<div dir="ltr"><div class="gmail_default" style="font-family:verdana,sans-serif">Hi Stephen and Michal</div><div class="gmail_default" style="font-family:verdana,sans-serif"><br></div><div class="gmail_default" style="font-family:verdana,sans-serif">Thanks a lot for all the discussions and progress made on this.Appreciate it.</div><div class="gmail_default" style="font-family:verdana,sans-serif">Sorry for the late reply. To answer your questions:</div><div class="gmail_default" style="font-family:verdana,sans-serif"><i><br></i></div><div class="gmail_default" style="font-family:verdana,sans-serif"><i><span style="font-family:Arial,Helvetica,sans-serif">1. Is the application you're using the single-process or multiprocess?</span><br style="font-family:Arial,Helvetica,sans-serif"><span style="font-family:Arial,Helvetica,sans-serif">If so, from which process are you probing for the xstats?</span></i></div><div class="gmail_default" style="font-family:verdana,sans-serif">>> System has both primary and secondary processes running. but the stats are being fetched from the<b> primary process</b> only. I'm not sure if the presence of secondary processes is causing the crash even if we try to fetch stats from the primary process. Can we confirm this from the code?</div><div class="gmail_default" style=""><font face="verdana, sans-serif"><br style=""></font><i style="font-family:verdana,sans-serif"><span style="font-family:Arial,Helvetica,sans-serif">2. Have you tried running latest DPDK v20.11 LTS?</span></i></div><div class="gmail_default" style=""><i style="font-family:verdana,sans-serif">>> </i><span style="font-family:verdana,sans-serif">It's DPDK v20.11.1. Did not try with the latest 20.11 LTS.</span></div><div class="gmail_default" style=""><font face="verdana, sans-serif"><br style=""></font><span style="font-family:Arial,Helvetica,sans-serif;font-style:italic">3. What kernel module are you using (igb_uio/vfio-pci)?</span></div><div class="gmail_default" style=""><span style="font-family:verdana,sans-serif">>> It's igb_uio.</span></div><div class="gmail_default" style=""><font face="verdana, sans-serif"><br style=""></font><span style="font-family:Arial,Helvetica,sans-serif;font-style:italic">4. On what AWS instance type it was reproduced?</span></div><div class="gmail_default" style=""><span style="font-family:verdana,sans-serif">>> It's c5n.2xlarge. ( 8 cores. 1 primary process and 6 secondary processes.)</span></div><div class="gmail_default" style=""><font face="verdana, sans-serif"><br style=""></font><span style="font-family:Arial,Helvetica,sans-serif;font-style:italic">5. Is the Seg Fault happening the first time you call for the xstats?</span><br></div><div class="gmail_default" style=""><span style="font-family:verdana,sans-serif"><span style="font-family:Arial,Helvetica,sans-serif">>> Yes. That's correct.</span></span></div><div class="gmail_default" style="font-family:verdana,sans-serif"><br></div><div class="gmail_default" style="font-family:verdana,sans-serif">Regards</div><div class="gmail_default" style="font-family:verdana,sans-serif">Amiya</div><div class="gmail_default" style="font-family:verdana,sans-serif"><br></div><div class="gmail_default" style="font-family:verdana,sans-serif"><br></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Wed, Apr 20, 2022 at 4:39 AM Stephen Hemminger <<a href="mailto:stephen@networkplumber.org">stephen@networkplumber.org</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">On Tue, 19 Apr 2022 22:27:32 +0200<br> Michał Krawczyk <<a href="mailto:mk@semihalf.com" target="_blank">mk@semihalf.com</a>> wrote:<br> <br> > Thanks Stephen, indeed the issue reproduces in the secondary process.<br> > <br> > Basically ENA v2.2.1 is not MP aware, meaning it cannot be used safely<br> > from the secondary process. The main obstacle is the admin queue which<br> > is used for processing the hardware requests which can be used safely<br> > only from the primary process. It's not strictly a bug, as we weren't<br> > exposing 'MP Awareness' in the PMD features list, it's more like a<br> > lack of proper MP support.<br> > <br> > The latest ENA PMD release should be MP safe. We currently don't have<br> > PMD backport ready for the older LTS release (but we're planning to do<br> > so for ENA v2.6.0 on the amzn-drivers repository:<br> > <a href="https://urldefense.com/v3/__https://github.com/amzn/amzn-drivers/tree/master/userspace/dpdk__;!!Mt_FR42WkD9csi9Y!ZAgIa147k7j0wwnu83K-vq8T9bH0gWwoldqHg9IshR1CSkTYpJOLzT35FhtlVPDkWbN9CZMv469Jj68fwxrqFsQQErwYHNc$" rel="noreferrer" target="_blank">https://urldefense.com/v3/__https://github.com/amzn/amzn-drivers/tree/master/userspace/dpdk__;!!Mt_FR42WkD9csi9Y!ZAgIa147k7j0wwnu83K-vq8T9bH0gWwoldqHg9IshR1CSkTYpJOLzT35FhtlVPDkWbN9CZMv469Jj68fwxrqFsQQErwYHNc$</a> ). <br> <br> I wish that ENA did not have its own versioning scheme.<br> Driver versions are meaningful only to the driver writer/vendor, they<br> don't help the end user.<br> <br> Since backporting is not part of stable process. I suggest doing what<br> XDP did for 21.11 and earlier releases.<br> <br> diff --git a/drivers/net/ena/ena_ethdev.c b/drivers/net/ena/ena_ethdev.c<br> index 634c97acf60d..3778349f3fe9 100644<br> --- a/drivers/net/ena/ena_ethdev.c<br> +++ b/drivers/net/ena/ena_ethdev.c<br> @@ -3212,6 +3212,12 @@ static int ena_rx_queue_intr_disable(struct rte_eth_dev *dev,<br> static int eth_ena_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,<br> struct rte_pci_device *pci_dev)<br> {<br> + if (rte_eal_process_type() == RTE_PROC_SECONDARY) {<br> + PMD_INIT_LOG(ERR,<br> + "Ena PMD does not support secondary processes\n");<br> + return -ENOTSUP;<br> + }<br> +<br> return rte_eth_dev_pci_generic_probe(pci_dev,<br> sizeof(struct ena_adapter), eth_ena_dev_init);<br> }<br> </blockquote></div>