4 Replies Latest reply on Apr 25, 2016 4:00 PM by Intel Corporation

    Frequently warning PD Reset with RES2CV240 SAS Expander

    nightTOB

      I have a RAID 6 array with 10 2TB SATA HDDs attach to RES2CV240(ph13 F/W).

      And I use Hard Disk Sentinel to monitor HDDs' SMART status.

       

      When HD Sentinel start or refresh status (default 5 minutes), the MegaRAID Storage Manager shows several warnings and informations, like:

      Controller ID: 0 Unexpected sense: PD = 8-Invaild field in CDB, CDB = 0x5a 0x00 0x1c 0x00 0x00 0x00 0x00 0x00 0xfc 0x00, Sense: 0x70 0x00 0x05 0x00 0x00 0x00 0x00 0x0a 0x00 0x00 0x00 0x00 0x24 0x00 0x00 0x00 0x00 0x00

      Controller ID: 0 Unexpected sense: PD = 8-Invaild field in CDB, CDB = 0x4d 0x00 0x40 0x00 0x00 0x00 0x00 0x00 0xfc 0x00, Sense: 0x70 0x00 0x05 0x00 0x00 0x00 0x00 0x0a 0x00 0x00 0x00 0x00 0x24 0x00 0x00 0x00 0x00 0x00

      Controller ID: 0 PD Reset: PD = 8, Error = 3, Path = 0x5001E673D9DDDFFD

      Controller ID: 0 PD Reset: PD = 8, Error = 3, Path = 0x5001E673D9DDDFFD

       

      The TTY Log is:

      04/20/16 21:03:07: DM: Chip 0 Paused
      04/20/16 21:03:07: Chip <0> Slots: Cur=[164]
      04/20/16 21:03:07: [a6]= 1
      04/20/16 21:03:09: DM: Timing wheel expired - Chip 0 Slot a6
      04/20/16 21:03:09: Chip <0> Slots: Cur=[166]
      04/20/16 21:03:09: [a6]= 1
      04/20/16 21:03:09: TIMEOUT: rdm 6055be00, devHandle 0014, mid 0975, Cmd 09, devId 0008, devState 0020, devFlags 1400005
      04/20/16 21:03:09: DM_TMWheelScanAllMsg (slot a6):Scanned 1, Timeout 1 Msg mask 21000
      04/20/16 21:03:09: DM_SetTMReqForDevH: tm request for deviceHandle[14] devid[8] path[0] tmRequired[1], tmActive[0], countReqTM[1] countActiveTM:0 flags:1400005 devState:20 tmReqAlt:0 tmActAlt:0
      04/20/16 21:03:09: MPT_ProcessTaskMgmtQueue: Task Mgmt Start Addr c113b900 DevId[8]  Index 8ff chip 0 type 3 numCmdIssued 2 cQDepth :1 devFlags:1482005 state:20 devHdl:14
      04/20/16 21:03:09: EVT#02746-04/20/16 21:03:09: 268=Encl PD 08 Path 5001e673d9dddffd  reset (Type 03)
      04/20/16 21:03:09: DM_IssuePendingTMs: reqd 0000 active 0001 countTmIssued 0001, nextDevH 15

      04/20/16 21:03:09: iopiEvent: EVENT_SAS_DISCOVERY
      04/20/16 21:03:09: DM_HandleDiscEvent: Discovery started on Port 0
      04/20/16 21:03:09: terminatated pRdm 6055be00 flags=21 TimeOutC=2 RetryC=1  Request c1142f00 Reply 60dd5e40 iocStatus 0048 retryC 1 devId:8 devFlags=1482005 iocLogInfo:31140000
      04/20/16 21:03:09: DM_ProcessDevWaitQueue: Task mgmt in process devId=x
      04/20/16 21:03:09: DM_HandleTopologyChgEvnt: PhysicalPort=0 NumEntries=1 StartPhyNum=18
      04/20/16 21:03:09:  - Exp RESPONDING
      04/20/16 21:03:09: MPT_HandleTopologyChgEvnt: curr_lr=0xa, prev_lr=0xa, DM_DevMgrIsReady=1
      04/20/16 21:03:09: MPT_TaskMgmtPostRoutine: TMIdx 8ff DevID[8] IOCStatus 0000 MsgAddr c113b900 type 3 chip 0 devhandle 14 numCmdIssued 281 Qdepth 0 TermCount 1 DevWQC 1 ChipWQC 0 retryCount 0 tmDevHandle:14 flags: 1480005
      04/20/16 21:03:09: DM_IssuePendingTMs: reqd 0000 active 0000 countTmIssued 0000, nextDevH 15
      04/20/16 21:03:09: SES device 8 Reset - Queued for 14 secs delay

      04/20/16 21:03:09: iopiEvent: EVENT_SAS_DISCOVERY
      04/20/16 21:03:09: DM_HandleDiscEvent: Discovery Completed on Port 0
      04/20/16 21:03:23: MPT_TaskMgmtSesCallback: device handle=14, path=0, Chip=0, devId=8, timerId=370, devhandle path=0
      04/20/16 21:03:23: DM_DevPathRemoveSM : devHandle[14] devId[8], path [0], currState [3] nextState [5] state [3], devState[20], devFlags[1400005] curPath:0 removalState:3 curQDepth:0 devState:20
      04/20/16 21:03:23: EVT#02747-04/20/16 21:03:23: 113=Unexpected sense: Encl PD 08 Path 5001e673d9dddffd, CDB: 4d 00 40 00 00 00 00 00 fc 00, Sense: 5/24/00
      04/20/16 21:03:23: Raw Sense for PD 8: 70 00 05 00 00 00 00 0a 00 00 00 00 24 00 00 00 00 00
      04/20/16 21:03:23: EVT#02748-04/20/16 21:03:23: 113=Unexpected sense: Encl PD 08 Path 5001e673d9dddffd, CDB: 5a 00 1c 00 00 00 00 00 fc 00, Sense: 5/24/00
      04/20/16 21:03:23: Raw Sense for PD 8: 70 00 05 00 00 00 00 0a 00 00 00 00 24 00 00 00 00 00

       

      When it happed, the read and writh speed of the array drop to ~10MB/s, as normal is ~500MB/s.

      Both LSI MegaRAID 9260-8i and LSI Nytro MegaRAID 8110-4i have the same situation.


      Is there any solution?

      Or just the RES2CV240 can not handle a SATA PIO command?