ssd

由 datahunter 在四, 25/06/2015 - 12:08 發表

最後更新: 2022-02-21

找出系上的 SSD

# To check if the kernel knows about SSDs try:

grep . /sys/block/sd?/queue/rotational

/sys/block/sda/queue/rotational:1
/sys/block/sdb/queue/rotational:0
/sys/block/sdc/queue/rotational:1

為 SSD 設定 IO scheduler

查看 scheduler 設定

grep . /sys/block/sd?/queue/scheduler

/sys/block/sda/queue/scheduler:noop [deadline] cfq
/sys/block/sdb/queue/scheduler:noop [deadline] cfq
/sys/block/sdc/queue/scheduler:noop deadline [cfq]

Set deadline scheduler for non-rotating disks

[方法1]

/etc/udev/rules.d/10-ssd.rules

# Kernel Verion: 3
ACTION=="add|change", KERNEL=="sd[a-z]", ATTR{queue/rotational}=="0", ATTR{queue/scheduler}="deadline"

# Kernel Version: 4, 5
ACTION=="add|change", KERNEL=="sd[a-z]", ATTR{queue/rotational}=="0", ATTR{queue/scheduler}="mq-deadline"

[方法2]

echo "block/sdX/queue/scheduler = deadline" >> /etc/sysfs.conf

systemctl restart sysfsutils

Checking

cat /sys/block/sdc/queue/scheduler

TRIM Command

The TRIM command should be translated from one layer to another until reaching the SSD.

i.e.

ext4 -> lvm -> ssd

* 每一層都要 support TRIM

定期 trim (fstrim)

日子久了 => degradation of write operations on SSDs

原因: 刪除了的資料沒有真正進行資料清空(erase)

系統支援 erase

OS >= Windows 7

Linux: util-linux package provides fstrim

fstrim - discard unused blocks on a mounted filesystem

Usage

# By default, fstrim will discard all unused blocks in the filesystem.

fstrim [-o offset] [-l length] [-m minimum-free-extent] [-v] mountpoint

Opts

-m, --minimum minimum-free-extent # Minimum contiguous free range to discard (Default value is zero => ALL )
# (Free ranges smaller than this will be ignored.)

-v, --verbose # Output the number of bytes passed from the filesystem down the block stack
# to the device for potential discard.

Unit

(2^N) suffixes KiB, MiB, GiB

i.e.

fstrim -v /ssd/xpenology

/ssd/xpenology: 6.4 GiB (6856876032 bytes) trimmed

Ubuntu

From 18.04 fstrim (discard unused blocks) is enabled to run weekly

by default for all mounted filesystems on devices that support the discard operation.

systemctl cat fstrim.timer

...
[Timer]
OnCalendar=weekly
...

systemctl cat fstrim.service

[Service]
Type=oneshot
ExecStart=/sbin/fstrim --listed-in /etc/fstab:/proc/self/mountinfo --verbose --quiet-unsupported

Info

journalctl -u fstrim.service
journalctl -u fstrim.timer

FS: btrfs, ext4 的 trim (Continuous TRIM)

/etc/fstab

# ext4

# commit=nrsec ( Default value is 5 seconds)

# This means that if you lose your power, you will lose as much as the latest 5 seconds of work

/dev/mapper/goofy-root / ext4 discard,noatime,commit=600,errors=remount-ro 0 1

Using the discard mount option for continuous TRIM in device operations

# btrfs

# ssd => optimizations for SSD drives

/dev/mapper/goofy-chroot /srv/chroot btrfs ssd,discard,noatime 0 2

* There is no need for the discard flag if you run fstrim periodically.

Speed Test on Sata Port

理論值:

SATA Express     16Gb/s     1600MB/s
SATA 3.0         6Gb/s      600MB/s
SATA 2.0         3Gb/s      300MB/s
SATA 1.0         1.5Gb/s    150MB/s

SATA 3.0 有 revision 3.1~3.5(Released in July 2020)

Checking Sata Port Version

Speed Test on Sata 2.0 Port

Speed Test on Sata 3.0 Port

1. Seq

速度會接近 Sata Port 的理論值

SATA3 : 520 MB/S
Native SATA3 : 380 MB/S
SATA2 : 270 MB/S
SATA1 : 130 MB/S

2. 4K

6 個速度中最低者

3. 4K-64Thrd

4k, 64隊列深度

軟件會生成64個16MB大小的測試文件（共計1GB）

然後同時以4KB的單位尺寸同時在這64個文件中進行讀取

Window 's tuning

* 關閉 Superfetch 服務

win10: sc stop SysMain & sc config SysMain start= disabled

* 關閉 Windows Search 服務

* 關閉 contents index

right click on SSD Drive

Click "Properties" then uncheck “Allow files on this drive to have contents indexed in addition to file properties“.

