base id was not taken into account, and therefore
some other (from zero base id) were falsely mp-safe instead.
Keep messages as mp-safe, as they falsely were before:
10 get_first_msg_id 0 1
12 api_versions 0 1
Messages that are no longer mp-safe as they weren't marked:
15 sockclnt_create 0 1
33 proxy_arp_intfc_dump 0 1
Fix messages to be really mp-safe:
809 bridge_domain_dump 0 1
920 ip_route_add_del 0 1
921 ip_route_add_del_v2 0 1
1362 get_node_graph 0 1
1671 create_vhost_user_if 0 1
1675 create_vhost_user_if_v2 0 1
Additionally mark messages as mp-safe, seems they need no barrier:
1360 show_threads 0 1
1370 show_version 0 1
1372 show_vpe_system_time 0 1
Type: fix
Change-Id: Ie6c1e3aa89f26bf51bfbcb7e7c4d9fee885487b7
Signed-off-by: Vladislav Grishenko <themiron@yandex-team.ru>
So error logs are displayed on console earlier....
Type: improvement
Change-Id: If31b76c9d06254b0fec5b5b3f4e92a881b4cf786
Signed-off-by: Damjan Marion <damarion@cisco.com>
To make out of tree plugins require a particular version, they need
access to the version they are built with. Install version.h.
Type: fix
Change-Id: I5916d0a16aed7e054ede452af956fee56cd078f0
Signed-off-by: Ole Troan <ot@cisco.com>
When a stats entry is removed it is marked empty.
The stats client did not check for that and returned an empty string.
This resulted in blank lines in vpp_get_stats. Fix by returning null instead
and checking value.
Type: fix
Signed-off-by: Ole Troan <ot@cisco.com>
Change-Id: I08a39ba3ef4421bf275747a6300f97fe36791b50
Session debug code does not compile anymore due to vlib_mains global
variable disappearing over time. Replace it with vlib_get_main_by_index
call.
Add a cmake variable and pass it from make command line to enable
session debug. Notice transport debug is required for session debug.
make rebuild VPP_EXTRA_CMAKE_ARGS=-DVPP_TCP_DEBUG_ALWAYS=ON VPP_EXTRA_CMAKE_ARGS+=-DVPP_SESSION_DEBUG=ON
Type: fix
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: Ic2e887c6b10b77cbabd56934f4931fcfa04a6751
When checking for CLIB_SANITIZE_ADDR to enable specific behavior for
AddressSanitizer, we must have vppinfra/clib.h included as it is defined
there.
Type: fix
Change-Id: I9060c3c29c1289d28596c215a1d1709b2ea7c84e
Signed-off-by: Benoît Ganne <bganne@cisco.com>
Add cmake option to enable TCP_DEBUG_ALWAYS.
make rebuild VPP_EXTRA_CMAKE_ARGS=-DVPP_TCP_DEBUG_ALWAYS=ON
make rebuild VPP_EXTRA_CMAKE_ARGS=-DVPP_TCP_DEBUG_ALWAYS=OFF
Type: improvement
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: I911a8d615f76516ae0a988bc6135c3b0d8fcb3df
This patch introduces DMA infrastructure into vlib. This is well known
that large amount of memory movements will drain core resource. Nowadays
more and more hardware accelerators were designed out for freeing core
from this burden. Meanwhile some restrictions still remained when
utilizing hardware accelerators, e.g. cross numa throughput will have a
significant drop compared to same node. Normally the number of hardware
accelerator instances will less than cores number, not to mention that
applications number will even beyond the number of cores. Some hardware
may support share virtual address with cores, while others are not.
Here we introduce new DMA infrastructure which can fulfill the
requirements of vpp applications like session and memif and in the
meantime dealing with hardware limitations.
Here is some design backgrounds:
Backend is the abstract of resource which allocated from DMA device
and can do some basic operations like configuration, DMA copy and
result query.
Config is the abstract of application DMA requirement. Application
need to request an unique config index from DMA infrastructure. This
unique config index is associated with backend resource. Two options
cpu fallback and barrier before last can be specified in config.
DMA transfer will be performed by CPU when backend is busy if cpu
fallback option is enabled. DMA transfer callback will be in order
if barrier before last option is enabled.
