Re: [dpdk-dev] FW: [SPDK] Re: Potential defect in pci_unplug()

2020-10-13 Thread Harris, James R
On 10/12/20, 9:31 PM, "Niu, Yawei" wrote: Thanks a lot for the reply, Gaetan! So seems we have to explicitly use failsafe PMD to deal with this re-plug case? I'm not quite sure if that'll cooperate with current SPDK hotplug code seamlessly. I think it would be great if SPDK/DPDK

Re: [dpdk-dev] FW: [SPDK] Re: Potential defect in pci_unplug()

2020-10-13 Thread Niu, Yawei
Thanks a lot for the reply, Gaetan! So seems we have to explicitly use failsafe PMD to deal with this re-plug case? I'm not quite sure if that'll cooperate with current SPDK hotplug code seamlessly. I think it would be great if SPDK/DPDK can fix it internally (reconstruct the devargs on re-plu

Re: [dpdk-dev] FW: [SPDK] Re: Potential defect in pci_unplug()

2020-10-09 Thread Gaëtan Rivet
Hello, On 29/09/20 01:15 +, Niu, Yawei wrote: > > > On 2020/9/28, 11:44 PM, "Harris, James R" wrote: > > Hi Niu, > > I agree, this doesn't look right. Could you file an SPDK issue for this > to make sure we track it? And then try sending an e-mail to the DPDK mailing > li

[dpdk-dev] FW: [SPDK] Re: Potential defect in pci_unplug()

2020-09-30 Thread Niu, Yawei
On 2020/9/28, 11:44 PM, "Harris, James R" wrote: Hi Niu, I agree, this doesn't look right. Could you file an SPDK issue for this to make sure we track it? And then try sending an e-mail to the DPDK mailing list? I'm open to submitting a patch to our DPDK submodule short-term,