> We plan to deliver improvements to [..] purging mechanisms
During my time at Facebook, I maintained a bunch of kernel patches to improve jemalloc purging mechanisms. It wasn't popular in the kernel or the security community, but it was more efficient on benchmarks for sure.
Many programs run multiple threads, allocate in one and free in the other. Jemalloc's primary mechanism used to be: madvise the page back to the kernel and then have it allocate it in another thread's pool.
One problem: this involves zero'ing memory, which has an impact on cache locality and over all app performance. It's completely unnecessary if the page is being recirculated within the same security domain.
The problem was getting everyone to agree on what that security domain is, even if the mechanism was opt-in.
I'm really surprised to see you still hocking this.
We did extensive benchmarking of HHVM with and without your patches, and they were proven to make no statistically significant difference in high level metrics. So we dropped them out of the kernel, and they never went back in.
I don't doubt for a second you can come up with specific counterexamples and microbenchnarks which show benefit. But you were unable to show an advantage at the system level when challenged on it, and that's what matters.
You probably weren't there when servers were running for many days at a time.
By the time you joined and benchmarked these systems, the continuous rolling deployment had taken over. If you're restarting the server every few hours, of course the memory fragmentation isn't much of an issue.
> But you were unable to show an advantage at the system level when challenged on it, and that's what matters.
You mean 5 years after I stopped working on the kernel and the underlying system had changed?
It wasn't any cgroup. If you put two untrusting processes in a memory cgroup, there is a lot that can go wrong.
If you don't like the idea of memory cgroups as a security domain, you could tighten it to be a process. But kernel developers have been opposed to tracking pages on a per address space basis for a long time. On the other hand memory cgroup tracking happens by construction.
I recently started using Microsoft's mimalloc (via an LD_PRELOAD) to better use huge (1 GB) pages in a memory intensive program. The performance gains are significant (around 20%). It feels rather strange using an open source MS library for performance on my Linux system.
There needs to be more competition in the malloc space. Between various huge page sizes and transparent huge pages, there are a lot of gains to be had over what you get from a default GNU libc.
We evaluated a few allocators for some of our Linux apps and found (modern) tcmalloc to consistently win in time and space. Our applications are primarily written in Rust and the allocators were linked in statically (except for glibc). Unfortunately I didn't capture much context on the allocation patterns. I think in general the apps allocate and deallocate at a higher rate than most Rust apps (or more than I'd like at least).
Our results from July 2025:
rows are <allocator>: <RSS>, <time spent for allocator operations>
app1:
glibc: 215,580 KB, 133 ms
mimalloc 2.1.7: 144,092 KB, 91 ms
mimalloc 2.2.4: 173,240 KB, 280 ms
tcmalloc: 138,496 KB, 96 ms
jemalloc: 147,408 KB, 92 ms
app2, bench1
glibc: 1,165,000 KB, 1.4 s
mimalloc 2.1.7: 1,072,000 KB, 5.1 s
mimalloc 2.2.4:
tcmalloc: 1,023,000 KB, 530 ms
app2, bench2
glibc: 1,190,224 KB, 1.5 s
mimalloc 2.1.7: 1,128,328 KB, 5.3 s
mimalloc 2.2.4: 1,657,600 KB, 3.7 s
tcmalloc: 1,045,968 KB, 640 ms
jemalloc: 1,210,000 KB, 1.1 s
app3
glibc: 284,616 KB, 440 ms
mimalloc 2.1.7: 246,216 KB, 250 ms
mimalloc 2.2.4: 325,184 KB, 290 ms
tcmalloc: 178,688 KB, 200 ms
jemalloc: 264,688 KB, 230 ms
tcmalloc was from github.com/google/tcmalloc/tree/24b3f29.
I’m surprised (unless they replaced the core tcmalloc algorithm but kept the name).
tcmalloc (thread caching malloc) assumes memory allocations have good thread locality. This is often a double win (less false sharing of cache lines, and most allocations hit thread-local data structures in the allocator).
Multithreaded async systems destroy that locality, so it constantly has to run through the exception case: A allocated a buffer, went async, the request wakes up on thread B, which frees the buffer, and has to synchronize with A to give it back.
This is similar to what I experienced when I tested mimalloc many years ago. If it was faster, it wasn't faster by much, and had pretty bad worst cases.
If you go into Dr Dobbs, The C/C++ User's Journal and BYTE digital archives, there will be ads of companies whose product was basically special cased memory allocator.
Even toolchains like Turbo Pascal for MS-DOS, had an API to customise the memory allocator.
One of the best parts about GC languages is they tend to have much more efficient allocation/freeing because the cost is much more lumped together so it shows up better in a profile.
