> Oh, certain browser will not work with this blog if it cannot negotiate ONLY for Cha-Cha/Poly. It's by design as a showcase of why that particular web browser refuses to do that.
I assume the "particular web browser" is Chromium, which won't load it on any OS I've tried. On Windows, Firefox and the built-in curl.exe also refuse to connect.
Article makes it look like nothing happened in the embed/low-memory/single-threaded malloc space in decades since Doug Lea's malloc.
I just implemented TLSF for my minimal Wasm libc: fragmentation is just as good, performance is a lot more consistent (and on average better), for a significant reduction in code size.
Interesting! I have also implemented a version of TLSF for my (currently single-threaded) programming language. I also found it to be good for my use case (embedded / minimal code size). I'll compare it against yours. One improvement I did is some kind of preallocation for small blocks.
https://github.com/thomasmueller/bau-lang/blob/main/src/main...
I don't get what this is supposed to prove. That my browser doesn't allow websites to declare what encryption they use? I am pretty sure there's a point to all of this, but please let me (and my browser) choose which encryptions I want to trust.
Isn't the idea that the server and client should agree on a common subset? Here, the server's subset is very small, but not esoteric – so then surely it's the client that's lacking in features?
On the bright side, lots of people will be saved from reading bad prose like "Malloc (libc) is the worst memory allocation API to use" and "Programs should avoid, if possible, allocating/deallocating memory too often". (By definition, "too often" means it can possibly be avoided, and usually that it can practically be avoided.)
The first one was offered with no explanation and no claimed better alternative. malloc() is probably the simplest interface for generic runtime allocation, and simplicity has a lot in its favor. malloc() does not provide type safety, is susceptible to external fragmentation, and makes it harder to meet the performance goals outlined in the rest of the blog post. So malloc() reflects trade-offs, but saying that the standard API "is the worst memory allocation API to use" should be supported, even if briefly, instead of simply asserted: meeting the goals I listed inflicts other drawbacks, like needing to create and manage separate heaps.
I thought my explanation for the second one was already clear: "Programs should avoid, if possible, [doing X] too often" is a truism because "too often" implies that some reduction is possible. One should leave out the ", if possible," -- although deciding what is "too often" can be challenging and sometimes a matter of taste. (Is reducing allocation frequency by 5% worth doubling the CPU usage or memory usage or code complexity? Maybe in some cases, but often not.)
FTA: “When multiple threads simultaneously allocate or deallocate memory from the allocator, the allocator will serialize them. Programs making intensive use of the allocator actually slow down as the number of processors increases.”
The article does later retract on that, but that’s no reason to lead with such a blatantly false (with current allocators) statement.
Also FTA “In 2006, a third pool was introduced (after operating system memory pool and library-based memory pool) called the “arena”. Arena is a jemalloc-term”
The tables look mostly correct, and that's what I'll be bookmarking this for… I don't think I've seen any elsewhere that are this extensive (in both axis, total allocators covered & details per allocator).
yup and the characterization of each allocator is so fuzzy, with zero methodology provided.
allocators are so simple to just swap into your program. if you can put together a few representative workloads, you should just try out a few allocators and profile whatever metrics you care about.
yeah that’s a common mistake when evaluating tcmalloc. gperftools tcmalloc diverged quite a while ago. doesn’t have a lot of the fancier features of modern tcmalloc [0].
ClickHouse has been tested with jemalloc, mimalloc, tcmalloc (both variants), rpmalloc, lfalloc, hualloc, and ended up using jemalloc after a few patches and bug fixes.
Yes, I do not know what this paragraph wants to say:
> "The first memory allocation scheme started with a stack-based memory allocation. Next came the dynamic-based memory allocation scheme where linked-list and bucket-heap mechanism are used to divide the private-heap using size class approach. Soon, garbage collection algorithm introduced the initial backend of the memory allocation scheme."