We constructs all the stuffs that DMA transfer request needed into
DMA batch. It contains the pattern of DMA descriptors and function
pointers for submission and callback. One DMA transfer request need
multiple times batch update and one time batch submission.
DMA backends will assigned to config's workers threads equally. Lock
will be used for thread-safety if same backends assigned to multiple
threads. Backend node will check all the pending requests in worker
thread and do callback with the pointer of DMA batch if transfer
completed. Application can utilize cookie in DMA batch for selves
usage.
DMA architecture:
+----------+ +----------+ +----------+ +----------+
| Config1 | | Config2 | | Config1 | | Config2 |
+----------+ +----------+ +----------+ +----------+
|| || || ||
+-------------------------+ +-------------------------+
| DMA polling thread A | | DMA polling thread B |
+-------------------------+ +-------------------------+
|| ||
+----------+ +----------+
| Backend1 | | Backend2 |
+----------+ +----------+
Type: feature
Signed-off-by: Marvin Liu <yong.liu@intel.com>
Change-Id: I1725e0c26687985aac29618c9abe4f5e0de08ebf
Type: fix
Currently, prometheus exporter may crash because of memory exhaustion
when dumps metrics if the FIB contains large number of routes.
With this fix, increase memory size for prometheus exporter to be able
to handle large number of FIB entries.
Signed-off-by: Alexander Chernavin <achernavin@netgate.com>
Change-Id: Ia2b9a665368883c87448deee9bcf8d2ac1168357
VPP_IP_FIB_MTRIE_16 should be defined only if the option is enabled
instead of being defined as "ON" or "OFF".
Type: fix
Change-Id: Ib4e29a827bcbd84c8012f05ad264c1408ffccee7
Signed-off-by: Benoît Ganne <bganne@cisco.com>
In some environment like when running a lot of functional tests, it can
be useful to run more VPP instances than CPU and let the Linux scheduler
decide what to do. This change disable cpu pinning altogether in the
single-threaded case, provided that no main-core is explicitely
specified in the config
Type: improvement
Change-Id: I8c2f36fdd49c00f9adaaeb4c81aefb27c3420a9b
Signed-off-by: Benoît Ganne <bganne@cisco.com>
Signed-off-by: Mohammed Hawari <mohammed@hawari.fr>
Use of _vec_len() to set vector length breaks address sanitizer.
Users should use vec_set_len(), vec_inc_len(), vec_dec_len () instead.
Type: improvement
Change-Id: I441ae948771eb21c23a61f3ff9163bdad74a2cb8
Signed-off-by: Damjan Marion <damarion@cisco.com>
- support of in-place growth of vectors (if there is available space next to
existing alloc)
- drops the need for alloc_aligned_at_offset from memory allocator,
which allows easier swap to different memory allocator and reduces
malloc overhead
- rework of pool and vec macros to inline functions to improve debuggability
- fix alignment - in many cases macros were not using native alignment
of the particular datatype. Explicitly setting alignment with XXX_aligned()
versions of the macro is not needed anymore in > 99% of cases
- fix ASAN usage
- avoid use of vector of voids, this was root cause of several bugs
found in vec_* and pool_* function where sizeof() was used on voids
instead of real vector data type
- introduce minimal alignment which is currently 8 bytes, vectors will
be always aligned at least to that value (underlay allocator actually always
provide 16-byte aligned allocs)
Type: improvement
Change-Id: I20f4b081bb13bbf7bc0ace85cc4e301787f12fdf
Signed-off-by: Damjan Marion <damarion@cisco.com>
Systemd always sends SIGCONT after KillSignal, to ensure that even suspended
tasks can be terminated cleanly. However, the default action of SIGCONT
handler in VPP such as unix_signal_handler() is process termination with
coredump, what is not really desired. So, leave it alike SIGSTOP with its
default handler.
Type: feature
Signed-off-by: Vladislav Grishenko <themiron@yandex-team.ru>
Change-Id: I54c06d21669ec3c709322d746db9e28448c31bb8
Deadly combination is clib_{set,long}jmp + lazy linking + tail call compiler
optimization. On the first call to clib_setjmp, dynamic linker executes loader
code which then calls clib_setjmp, so stored stack position contains dynamic
loader data. Tail call optimization simply jumps back to the calling
code when clib_longjump is called and that results in wrong return
address used from the stack.
