December 28, 201213 yr So two times I've started a parity check, and about 12 hours into it samba and emhttpd become unresponsive. I can telnet to the box and look at the log (which shows nothing special at all, just the scrolling "notifications" errors from simpleFeatures. All of my Plugins work and are very responsive (SAB, SB, CP, Transmission)...just the unRAID processes have the issue. This happened first yesterday, and I figured it was a fluke so restarted the box...and started a new parity check. Now it's happening again I've looked at every log I can find, nothing special noted. iostat shows: root@Storage:/tmp# iostat Linux 3.0.35-unRAID (Storage) 12/28/2012 _i686_ (8 CPU) avg-cpu: %user %nice %system %iowait %steal %idle 4.21 0.00 2.99 3.83 0.00 88.97 Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn sdb 443.63 607.98 4665.00 35083652 269193380 sda 645.15 32439.77 399.19 1871935635 23035224 sdd 452.53 32041.10 0.00 1848930312 88 sdc 450.60 32110.72 0.00 1852947872 48 sde 0.03 1.29 0.00 74455 230 sdf 0.00 0.00 0.00 200 0 sdg 441.22 32040.84 0.00 1848915172 48 sdh 453.48 32040.74 0.00 1848909392 48 sdi 416.39 32040.71 0.00 1848907904 48 sdj 398.49 32040.68 0.00 1848906340 48 sdk 389.02 32438.63 397.93 1871869831 22962252 sdl 361.34 32112.15 0.00 1853030375 48 sdm 335.27 32119.82 0.00 1853472700 48 sdn 147.50 32064.19 1.26 1850262908 72548 md1 0.13 0.52 0.00 29796 88 md2 0.71 70.14 0.00 4047396 48 md3 0.03 0.10 0.00 5864 48 md4 0.03 0.13 0.00 7428 48 md5 0.04 0.15 0.00 8916 48 md6 0.07 0.28 0.00 16236 48 md7 0.64 22.35 1.26 1289932 72548 md8 0.75 79.23 0.00 4572220 48 md9 0.70 71.57 0.00 4129860 48 md10 99.51 0.12 397.93 7112 22962252 But I noticed as I was looking around that the "load" on the box which was at 3-5 during the parity check until this point is climbing slowly. After ~60 minutes it is up to 30 and still climbing. Any ideas? Should I let the thing sit until the parity check is over? How can I see what is going on with the check without web access? ServerSpecs in Sig, running 5.0-rc5-r8168
December 28, 201213 yr Author Checked on the console, no messages since boot. Syslog has had no updates at all since the issue started (Other than the in.telnetd line for my connection) Finally checked the dmesg and now am VERY concerend! sas: command 0xe9db8c00, task 0xf7510a00, timed out: BLK_EH_NOT_HANDLED sas: Enter sas_scsi_recover_host sas: trying to find task 0xf7510a00 sas: sas_scsi_find_task: aborting task 0xf7510a00 sas: sas_scsi_find_task: querying task 0xf7510a00 drivers/scsi/mvsas/mv_sas.c 1747:mvs_query_task:rc= 5 sas: sas_scsi_find_task: task 0xf7510a00 failed to abort sas: task 0xf7510a00 is not at LU: I_T recover sas: I_T nexus reset for dev 0000000000000000 sas: sas_form_port: phy0 belongs to port0 already(1)! drivers/scsi/mvsas/mv_sas.c 1701:mvs_I_T_nexus_reset for device[0]:rc= 0 sas: I_T 0000000000000000 recovered sas: sas_ata_task_done: SAS error 8d ata8: sas eh calling libata port error handler sas: sas_ata_task_done: SAS error 2 ata8: failed to read log page 10h (errno=-5) ata8.00: exception Emask 0x1 SAct 0x1 SErr 0x0 action 0x6 t0 ?????????????? ata8.00: failed command: READ FPDMA QUEUED ata8.00: cmd 60/00:00:27:e9:67/02:00:dc:00:00/40 tag 0 ncq 262144 in res 01/04:04:27:e7:67/00:00:dc:00:00/40 Emask 0x3 (HSM violation) ata8.00: status: { ERR } ata8.00: error: { ABRT } ata8: hard resetting link sas: sas_form_port: phy0 belongs to port0 already(1)! drivers/scsi/mvsas/mv_sas.c 1701:mvs_I_T_nexus_reset for device[0]:rc= 0 sas: sas_ata_hard_reset: Found ATA device. ata8.00: configured for UDMA/133 ata8: EH complete ata9: sas eh calling libata port error handler ata10: sas eh calling libata port error handler 1 ata11: sas eh calling libata port error handler ard/sickbeard.pid > /dev/null 2>&1 ata12: sas eh calling libata port error handler pData/mysql/Storage.err --pid-file= ata13: sas eh calling libata port error handler ata14: sas eh calling libata port error handler ata15: sas eh calling libata port error handler sas: --- Exit sas_scsi_recover_host sas: command 0xe9db8c00, task 0xf70c0f00, timed out: BLK_EH_NOT_HANDLED root@Storage:/var/log# tail -f dmesg sas: DONE DISCOVERY on port 7, pid:958, result:0 sd 8:0:4:0: [sdk] Attached SCSI disk sd 8:0:7:0: [sdn] 4096-byte physical blocks sd 8:0:7:0: [sdn] Write Protect is off sd 8:0:7:0: [sdn] Mode Sense: 00 3a 00 00 sd 8:0:7:0: [sdn] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA sdl: sdl1 sd 8:0:5:0: [sdl] Attached SCSI disk sdn: sdn1 sd 8:0:7:0: [sdn] Attached SCSI disk Going to shut down and remove the second card. Only one tiny disk on it right now that isn't in the array...but it looks like that's what's causing the issue (figuring ata8-15 are on the second of the expansion cards?)
December 28, 201213 yr Author Ok, searching with those errors leads me to upgrade. Will hold this thread open until I can test the most current rc. Sorry!
Archived
This topic is now archived and is closed to further replies.