Since no specific operating system is mentioned, these sentences appear to refer to the general history of dynamic memory allocation, in which case they are wrong.
"malloc" is a late comer in this history. It has appeared as the statement "ALLOCATE", together with the statement "FREE", in the programming language PL/I of IBM, by the end of 1964.
At that time many other techniques of managing memory had already been used for a few years.
Dynamic allocation of memory has started with allocation without ever freeing the allocated memory before the termination of the process.
Then, in 1960, 3 methods of handling dynamic memory allocation were published: the use of garbage collectors in April (John McCarthy), the use of stacks in May (E. W. Dijkstra), and the use of reference counts in December (George E. Collins @ IBM).
So the use of garbage collectors is actually the oldest published method for handling dynamic memory allocation, not a newer method.
Garbage collectors: "Recursive Functions of Symbolic Expressions and Their Computation by Machine, Part I", John McCarthy, Communications of the ACM, 1960-04, pp. 184-195.
Stacks and stack pointers: "Recursive Programming", Edsger Wybe Dijkstra, 1960-05-11.
Reference counts for memory allocation: "A Method for Overlapping and Erasure of Lists", George E. Collins (IBM), Communications of the ACM, Volume 3, Issue 12, 1960-12, pp. 655–657.
Couldn't read the article (ERR_SSL_VERSION_OR_CIPHER_MISMATCH, Chrome on Windows). But I'm remembering something a coworker told me some time around... 1991 to 1993, maybe? Forgive me if I repeat some of what the article says - I did try to read it!
While he was at the university, they were experimenting with different kind of mallocs. One was called the "buddy" malloc. It kept a list of free blocks of various sizes, and when you asked for a block and it didn't have one, it asked the OS for twice as much as you asked for. From the rest, it made another block (identical to yours, called the "buddy" block), and put it on the free list of that size.
Well, they experimented with a similar algorithm, but the idea was that most requests were small. So it took the buddy block and broke it into smaller pieces, one half the size of the request, one a quarter the size, and so on, and put those on their respective free lists. They called this the "donner" malloc, because you carved up your buddy.
From the way my coworker smiled, I think he thought it was amusing, but I don't think he was making it up.
52 comments
[ 3.9 ms ] story [ 84.1 ms ] threadFunny SSL setup. Explanation from here https://news.ycombinator.com/item?id=49133598
> Oh, certain browser will not work with this blog if it cannot negotiate ONLY for Cha-Cha/Poly. It's by design as a showcase of why that particular web browser refuses to do that.
I assume the "particular web browser" is Chromium, which won't load it on any OS I've tried. On Windows, Firefox and the built-in curl.exe also refuse to connect.
Article makes it look like nothing happened in the embed/low-memory/single-threaded malloc space in decades since Doug Lea's malloc.
I just implemented TLSF for my minimal Wasm libc: fragmentation is just as good, performance is a lot more consistent (and on average better), for a significant reduction in code size.
http://www.gii.upv.es/tlsf/index.html
https://github.com/ncruces/wasm2go/blob/main/libc-gen/c/mall...
I do do have a malloc() benchmark but it is in bad shape and directories have not coalesce nicely yet, tor a single run or a menu-driven one.
Is this a spec violation or something?
I thought my explanation for the second one was already clear: "Programs should avoid, if possible, [doing X] too often" is a truism because "too often" implies that some reduction is possible. One should leave out the ", if possible," -- although deciding what is "too often" can be challenging and sometimes a matter of taste. (Is reducing allocation frequency by 5% worth doubling the CPU usage or memory usage or code complexity? Maybe in some cases, but often not.)
FTA: “When multiple threads simultaneously allocate or deallocate memory from the allocator, the allocator will serialize them. Programs making intensive use of the allocator actually slow down as the number of processors increases.”
The article does later retract on that, but that’s no reason to lead with such a blatantly false (with current allocators) statement.
