<?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 P1022 eTSEC speed test issue in P-Series</title>
    <link>https://community.nxp.com/t5/P-Series/P1022-eTSEC-speed-test-issue/m-p/467411#M2749</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;I use iperf3 to test P1022 eTSEC Speed. if just test only one eTSEC, use UDP protocol,&amp;nbsp; the speed will be over 900Mbps.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;but, if the two eTSEC tested at the same time, use UDP protocol, one eTSEC speed is 600Mbps, and the other eTSEC speed is 400Mbps&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;So, I want to know how can i optimize the system in order to improve the two eTSEC performance&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Or, can you tell me the performance that the two eTSEC be used at the same time?&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Wed, 01 Jun 2016 02:27:47 GMT</pubDate>
    <dc:creator>wangruolong1</dc:creator>
    <dc:date>2016-06-01T02:27:47Z</dc:date>
    <item>
      <title>P1022 eTSEC speed test issue</title>
      <link>https://community.nxp.com/t5/P-Series/P1022-eTSEC-speed-test-issue/m-p/467411#M2749</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;I use iperf3 to test P1022 eTSEC Speed. if just test only one eTSEC, use UDP protocol,&amp;nbsp; the speed will be over 900Mbps.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;but, if the two eTSEC tested at the same time, use UDP protocol, one eTSEC speed is 600Mbps, and the other eTSEC speed is 400Mbps&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;So, I want to know how can i optimize the system in order to improve the two eTSEC performance&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Or, can you tell me the performance that the two eTSEC be used at the same time?&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Wed, 01 Jun 2016 02:27:47 GMT</pubDate>
      <guid>https://community.nxp.com/t5/P-Series/P1022-eTSEC-speed-test-issue/m-p/467411#M2749</guid>
      <dc:creator>wangruolong1</dc:creator>
      <dc:date>2016-06-01T02:27:47Z</dc:date>
    </item>
    <item>
      <title>Re: P1022 eTSEC speed test issue</title>
      <link>https://community.nxp.com/t5/P-Series/P1022-eTSEC-speed-test-issue/m-p/467412#M2750</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;iperf3, according to the first sentence on it's home page, is a tool&lt;/P&gt;&lt;P&gt;to measure the bandwidth of a _network_ , not a network node (host).&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;A class="jive-link-external-small" href="https://community.nxp.com/external-link.jspa?url=https%3A%2F%2Fiperf.fr%2F" rel="nofollow" target="_blank"&gt;https://iperf.fr/&lt;/A&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Since iperf utilized L4 protocols,&amp;nbsp; which require significant&lt;/P&gt;&lt;P&gt;processing in software, the result depends on the&lt;/P&gt;&lt;P&gt;core and platform speed as well as on the memory bandwidth. If you&lt;/P&gt;&lt;P&gt;run several instantiations of such tests, it is normal that the observed&lt;/P&gt;&lt;P&gt;performance degrades, although both eTSECs operate fully independently.&lt;/P&gt;&lt;P&gt;Some steps that may improve the result include:&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;1. Affine eTSEC interrupts to CPUs&lt;/P&gt;&lt;P&gt;2. Affine the test tasks to CPUs&lt;/P&gt;&lt;P&gt;3. Disable PTP support&lt;/P&gt;&lt;P&gt;4. Play with interrupt coalescing and Rx/Tx buffer ring sizes.&lt;/P&gt;&lt;P&gt;&amp;nbsp; These parameters are controlled by ethtool&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;We do not use iperf for benchmarking. There is a simiar test (with similar&lt;/P&gt;&lt;P&gt;limitations), netperf, for which we have a brief reproducibility guide:&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;&lt;A class="jive-link-external-small" href="https://community.nxp.com/external-link.jspa?url=https%3A%2F%2Ffreescale.sdlproducts.com%2FLiveContent%2Fcontent%2Fen-US%2FQorIQ_SDK%2FGUID-78005E19-F68E-4169-9828-952BAD67A1B0" rel="nofollow" target="_blank"&gt;https://freescale.sdlproducts.com/LiveContent/content/en-US/QorIQ_SDK/GUID-78005E19-F68E-4169-9828-952BAD67A1B0&lt;/A&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;As of the performance you can expect, benchmarking information requires&lt;/P&gt;&lt;P&gt;NDA and cannot be posted here. Please contact your distributor for&lt;/P&gt;&lt;P&gt;practically obtained performance figures.&lt;/P&gt;&lt;P&gt;&lt;BR /&gt;Have a great day,&lt;BR /&gt;Platon&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;-----------------------------------------------------------------------------------------------------------------------&lt;BR /&gt;Note: If this post answers your question, please click the Correct Answer button. Thank you!&lt;BR /&gt;-----------------------------------------------------------------------------------------------------------------------&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Wed, 01 Jun 2016 14:46:33 GMT</pubDate>
      <guid>https://community.nxp.com/t5/P-Series/P1022-eTSEC-speed-test-issue/m-p/467412#M2750</guid>
      <dc:creator>bpe</dc:creator>
      <dc:date>2016-06-01T14:46:33Z</dc:date>
    </item>
    <item>
      <title>Re: P1022 eTSEC speed test issue</title>
      <link>https://community.nxp.com/t5/P-Series/P1022-eTSEC-speed-test-issue/m-p/467413#M2751</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;firstly, thank you for your reply!!&lt;/P&gt;&lt;P&gt;here is my ethtool print information, i can not get the method to modify the Rx/Tx buffer and cannot play with interrupt coalescing. You can see that all of the buffer size is 256,how can i improve it? So，do you have some suggestion or some paper for config rx/tx buffer issues?&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;root@p1022ds:~# ethtool -g eth0&lt;/P&gt;&lt;P&gt;Ring parameters for eth0:&lt;/P&gt;&lt;P&gt;Pre-set maximums:&lt;/P&gt;&lt;P&gt;RX:&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; 256&lt;/P&gt;&lt;P&gt;RX Mini:&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; 256&lt;/P&gt;&lt;P&gt;RX Jumbo:&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; 256&lt;/P&gt;&lt;P&gt;TX:&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; 256&lt;/P&gt;&lt;P&gt;Current hardware settings:&lt;/P&gt;&lt;P&gt;RX:&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; 256&lt;/P&gt;&lt;P&gt;RX Mini:&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; 256&lt;/P&gt;&lt;P&gt;RX Jumbo:&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; 256&lt;/P&gt;&lt;P&gt;TX:&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp; 256&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Tue, 07 Jun 2016 06:17:02 GMT</pubDate>
      <guid>https://community.nxp.com/t5/P-Series/P1022-eTSEC-speed-test-issue/m-p/467413#M2751</guid>
      <dc:creator>wangruolong1</dc:creator>
      <dc:date>2016-06-07T06:17:02Z</dc:date>
    </item>
  </channel>
</rss>