Agreed, however there is also a reason why the best ones also pack multiple GC algorithms, like in Java and .NET, because one approach doesn't fit all workloads.
Any extra throughput is far overshadowed by trying to control pauses and too much heap allocations happening because too much gets put on the heap. For anything interactive the options are usually fighting the gc or avoiding gc.
When it works. Many programs in GC language end up fighting the GC by allocating a large buffer and managing it by hand anyway because when performance counts you can't have allocation time in there at all. (you see this in C all the time as well)
I remember in the early days of web services, using the apache portable runtime, specifically memory pools.
If you got a web request, you could allocate a memory pool for it, then you would do all your memory allocations from that pool. And when your web request ended - either cleanly or with a hundred different kinds of errors, you could just free the entire pool.
it was nice and made an impression on me.
I think the lowly malloc probably has lots of interesting ways of growing and changing.
In many cases you can also do better than using malloc e.g. if you know you need a huge page, map a huge page directly with mmap
Yes, if you want to use huge pages with arbitrary alloc/free, then use a third-party malloc. If your alloc/free patterns are not arbitrary, you can do even better. We treat malloc as a magic black box but it's actually not very good.
I think some operating system improvements could get people motivated to use huge pages a lot better. In particular make them less fragile on linux and make them not need admin rights on windows. The biggest factor causing problems there is that neither OS can swap a 2MB page. So someone needs to care enough to fix that.
I've been using jemalloc for over 10 years and don't really see a need for it to be updated. It always holds up in benchmarks against any new flavor of the month malloc that comes out.
Last time I checked mimalloc which was admittedly a while ago, probably 5 years, it was noticebly worse and I saw a lot of people on their github issues agreeing with me so I just never looked at it again.
Benchmarks age fast. Treating a ten-year-old allocator as done just because it still wins old tests is tempting fate, since distros, glibc, kernel VM behavior, and high-core alloc patterns keep moving and the failures usually show up as weird regressions in production, not as a clean loss on someone's benchmark chart.
I feel like the real thing that needs to change is we need a more expressive allocation interface than just malloc/realloc. I'm sure that memory allocators could do a significantly better job if they had more information about what the program was intending to do.
Just out of curiosity are you getting 1GB huge pages on Xeon or some other platform? I always thought this class of page is the hardest to exploit, considering that the machine only has, if I recall correctly, one TLB slot for those.
Modern x86_64 has supported multiple page sizes for a long time. I'm on commodity Zen 5 hardware (9900X) with 128 GiB of RAM. Linux will still use a base page size of 4kb but also supports both 2 MiB and 1 GiB huge pages. You can pass something like `default_hugepagesz=2M hugepagesz=1G hugepages=16` to your kernel on boot to use 2 MiB pages but reserve 16 1 GiB pages for later use.
The nice thing about mimalloc is that there are a ton of configurable knobs available via env vars. I'm able to hand those 16 1 GiB pages to the program at launch via `MIMALLOC_RESERVE_HUGE_OS_PAGES=16`.
EDIT: after re-reading your comment a few times, I apologize if you already knew this (which it sounds like you did).
If there is so much performance difference among generic allocators, it means you need semantic optimized allocators (unless performance is actually not that much important in the end).
Agreed mostly. Going from standard library to something like jemalloc or tcmalloc will give you around 5-10% wins which can be significant, but the difference between those generic allocators seem small. I just made a slab allocator recently for a custom data type and got speedups of 100% over malloc.
One has to wonder if this due to the global memory shortage. ("Oh - changing our memory allocator to be more efficient will yield $XXM dollar savings over the next year").
Facebook had talks already years ago (10+) - nobody was allowed to share real numbers, but several facebook employed where allowed to share that the company has measured savings from optimizations. Reading between the lines, a 0.1% efficiency improvement to some parts of Facebook would save them $100,000 a month (again real numbers were never publicly shared so there is a range - it can't be less than $20,000), and so they had teams of people whose job it was to find those improvements.
Most of the savings seemed to come from HVAC costs, followed by buying less computers and in turn less data centers. I'm sure these days saving memory is also a big deal but it doesn't seem to have been then.
The above was already the case 10 years ago, so LLMs are at most another factor added on.
I don't have many regrets about having spent my career in (relatively) tiny companies by comparison, but it sure does sound fun to be on the other side for this kind of thing - the scale where micro-optimizations have macro impact.
In startups I've put more effort into squeezing blood from a stone for far less change; even if the change was proportionally more significant to the business. Sometimes it would be neat to say "something I did saved $X million dollars or saved Y kWh of energy" or whatever.
