This is what I'm getting now, with a Crucial MX300 750GB SSD (with latest firmware [there are no firmware updates yet]).
lptp [ blah ]: sudo hdparm -Tt /dev/sda
/dev/sda:
Timing cached reads: 10202 MB in 2.00 seconds = 5103.20 MB/sec
Timing buffered disk reads: 128 MB in 3.06 seconds = 41.88 MB/sec
See that buffered disk read speed!!!! SOOOO SLOWWW!!!! When I first setup my laptop, I was seeing over 400MB/sec, which was perfectly fine with me considering this is an older laptop, and everything is luks encrypted is well.
This is my /etc/fstab. I've enabled trim, manually ran trim, enabled/disabled features, rebooted, everything. I can't get those fast speeds to come back:
/dev/mapper/ubuntu--gnome--vg-root / ext4 noatime,nodiratime,errors=remount-ro,barrier=0,discard 0 1
Just so it's clear, these are the options I'm using. I've tried various combinations of them to no avail:
noatime,nodiratime,errors=remount-ro,barrier=0,discard
Any tips? This is driving me crazy.
Oh, also, I'm running Ubuntu 16.04 (x64) on a Lenovo T420 with 16GB ram and an i7 processor:
lptp [ blah ]: lsb_release -a
No LSB modules are available.
Distributor ID: Ubuntu
Description: Ubuntu 16.04.1 LTS
Release: 16.04
Codename: xenial
Smartctl output:
lptp [ blah ]: sudo smartctl /dev/sda -a
smartctl 6.5 2016-01-24 r4214 [x86_64-linux-4.4.0-38-generic] (local build)
Copyright (C) 2002-16, Bruce Allen, Christian Franke, www.smartmontools.org
=== START OF INFORMATION SECTION ===
Device Model: Crucial_CT750MX300SSD1
Serial Number: XXXXXX
LU WWN Device Id: 5 XXXXX XXXXXXX
Firmware Version: M0CR011
User Capacity: 750,156,374,016 bytes [750 GB]
Sector Size: 512 bytes logical/physical
Rotation Rate: Solid State Device
Form Factor: 2.5 inches
Device is: Not in smartctl database [for details use: -P showall]
ATA Version is: ACS-3 T13/2161-D revision 5
SATA Version is: SATA 3.2, 6.0 Gb/s (current: 6.0 Gb/s)
Local Time is: Tue Nov 1 21:22:05 2016 CDT
SMART support is: Available - device has SMART capability.
SMART support is: Enabled
=== START OF READ SMART DATA SECTION ===
SMART overall-health self-assessment test result: PASSED
General SMART Values:
Offline data collection status: (0x00) Offline data collection activity
was never started.
Auto Offline Data Collection: Disabled.
Self-test execution status: ( 0) The previous self-test routine completed
without error or no self-test has ever
been run.
Total time to complete Offline
data collection: ( 1987) seconds.
Offline data collection
capabilities: (0x7b) SMART execute Offline immediate.
Auto Offline data collection on/off support.
Suspend Offline collection upon new
command.
Offline surface scan supported.
Self-test supported.
Conveyance Self-test supported.
Selective Self-test supported.
SMART capabilities: (0x0003) Saves SMART data before entering
power-saving mode.
Supports SMART auto save timer.
Error logging capability: (0x01) Error logging supported.
General Purpose Logging supported.
Short self-test routine
recommended polling time: ( 2) minutes.
Extended self-test routine
recommended polling time: ( 10) minutes.
Conveyance self-test routine
recommended polling time: ( 3) minutes.
SCT capabilities: (0x0035) SCT Status supported.
SCT Feature Control supported.
SCT Data Table supported.
