hi all, recently i implemented rbd backend for tcmu-runner, but i met some issues, i used dd to fill data into the lun case 1: dd if=/dev/zero of=/dev/sdb bs=4K count=100, everything works fine, and file size is changed to 409600 byte case 2: dd if=/dev/zero of=/dev/sdb bs=4K count=1000, dmesg shows below error: [ 193.952776] Rounding down aligned max_sectors from 4294967295 to 4294967288 [ 261.358350] scsi host2: iSCSI Initiator over TCP/IP [ 261.364724] scsi 2:0:0:0: Direct-Access LIO-ORG TCMU device 0002 PQ: 0 ANSI: 5 [ 261.365999] sd 2:0:0:0: Attached scsi generic sg2 type 0 [ 261.366575] sd 2:0:0:0: [sdb] 20971520 512-byte logical blocks: (10.7 GB/10.0 GiB) [ 261.369692] sd 2:0:0:0: [sdb] Write Protect is off [ 261.369694] sd 2:0:0:0: [sdb] Mode Sense: 03 00 00 00 [ 261.369865] sd 2:0:0:0: [sdb] Asking for cache data failed [ 261.369923] sd 2:0:0:0: [sdb] Assuming drive cache: write through [ 261.375970] sd 2:0:0:0: [sdb] Attached SCSI disk [ 263.883541] blk_update_request: I/O error, dev fd0, sector 0 [ 263.883603] floppy: error -5 while reading block 0 [ 267.870538] blk_update_request: I/O error, dev fd0, sector 0 [ 267.870591] floppy: error -5 while reading block 0 [ 344.299712] TCMU: Request of size 16096/4096000 may be too big for 65408/1052672 cmd/data ring buffers [ 361.592534] connection1:0: ping timeout of 5 secs expired, recv timeout 5, last rx 4295018624, last ping 4295016352, now 4295028642 [ 361.592689] connection1:0: detected conn error (1022) [ 378.902500] iSCSI Login timeout on Network Portal 0.0.0.0:3260 [ 482.006579] session1: session recovery timed out after 120 secs [ 482.006625] sd 2:0:0:0: rejecting I/O to offline device [ 482.006697] sd 2:0:0:0: [sdb] killing request [ 482.006970] sd 2:0:0:0: [sdb] FAILED Result: hostbyte=DID_NO_CONNECT driverbyte=DRIVER_OK [ 482.006996] sd 2:0:0:0: [sdb] CDB: Write(10) 2a 00 00 00 00 00 00 1f 40 00 [ 482.007010] blk_update_request: I/O error, dev sdb, sector 0 [ 482.007075] Buffer I/O error on dev sdb, logical block 0, lost async page write [ 482.007161] Buffer I/O error on dev sdb, logical block 1, lost async page write [ 482.007224] Buffer I/O error on dev sdb, logical block 2, lost async page write [ 482.007292] Buffer I/O error on dev sdb, logical block 3, lost async page write [ 482.007340] Buffer I/O error on dev sdb, logical block 4, lost async page write [ 482.007400] Buffer I/O error on dev sdb, logical block 5, lost async page write [ 482.007450] Buffer I/O error on dev sdb, logical block 6, lost async page write [ 482.007504] Buffer I/O error on dev sdb, logical block 7, lost async page write [ 482.007560] Buffer I/O error on dev sdb, logical block 8, lost async page write [ 482.007606] Buffer I/O error on dev sdb, logical block 9, lost async page write it seems that the data size is greater than the ring buffer size, also there is timeout, but i am not sure this is due to large data size, any help will be appreciated? -- To unsubscribe from this list: send the line "unsubscribe target-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
