Taxa de erro de leitura bruta para Intel SSDs

Question

Eu provisionei alguns servidores com um monte de Intel S3610 e estou um pouco preocupado com os valores de "Raw Read Error Rate". As ferramentas mostram todas as unidades como íntegras e não há outros erros, conforme mostrado como dados SMART completos colados abaixo para uma unidade.

Esses valores significam alguma coisa?

:~# isdct show -smart 01 -intelssd

- SMART Attributes BTHXXXXXXXX800NGN -


- 01 -

Action : Pass
Description : Raw Read Error Rate
ID : 01
Normalized : 130
Raw : 3163710634
Status : 14
Threshold : 39
Worst : 130

- SMART Attributes BTHXXXXXXXX800NGN -


- 01 -

Action : Pass
Description : Raw Read Error Rate
ID : 01
Normalized : 130
Raw : 3158519941
Status : 14
Threshold : 39
Worst : 130

- SMART Attributes BTHXXXXXXXX800NGN -


- 01 -

Action : Pass
Description : Raw Read Error Rate
ID : 01
Normalized : 130
Raw : 3164737702
Status : 14
Threshold : 39
Worst : 130

- SMART Attributes BTHXXXXXXXX800NGN -


- 01 -

Action : Pass
Description : Raw Read Error Rate
ID : 01
Normalized : 130
Raw : 3152729088
Status : 14
Threshold : 39
Worst : 130

- SMART Attributes BTHXXXXXXXX800NGN -


- 01 -

Action : Pass
Description : Raw Read Error Rate
ID : 01
Normalized : 130
Raw : 3161462193
Status : 14
Threshold : 39
Worst : 130

- SMART Attributes BTHXXXXXXXX800NGN -


- 01 -

Action : Pass
Description : Raw Read Error Rate
ID : 01
Normalized : 130
Raw : 3155225677
Status : 14
Threshold : 39
Worst : 130

- SMART Attributes BTHXXXXXXXX800NGN -


- 01 -

Action : Pass
Description : Raw Read Error Rate
ID : 01
Normalized : 130
Raw : 3159076215
Status : 14
Threshold : 39
Worst : 130

- SMART Attributes BTHXXXXXXXX800NGN -


- 01 -

Action : Pass
Description : Raw Read Error Rate
ID : 01
Normalized : 130
Raw : 3156418161
Status : 14
Threshold : 39
Worst : 130