* 關閉休眠(hibernate)功能

powercfg -h off

* Disable 碎片整理

* Turn Off the Page File on SSD Disk

* Verify TRIM is Functioning:

fsutil behavior query DisableDeleteNotify

# “1” => TRIM is disabled and you need to enable it.

NTFS DisableDeleteNotify = 0  (Disabled)

M.2 NVMe PCIe SSD

/dev/nvmeXnYpZ

linux 認唔到 M.2 NVMe PCIe SSD 時 => uefi boot -> legacy boot

Window 7 install on SSD

BIOS設置

啟用 SATA AHCI 糢式

Intel Driver

iaStorA 驅動程式模組是 Intel SATA AHCI Driver
iaStorAC 驅動程式模組是 Intel SATA AHCI RAID Driver
iaStorAVC

Speed: intelide(有開啟AHCI模式) < msahci < iastora ...

Linux Check SSD SMART Script

chkssd.sh

#!/bin/bash

opt="-e Reallocated_Sector_Ct \
        -e Program_Fail_Cnt_Total \
        -e Erase_Fail_Count_Total \
        -e Uncorrectable_Error_Cnt \
        -e Total_LBAs_Written \
        -e Wear_Leveling_Count"

chkdsk() {
        echo "Checking $1"
        smartctl -d sat -A /dev/$1 | grep $opt
}

chkdsk sdc

Low-level Format

1) If the drive shows "frozen" you must first "un-freeze" it

[方案1]

cat /sys/power/state

freeze mem

echo -n mem > /sys/power/state

After letting the computer sleep for a few seconds,

wake it up and check to see if the drive is no longer in frozen state by issuing the command

原因:

Your BIOS freezes the disk when booting,

that's why suspend/resume helps because it power cycles the drive without the BIOS getting its hands on it again.

BIOS 係有掌管的: Dell 1420 NB: BIOS > Security > Internal HDD PW

[方案2]

Hotplug SSD to Hotplug SATA Port

2) set a temporary password "p" in order to issue the secure erase command:

Hardware

Samsung 860 EVO HK$ 480@202010

Kingston 480GB A400 Series 2.5" SATA 3 6Gb/s SSD SA400S37/480G HK$ 435@202001

Kingston 480GB UV500 2.5" SATA 3 6Gb/s SSD SUV500/480G HK$ 490@202001

Kingston A400, UV500 的分別

A400 (TLC)[ 3 年保固]

讀取速度高達500MB/秒，寫入速度320M/秒

UV500 (TLC) [ 5 年保固]

採用Marvell 88SS1074 控制器及 3D Nand
其讀寫速度最高可達 520MB/s 和 500MB/s
支持256位 AES硬件加密（SED）和 TCG Opal 2.0 安全管理解決方案

2015 HW

Samsung SSD 850 EVO 250GB

Cache Memory

Samsung SSD 850 EVO 250GB: Samsung 512 MB Low Power DDR3 SDRAM

Total/Terrabytes Bytes Written (TBW)

Samsung SSD 850 EVO 250GB: 75 TBW

計算程式

V = SMART attribute #241 (Total_LBAs_Written)

V X 512 / 1024^4 = N TB

Wear_Leveling_Count (ID 177)

This attribute represents the number of media program and erase operations

(the number of times a block has been erased)

This value is directly related to the lifetime of the SSD

The raw value of this attribute shows the total count of P/E Cycles

SLC: 100,000
MLC: 3,000

* The ssd will die from other reasons before wearing out.

POR_Recovery_Count

A count of the number of sudden power off cases.

the firmware must recover all of the mapping and user data during the next power on

Notes

如果平日工作有大量寫入 (40-50 GB per day), 唔建議用 TLC / QLC NAND

瀏覽次數： 2616

夢想家

ssd

目錄