SMART Attributes Data Structure revision number: 16
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME FLAG VALUE WORST THRESH TYPE UPDATED WHEN_FAILED RAW_VALUE
1 Raw_Read_Error_Rate 0x002f 100 100 000 Pre-fail Always - 0
5 Reallocated_Sector_Ct 0x0032 100 100 010 Old_age Always - 0
9 Power_On_Hours 0x0032 100 100 000 Old_age Always - 52
12 Power_Cycle_Count 0x0032 100 100 000 Old_age Always - 41
171 Unknown_Attribute 0x0032 100 100 000 Old_age Always - 0
172 Unknown_Attribute 0x0032 100 100 000 Old_age Always - 0
173 Unknown_Attribute 0x0032 100 100 000 Old_age Always - 1
174 Unknown_Attribute 0x0032 100 100 000 Old_age Always - 11
183 Runtime_Bad_Block 0x0032 100 100 000 Old_age Always - 0
184 End-to-End_Error 0x0032 100 100 000 Old_age Always - 0
187 Reported_Uncorrect 0x0032 100 100 000 Old_age Always - 0
194 Temperature_Celsius 0x0022 059 052 000 Old_age Always - 41 (Min/Max 21/48)
196 Reallocated_Event_Count 0x0032 100 100 000 Old_age Always - 0
197 Current_Pending_Sector 0x0032 100 100 000 Old_age Always - 0
198 Offline_Uncorrectable 0x0030 100 100 000 Old_age Offline - 0
199 UDMA_CRC_Error_Count 0x0032 100 100 000 Old_age Always - 0
202 Unknown_SSD_Attribute 0x0030 100 100 001 Old_age Offline - 0
206 Unknown_SSD_Attribute 0x000e 100 100 000 Old_age Always - 0
246 Unknown_Attribute 0x0032 100 100 000 Old_age Always - 138859820
247 Unknown_Attribute 0x0032 100 100 000 Old_age Always - 4354463
248 Unknown_Attribute 0x0032 100 100 000 Old_age Always - 1675456
180 Unused_Rsvd_Blk_Cnt_Tot 0x0033 000 000 000 Pre-fail Always - 3558
210 Unknown_Attribute 0x0032 100 100 000 Old_age Always - 0
SMART Error Log Version: 1
No Errors Logged
SMART Self-test log structure revision number 1
No self-tests have been logged. [To run self-tests, use: smartctl -t]
SMART Selective self-test log data structure revision number 1
SPAN MIN_LBA MAX_LBA CURRENT_TEST_STATUS
1 0 0 Not_testing
2 0 0 Not_testing
3 0 0 Not_testing
4 0 0 Not_testing
5 0 0 Not_testing
Selective self-test flags (0x0):
After scanning selected spans, do NOT read-scan remainder of disk.
If Selective self-test is pending on power-up, resume after 0 minute delay.
What's killing me is that IT WAS WORKING FOR A WHILE. It worked one day, and then it stopped the next, and I didn't even do anything (that I can think of) that should have changed it.
UPDATE
Tested a specific device (/dev/sda1), but same slow results:
lptp [ ~ ]: sudo hdparm -Tt /dev/sda1
/dev/sda1:
Timing cached reads: 13130 MB in 2.00 seconds = 6568.77 MB/sec
Timing buffered disk reads: 128 MB in 3.06 seconds = 41.79 MB/sec
UPDATE
Tested on a logical partition too:
lptp [ ~ ]: sudo hdparm -Tt /dev/mapper/ubuntu--gnome--vg-root
/dev/mapper/ubuntu--gnome--vg-root:
Timing cached reads: 11468 MB in 2.00 seconds = 5736.85 MB/sec
Timing buffered disk reads: 178 MB in 3.04 seconds = 58.47 MB/sec
UPDATE dd test
This test shows that it's even slower than hdparm shows…
lptp [ blah ]: dd if=/dev/zero of=tempfile bs=1M count=1024 conv=fdatasync,notrunc status=progress
1024+0 records in
1024+0 records out
1073741824 bytes (1.1 GB, 1.0 GiB) copied, 35.0156 s, 30.7 MB/s
lptp [ blah ]: sudo bash -c "echo 3 > /proc/sys/vm/drop_caches"
lptp [ blah ]: dd if=tempfile of=/dev/null bs=1M count=1024 status=progress
1066401792 bytes (1.1 GB, 1017 MiB) copied, 34.0193 s, 31.3 MB/s
1024+0 records in
1024+0 records out
1073741824 bytes (1.1 GB, 1.0 GiB) copied, 34.256 s, 31.3 MB/s
UPDATE: Partition Alignment
Here's the partition alignment on my laptop:
lptp [ ~ ]: sudo parted
GNU Parted 3.2
Using /dev/sda
Welcome to GNU Parted! Type 'help' to view a list of commands.
