I was just looking to see if it is a known problem before I submit it as a bug. What would be the best category to submit the bug under? I am not sure if it is driver/kernel issue. I would be more than glad to help. One of the machines is a test environment and I can run any dumps/debug versions you want.
The issue is reproducible on the two servers Sun and Dell and with different SAS JBOD storage. The systems consist of raidz2 pool, made from 11 SATA large disks (1.5TB Seagate). The pool is 60% or so full. The easiest way to reproduce it is when running bacula client to back the whole pool overnight. After couple of hours the issue will manifest. The machine will just print these messages and not respond to any connections, even keyboard. I was looking into one other machine that we have – a relatively old custom build machine with 11 1TB (Western Digital) disks connected to 8 port SATA controller (+3 from the motherboard). I noticed that there are similar messages for the disks there. The machine doesn’t lock, just prints the messages when under heavy load (backup), see bellow: ============================ Operating System: Solaris 10 8/07 s10x_u4wos_12b X86 Adapter: 8 port SATA: http://www.supermicro.com/products/accessories/addon/AOC-SAT2-MV8.cfm Oct 21 17:47:22 mirror sata: [ID 801593 kern.notice] NOTICE: /p...@0,0/pci10de,2...@10/pci11ab,1...@6: Oct 21 17:47:22 mirror port 1: link lost Oct 21 17:47:22 mirror sata: [ID 801593 kern.notice] NOTICE: /p...@0,0/pci10de,2...@10/pci11ab,1...@6: Oct 21 17:47:22 mirror port 1: link established Oct 21 17:47:22 mirror marvell88sx: [ID 812950 kern.warning] WARNING: marvell88sx0: error on port 1: Oct 21 17:47:22 mirror marvell88sx: [ID 517869 kern.info] device disconnected Oct 21 17:47:22 mirror marvell88sx: [ID 517869 kern.info] device connected Oct 21 17:47:22 mirror scsi: [ID 107833 kern.warning] WARNING: /p...@0,0/pci10de,2...@10/pci11ab,1...@6/d...@1,0 (sd2): Oct 21 17:47:22 mirror Error for Command: read(10) Error Level: Retryable Oct 21 17:47:22 mirror scsi: [ID 107833 kern.notice] Requested Block: 178328863 Error Block: 178328863 Oct 21 17:47:22 mirror scsi: [ID 107833 kern.notice] Vendor: ATA Serial Number: Oct 21 17:47:22 mirror scsi: [ID 107833 kern.notice] Sense Key: No Additional Sense Oct 21 17:47:22 mirror scsi: [ID 107833 kern.notice] ASC: 0x0 (no additional sense info), ASCQ: 0x0, FRU: 0x0 Oct 21 17:58:51 mirror sata: [ID 801593 kern.notice] NOTICE: /p...@0,0/pci10de,2...@10/pci11ab,1...@6: Oct 21 17:58:51 mirror port 0: device reset Oct 21 17:58:51 mirror sata: [ID 801593 kern.notice] NOTICE: /p...@0,0/pci10de,2...@10/pci11ab,1...@6: Oct 21 17:58:51 mirror port 0: device reset Oct 21 17:58:51 mirror sata: [ID 801593 kern.notice] NOTICE: /p...@0,0/pci10de,2...@10/pci11ab,1...@6: Oct 21 17:58:51 mirror port 0: link lost Oct 21 17:58:51 mirror sata: [ID 801593 kern.notice] NOTICE: /p...@0,0/pci10de,2...@10/pci11ab,1...@6: Oct 21 17:58:51 mirror port 0: link established Oct 21 17:58:51 mirror marvell88sx: [ID 812950 kern.warning] WARNING: marvell88sx0: error on port 0: Oct 21 17:58:51 mirror marvell88sx: [ID 517869 kern.info] device disconnected Oct 21 17:58:51 mirror marvell88sx: [ID 517869 kern.info] device connected Oct 21 17:58:51 mirror scsi: [ID 107833 kern.warning] WARNING: /p...@0,0/pci10de,2...@10/pci11ab,1...@6/d...@0,0 (sd1): Oct 21 17:58:51 mirror Error for Command: read(10) Error Level: Retryable Oct 21 17:58:51 mirror scsi: [ID 107833 kern.notice] Requested Block: 929071121 Error Block: 929071121 Oct 21 17:58:51 mirror scsi: [ID 107833 kern.notice] Vendor: ATA Serial Number: Oct 21 17:58:51 mirror scsi: [ID 107833 kern.notice] Sense Key: No Additional Sense Oct 21 17:58:51 mirror scsi: [ID 107833 kern.notice] ASC: 0x0 (no additional sense info), ASCQ: 0x0, FRU: 0x0 Oct 21 18:02:10 mirror sata: [ID 801593 kern.notice] NOTICE: /p...@0,0/pci10de,2...@10/pci11ab,1...@6: Oct 21 18:02:10 mirror port 4: device reset Oct 21 18:02:10 mirror sata: [ID 801593 kern.notice] NOTICE: /p...@0,0/pci10de,2...@10/pci11ab,1...@6: Oct 21 18:02:10 mirror port 4: device reset Oct 21 18:02:10 mirror sata: [ID 801593 kern.notice] NOTICE: /p...@0,0/pci10de,2...@10/pci11ab,1...@6: Oct 29 00:03:24 mirror sata: [ID 801593 kern.notice] NOTICE: /p...@0,0/pci10de,2...@10/pci11ab,1...@6: Oct 29 00:03:24 mirror port 5: device reset Oct 29 00:03:24 mirror sata: [ID 801593 kern.notice] NOTICE: /p...@0,0/pci10de,2...@10/pci11ab,1...@6: Oct 29 00:03:24 mirror port 5: device reset Oct 29 00:03:24 mirror sata: [ID 801593 kern.notice] NOTICE: /p...@0,0/pci10de,2...@10/pci11ab,1...@6: Oct 29 00:03:24 mirror port 5: link lost Oct 29 00:03:24 mirror sata: [ID 801593 kern.notice] NOTICE: /p...@0,0/pci10de,2...@10/pci11ab,1...@6: Oct 29 00:03:24 mirror port 5: link established Oct 29 00:03:24 mirror marvell88sx: [ID 812950 kern.warning] WARNING: marvell88sx0: error on port 5: Oct 29 00:03:24 mirror marvell88sx: [ID 517869 kern.info] device disconnected Oct 29 00:03:24 mirror marvell88sx: [ID 517869 kern.info] device connected Oct 29 00:03:24 mirror scsi: [ID 107833 kern.warning] WARNING: /p...@0,0/pci10de,2...@10/pci11ab,1...@6/d...@5,0 (sd6): Oct 29 00:03:24 mirror Error for Command: write(10) Error Level: Retryable Oct 29 00:03:24 mirror scsi: [ID 107833 kern.notice] Requested Block: 1513181930 Error Block: 1513181930 Oct 29 00:03:24 mirror scsi: [ID 107833 kern.notice] Vendor: ATA Serial Number: Oct 29 00:03:24 mirror scsi: [ID 107833 kern.notice] Sense Key: No Additional Sense Oct 29 00:03:24 mirror scsi: [ID 107833 kern.notice] ASC: 0x0 (no additional sense info), ASCQ: 0x0, FRU: 0x0 -- This message posted from opensolaris.org _______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
