<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"> <head> <meta http-equiv="Content-Type" content="text/html; charset=utf-8"> <meta name="Generator" content="Microsoft Word 15 (filtered medium)"> <style></style> </head> <body lang="en-IL" link="#0563C1" vlink="#954F72" style="word-wrap:break-word"> <div class="WordSection1"> Hi Ori Thank you for your answer it helped me But I can see the load balancing is not done to the same instance for both directions I would like to have ip + port pairs arrive to same instance Now ip1+port1 -> ip2+port2 arrive to instance x and ip2+port2 -> ip1+port1 arrive to another instance How can I solve this?<o:p></o:p> <o:p> </o:p> <div> <div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0cm 0cm 0cm"> From: Ori Kam <orika@nvidia.com> Sent: Wednesday, February 14, 2024 6:07 PM To: Yaron Illouz <yaroni@radcom.com>; dev@dpdk.org; 'users@dpdk.org' <users@dpdk.org> Subject: RE: rss calculation as the nic<o:p></o:p> </div> </div> <o:p> </o:p> <table class="MsoNormalTable" border="0" cellspacing="0" cellpadding="0" style="background:#FFF2CC;border-collapse:collapse"> <tbody> <tr> <td width="576" valign="top" style="width:432.35pt;background:#FBE4D5;padding:0cm 5.4pt 0cm 5.4pt"> <a name="_Hlk88152779">EXTERNAL EMAIL:</a> Do not click links or attachments unless you recognize the sender and know the content is safe<o:p></o:p> </td> </tr> </tbody> </table> <o:p></o:p> <div> Hi Yaron,<o:p></o:p> <o:p> </o:p> I can see some possible issues with your code, please see below.<o:p></o:p> <o:p> </o:p> <div style="border:none;border-left:solid blue 1.5pt;padding:0cm 0cm 0cm 4.0pt"> <div> <div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0cm 0cm 0cm"> From: Yaron Illouz <<a href="mailto:yaroni@radcom.com">yaroni@radcom.com</a>> Sent: Saturday, February 3, 2024 7:03 PM To: <a href="mailto:dev@dpdk.org">dev@dpdk.org</a>; 'users@dpdk.org' <<a href="mailto:users@dpdk.org">users@dpdk.org</a>> Subject: rss calculation as the nic<o:p></o:p> </div> </div> <o:p> </o:p> [Snip]<o:p></o:p> <o:p> </o:p> static inline uint32_t<o:p></o:p> do_softrss(struct rte_mbuf *m)<o:p></o:p> {<o:p></o:p> uint32_t input_len;<o:p></o:p> struct rte_ipv4_tuple ipv4_tuple;<o:p></o:p> <o:p></o:p> char * pRawPacket = static_cast<char*>(rte_pktmbuf_mtod(pi_mbuf, void* ));<o:p></o:p> IpHeader * pIpHeader = (IpHeader *)(pRawPacket + offsetOfIp);<o:p></o:p> if(pIpHeader->GetVersion()==4)<o:p></o:p> {<o:p></o:p> ipv4_tuple.src_addr = rte_be_to_cpu_32(pIpHeader->dwSrcAddressBigEndian);<o:p></o:p> ipv4_tuple.dst_addr = rte_be_to_cpu_32(pIpHeader->dwDstAddressBigEndian);<o:p></o:p> [Ori] here you are converting BE to CPU <o:p></o:p> ipv4_tuple.sport = *(uint16_t*)(pRawPacket + transportLayerOffset);<o:p></o:p> ipv4_tuple.dport = *(uint16_t*)(pRawPacket + transportLayerOffset+2);<o:p></o:p> [Ori] here you keep the values as BE<o:p></o:p> input_len = RTE_THASH_V4_L3_LEN;<o:p></o:p> return rte_softrss_be((uint32_t *)&ipv4_tuple, input_len, rss_key_be);<o:p></o:p> [Ori] the above function expects to get everything in BE and you should also call rte_convert_rss_key before the use of the above function.<o:p></o:p> }<o:p></o:p> return 0;<o:p></o:p> }<o:p></o:p> new_rss = do_softrss(mbuf_pointer);<o:p></o:p> std::cout<< std::hex << mbuf_pointer->hash.rss << " -> " << new_rss << std::dec << std::endl;<o:p></o:p> <o:p> </o:p> And i get a different value than the mbuf_pointer->hash.rss<o:p></o:p> 5ed28a5c -> 33eb33eb<o:p></o:p> 974c1896 -> 24e224e2<o:p></o:p> 1edf1638 -> 21752175<o:p></o:p> 8a54c19 -> 80638063<o:p></o:p> 459a6f76 -> 1b351b35<o:p></o:p> 1cdf1d1c -> e53be53b<o:p></o:p> <o:p> </o:p> <o:p> </o:p> **** I understand it is possible to do it, but i don't get the same value ***<o:p></o:p> ethtool -i ens5f0<o:p></o:p> driver: mlx5_core<o:p></o:p> version: 5.8-3.0.7<o:p></o:p> firmware-version: 22.32.2004 (MT_0000000437)<o:p></o:p> expansion-rom-version:<o:p></o:p> bus-info: 0000:83:00.0<o:p></o:p> supports-statistics: yes<o:p></o:p> supports-test: yes<o:p></o:p> supports-eeprom-access: no<o:p></o:p> supports-register-dump: no<o:p></o:p> supports-priv-flags: yes<o:p></o:p> <o:p> </o:p> </div> </div> </div> </body> </html>