Jump to content

How Much Does SSD Read/Write Latency Matter?

hihihi8

Hi guys and gals, I'm looking to buy a cheap 512GB SSD since I have a strict budget for my current build, and I'm currently deciding between the Intel 545S and Micron 1100.

 

The Intel has a slightly higher sequential read (550 vs 530MB/s), a slightly higher 4K random write (85k vs 83k IOPS), but a significantly lower 4k random read (75k vs 92k IOPS). Both drives have the same sequential write speeds.

 

However, the intel has a lower read latency (50 vs 85 microseconds), yet the Micron has a better write latency (40 vs 60 microseconds).

Screenshot_8.png.f0702f76aacf3478a0b0adecd878fc48.pngScreenshot_7.png.b79c65488dc5dc4e50d061ca1418a058.png

Top Left: Intel

Top Right: Micron

 

I heard 4k read is more important for start times and application opening and overall responsiveness, but how much does latency matter?

 

Which once would you choose? Right now, I'm inclined to go with the Micron, since it's considerably cheaper (15 dollars).

 

Thanks in advance!

 

PS: This is a system drive.

PC 0: Pinky 2.0

Ryzen 9 5950x — 64GB G.Skill Ripjaws 5 @3600Mhz CL14-13-13-28-288 — ROG Crosshair 8 Dark Hero — RX 6900 XT — Hardline Loop — Sabrent Rocket 4.0 2TB — Samsung PM961 1TB  WD Blue 4TB HDD — Corsair AX1500i — Thermaltake Core P5 

 

PC 1: Pinky (Yes that is her name) Here's the build

Xeon E5-1680V3 — 64GB G.Skill Ripjaws 4 @2400Mhz — MSi X99A Godlike Gaming — GTX 980Ti SLI (2-WAY) — Hardline Loop — Samsung 950Pro 512GB — Seagate 2TB HDD — Corsair RM1000 — Thermaltake Core P5

 

PC 1.1: Pinky (Mom Edition) Here's the build

i7-5960X — 64GB G.Skill Ripjaws 4 @2400Mhz — MSi X99A Godlike Gaming — GTX 980Ti SLI (2-WAY) — Hardline Loop — Sabrent Rocket 3 1TB — Samsung Q 870 Evo 4TB — Corsair HX850i — InWin S-Frame #190

 

PC 2: Red Box/Scarlet Overkill (Dual Xeon)

Xeon E5-2687W x2 — 96GB Kingston DDR3 ECC REG @1333Mhz — EVGA Classified SR-X Dual CPU — GTX 1070 SLI (2-WAY) —Hardline Loop — Samsung 750 EVO 256GB — Seagate 2TB 2.5" HDD x3 — Self-Built Case

Link to comment
Share on other sites

Link to post
Share on other sites

If the latency values are in microseconds, it doesn't matter unless your use-case involves a huge amount of file I/O over extended periods of time. Most consumers won't ever really have a use case like that.

 

To put in perspective, even if you make 1000 file requests, it's still less than a 1/10 of a second of latency (not including any other latency due to protocol overhead).

Link to comment
Share on other sites

Link to post
Share on other sites

Went with the Micron 1100 in the end! 

PC 0: Pinky 2.0

Ryzen 9 5950x — 64GB G.Skill Ripjaws 5 @3600Mhz CL14-13-13-28-288 — ROG Crosshair 8 Dark Hero — RX 6900 XT — Hardline Loop — Sabrent Rocket 4.0 2TB — Samsung PM961 1TB  WD Blue 4TB HDD — Corsair AX1500i — Thermaltake Core P5 

 

PC 1: Pinky (Yes that is her name) Here's the build

Xeon E5-1680V3 — 64GB G.Skill Ripjaws 4 @2400Mhz — MSi X99A Godlike Gaming — GTX 980Ti SLI (2-WAY) — Hardline Loop — Samsung 950Pro 512GB — Seagate 2TB HDD — Corsair RM1000 — Thermaltake Core P5

 

PC 1.1: Pinky (Mom Edition) Here's the build

i7-5960X — 64GB G.Skill Ripjaws 4 @2400Mhz — MSi X99A Godlike Gaming — GTX 980Ti SLI (2-WAY) — Hardline Loop — Sabrent Rocket 3 1TB — Samsung Q 870 Evo 4TB — Corsair HX850i — InWin S-Frame #190

 

PC 2: Red Box/Scarlet Overkill (Dual Xeon)

Xeon E5-2687W x2 — 96GB Kingston DDR3 ECC REG @1333Mhz — EVGA Classified SR-X Dual CPU — GTX 1070 SLI (2-WAY) —Hardline Loop — Samsung 750 EVO 256GB — Seagate 2TB 2.5" HDD x3 — Self-Built Case

Link to comment
Share on other sites

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

×