aboutsummaryrefslogtreecommitdiffstats
path: root/vlib
AgeCommit message (Collapse)AuthorFilesLines
2016-02-26Add packet tracing hintBud Grise2-0/+7
This avoids checking the buffer flags bit if tracing is not enabled. Change-Id: I32e1a90b5fd10318254c611344488bc2a441c71e Signed-off-by: Todd Foggoa (tfoggoa) <tfoggoa@cisco.com>
2016-02-26Add support for native vpp_lite (non-dpdk) platformDamjan Marion1-1/+2
Change-Id: Icaa71957f67b923bc9795baa78c7495055615672 Signed-off-by: Damjan Marion <damarion@cisco.com>
2016-02-24Link the vpp application against libvnet.so, not libvnet.aDave Barach2-1/+10
Turn of srp, mainly as an example of how to restructure a featurette for selective disablement. Change-Id: Id3364c58a8711b103939f4434adfa67177380f67 Signed-off-by: Dave Barach <dave@barachs.net>
2016-02-18Add jumbo frames support to non-dpdk vhost interfaces.Pierre Pfister3-0/+165
This code provided inter-VM (2 cores per VM) throughput of 22Gbps using iperf through VPP (1 core) with 9k frames. With the same setup and pktgen running on both sides, it reached 5Mpps with no packets drop (Equivalent to before the patch). During the tests the average vector length was about 1, which likely means that VPP is not the bottleneck. The patch also includes some generic functions for vlib buffers allowing for chained buffer construction whether or not DPDK is enabled. Change-Id: Icfd1803e84b2b4578f305ab730576211f6242d6a Signed-off-by: Pierre Pfister <ppfister@cisco.com>
2016-02-16Increase number of per-cpu mheaps to 256Damjan Marion1-0/+4
It also includes check to ensure that number of per-cpu mheaps is not lower than number of cpus. Change-Id: Ibc68b34dda130f922243f9ea15b03e44bbcac269 Signed-off-by: Damjan Marion <damarion@cisco.com>
2016-02-14Increase VLIB_MAX_CPUS to 256Damjan Marion3-9/+7
Change-Id: Iac68b38dda1a0f9e2242f9eab5b03e44bbcac269 Signed-off-by: Damjan Marion <damarion@cisco.com>
2016-02-14Make size of per-thread mini counter vector equal to number of threadsDamjan Marion2-38/+30
Change-Id: Icfd91cca3cd686e5efa8a988f04483238605e1cb Signed-off-by: Damjan Marion <damarion@cisco.com>
2016-02-10Replace AC_PROG_LIBTOOL with LT_INITDave Barach1-1/+1
Change-Id: I642c4b8e83dd07708658a10ad46e9fd2c28a7f1f Signed-off-by: Dave Barach <dave@barachs.net>
2016-02-10Clean up gcc-5.2 warningsDave Barach1-1/+1
Change-Id: I7b0aa42a61607d4d30fe3627032d3837b2838982 Signed-off-by: Dave Barach <dave@barachs.net>
2016-02-05Clean up per-thread elog track nomenclature.Dave Barach1-3/+5
Change-Id: I4b65b29f9291b3fd47e05576d9a0789af8912982 Signed-off-by: Dave Barach <dave@barachs.net>
2016-01-27CLI: If an error happens on the socket being polled, then the CLIOle Troan1-0/+2
does not close the socket. Resulting in the main thread being stuck in a tight infinite loop polling on the erronous socket. Change-Id: I630b84b97c059acce117d56e41cd201131db4cab Signed-off-by: Ole Troan <ot@cisco.com>
2016-02-04dpdk_buffer.c: Honor clone_count even when there isn't a freelist handlerKevin Paul Herbert1-4/+7
The DPDK glue did not support cloned packets which do not have a freelist handler. Add support for this case. Change-Id: I8f17cd4952df97989d90d3f3e39792bc3739705c Signed-off-by: Kevin Paul Herbert <kph@cisco.com>
2016-02-02Tracing enhancements.Bud Grise3-5/+221
Limit buffer tracing to 50 in order to limit large output, unless the user over rides the max "sh trace max <number>". Add trace filtering, to be able to only trace packets that were processed by a specific node or exclude packets processed by a node. Example, only include packets processed by error-drop: # trace filter include error-drop 1 # trace add dpdk-input 1000000 <wait for packets, to come in> # show trace Change-Id: I5d9e15d2268ea55e6ef87b2b8756049c49b2791b Signed-off-by: Todd Foggoa <tfoggoa@cisco.com>
2016-01-27Warnings be gone.Dave Barach2-3/+3
Change-Id: I53730fd2ccd78fb73e11af77f8ffff19d75ebd95 Signed-off-by: Dave Barach <dave@barachs.net>
2016-01-27dpdk_buffer.c: Ensure that the mbuf reference count is as expectedKevin Paul Herbert1-0/+3
Add some more ASSERTs to track down improper frees. Change-Id: I2bd4b69fb14f522c82e6006131b6ad982f6f7e6b Signed-off-by: Kevin Paul Herbert <kph@cisco.com>
2016-01-27Print worker thread name as a c-string, not a vector. Otherwise, theDave Barach1-2/+2
output is certain to contain a NULL byte. Change-Id: Id80e1334d7a2cb6788f1db33cde142f84826db36 Signed-off-by: Dave Barach <dave@barachs.net>
2016-01-21PowerPC64-be arch support. Qemu ("qppc") platform support.Dave Barach5-11/+35
Change-Id: Ib0a05f9d1b08bacef09f6d7c101391737031ee0d Signed-off-by: Dave Barach <dave@barachs.net>
2015-12-22Fix to show trace output.Ed Warnicke1-4/+7
Change-Id: I0834eac9c17941d3d5b2aa5791d6deaabd8f6977 Signed-off-by: Ed Warnicke <eaw@cisco.com>
2015-12-18Fix warnings/errors reported by clangDamjan Marion4-3/+5
Change-Id: Ifb2de64347526e3218e22067452f249ff878fd32 Signed-off-by: Damjan Marion <damarion@cisco.com>
2015-12-17Remove redundant functionDamjan Marion1-18/+0
Change-Id: I30db8f678b14303a64ad3aaa16b5caf9081603d8 Signed-off-by: Damjan Marion <damarion@cisco.com>
2015-12-17Store per-thread node error countersDamjan Marion2-15/+65
This fixed performance issue in muti-threaded setup due to sharing of the same cacheline between multiple threads Change-Id: I930ee44c17a83d4da350d15b4b97b8bb4633a9b0 Signed-off-by: Damjan Marion <damarion@cisco.com>
2015-12-15Remove autotools generated productsDave Barach10-39304/+0
Change-Id: I7f23b8b8e5136cb56768bac3a7473e6df5ee4993 Signed-off-by: Dave Barach <dave@barachs.net>
2015-12-15replacing all vec_sort() invocations to vec_sort_with_function()Matus Fabian5-13/+52
Change-Id: I05895827ed52be292112484cee7d0a2591b67335 Signed-off-by: Matus Fabian <matfabia@cisco.com>
2015-12-08Initial commit of vpp code.v1.0.0Ed Warnicke70-0/+63582
Change-Id: Ib246f1fbfce93274020ee93ce461e3d8bd8b9f17 Signed-off-by: Ed Warnicke <eaw@cisco.com>