I've worked on optimizing systems in that ballpark range, memory is worth saving but it isn't necessarily 1:1 with increasing revenue like CPU is. For CPU we have tables to calculate the infra cost savings (we're not really going to free up the server, more like the system is self balancing so it can run harder with the freed CPU), but for memory as long as we can load in whatever we want to (rec systems or ai models) we're in the clear so the marginal headroom isn't as important. It's more of a side thing that people optimizing CPU also get wins in by chance because the skillsets are similar.
On top of cost, they probably cannot get as much memory as they order in a timely fashion so offsetting that with greater efficiency matters right now.
Yeah, identifying single-digit millions of savings out of profiles is relatively common practice at Meta. It's ~easy to come up with a big number when the impact is scaled across a very large numbers of servers. There is a culture of measuring and documenting these quantified wins.
Not just shortage, any improvements to LLMs/electricity/servers memory footprint is becoming much more valuable as the time goes. If we can get 10% faster, you can easily get a lead in the LLM race. The incentives to transparently improving performance are tremendous
We migrated to jemalloc from glibc malloc two years ago and saw 15-20% memory reduction in our Python services. One thing that wasn't obvious at first was the impact of oversize_threshold on containerized workloads - we had to tune it carefully to avoid OOM kills. Has anyone benchmarked jemalloc vs mimalloc for long-running services?
As an Australian who was just made redundant from a role that involved this type of low level programming - I love working on these these kinds of challenges.
I'm saddened that the job market in Australia is largely React CRUD applications and that it's unlikely I will find a role that lets me leverage my niche skill set (which is also my hobby)
Speaking as an Australian that works on React CRUD applications because there's nothing else in the market, I've been reading through this thread thinking the exact same thing.
Google had some position open working on the kernel for ChromeOS, and Microsoft had some positions working on data center network drivers.
I applied for both and got ghosted, haha.
I also saw a government role as a security researcher. Involves reverse engineering, ghidra and that sort of thing. Super awesome - but the pay is extremely uncompetitive. Such a shame.
Other than that, the most interesting roles are in finance (like HFT) - where you need to juggle memory allocations, threads and use C++ (hoping I can pitch Rust but unlikely).
Sadly they have a reputation of having pretty rough cultures, uncompetitive salaries and it's all in-office
I'm actually looking at HFT companies. Hoping I find one that allows remote working - but looks like there are basically no remote roles going at the moment
I remember I was a senior lead softeng of a worldbank funded startup project, and have deployed Ruby with jemalloc in prod. There's a huge noticeable speed and memory efficiency. It did saved us a lot of AWS costs, compare to just using normal Ruby. This was 8 years ago, why haven't projects adopt it yet as de facto.
Usually lack of knowledge that such a thing exists, or just plain ol' momentum. Changing something long in production at established companies, even if there is a tangible benefit, can be a real challenge.
If you filter the commits to the past five years, four of the top six committers are Meta employees. The other two might be as well, it just doesn't say that on their Github / personal website.
Surprised not to see any mention of the global memory supply shock. Would love to learn more about how that economic is shifting software priorities toward memory allocation for the first time in my (relatively young) career
While it may seem directly related, it's just not. These things are worked on regardless of how cheap or expensive RAM is, because optimizing memory footprint pretty much always leads to fewer machines leased, which is a worthwhile goal even for smaller shops.
Few months back, some of the services switched to jemalloc for the Java VM. It took months (of memory dumps and tracing sys-calls) to blame the JVM, itself, for getting killed by the oom_killer.
Initially the idea was diagnostics, instead the the problem disappeared on its own.
Large engineering orgs often underestimate how much CI pipelines amplify performance issues. Even small inefficiencies multiply when builds run hundreds of times a day.
Allocators like that aren't the default for every process because they have higher startup costs. They are targeted to server workloads where startup cost doesn't matter, but it matters a lot if you're doing crud like starting millions of short-lived processes.
First impressions: LOL, the blunt commentary in the HN thread title compared to the PR-speak of the fb.com post.
Second thoughts: Actually the fb.com post is more transparent than I'd have predicted. Not bad at all. Of course it helps that they're delivering good news!
> Building a software system is a lot like building a skyscraper: The product everyone sees is the top, but the part that keeps it from falling over is the foundation buried in the dirt and the scaffolding hidden from sight.
They should have just called it an ivory tower, as that's what they're building whenever they're not busy destroying democracy with OS Backdoor lobbyism or Cambridge Analytica shenanigans.
Edit: If every thread about any of Elon Musk's companies can contain at least 10 comments talking about Elon's purported crimes against humanity, threads about Zuckerberg's companies can contain at least 1 comment. Without reminders like this, stories like last week's might as well remain non-consequential.
scudo has been the default allocator for Android since Android 11, and we are hoping to make it mandatory for the few remaining places that don't use it. Using an allocator without memory protections in 2026 (especially after we have closed nearly all known performance gaps with jemalloc) is really not a great choice.