Change-Id: Ia7d8dbd5b2c425cdd0449374aa07ab6b684a330e
Type: fix
Signed-off-by: Damjan Marion <damarion@cisco.com>
It is annoying to see unsolicited message like this spew out to the
console which an end-user cares less about.
vlib_stats_rename_symlink:301: RENAME new name: /nodes/unix-cli-local:52/clocks
Type: fix
Fixes: I92a62bb1cb799e8fdc3ec4110ae3428825254f8a
Signed-off-by: Steven Luong <sluong@cisco.com>
Change-Id: I071f3d3736c06cd95a38ec46c7e2222caad01283
Check that provided path fits into defined buffer. Don't write too many
bytes to avoid having an unterminated string.
Type: fix
Fixes: 31f1924346
Signed-off-by: Klement Sekera <ksekera@cisco.com>
Change-Id: I1ea8b6d6a3474c032e542b6980ed14bac72093a8
This code was actually never working. It was just used as workaround for
Cisco ENIC issue with tagged default vlan frames.
Today Cisco ENIC provides solution to this problem with devargs flags...
Change-Id: Ia8284274117cb200bf6c7f7911d945d5a093d878
Type: refactor
Signed-off-by: Damjan Marion <damarion@cisco.com>
1. Malloc may return not zero buffer, causing strncat buffer overflow
2. Malloc buffer not freed
Type: fix
Fixes: 31f1924346 ("misc: vppctl - remove the dependency on vppinfra")
Signed-off-by: Tianyu Li <tianyu.li@arm.com>
Change-Id: I5aebaccf3d0f8b7e3617068267f62cc2aa39d827
Check the return value and log failure in case send() fails.
Type: fix
Fixes: 31f1924346
Signed-off-by: Klement Sekera <ksekera@cisco.com>
Change-Id: I1809598ff4816f67c28a88264b6524b10d7ff6ce
56f54af21d introduced the new memcpy.
It also made a vector support mandatory in order to compile anything
that depends on vppinfra.
This broke extras/scripts/build_static_vppctl.sh
Since the vppctl is just a two-pronged epoll+basic telnet client handler,
remove dependencies on the vpp infra libs, and trim the build script accordingly.
Change-Id: I394bc65c485cbf8e7143a818ca0c86367bb15d90
Type: improvement
Signed-off-by: Andrew Yourtchenko <ayourtch@gmail.com>
This is the last in the series of moving API messages from vpp/api/vpe.api to vlibmemory/memclnt.api.
This patch makes the remaining vpe.api messages dynamic, to help VAT2 binary-api command.
Moves the VAT test code to a separate file and removes the now unnused API meta files.
Type: improvement
Signed-off-by: Ole Troan <ot@cisco.com>
Change-Id: I01dd78eaff1d3715dff17d2643bf0f7f0089935b
Signed-off-by: Ole Troan <ot@cisco.com>
Type: improvement
Counters are labeled with interface indices in the Prometheus exporter
output. For example:
# TYPE _if_drops counter
_if_drops{thread="0",interface="0"} 0
_if_drops{thread="0",interface="1"} 0
_if_drops{thread="0",interface="2"} 2112
[..]
Currently, it's unable to map interface indices to the interface names
using only output provided by the Prometheus exporter. However, this
mapping is present in the vpp_get_stats output:
# vpp_get_stats dump /if/names
[0]: local0 /if/names
[1]: GigabitEthernet0/8/0 /if/names
[2]: GigabitEthernet0/9/0 /if/names
[..]
With this change, add name vectors to Prometheus exporter output as info
metrics. Thus exposing interfaces and their indices:
# TYPE _if_names_info gauge
_if_names_info{index="0",name="local0"} 1
_if_names_info{index="1",name="GigabitEthernet0/8/0"} 1
_if_names_info{index="2",name="GigabitEthernet0/9/0"} 1
[..]
Signed-off-by: Alexander Chernavin <achernavin@netgate.com>
Change-Id: Iff86c4d6fea8805e71fb04fccf278bae855e88d1