(parted) p
Model: ATA Crucial_CT750MX3 (scsi)
Disk /dev/sda: 750GB
Sector size (logical/physical): 512B/512B
Partition Table: msdos
Disk Flags:
Number Start End Size Type File system Flags
1 1049kB 512MB 511MB primary ext2 boot
2 513MB 750GB 750GB extended
5 513MB 750GB 750GB logical
(parted) align-check opt 1
1 aligned
(parted) align-check opt 2
2 not aligned
(parted) align-check opt 5
5 aligned
(parted)
I'm not sure what to think of partition 2 not being aligned :^/ but partitions 1 and 5 are though.
Also, here's the partitions as seen from fdisk -l
Device Boot Start End Sectors Size Id Type
/dev/sda1 * 2048 999423 997376 487M 83 Linux
/dev/sda2 1001470 1465147391 1464145922 698.2G 5 Extended
/dev/sda5 1001472 1465147391 1464145920 698.2G 83 Linux
UPDATE: FIXED?
I changed the scheduler to a noop scheduler (instead of deadline). That seems to have worked (did this by changing /etc/default/grub to have the line:
GRUB_CMDLINE_LINUX_DEFAULT="quiet splash elevator=noop"
And then updating grub with sudo update-grub2 and rebooting.
I'm going to wait a few days to see if it works after a few more reboots/usage before I make an answer and accept it.
Current speeds now after changing the scheduler:
lptp [ ~ ]: sudo hdparm -Tt /dev/sda
/dev/sda:
Timing cached reads: 12388 MB in 2.00 seconds = 6197.19 MB/sec
Timing buffered disk reads: 1454 MB in 3.00 seconds = 484.59 MB/sec
Options in fstab are:
noatime,nodiratime,errors=remount-ro,barrier=0
"FIX" UPDATE
After using it for a bit and rebooting a few times, it's BACK TO THE SLOW SPEEDS 🙁 🙁 🙁 🙁 🙁 🙁
UPDATE – POSSIBLE "FIX"
I had the thought that perhaps my laptop is doing some battery-saving optimizations when it's booted and running off the battery. After one simple test of booting with the charger plugged in, it's back to its really fast speeds. I'm fairly certain this is the case – all the time it tested at fast speeds I had the charger plugged in. I'll run a few more tests to verify, but I'm fairly certain this is what was causing the slowdown.
Best Answer
The quick answer:
The long answer:
It appears that Linux or laptops in general (verified on both Lenovo and Dells) default to APM level 80h (128) when booted on battery and FEh (254) when booted on AC power.
For most SSDs, you won't notice much difference. Lite-on SSDs seem to not support power management at all and always run at max speed. Intel SSDs seem to run at about 75% full speed at APM level 128, and 100% speed at APM level 254/255. Crucial SSDs however seem to run at about 6% full speed at APM level 128 (booted on battery) when compared to APM level 254 (booted on AC power).
The bad news is that there is no bug and no fault here. The ATA spec is sufficiently vague that Crucial SSDs running super slow in APM mode 128 is allowed and is compliant with the spec. Similarly a laptop defaulting to APM level 80h (128) is perfectly reasonable. The spec just says:
Table 106 — APM levels
COUNT field Level
00h Reserved
01h Minimum power consumption with Standby mode
02h..7Fh Intermediate power management levels with Standby mode
80h Minimum power consumption without Standby mode
81h..FDh Intermediate power management levels without Standby mode
FEh Maximum performance
FFh Reserved
(From the ATA spec)
Here is my experience with a Crucial MX300 SSD booted on battery power: