Support for startup node multi-arch variant selection through startup.conf.
This is to facilitate unit, functional testing and benchmarking of non-default
multi-arch variant node code path. Also added parameters to make test, to
specific using multi-arch variants in unit testing.
Type: improvement
Signed-off-by: Ray Kinsella <mdr@ashroe.eu>
Change-Id: I94fd332bb629683b7a7dd770ee9f615a9a424060
vlib_free_simple_counter()
vlib_free_combined_counter()
Frees the name and two dimensional vector from the stats segment.
Type: fix
Signed-off-by: Ole Troan <ot@cisco.com>
Change-Id: If1becf7d09520ba41a3d59e2df94958ecfcf6948
i2c follows its only use case - the original 82599 driver - into
extras/deprecated.
cj is/was an emergency debug tool unused in several years. Move to
extras/deprecated/vlib
Type: refactor
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: Ib55b65373f62630db295c562974bd8f2456c3107
Adapt queue_hi_thresh value using num_threads to avoid risk of deadlock
between threads which could happen for example when different NAT
threads try to handoff work to each other at the same time when their
frame queues are congested. This change ensures that each thread can
reserve a queue entry without causing problems even in the most extreme
case when all threads attempt to add to the same queue simultaneously
when the queue is nearly full.
Type: fix
Signed-off-by: Elias Rudberg <elias.rudberg@bahnhof.net>
Change-Id: I9e02f753bd00833d8dd500d181b0d4f9a454d703
When configured at compile time via the cmake
VPP_BUFFER_FAULT_INJECTOR option, the buffer allocator will appear to
fail a certain fraction of the time.
By default, the allocator succeeds 80% of the time. Detailed command
line configuration options are available, but only when the image has
been compiled with cmake option described above:
vlib { buffer-alloc-success-rate [0.0 ... 1.0]
buffer-alloc-success-seed <nnnn> }
Modify vlib_buffer_pool_create(...) so 0 is always an invalid buffer
index.
Debug images: add checks for bad buffer index enqueues, and also
verify that f->n_vectors doesn't accidentally map one or more
instances of the frame poison pattern 0xfefefefe.
Type: improvement
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: Iab939858014463d1e664682805013d334d6fcbe5
If vlib_buffer_clone (...) fails due to a buffer allocation error, update
*n_dispatched with the actual number of clones, not the requested
number of clones.
Punt_replicate(...) should not set *to_next[0] = bi0. The original
buffer is enqueued separately in punt_dispatch_node(...)
Type: fix
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: I774ad8f8c1a0633de4cf8ae5530629201c229347
vlib_buffer_clone(...) may not manage to produce any buffer clones at
all.
vlib_buffer_clone_256 should not smash the original buffer reference
count if no clones are produced.
Type: fix
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: I14d9d53637a220485c7a0036cfc75a4149b264ea
When profiling VPP with MAP (a software profile suite on Arm CPUs, see details in
https://www.arm.com/products/development-tools/server-and-hpc/forge/map) on Arm
servers, VPP will receive SIGPROF signal because MAP uses SIGPROF signal to drive
its sampler to do profiling on VPP. However, the default action of SIGPROF signal
handler in VPP such as unix_signal_handler() is process termination. To profile
VPP with MAP, the SIGPROF handler should be left as default, and MAP sampler will
overwrite it with its own implementation.
Type: feature
Change-Id: Ie14e513d35ec27a66e95067689408bad8ed1ad6b
Signed-off-by: Jieqiang Wang <jieqiang.wang@arm.com>
Right now even following configuration fails:
cpu {
corelist-workers 0
}
I think we should allow user to use CPU 0 if he explicitly
configured it or as the last automatically assigned core.
Type: improvement
Signed-off-by: Vladimir Isaev <visaev@netgate.com>
Change-Id: I041c30349bace558c673475e9a0cffccae5821f7
Right now following configuration leads to crash:
cpu {
corelist-workers 2
workers 2
}
because threads count will be set to 2, but we have only
one core in coremask.
Type: fix
Signed-off-by: Vladimir Isaev <visaev@netgate.com>
Change-Id: Ia93b892733971e7c8ddfceaaec5f4eb8bf9063ac
On SMP architecture, '/sys/bus/pci/devices/<devices id>/numa_node' file
will return -1 as a valid value if it does not have any NUMA node information.
Using -1 as a valid node id to access data structures will cause memory issue.
