Comparison of Malloc() Algorithms(egbert.net) |
Comparison of Malloc() Algorithms(egbert.net) |
Funny 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.
Certain browsers will suffer. Meh.
Is this a spec violation or something?
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.
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
Your CPU is obviously able to handle your purportedly high-transactional workload ... until it doesn't.
> "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. The C programming language has inherited these 2 functions from IBM PL/I, together with several other features.
At that time (1964-12), many other techniques of managing memory had already been used for a few years.
Dynamic allocation of memory has started during the fifties, with allocation without ever freeing the allocated memory before the termination of the process.
Then, in 1960, 3 methods of handling dynamic memory allocation and implicit freeing were published, which have remained important until today: 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, being used in LISP I about 5 years before the first release of PL/I with explicit allocation and freeing (mid 1965).
Will research that, citations and all
I got tired of reading AI prose so I compiled and wrote it from my collections of others' whitepapers.
As a "For Reference Only", at the very least, for me.
As usual, anyone is welcome to improve upon it under CC BY-NC-SA.
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.
Compilations are hard to get 100% right.
Fix the browser.
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.)
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 (open access at ACM).
Stacks and stack pointers: "Recursive Programming", Edsger Wybe Dijkstra, 1960-05-11 (available at the Dijkstra Archive).
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 (open access at ACM).
The first "malloc", i.e. the statements "ALLOCATE" and "FREE" appeared in "NPL Technical Report" at IBM in 1964-12 (available at bitsavers.org).
"NPL" was a provisional name for the new programming language of IBM, which was rebranded as "PL/I" when it was launched officially, a half of year later.
IBM did not document what kind of algorithm was used by their "malloc" implementation, but it already had to handle multi-threaded programs and it was specified that when a new thread was spawned, it could still access any variable that had been dynamically allocated in the parent thread, before the launching of the new thread, but the variables that were allocated in the new thread were private to that thread.
The C "malloc" became compatible with multi-threading only many decades after its ancestor from PL/I.
And then THeIR citations too!
Thank you very much!
I am intrigued.
Is there a source for them?
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.
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...