Rustls Multi-Threaded Performance Is Battering OpenSSL

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts
  • Errinwright
    Senior Member
    • Aug 2023
    • 187

    #21
    Originally posted by Britoid View Post

    Winning? Trump won
    Let the healing begin

    Comment

    • fotomar
      Phoronix Member
      • Jun 2024
      • 93

      #22
      Originally posted by cynic View Post

      we have a exact idea of what happeneded, and Andrew was perfectly right.
      to those who missed it: http://tomazos.com/ub_question_incident.pdf
      This whole ridiculous “taking offense” thing seems to make me think that efforts to stamp out bullying have been a net-negative to society.

      Furthermore, why are “those people” so sensitive about their own behavior? Seems like they’re struggling against some internalized guilt, no?

      Comment

      • blackshard
        Senior Member
        • Oct 2009
        • 602

        #23
        Originally posted by caligula View Post
        OpenSSL is written in C, Assembly, and Perl. Those are all known for their shittiness in multi-core contexts.
        Sorry but that could be true for Perl, but I don't know Perl, but surely C and assembly have no issues with "multi-core context", or at least they share the same "shittiness" with mostly all other languages in the world, in the sense that the developer has to deal with concurrency and race conditions. Rust, from this point of view, is innovative because changes the paradigm and the developer has not to deal with concurrency, but with a higher level problem that solves the concurrency issue as a "side effect".

        Comment

        • sdack
          Senior Member
          • Mar 2011
          • 1724

          #24
          No better way to stoke the flames than through false attribution. As if Rust was magically faster than C/C++ or assembly. It is not. It is simply a false attribution by people trying to create the image it was. It is a newer implementation of SSL, which takes from previous implementations and improves upon these. This can be achieved with C/C++ and assembly, too. What plays a factor here is that the primary criteria of SSL implementations is not speed, but security. It makes it easier to improve upon speed when speed is not the primary concern of users. In return can one ask how secure Rustls is. We already know OpenSSL is worse than LibreSSL in terms of security. What should not be done is to assume Rustls was more secure, making it another false attribution. Security has to remain the dominant factor and should not be implied based on what language was used. It is however good to see competition, because it may lead to improvements in security, speed, compatibility and other factors.
          Last edited by sdack; 03 December 2024, 02:10 PM.

          Comment

          • Volta
            Senior Member
            • Apr 2019
            • 2274

            #25
            Originally posted by caligula View Post
            OpenSSL is written in C, Assembly, and Perl. Those are all known for their shittiness in multi-core contexts.
            Yeah, right. Currently rust is probably the shittiest one when comes to multithreading. It's only easier to do multithreading with it. At least in some part. OpenSSL is just bad example. Let's take Linux and PostgreSQL. They eat any shit written in rust for breakfast.

            But it's great to see these piece of shit languages are slowly but surely dying. They're not really designed for modern post-2005 computers, anyways.
            The piece of shit called rust will die sooner.

            Comment

            • oleid
              Senior Member
              • Sep 2007
              • 2504

              #26
              Originally posted by sdack View Post
              What should not be done is to assume Rustls was more secure, making it only another false attribution. Security has to remain the dominant factor and should not be implied. It is however good to see competition, because it may lead to improvements in security, speed, compatibility and other factors.
              What would it take to convince you that rusttls is secure?

              There was, for example a formal audit a few years back: https://github.com/rustls/rustls/blo...-01-report.pdf

              Comment

              • darkonix
                Senior Member
                • Sep 2021
                • 383

                #27
                Originally posted by Volta View Post

                Yeah, right. Currently rust is probably the shittiest one when comes to multithreading. It's only easier to do multithreading with it. At least in some part. OpenSSL is just bad example. Let's take Linux and PostgreSQL. They eat any shit written in rust for breakfast.



                The piece of shit called rust will die sooner.
                Linus Torvalds is sponsoring adding Rust code to the Linux kernel. Just saying.

                Comment

                • patrick1946
                  Senior Member
                  • Sep 2021
                  • 353

                  #28
                  Originally posted by oleid View Post

                  That's not entirely true. You can use 100% rust in rustls, however, there are also configuration variants where certain crypto primitives use well-tested assembly implementations.
                  As stated in the benchmark, "This was used with aws-lc-rs". So Amazon's crypto primitives were being used.

                  Still, the multi-core performance is quite nice.
                  Is not aws-lc doing the heavy lifting. And is it not written in C++?

                  I really ask myself how many of the commenter here have a really deep experience with programming system languages?

                  Comment

                  • oleid
                    Senior Member
                    • Sep 2007
                    • 2504

                    #29
                    Originally posted by Volta View Post
                    Yeah, right. Currently rust is probably the shittiest one when comes to multithreading.
                    Care to explain, Waldorf?


                    Originally posted by Volta View Post
                    It's only easier to do multithreading with it.
                    It is easer to do multi-threading correctly - at least when it comes to race conditions due to accessing shared data.
                    It is harder to convince the compiler that what you are doing is safe.


                    Comment

                    • patrick1946
                      Senior Member
                      • Sep 2021
                      • 353

                      #30
                      Originally posted by cynic View Post

                      we have a exact idea of what happeneded, and Andrew was perfectly right.
                      to those who missed it: http://tomazos.com/ub_question_incident.pdf
                      So you quote a document from the guy who is not anymore sponsored. Hmm.

                      Comment

                      Working...
                      X