Matt Stancliff

Roundup: - quick review: the original message here basically said "I want to add a thing." Not enough details to provide any help. :) - should all non-bug-fix PRs be...

For comparison: the original encode took 140 ns on my machine (compiled with clang -O2) and the new encode now takes 0.57 ns to encode. Decodes went from 100 ns...

Thanks for offering to check. I put files at https://gist.github.com/mattsta/cd338cb0253e85d8dfe0. It will be easier to just clone the gist and compare locally (`git clone https://gist.github.com/mattsta/cd338cb0253e85d8dfe0`). If you're feeling dangerous, you...

Using the new divide & shift decode, my time for a decode (gcc-4.9 -O2) is now 29 ns from the previous 50 ns. Good fix!

That's some crazy compiler voodoo there. After fixing 8 syntax errors, it decodes at 36 ns compared to 29 ns for the all-shifting version. (gcc-4.9 -O2) I think we've found...

Just bumping this a bit (related to #41 too—would love a binary stream since it would decrease latency by streaming faster due to no need for your servers to buffer+chunk+format...

> I think we should be deeply fearful of breaking changes for Redis, given it's place in the stack, but definitely believe we need to be moving faster. Exactly. There...

I still have drafts of a redis binary network protocol from 2014-2015 based on http/2 I was planning (including things like multiplexing using per-command client command ids matched to reply...

Just a note looking through more recent issues people are adding: - https://github.com/valkey-io/valkey/issues/59 - https://github.com/valkey-io/valkey/issues/58 - https://github.com/valkey-io/valkey/issues/57 - https://github.com/valkey-io/valkey/issues/54 These are all literally things I brought up as major design...

> Speak for yourself, such is the default state of speaking > and maybe do some research or provide evidence before you make such a claim? ??? if you have...