Hi Sagi, Thanks! It works with kernel version 4.17.3-1. $ uname -v #1 SMP Debian 4.17.3-1 (2018-07-02) Best, Bairen > On 11 Jul 2018, at 18:37, Sagi Grimberg <sagi@xxxxxxxxxxx> wrote: > > >> The exact kernel version is 4.15.0-23.25 as in >> https://packages.ubuntu.com/bionic/linux-image-4.15.0-23-generic >> I tried again with the latest Debian unstable (kernel version 4.16.5) and the symptoms remain the same. > > Looking at linux-stable, looks like the suspected missing commit [1] > entered in tag v4.16.17, so I'm not sure it exists in your tested > kernel, Not sure where I can access the source to verify. > > [1] >>> Possible suspect might be: >>> -- >>> commit 2da36d44a9d54a2c6e1f8da1f7ccc26b0bc6cfec >>> Author: Jianchao Wang <jianchao.w.wang@xxxxxxxxxx> >>> Date: Thu Apr 26 11:52:39 2018 +0800 >>> >>> IB/rxe: add RXE_START_MASK for rxe_opcode IB_OPCODE_RC_SEND_ONLY_INV >>> >>> w/o RXE_START_MASK, the last_psn of IB_OPCODE_RC_SEND_ONLY_INV >>> will not be updated in update_wqe_psn, and the corresponding >>> wqe will not be acked in rxe_completer due to its last_psn is >>> zero. Finally, the other wqe will also not be able to be acked, >>> because the wqe of IB_OPCODE_RC_SEND_ONLY_INV with last_psn 0 >>> is still there. This causes large amount of io timeout when >>> nvmeof is over rxe. >>> >>> Add RXE_START_MASK for IB_OPCODE_RC_SEND_ONLY_INV to fix this. >>> >>> Signed-off-by: Jianchao Wang <jianchao.w.wang@xxxxxxxxxx> >>> Reviewed-by: Zhu Yanjun <yanjun.zhu@xxxxxxxxxx> >>> Signed-off-by: Doug Ledford <dledford@xxxxxxxxxx> >>> -- -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