"SMART Attributes BTHXXXXXXXX800NGN":
{
    "01":
    {
        "Action":"Pass",
        "Description":"Raw Read Error Rate",
        "ID":"01",
        "Normalized":130,
        "Raw":1925235567,
        "Status":14,
        "Threshold":39,
        "Worst":130
    },
    "05":
    {
        "Action":"Pass",
        "Description":"Re-allocated Sector Count",
        "ID":"05",
        "Normalized":100,
        "Raw":0,
        "Status":51,
        "Threshold":1,
        "Worst":100
    },
    "09":
    {
        "Action":"Pass",
        "Description":"Power-On Hours Count",
        "ID":"09",
        "Normalized":100,
        "Raw":353,
        "Status":50,
        "Threshold":0,
        "Worst":100
    },
    "0C":
    {
        "Action":"Pass",
        "Description":"Power Cycle Count",
        "ID":"0C",
        "Normalized":100,
        "Raw":30,
        "Status":50,
        "Threshold":0,
        "Worst":100
    },
    "0D":
    {
        "Action":"Pass",
        "Description":"ECC Rate",
        "ID":"0D",
        "Normalized":119,
        "Raw":719184773999,
        "Status":30,
        "Threshold":0,
        "Worst":100
    },
    "B3":
    {
        "Action":"Pass",
        "Description":"Used reserved block count (total)",
        "ID":"B3",
        "Normalized":100,
        "Raw":0,
        "Status":51,
        "Threshold":10,
        "Worst":100
    },
    "B4":
    {
        "Action":"Pass",
        "Description":"Unused Reserved block count (total)",
        "ID":"B4",
        "Normalized":100,
        "Raw":17930,
        "Status":50,
        "Threshold":0,
        "Worst":100
    },
    "B5":
    {
        "Action":"Pass",
        "Description":"Program fail count (total)",
        "ID":"B5",
        "Normalized":100,
        "Raw":0,
        "Status":58,
        "Threshold":0,
        "Worst":100
    },
    "B6":
    {
        "Action":"Pass",
        "Description":"Erase fail count (total)",
        "ID":"B6",
        "Normalized":100,
        "Raw":0,
        "Status":58,
        "Threshold":0,
        "Worst":100
    },
    "B8":
    {
        "Action":"Pass",
        "Description":"End-to-End Error Detection Count",
        "ID":"B8",
        "Normalized":100,
        "Raw":0,
        "Status":50,
        "Threshold":0,
        "Worst":100
    },
    "C2":
    {
        "Action":"Pass",
        "Description":"Drive Temperature",
        "ID":"C2",
        "Normalized":100,
        "Raw":27,
        "Status":34,
        "Threshold":0,
        "Worst":100
    },
    "C3":
    {
        "Action":"Pass",
        "Description":"Uncorrectable Error Count",
        "ID":"C3",
        "Normalized":100,
        "Raw":0,
        "Status":50,
        "Threshold":0,
        "Worst":100
    },
    "C6":
    {
        "Action":"Pass",
        "Description":"Offline Scan Uncorrectable LBA Count",
        "ID":"C6",
        "Normalized":100,
        "Raw":0,
        "Status":16,
        "Threshold":0,
        "Worst":100
    },
    "C7":
    {
        "Action":"Pass",
        "Description":"CRC Error Count",
        "ID":"C7",
        "Normalized":100,
        "Raw":0,
        "Status":62,
        "Threshold":0,
        "Worst":100
    },
    "C9":
    {
        "Action":"Pass",
        "Description":"Volatile Memory Backup Source Failure",
        "ID":"C9",
        "Normalized":100,
        "Raw":55857979570,
        "Status":51,
        "Threshold":10,
        "Worst":100
    },
    "CA":
    {
        "Action":"Pass",
        "Description":"Exception Mode Status (Read-only mode)",
        "ID":"CA",
        "Normalized":100,
        "Raw":0,
        "Status":39,
        "Threshold":0,
        "Worst":100
    },
    "E2":
    {
        "Action":"Pass",
        "Description":"Timed Workload - Media Wear",
        "ID":"E2",
        "Normalized":100,
        "Raw":102400,
        "Status":50,
        "Threshold":0,
        "Worst":100
    },
    "E3":
    {
        "Action":"Pass",
        "Description":"Timed Workload - Host Read/Write Ratio",
        "ID":"E3",
        "Normalized":100,
        "Raw":0,
        "Status":50,
        "Threshold":0,
        "Worst":100
    },
    "E4":
    {
        "Action":"Pass",
        "Description":"Timed Workload Timer",
        "ID":"E4",
        "Normalized":100,
        "Raw":3783287515,
        "Status":50,
        "Threshold":0,
        "Worst":100
    },
    "E9":
    {
        "Action":"Pass",
        "Description":"Number of write count",
        "ID":"E9",
        "Normalized":100,
        "Raw":85593,
        "Status":50,
        "Threshold":0,
        "Worst":100
    },
    "F5":
    {
        "Action":"Pass",
        "Description":"Percent Drive Life Remaining",
        "ID":"F5",
        "Normalized":100,
        "Raw":0,
        "Status":50,
        "Threshold":0,
        "Worst":100
    }
}

    

Answer 1

O campo Raw Read Error Rate é frequentemente formatado de forma proprietária, não divulgada, ou totalmente usado para codificar outras informações. Em suma, não preste atenção ao valor bruto por si só.

Em vez disso, examine cuidadosamente os dados normalized , threshold e worse : a partir deles, podemos ver que seu disco está com boa saúde.

Outros campos importantes são Uncorrectable Error Count , Re-allocated Sector Count e Percent Drive Life Remaining : seus valores brutos geralmente são codificados em valores absolutos e mostram suas unidades como saudáveis.