Hi Vinay, This is Michael from Marvell. This bug was brought to our attention and we would like to help resolve this issue.
We analyzed the logs attached to this bug and below is our analysis : err_warn_bitmap=00000000:00400000 - 22 BIT means FCOE_ERROR_CODE_FCP_RSP_INVALID_PAYLOAD_SIZE 00000040:00000000 - BIT 38 set - means FCOE_ERROR_CODE_COMMON_INCORRECT_SEQ_CNT So it appears that there is something wrong with either the target or the fabric as the firmware is reporting invalid payload size and sequence count errors. To debug the issue further we would need a wire trace between the IOM and the target. Also TCP dump on the adapter ports of the system along with driver logs again. It will also be helpful if you can enable driver debug. Steps to enable driver debug: Load the driver with following parameters modprobe -v qedf debug=1 Thanks, Michael. -- You received this bug notification because you are a member of Kernel Packages, which is subscribed to linux in Ubuntu. https://bugs.launchpad.net/bugs/1950778 Title: Ubuntu 20.04.3 generates IO error message during FIO stress. Status in linux package in Ubuntu: Incomplete Bug description: With fio stress on Powerstore fcoe drives (lun) attached by using Qlogic QL41000 series controller, ubuntu 20.04.3 on MX740c blade server generates below mentioned i/o errors. Nov 11 20:25:17 e2e-l10-058234 kernel: [0000:3b:00.3]:[qedf_process_error_detect:1523]:13: Error detection CQE, xid=0x7bd Nov 11 20:25:17 e2e-l10-058234 kernel: [0000:3b:00.3]:[qedf_process_error_detect:1525]:13: err_warn_bitmap=00000040:00000000 Nov 11 20:25:17 e2e-l10-058234 kernel: [0000:3b:00.3]:[qedf_process_error_detect:1529]:13: tx_buff_off=00000000, rx_buff_off=00000000, rx_id=041b Nov 11 20:25:19 e2e-l10-058234 kernel: [0000:3b:00.2]:[qedf_process_error_detect:1523]:3: Error detection CQE, xid=0x34d Nov 11 20:25:19 e2e-l10-058234 kernel: [0000:3b:00.2]:[qedf_process_error_detect:1525]:3: err_warn_bitmap=00000040:00000000 Nov 11 20:25:19 e2e-l10-058234 kernel: [0000:3b:00.2]:[qedf_process_error_detect:1529]:3: tx_buff_off=00000000, rx_buff_off=00000000, rx_id=01f7 Steps to reproduce. 1. Configure QL41000 series controller on MX MX740c blade server. 2. Configure APM3246 array directly connected to chassis module MX9116n. 3. Install Ubuntu 20.04.3 in any local drive. 4. start I/O by using fio : # fio FileSystemCreateSingle/fio_test.cfg then we can observe error message in syslog To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1950778/+subscriptions -- Mailing list: https://launchpad.net/~kernel-packages Post to : kernel-packages@lists.launchpad.net Unsubscribe : https://launchpad.net/~kernel-packages More help : https://help.launchpad.net/ListHelp
