summaryrefslogtreecommitdiffstats
path: root/src/plugins/marvell/pp2
AgeCommit message (Collapse)AuthorFilesLines
2018-07-26pp2: change default queue sizeBrian Brooks1-2/+2
Reduce default queue size to twice the vlib frame size. This throttles the PP from transferring more packets than are necessary for the next round of graph execution on a core. When combined with DMA'ing into L3 cache, Mpps for 64B packets increases 35%. Change-Id: I0afe426d23560f262fdc56accb6302b099bd0076 Signed-off-by: Brian Brooks <brian.brooks@arm.com>
2018-07-11avoid using thread local storage for thread indexDamjan Marion2-2/+2
It is cheaper to get thread index from vlib_main_t if available... Change-Id: I4582e160d06d9d7fccdc54271912f0635da79b50 Signed-off-by: Damjan Marion <damarion@cisco.com>
2018-07-10pp2: increase recycle batch sizeBrian Brooks1-1/+3
Increase batch size when recycling buffers. This increases Mpps by 7%. Change-Id: I2a460611d9c36e9bf087b076fc4e187acf61108f Signed-off-by: Brian Brooks <brian.brooks@arm.com>
2018-07-10pp2: use configured RX queue sizeBrian Brooks1-1/+1
Change-Id: I5e5b2dd4f4bc3e257824015c723228ac5128d6a0 Signed-off-by: Brian Brooks <brian.brooks@arm.com>
2018-01-15Marvell device pluginDamjan Marion6-0/+1394
Depends in musdk 17.10 [1], tested on MACCHIATObin [2] board. currently only coves PP2. musdk must be compiled with: ./configure --enable-bpool-dma=64 [1] https://github.com/MarvellEmbeddedProcessors/musdk-marvell [2] http://macchiatobin.net Change-Id: I0247a6b860b0a067c54190eae0bd3fe08de234ad Signed-off-by: Damjan Marion <damarion@cisco.com>