Hi,
We're running proxmox 6.0-4 on a couple of HP DL360ps, with HP 220 HBAs, and four Intel S3520 Series 960GB MLC SSDs in each.
The four SSDs are in ZFS RAID10 for VMs to sit on, while we have two mirror ZFS 146GB 15K SAS drives for the OS.
We're getting some uncomfortable feedback from the SMART values for the SSDs. Here's an example of one of the drives, all which show similar results. Note that these drives have just started to be used.
ID# ATTRIBUTE_NAME FLAG VALUE WORST THRESH TYPE UPDATED WHEN_FAILED RAW_VALUE
1 Raw_Read_Error_Rate 0x000f 130 130 039 Pre-fail Always - 14680932
5 Reallocated_Sector_Ct 0x0033 100 100 001 Pre-fail Always - 0
9 Power_On_Hours 0x0032 100 100 000 Old_age Always - 349
173 Unknown_Attribute 0x0033 100 100 001 Pre-fail Always - 0
175 Program_Fail_Count_Chip 0x0033 100 100 010 Pre-fail Always - 146243860634
180 Unused_Rsvd_Blk_Cnt_Tot 0x003b 130 130 039 Pre-fail Always - 100924306
194 Temperature_Celsius 0x0022 100 100 000 Old_age Always - 25
196 Reallocated_Event_Count 0x0033 100 100 010 Pre-fail Always - 0
The value of raw read error rate, program fail count chip, and unused rsbd blk cnt keep increasing.
Also, in the GUI, the SMART value for each SSD says "PASSED", but the wearout says "N/A". Shouldn't we be able to see the wearout value?
Should we be concerened? Is there maybe some ZFS tuning that we need implement?
Thank you in advance.
We're running proxmox 6.0-4 on a couple of HP DL360ps, with HP 220 HBAs, and four Intel S3520 Series 960GB MLC SSDs in each.
The four SSDs are in ZFS RAID10 for VMs to sit on, while we have two mirror ZFS 146GB 15K SAS drives for the OS.
We're getting some uncomfortable feedback from the SMART values for the SSDs. Here's an example of one of the drives, all which show similar results. Note that these drives have just started to be used.
ID# ATTRIBUTE_NAME FLAG VALUE WORST THRESH TYPE UPDATED WHEN_FAILED RAW_VALUE
1 Raw_Read_Error_Rate 0x000f 130 130 039 Pre-fail Always - 14680932
5 Reallocated_Sector_Ct 0x0033 100 100 001 Pre-fail Always - 0
9 Power_On_Hours 0x0032 100 100 000 Old_age Always - 349
173 Unknown_Attribute 0x0033 100 100 001 Pre-fail Always - 0
175 Program_Fail_Count_Chip 0x0033 100 100 010 Pre-fail Always - 146243860634
180 Unused_Rsvd_Blk_Cnt_Tot 0x003b 130 130 039 Pre-fail Always - 100924306
194 Temperature_Celsius 0x0022 100 100 000 Old_age Always - 25
196 Reallocated_Event_Count 0x0033 100 100 010 Pre-fail Always - 0
The value of raw read error rate, program fail count chip, and unused rsbd blk cnt keep increasing.
Also, in the GUI, the SMART value for each SSD says "PASSED", but the wearout says "N/A". Shouldn't we be able to see the wearout value?
Should we be concerened? Is there maybe some ZFS tuning that we need implement?
Thank you in advance.