Fix the error by setting the value of numa_node to 0 if '/sys/bus/pci/devices/
<devices id>/numa_node' returns -1 and it is a SMP system.
Type: fix
Change-Id: Ib60e79c3656fe5b17e08fd9011122683e8b08b6f
Signed-off-by: Jieqiang Wang <jieqiang.wang@arm.com>
Add a clib_time_t * argument to clib_timebase_init(...), to encourage
client code to share the vlib_main_t's clib_time_t object.
Display the current day / date in GMT via the "show time" debug CLI.
Fix the test framework so it processes the new "show time" output format.
Type: refactor
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: I5e52d57eb164b7cdb6355362d520df6928491711
When logging is enabled, an empty line input (press Enter only)
will cause SIGSEGV. This patch fixes the problem by checking
the command length first.
Type: fix
Signed-off-by: Fan Zhang <roy.fan.zhang@intel.com>
Change-Id: Ib4cbd1c7bfd6a694e289d28958875c7d2356a93e
Type: improvement
allow clients that allocate punt reasons to pass a callback function
that is invoked when the first/last client registers to use/listen on
that punt reason. This allows the client to perform some necessary
configs that might not otherwise be enabled.
IPSec uses this callback to register the ESP proto and UDP handling
nodes, that would not otherwise be enabled unless a tunnel was present.
Change-Id: I9759349903f21ffeeb253d4271e619e6bf46054b
Signed-off-by: Neale Ranns <nranns@cisco.com>
Type: improvement
for those that find that name usefull.
Signed-off-by: Neale Ranns <nranns@cisco.com>
Change-Id: I6c99bcdbb10ca1615aeea6924c2d93a68b5b7684
Use exponential smoothing. Each sample has a half-life of 1
second. reported_rate(t) = reported_rate(t-1) * K + rate(t)*(1-K)
Sample every 20ms, i.e. 50 samples per second
K = exp (-1.0/20.0);
K = 0.95;
Type: feature
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: I9aea5dd5fecfaefffb78245316adb4bf62eb2bd4
Use below sysfs files to check which numa node a specific cpu_id belongs to.
/sys/devices/system/node/online
/sys/devices/system/node/node0/cpulist
/sys/devices/system/node/node1/cpulist
Type: fix
Change-Id: I124b80b1fd4a20dd7bd76f0ae27d5ab23a3a8ff1
Signed-off-by: Lijian Zhang <Lijian.Zhang@arm.com>
The mheap allocator has been turned off for several releases. This
commit removes the cmake config parameter, parallel support for
dlmalloc and mheap, and the mheap allocator itself.
Type: refactor
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: I104f88a1f06e47e90e5f7fb3e11cd1ca66467903
According to the description in the startup.conf, the assignment
of worker threads starts with the lcore following the main_lcore.
A non-zero skip_cores will correctly achieve this assignment.
However, prior to this patch when workers are assigned, the code
picks up and assigns core 0 even thought it shouldn't.
This patch determins if a non-zero number of workers are desired
and if so, marks CPU unavailable for a worker assignment.
Type: fix
Change-Id: I1fdf73a6f218dcbf146fda2efc90c553f7cd6d20
Signed-off-by: Jon Loeliger <jdl@netgate.com>
Prior to this patch, the main thread's core id was
always reported as 0.
This patch makes a call to vlib_get_thread_core_socket() on
the main thread so that its core id is set properly.
Type: fix
Fixes: 5d64c7868f
Change-Id: I019cb95eec031da25197e48d956038c4bd6b5040
Signed-off-by: Jon Loeliger <jdl@netgate.com>
For src/vnet/classify, src/vnet/cop, src/vnet/pg, and src/vlib/unix
Type: docs
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: Ib6ab734608693a1e9562a44808246950616e8d36
Allow a plugin to override (suppress loading of) other plugins. This
mechanism allows a developer to prevent specific plugins from being
loaded.
To do so, provide an "overrides" list in the plugin definition:
VLIB_PLUGIN_REGISTER () =
{
<snip>
.overrides = "avf_plugin.so,ioam_plugin.so,dpdk_plugin.so",
};
or some such. Simply list the plugins in question as shown above. The
.overrides structure member is limited to 256 octets. The named .elf
section mechanism used to discover the vlib_plugin_registration_t's
precludes the use of a variable-length array of strings.
Use the vlib log to eliminate plugin and built-in vat plugin loader
console spew.
