Hi,
did anyone has an idea for this erro of dmesg (host):
2016-12-30T16:15:32.222Z cpu0:65555)WARNING: NMP: nmp_DeviceRequestFastDeviceProbe:237: NMP device "t10.ATA_____Crucial_CT525MX300SSD1__________________________163413BAA738" state in doubt; requested fast path state update...
I have poor perfromance on vsphere 6.5
and some more errors:
2016-12-30T17:49:51.037Z cpu1:65556)ScsiDeviceIO: 2927: Cmd(0x4395009d1880) 0x2a, CmdSN 0x9172b from world 182413 to dev "t10.ATA_____Crucial_CT525MX300SSD1__________________________163413BAA738" failed H:0x2 D:0x0 P:0x0 Invalid sense data: 0x75 0x70 0x$
2016-12-30T17:49:51.054Z cpu1:65670)vmw_ahci[0000001f]: scsiUnmapCommand:Unmap transfer 0x18 byte
2016-12-30T17:49:51.331Z cpu0:65555)ScsiDeviceIO: 2927: Cmd(0x4395009fbc00) 0x2a, CmdSN 0x91735 from world 65545 to dev "t10.ATA_____Crucial_CT525MX300SSD1__________________________163413BAA738" failed H:0x2 D:0x0 P:0x0 Invalid sense data: 0x0 0x0 0x0.
2016-12-30T17:49:51.573Z cpu1:65670)vmw_ahci[0000001f]: scsiUnmapCommand:Unmap transfer 0x18 byte
2016-12-30T17:49:51.902Z cpu1:65556)ScsiDeviceIO: 2927: Cmd(0x4395009bb000) 0x2a, CmdSN 0x91748 from world 65545 to dev "t10.ATA_____Crucial_CT525MX300SSD1__________________________163413BAA738" failed H:0x2 D:0x0 P:0x0 Invalid sense data: 0x0 0x0 0x0.
2016-12-30T17:49:52.075Z cpu0:65555)ScsiDeviceIO: 2927: Cmd(0x4395009da480) 0x2a, CmdSN 0x91749 from world 182413 to dev "t10.ATA_____Crucial_CT525MX300SSD1__________________________163413BAA738" failed H:0x2 D:0x0 P:0x0 Invalid sense data: 0x0 0x0 0x0.
SSD broken?
I tried this: LINK
but not better
2016-12-30T19:58:21.330Z cpu0:65754)<6>ahci_scsi_abort: cmd 0x85 (0x4395055c1fc0), entering...
2016-12-30T19:58:21.330Z cpu0:65754)<7>ata2: ahci_port_reset, entering...
2016-12-30T19:58:21.330Z cpu0:65754)<6>ata2: reset in progress...
I think, I got it.
Don't use AHCI in HP gen8 MicroServer! I switch to Raid Controller, and no more errors in dmesg.
Thanks for assist.
Hi,
As you mention poor performance on ESXi6.5, have a look at this blog post:
http://www.nxhut.com/2016/11/fix-slow-disk-performance-vmwahci.html
--
Wil
Thanks for your link!
Are the Errors normal?
I got sill troubles:
esxcli storage core adapter stats get
vmhba0
Successful Commands: 1174605
Blocks Read: 16466433
Blocks Written: 229934646
Read Operations: 477974
Write Operations: 679705
Reserve Operations: 3033
Reservation Conflicts: 0
Failed Commands: 46031
Failed Blocks Read: 0
Failed Blocks Written: 0
Failed Read Operations: 3250
Failed Write Operations: 37953
Failed Reserve Operations: 0
Total Splits: 0
PAE Commands: 0
also on normal hdd. I checked the disk outside the server, and seems okay.
Also I have freeze of the client system. Most time if I am on ssh and change e.g. smb.conf.
Any hints for me?
I use a HP gen8 Microserver 8 GB RAM / AHCI mode.
Hi,
Sorry for the delay, got a bit busy.
No the errors are not normal.
For comparison on a system that I have which also has a Crucial SSD I get the following stats:
esxcli storage core adapter stats get
vmhba0
Successful Commands: 506241886
Blocks Read: 8145501146
Blocks Written: 5260614764
Read Operations: 330918587
Write Operations: 172433241
Reserve Operations: 1381695
Reservation Conflicts: 0
Failed Commands: 10552112
Failed Blocks Read: 0
Failed Blocks Written: 0
Failed Read Operations: 0
Failed Write Operations: 0
Failed Reserve Operations: 0
Total Splits: 0
PAE Commands: 0
No Failed read/write operations at all.
Freezing can have other reasons, I have seen this for example when there was some DNS issues.
--
Wil
I think, I got it.
Don't use AHCI in HP gen8 MicroServer! I switch to Raid Controller, and no more errors in dmesg.
Thanks for assist.
I have the exact same problem with Crucial CT525MX300 drives in my HP Proliant Microserver Gen7, getting lots of these messages:
2017-01-11T08:54:01.662Z cpu0:65555)NMP: nmp_ThrottleLogForDevice:3617: Cmd 0x2a (0x4395009e6c00, 65545) to dev t10.ATA_____Crucial_CT525MX300SSD1__________________________164814DCA70F" on path "vmhba0:C0:T0:L0" Failed: H:0x2 D:0x0 P:0x0 Invalid sense $
Rather than switch from AHCI to RAID in the BIOS, I switched drivers from vmw_ahci to ahci and now I can see all 5 SATA controllers rather than just 1, and so far no more errors!
Not sure if there's any performance difference between the two BIOS settings though.