<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Queue congestion in dpaa2_dev_tx in Layerscape</title>
    <link>https://community.nxp.com/t5/Layerscape/Queue-congestion-in-dpaa2-dev-tx/m-p/2054808#M15462</link>
    <description>&lt;P&gt;Hi NXP Team,&lt;BR /&gt;&lt;BR /&gt;While doing continues tx stream using rte_eth_tx_burst(), tx abruptly stops after a few minutes (in range of 120379673544 bytes).&lt;BR /&gt;&lt;BR /&gt;It turns out&amp;nbsp;dpaa2_dev_tx() api is checking the queue state for congestion and skipping tx.&lt;BR /&gt;After this incident tx only goes like a packet per 3-4 seconds.&lt;BR /&gt;&lt;BR /&gt;Is there any way to over come tx queue congestion and still support continues tx stream at 8GBps.&lt;BR /&gt;&lt;BR /&gt;Our setup is&amp;nbsp;&lt;SPAN&gt;LA1224-RDB (25G mac).&lt;/SPAN&gt;&amp;nbsp;&lt;BR /&gt;&lt;BR /&gt;I have also tried 4GBps and also max throughput around 24.6GBps. Observations are the same, in the range of around&amp;nbsp;120379673544 -&amp;nbsp;125916090872&amp;nbsp;bytes Queue congestion occurs&lt;BR /&gt;&lt;BR /&gt;DPDK version&amp;nbsp;19.11.6-rc1&amp;nbsp; (also tried 20.11.2)&lt;BR /&gt;MC version&amp;nbsp;10.33.0&lt;BR /&gt;LSK version&amp;nbsp;20.04&lt;BR /&gt;&lt;BR /&gt;I'm attaching a few logs below for debugging&amp;nbsp;&lt;BR /&gt;&lt;BR /&gt;&lt;/P&gt;</description>
    <pubDate>Mon, 03 Mar 2025 15:13:40 GMT</pubDate>
    <dc:creator>anagh_ram</dc:creator>
    <dc:date>2025-03-03T15:13:40Z</dc:date>
    <item>
      <title>Queue congestion in dpaa2_dev_tx</title>
      <link>https://community.nxp.com/t5/Layerscape/Queue-congestion-in-dpaa2-dev-tx/m-p/2054808#M15462</link>
      <description>&lt;P&gt;Hi NXP Team,&lt;BR /&gt;&lt;BR /&gt;While doing continues tx stream using rte_eth_tx_burst(), tx abruptly stops after a few minutes (in range of 120379673544 bytes).&lt;BR /&gt;&lt;BR /&gt;It turns out&amp;nbsp;dpaa2_dev_tx() api is checking the queue state for congestion and skipping tx.&lt;BR /&gt;After this incident tx only goes like a packet per 3-4 seconds.&lt;BR /&gt;&lt;BR /&gt;Is there any way to over come tx queue congestion and still support continues tx stream at 8GBps.&lt;BR /&gt;&lt;BR /&gt;Our setup is&amp;nbsp;&lt;SPAN&gt;LA1224-RDB (25G mac).&lt;/SPAN&gt;&amp;nbsp;&lt;BR /&gt;&lt;BR /&gt;I have also tried 4GBps and also max throughput around 24.6GBps. Observations are the same, in the range of around&amp;nbsp;120379673544 -&amp;nbsp;125916090872&amp;nbsp;bytes Queue congestion occurs&lt;BR /&gt;&lt;BR /&gt;DPDK version&amp;nbsp;19.11.6-rc1&amp;nbsp; (also tried 20.11.2)&lt;BR /&gt;MC version&amp;nbsp;10.33.0&lt;BR /&gt;LSK version&amp;nbsp;20.04&lt;BR /&gt;&lt;BR /&gt;I'm attaching a few logs below for debugging&amp;nbsp;&lt;BR /&gt;&lt;BR /&gt;&lt;/P&gt;</description>
      <pubDate>Mon, 03 Mar 2025 15:13:40 GMT</pubDate>
      <guid>https://community.nxp.com/t5/Layerscape/Queue-congestion-in-dpaa2-dev-tx/m-p/2054808#M15462</guid>
      <dc:creator>anagh_ram</dc:creator>
      <dc:date>2025-03-03T15:13:40Z</dc:date>
    </item>
  </channel>
</rss>