Also FTA “In 2006, a third pool was introduced (after operating system memory pool and library-based memory pool) called the “arena”. Arena is a jemalloc-term”
Jemalloc is from around 2005 (http://jemalloc.net/), the idea of arenas is from the 1960s, and Wikipedia claims the term was coined in 1990 (https://en.wikipedia.org/wiki/Region-based_memory_management...), and the linked paper (https://www.cs.princeton.edu/techreports/1988/191.pdf) is from 1988.
Then, a typo: “as well as memory tied to specific to each of the multiple CPU core or even CPU infinity.”
“Infinity” should be “affinity” there.
allocators are so simple to just swap into your program. if you can put together a few representative workloads, you should just try out a few allocators and profile whatever metrics you care about.
for us, tc was among the fastest in runtime while being very space efficient [0]. large rust application using far too many threads.
we’ve since also had great success with tc’s built in profiling tools.
[0]: https://news.ycombinator.com/item?id=47403847
We've tried tcmalloc, too. I don't remember the exact details, but we basically ended using jemalloc because it was using way less memory.
Same story with mimalloc - it usually provided a tiny bit more speed, but required more cpu and memory.
to confirm, you were using tcmalloc from https://github.com/google/tcmalloc and not from https://github.com/gperftools/gperftools, right?
the latter is a lot worse iiuc.
[0]: https://github.com/google/tcmalloc/blob/master/docs/gperftoo...
https://news.ycombinator.com/item?id=47403847
> "The first memory allocation scheme started with a stack-based memory allocation. Next came the dynamic-based memory allocation scheme where linked-list and bucket-heap mechanism are used to divide the private-heap using size class approach. Soon, garbage collection algorithm introduced the initial backend of the memory allocation scheme."
Since no specific operating system is mentioned, these sentences appear to refer to the general history of dynamic memory allocation, in which case they are wrong.
"malloc" is a late comer in this history. It has appeared as the statement "ALLOCATE", together with the statement "FREE", in the programming language PL/I of IBM, by the end of 1964.
At that time many other techniques of managing memory had already been used for a few years.
Dynamic allocation of memory has started with allocation without ever freeing the allocated memory before the termination of the process.
Then, in 1960, 3 methods of handling dynamic memory allocation were published: the use of garbage collectors in April (John McCarthy), the use of stacks in May (E. W. Dijkstra), and the use of reference counts in December (George E. Collins @ IBM).
So the use of garbage collectors is actually the oldest published method for handling dynamic memory allocation, not a newer method.
Garbage collectors: "Recursive Functions of Symbolic Expressions and Their Computation by Machine, Part I", John McCarthy, Communications of the ACM, 1960-04, pp. 184-195.
Stacks and stack pointers: "Recursive Programming", Edsger Wybe Dijkstra, 1960-05-11.
Reference counts for memory allocation: "A Method for Overlapping and Erasure of Lists", George E. Collins (IBM), Communications of the ACM, Volume 3, Issue 12, 1960-12, pp. 655–657.
While he was at the university, they were experimenting with different kind of mallocs. One was called the "buddy" malloc. It kept a list of free blocks of various sizes, and when you asked for a block and it didn't have one, it asked the OS for twice as much as you asked for. From the rest, it made another block (identical to yours, called the "buddy" block), and put it on the free list of that size.
Well, they experimented with a similar algorithm, but the idea was that most requests were small. So it took the buddy block and broke it into smaller pieces, one half the size of the request, one a quarter the size, and so on, and put those on their respective free lists. They called this the "donner" malloc, because you carved up your buddy.
From the way my coworker smiled, I think he thought it was amusing, but I don't think he was making it up.
Rhapsody and early MacOS X, Darwin also used zone-based
Early iPhone also zone-based.
Later MacOS X implemented scalable zone, magazine allocator.
iPhone 12+ then went Nano allocator, ScalableZone + large/VM allocator
Latest iOS/iPadOS use Nano2