From mboxrd@z Thu Jan 1 00:00:00 1970 From: mr.nuke.me@gmail.com (Alex G.) Date: Fri, 6 Apr 2018 10:46:11 -0500 Subject: IRQ/nvme_pci_complete_rq: NULL pointer dereference yet again In-Reply-To: <20180406153236.GK10098@localhost.localdomain> References: <5d6d1a8c-6490-4046-0fba-da0a0df3d00c@gmail.com> <20180405213847.GG10098@localhost.localdomain> <20180405212205.33dqwqck2co25a3x@sbauer-Z170X-UD5> <719ea777-e57d-511e-52c5-cf83027d1fd0@gmail.com> <20180405224138.GH10098@localhost.localdomain> <20180405224830.GI10098@localhost.localdomain> <20180405230515.GJ10098@localhost.localdomain> <75edea4e-b961-82a1-3612-fc682a248819@gmail.com> <20180406153236.GK10098@localhost.localdomain> Message-ID: <43f32a5a-b147-3620-154c-e3bb839c5aba@gmail.com> On 04/06/2018 10:32 AM, Keith Busch wrote: > On Thu, Apr 05, 2018@06:44:21PM -0500, Alex G. wrote: >> Actually, it crashed very fast [1] > > Could you possibly do an experiment for this? Does this happen if you're > not using MD RAID and disable NVME_MULTIPATH? I can, though the whole point of the lvm mirror is to cause IO to the drive after hot-insert. Without that IO, there's a much smaller window to get PCIe errors on SURPRISE!!! removal. Alex