Sendo um testador beta da VSAN, decidi atualizar para a versão GA, como a VMWare sugere para sites de produção. Eles dizem que não é possível / suportado fazer upgrade da versão beta para a versão GA e eu não atualizei, mas limpe / reinstale completamente os hosts ESX.
No entanto, durante a instalação, descobri que o sistema é extremamente lento, o instalador é inicializado em algumas horas e, em seguida, todas as operações de varredura do sistema levaram cerca de 30 a 40 minutos cada. Sistema instalado sempre preso em
usbarbitrator start
mensagem.
Eu habilitei o registro em um console serial e aqui o que eu vejo essas mensagens:
2014-03-31T20:00:54.517Z cpu2:33262)LSOMCommon: LSOM_RegisterDiskAttrHandle:99: t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710 is a SATA disk
2014-03-31T20:00:54.532Z cpu2:33262)LSOMCommon: LSOM_RegisterDiskAttrHandle:103: DiskAttrHandle:0x4111c977b928 is added to disk:t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710 by module:plog
2014-03-31T20:00:54.551Z cpu2:33262)PLOG: PLOG_InitMDDevice:830: Registered diskAttrHandle:0x4111c977b928 on disk t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710
2014-03-31T20:00:54.568Z cpu2:33262)PLOG: PLOG_AllocOneRDT:539: You're wasting 524288 bytes by not requesting a length that is not a multiple of the allocation granularity 1048576
2014-03-31T20:00:54.583Z cpu2:33262)PLOG: PLOG_InitElevator:1782: Initializing PLOG Elevator UUID 5287745f-e1c5-269f-ce67-c8d8d4c03967
2014-03-31T20:00:54.595Z cpu2:33262)LSOMCommon: LSOMSetWCEnableSATA:1071: SATA disk t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710 disabling cache...
2014-03-31T20:00:54.611Z cpu2:33262)PLOG: PLOG_InitElevator:1845: Initializing PLOG Elevator UUID on device t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710:2 5287745f-e1c5-269f-ce67-c8d8d4c03967
2014-03-31T20:00:54.630Z cpu2:33262)PLOG: PLOG_InitMDDevice:843: PLOG device t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710:2 is initialized with device handles
2014-03-31T20:01:24.648Z cpu1:32798)NMP: nmp_ThrottleLogForDevice:2321: Cmd 0x28 (0x4136804461c0, 0) to dev "t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710" on path "vmhba37:C0:T0:L0" Failed: H:0x5 D:0x0 P:0x0 Possible sense $
2014-03-31T20:01:24.670Z cpu1:32798)WARNING: NMP: nmp_DeviceRequestFastDeviceProbe:237: NMP device "t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710" state in doubt; requested fast path state update...
2014-03-31T20:01:24.691Z cpu1:32798)ScsiDeviceIO: 2337: Cmd(0x4136804461c0) 0x28, CmdSN 0x1 from world 0 to dev "t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710" failed H:0x5 D:0x0 P:0x0 Possible sense data: 0x5 0x24 0x0.
2014-03-31T20:01:24.713Z cpu1:32798)LSOMCommon: IORETRYCompleteIO:389: Throttled: 0x4136c8c6af00 IO type 264 (READ) isOdered:NO since 30065 msec status Maximum kernel-level retries exceeded
2014-03-31T20:01:24.729Z cpu9:33541)WARNING: LSOM: LSOMEventNotify:4570: VSAN device 5287745f-e1c5-269f-ce67-c8d8d4c03967 is under permanent error.
2014-03-31T20:01:24.743Z cpu9:33541)WARNING: LSOM: LSOMPostDiskEvent:2114: Unable to post disk event for 5287745f-e1c5-269f-ce67-c8d8d4c03967: Not ready
2014-03-31T20:01:24.757Z cpu9:33541)LSOM: LSOMPublishDisk:1959: Throttled: Unable to post disk event for 5287745f-e1c5-269f-ce67-c8d8d4c03967: Not ready
2014-03-31T20:01:54.774Z cpu1:32798)NMP: nmp_ThrottleLogForDevice:2321: Cmd 0x28 (0x413680441bc0, 0) to dev "t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710" on path "vmhba37:C0:T0:L0" Failed: H:0x5 D:0x0 P:0x0 Possible sense $
2014-03-31T20:01:54.797Z cpu1:32798)WARNING: NMP: nmp_DeviceRequestFastDeviceProbe:237: NMP device "t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710" state in doubt; requested fast path state update...
2014-03-31T20:01:54.817Z cpu1:32798)ScsiDeviceIO: 2337: Cmd(0x413680441bc0) 0x28, CmdSN 0x2 from world 0 to dev "t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710" failed H:0x5 D:0x0 P:0x0 Possible sense data: 0x0 0x0 0x0.
2014-03-31T20:01:54.839Z cpu1:32798)LSOMCommon: IORETRYCompleteIO:389: Throttled: 0x4136c8c6ae40 IO type 264 (READ) isOdered:NO since 30063 msec status Maximum kernel-level retries exceeded
2014-03-31T20:02:05.014Z cpu15:32958)VMW_SATP_LOCAL: satp_local_updatePathStates:458: Failed to update path "vmhba37:C0:T0:L0" state. Status=Transient storage condition, suggest retry
2014-03-31T20:02:19.017Z cpu1:32798)WARNING: NMP: nmp_DeviceRequestFastDeviceProbe:237: NMP device "t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710" state in doubt; requested fast path state update...
2014-03-31T20:02:19.038Z cpu1:32798)ScsiDeviceIO: 2337: Cmd(0x413680444b40) 0x12, CmdSN 0x318 from world 0 to dev "t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710" failed H:0x5 D:0x0 P:0x0 Possible sense data: 0x2 0x3a 0x0.
2014-03-31T20:02:24.857Z cpu1:32798)NMP: nmp_ThrottleLogForDevice:2321: Cmd 0x28 (0x4136804411c0, 0) to dev "t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710" on path "vmhba37:C0:T0:L0" Failed: H:0x5 D:0x0 P:0x0 Possible sense $
2014-03-31T20:02:24.879Z cpu1:32798)ScsiDeviceIO: 2337: Cmd(0x4136804411c0) 0x28, CmdSN 0x3 from world 0 to dev "t10.ATA_____WDC_WD2000FYYZ2D01UL1B0_______________________WD2DWCC1P0395710" failed H:0x5 D:0x0 P:0x0 Possible sense data: 0x0 0x0 0x0.
Eu não os vejo se eu tirar todos os discos.
Eu verifiquei todos os discos são legíveis, sem erros, sem bloqueios ruins, etc.
Entendo que meu servidor pode não estar na HCL, mas a versão Beta funcionou bem, apenas a GA tem esse problema.