Added vlib_log_register_class_rate_limit(...) to allow procedural
configuration of the log rate-limit. We *never* want to rate-limit
plugin loader messages.
Type: feature
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: I0a9327b8cf5508482f057342783252112cb44170
Apply exponential smoothing to the clock rate update calculation in
clib_time_verify_frequency(), with a half-life of 1 minute and a
sampling frequency of 16 seconds. Within 5 minutes or so, the
calculation converges
With each rate recalculation: reset total_cpu_time based on the kernel
timebase delta since vpp started, and the new clock rate
Improve the "show clock [verbose]" debug CLI command.
BFD echo + echo fail tests marked off until the BFD code can be
reworked a bit.
Type: fix
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: I24e88a78819b12867736c875067b386ef6115c5c
The path must be next-to-impossible to hit, because the code has been
wrong for at least 5 years.
Type: fix
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: I23b8c4e1631827e7931f353c561c1e19c596c598
It's not typical for a program to core when it receives a SIGINT, so
keep this from happening.
Type: fix
Signed-off-by: Christian E. Hopps <chopps@chopps.org>
Change-Id: I2c15985a57e6ea898ff05c4001e4b30b41154eba
Enable 'max-size' configuration parameter to set maximum size of
memory space allocated for pmalloc module. This parameter along
with existing 'base-addr' falls into physmem section. Both are
dedicated parameters to pmalloc module.
Type: feature
Change-Id: I939f25156b9a43440a24d69a7397d57eb6c2d392
Signed-off-by: Jieqiang Wang <Jieqiang.Wang@arm.com>
Type: fix
Startup config setting an i40e/ice interface
up in Debug VPP consumes more than the currently
available stack space.
Signed-off-by: GordonNoonan <gordon.noonan@intel.com>
Change-Id: I98b52c5596799017b97f802a8661b76cd1bb3245
Walk the sub_commands vector directly.
Type: fix
Fixes: 6b3f25caff
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: I3022b39e5a739647ec68effc6756166ce2da85b6
Configure n-tuple classifier filters which apply to the vpp packet
tracer.
Update the documentation to reflect the new feature.
Add a test vector.
Type: feature
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: Iefa911716c670fc12e4825b937b62044433fec36
When running exec scripts, there can be a need to wait between statements.
Type: feature
Change-Id: I2a45b390697e09fc222358c9354f28e3368a06ba
Signed-off-by: Paul Vinciguerra <pvinci@vinciconsulting.com>
Type: feature
For some deployments(mobile traffic) we need few extra bytes of space
Signed-off-by: Srikanth Akula <srakula@cisco.com>
Change-Id: I3367561dc23dbb8b266dea583e23b9430fd7dcab
Set vm->check_frame_queues after actually enqueuing a frame. Under
obscure circumstances, the code managed to set check_frame_queues so
far in advance that 100 dispatch cycles could elapse before the frame
enqueue succeeded. That resulted in permanent lack of queue service.
Type: fix
Ticket: VPP-1734
Fixes: 18191
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: If2d398202b4ba2b96581d25e8142daef3f74c9e5
- vlib_node_add_next_with_slot was not cleaning the old next node
references to the given slot when replacing it with new next node. This mostly
worked until one tried to set the slot to a previously (but not currently) used
next node for that slot.
Type: fix
Signed-off-by: Christian Hopps <chopps@labn.net>
Change-Id: I7ee607625da874e320158b80f12ddc16e377f8e9
Dump the entire CLI, mp-safe commands, non-mp-safe commands, commands
which have been executed. Optionally, clear the hit counters.
Type: feature
Signed-off-by: Dave Barach <dave@barachs.net>
Change-Id: Ie38fc664b7deaabc35ca35be68db7e159272f551
When CLIB_DEBUG is enabled, vlib_foreach_main macro asserts that
vlib_main it currently looks at is safely parked in barrier, by
checkling that vlib_main->parked_at_barrier is not 0.
Unfortunately, the check is racy - workers first increment the
atomic counter to indicate that they have reached the barrier
and _then_ set this_main->parked_at_barrier to 1. For the last
worker to suspend this opens the race - main thread is free
to execute and assert immediately after atomic counter has been
incremented, before worker gets to write to own parked_at_barrier.
Fix this by simply swapping the order of two operations.
Type: fix
Signed-off-by: Alexnader Kabaev <kan@FreeBSD.org>
Change-Id: Iae47abd6ca0be1c5413f5ecaefabc64cd7eac2ed
