SSD Speeds: Faster Reads or equal?

[As Seen on TV]

Looking at the benchmarks of the two leading SSDs on today's market, Samsung 840 Pro and the Vector, I notice something odd between them. Samsung had faster reads than writes. While the Vector had roughly equal write/read throughput.

Write
467.3MB/s: Samsung 840 Pro
490.5MB/s: OCZ Vector

Read
515.3MB/s: Samsung 840 Pro
497.0MB/s: OCZ Vector

Benchmark used is Blackmagicdesign's Disk Speed Test.

My guess is that this was purposely done. For reasons I do not know and would like to know through your comments below.

 

[blastingcap]

Repeat after me: for almost all home users, random 4k read speeds are the only metric you need to care about, because every other metric will be faster than hard drives and faster than you will realistically need, because how often do you move large amounts of data between one SSD to another? Not often, and whether it's 400MB/s or 500MB/s nobody cares.

 

[As Seen on TV]

My usage is mostly RAW images and 1080p video.

I don't play games.

 

[corkyg]

Where the rubber meets the road, those differences are nearly insignificant. The same bench test an hour later could have different results. Of more importance to me are reliability of the OEM, and the warranty each provides along with a general reputation. Too much bench testing is bad for SSD health.

 

[Zap]

My guess is that this was purposely done. For reasons I do not know and would like to know through your comments below.

It probably was for two reasons.
1) It is easier to read than to write.
2) "Normal" workloads benefit more from reads than from writes.

What I would like to know is why you linked to a Toms Hardware forum smiley icon?

 

[cantholdanymore]

It probably was for two reasons.
1) It is easier to read than to write.
2) "Normal" workloads benefit more from reads than from writes.

What I would like to know is why you linked to a Toms Hardware forum smiley icon?

LOL

 

[blastingcap]

My usage is mostly RAW images and 1080p video.

I don't play games.

And? You are like most home users and will not see any appreciable benefit by going from say, 400 MB/s to 500 MB/s under your usage scenario. And if the difference is even less, you will see even less difference.

Where the rubber meets the road, those differences are nearly insignificant. The same bench test an hour later could have different results. Of more importance to me are reliability of the OEM, and the warranty each provides along with a general reputation. Too much bench testing is bad for SSD health.

I completely agree. I would never sacrifice even a little reliability for the sake of any speed gain above above 200 MB/s, which is the realistic limit in for now and the near future, of how fast you can transfer data to or from the fastest reasonably-priced hard drive at that HDD's maximum transfer rate (meaning, optimum portion of the platter; this is excluding HDD cache of course, but you'd burn through that quickly at 200 MB/s anyway). And even below 200 MB/s, I would not trade much reliability for speed unless it was an extreme circumstance like sacrificing a tiny bit of reliability to go from 1.9 MB/s to 199 MB/s.

 

[As Seen on TV]

It probably was for two reasons.
1) It is easier to read than to write.
2) "Normal" workloads benefit more from reads than from writes.

What I would like to know is why you linked to a Toms Hardware forum smiley icon?

Ah...

I hope you do not get mad but I wrote the original draft of my post on Tom's then copy pasted it to all the technical forums I respect. I was not expecting anyone to notice but the shade of yellow must have stuck out.

I did this as I was afraid I would not get a response to this rather unique question.

I would like to learn about SSDs as questions pop up. And the read/write difference is something that stuck out.

But looking back at my flash memory cards like CF & SDXC the reads are always published as faster than the writes. So it could be a technical or how data is often used. Seldom written and mostly read.