loading...

re: How to build unique indexes in PostgreSQL on large text VIEW POST

FULL DISCUSSION
 

is where the magic happens: we tell PostgreSQL to build a SHA512 hash (go away MD5 😅)

In this use case, md5 looks good imo, i mean, the sha-2 familiy is more robust but this means more time to compute it, not really good, but the CONCURRENTLY is the heroe here, but...

Why choose sha-512 instead of md5 ? if your use case isnt related to crypt stuff or something similar, btw both could have a collision.

 

Hi kip, you're right, MD5 tends to be faster than SHA2, but as we're not building a brute forcing app the time difference of computing the hash in C (PostgreSQL pgcrypto is written in it AFAIK) is not that big, also given the fact it's going to be done asynchronously.

Fun fact: SHA-512 is faster than SHA-256 on 64bit processors:

Benchmarks

I would like to see also some real-life measurements here, so I hope you'll like it ;)


Intel Core i7-7700HQ (7th gen = Kaby Lake); RAM (DDR4)

HW / OS configuration:

 

Yes, i understand, my idea here is give some thoughts about why exists the expression go away MD5, use md5 for id signature isnt too bad.

Like you said the async execution of computing is a big advantage here, whatever was the hash.

SHA-512 is faster than SHA-256 on 64bit processors

Lets digging in that !

Yes, i understand, my idea here is give some thoughts about why exists the expression go away MD5, use md5 for id signature isnt too bad.

Ah ah yeah, it's not too bad. My parenthesis was probably too harsh :)

code of conduct - report abuse