<html 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=us-ascii"> <meta name="Generator" content="Microsoft Word 15 (filtered medium)"> <style></style> </head> <body lang="EN-US" link="#467886" vlink="#96607D" style="word-wrap:break-word"> <div class="WordSection1"> <div id="mail-editor-reference-message-container"> <div> <div> <div> > I'm having segfault issues when running pktgen in a virtualbox virtual > machine. > > Here's what I run it in and some details about running the commands, > > and what I can do to get it to run correctly > > > pktgen version: git main brunch > > # git log > commit cc1d4c606dea3939adf75cc02de0f7cf2b28cf1e (HEAD -> main, tag: > pktgen-24.07.0, origin/main, origin/HEAD) > > dpdk version: dpdk-24.07 > > [root@localhost dpdk-24.07]# ./usertools/dpdk-devbind.py -s > > Network devices using DPDK-compatible driver > ============================================ > 0000:00:09.0 '82540EM Gigabit Ethernet Controller 100e' drv=igb_uio > unused=e1000,vfio-pci > 0000:00:0a.0 '82540EM Gigabit Ethernet Controller 100e' drv=igb_uio > unused=e1000,vfio-pci > > pktgen run command: > > gdb --args /root/pktgen-dpdk/usr/local/bin/pktgen -m 1.0 > > Port DevName Index NUMA PCI Information Src MAC > Promiscuous > Thread 1 "pktgen" received signal SIGSEGV, Segmentation fault. > 0x000000000043c38b in dump_device_info () at ../app/pktgen-port-cfg.c:102 > 102 pkt = &pinfo->seq_pkt[SINGLE_PKT]; > > (gdb) bt > #0 0x000000000043c38b in dump_device_info () at > ../app/pktgen-port-cfg.c:102 > #1 0x000000000043e3cf in pktgen_config_ports () at > ../app/pktgen-port-cfg.c:325 > #2 0x000000000043aa23 in main (argc=1, argv=0x7fffffffe2d8) at > ../app/pktgen-main.c:465 > > (gdb) n > 89 bus = rte_bus_find_by_device(dev.device); > (gdb) > 90 if (bus && !strcmp(rte_bus_name(bus), "pci")) { > (gdb) > 94 vend[0] = device[0] = '\0'; > (gdb) > 95 sscanf(rte_dev_bus_info(dev.device), "vendor_id=%4s, > device_id=%4s", vend, device); > (gdb) > 97 rte_eth_dev_get_name_by_port(i, name); > (gdb) > 98 snprintf(buff, sizeof(buff), "%s:%s/%s", vend, > device, rte_dev_name(dev.device)); > (gdb) > 90 if (bus && !strcmp(rte_bus_name(bus), "pci")) { > (gdb) > 101 pinfo = l2p_get_port_pinfo(i); > (gdb) > 102 pkt = &pinfo->seq_pkt[SINGLE_PKT]; > (gdb) > > Thread 1 "pktgen" received signal SIGSEGV, Segmentation fault. > 0x000000000043c38b in dump_device_info () at ../app/pktgen-port-cfg.c:102 > 102 pkt = &pinfo->seq_pkt[SINGLE_PKT]; > (gdb) p pinfo > $3 = (port_info_t *) 0x0 > (gdb) > > > Pktgen no longer has a maintainer, so it considered abandoned at this point. What does DPDK startup show? The problem is probably that virtualbox doesn't fully emulate the Intel NIC and the DPDK PMD doesn't like that.<o:p></o:p> <o:p> </o:p> Hi Stephen,<o:p></o:p> (sorry if formatting is bad as MacOS Outlook has some issues with plain text replies)<o:p></o:p> <o:p> </o:p> I still maintain Pktgen, but mostly from GitHub issues @ <a href="https://github.com/pktgen/Pktgen-DPDK"> https://github.com/pktgen/Pktgen-DPDK</a> I do have very limited time, so not always the fastest responses.<o:p></o:p> DPDK gets a lot of emails and sometimes I miss these emails (need to improve my emails rule filter).<o:p></o:p> I do update dpdk.org Pktgen repo when I can, but it seemed like most of the requests were coming from GitHub.<o:p></o:p> <o:p> </o:p> This person created an issue at Pktgen GitHub and also posted to this group at the same time. I did respond to his issue and try to work out a solution. I never test using a VM or containers, so it is difficult to help them sometimes.<o:p></o:p> <o:p> </o:p> If you wish you can remove Pktgen from dpdk.org, but if you do please include a link to the GitHub repository.<o:p></o:p> Thank you.<o:p></o:p> <o:p></o:p> </div> </div> </div> </div> </div> </body> </html>