From mboxrd@z Thu Jan 1 00:00:00 1970 From: swise@opengridcomputing.com (Steve Wise) Date: Fri, 9 Sep 2016 10:57:45 -0500 Subject: nvmf/rdma host crash during heavy load and keep alive recovery In-Reply-To: <01bb01d209f5$1b7585d0$52609170$@opengridcomputing.com> References: <018301d1e9e1$da3b2e40$8eb18ac0$@opengridcomputing.com> <010f01d1f31e$50c8cb40$f25a61c0$@opengridcomputing.com> <013701d1f320$57b185d0$07149170$@opengridcomputing.com> <018401d1f32b$792cfdb0$6b86f910$@opengridcomputing.com> <01a301d1f339$55ba8e70$012fab50$@opengridcomputing.com> <2fb1129c-424d-8b2d-7101-b9471e897dc8@grimberg.me> <004701d1f3d8$760660b0$62132210$@opengridcomputing.com> <008101d1f3de$557d2850$007778f0$@opengridcomputing.com> <00fe01d1f3e8$8992b330$9cb81990$@opengridcomputing.com> <01c301d1f702$d28c7270$77a55750$@opengridcomputing.com> <6ef9b0d1-ce84-4598-74db-7adeed313bb6@grimberg.me> <045601d1f803$a9d73a20$fd85ae60$@opengridcomputing.com> <69c0e819-76d9-286b-c4fb-22f087f36ff1@grimberg.me> <08b701d1f8ba$a709ae10$f51d0a30$@opengridcomputing.com> <01c301d20485$0dfcd2c0$29f67840$@opengridcomputing.com> <0c159abb -24ee-21bf-09d2-9fe7d2 69a2eb@grimberg.me> <039601d2094f$80481640$80d842c0$@opengridcomputing.com> <9fd1f090-3b86-b496-d8c0-225ac0815fbe@grimbe rg.me> <01bb01d209f5$ 1b7585d0$52609170$@opengridcomputing.com> Message-ID: <00b501d20ab2$e7f78320$b7e68960$@opengridcomputing.com> > > > > I can't explain this, but the nvme_rdma_queue.flags field has a bit set that > shouldn't be set: > > crash> nvme_rdma_queue.flags -x ffff880e52b8e7e8 > flags = 0x14 > > Bit 2 is set, NVME_RDMA_Q_DELETING, but bit 4 is also set and should never be... > > enum nvme_rdma_queue_flags { > NVME_RDMA_Q_CONNECTED = (1 << 0), > NVME_RDMA_IB_QUEUE_ALLOCATED = (1 << 1), > NVME_RDMA_Q_DELETING = (1 << 2), > }; > > The rest of the structure looks fine. I've also seen crash dumps where bit 3 is > set which is also not used. > > /me confused... I'm dumb: 1<<0 is 1, so CONNECTED is bit 1, QUEUE_ALLOCATED is bit 2, and Q_DELETING is bit 4! Bits 0 and 3 are not used. So 0x14 is bits 4 and 2: DELETING and QUEUE_ALLOCATED. The queue_flags enum should not be using the (1<