I was recently debugging an app double-free segfault on my android 13 samsung galaxy A51 phone, and the internal stack trace pointed to jemalloc function calls (je_free).
Meta never abandoned jemalloc. https://github.com/facebook/jemalloc remained public the entire time. It's my understanding that Jason Evans, the creator of jemalloc, had ownership over the jemalloc/jemalloc repo which is why that one stopped being updated after he left.
Meta still maintained it and actively pushed commits to it fixing bugs and adding improvements. From this blog post it sounds like they are increasing investment into it along with resurrecting the original repo. When the repo was archived Meta said that development on jemalloc would be focused towards Meta's own goals and needs as opposed to the larger ecosystem.
> We plan to deliver improvements to [..] purging mechanisms
During my time at Facebook, I maintained a bunch of kernel patches to improve jemalloc purging mechanisms. It wasn't popular in the kernel or the security community, but it was more efficient on benchmarks for sure.
Many programs run multiple threads, allocate in one and free in the other. Jemalloc's primary mechanism used to be: madvise the page back to the kernel and then have it allocate it in another thread's pool.
One problem: this involves zero'ing memory, which has an impact on cache locality and over all app performance. It's completely unnecessary if the page is being recirculated within the same security domain.
The problem was getting everyone to agree on what that security domain is, even if the mechanism was opt-in.
https://marc.info/?l=linux-kernel&m=132691299630179&w=2
I'm really surprised to see you still hocking this.
We did extensive benchmarking of HHVM with and without your patches, and they were proven to make no statistically significant difference in high level metrics. So we dropped them out of the kernel, and they never went back in.
I don't doubt for a second you can come up with specific counterexamples and microbenchnarks which show benefit. But you were unable to show an advantage at the system level when challenged on it, and that's what matters.
You probably weren't there when servers were running for many days at a time.
By the time you joined and benchmarked these systems, the continuous rolling deployment had taken over. If you're restarting the server every few hours, of course the memory fragmentation isn't much of an issue.
> But you were unable to show an advantage at the system level when challenged on it, and that's what matters.
You mean 5 years after I stopped working on the kernel and the underlying system had changed?
I don't recall ever talking to you on the matter.
17 replies →
What metrics were improved by your patches?
Maybe I'm misreading, but considering it OK to leak memory contents across a process boundary because it's within a cgroup sounds wild.
It wasn't any cgroup. If you put two untrusting processes in a memory cgroup, there is a lot that can go wrong.
If you don't like the idea of memory cgroups as a security domain, you could tighten it to be a process. But kernel developers have been opposed to tracking pages on a per address space basis for a long time. On the other hand memory cgroup tracking happens by construction.
1 reply →
I recently started using Microsoft's mimalloc (via an LD_PRELOAD) to better use huge (1 GB) pages in a memory intensive program. The performance gains are significant (around 20%). It feels rather strange using an open source MS library for performance on my Linux system.
There needs to be more competition in the malloc space. Between various huge page sizes and transparent huge pages, there are a lot of gains to be had over what you get from a default GNU libc.
We evaluated a few allocators for some of our Linux apps and found (modern) tcmalloc to consistently win in time and space. Our applications are primarily written in Rust and the allocators were linked in statically (except for glibc). Unfortunately I didn't capture much context on the allocation patterns. I think in general the apps allocate and deallocate at a higher rate than most Rust apps (or more than I'd like at least).
Our results from July 2025:
rows are <allocator>: <RSS>, <time spent for allocator operations>
tcmalloc was from github.com/google/tcmalloc/tree/24b3f29.
i don't recall which jemalloc was tested.
I’m surprised (unless they replaced the core tcmalloc algorithm but kept the name).
tcmalloc (thread caching malloc) assumes memory allocations have good thread locality. This is often a double win (less false sharing of cache lines, and most allocations hit thread-local data structures in the allocator).
Multithreaded async systems destroy that locality, so it constantly has to run through the exception case: A allocated a buffer, went async, the request wakes up on thread B, which frees the buffer, and has to synchronize with A to give it back.
Are you using async rust, or sync rust?
5 replies →
That’s a considerable regression for mimalloc between 2.1 and 2.2 – did you track it down or report it upstream?
Edit: I see mimalloc v3 is out – I missed that! That probably moots this discussion altogether.
1 reply →
This is similar to what I experienced when I tested mimalloc many years ago. If it was faster, it wasn't faster by much, and had pretty bad worst cases.
If you go into Dr Dobbs, The C/C++ User's Journal and BYTE digital archives, there will be ads of companies whose product was basically special cased memory allocator.
Even toolchains like Turbo Pascal for MS-DOS, had an API to customise the memory allocator.
The one size fits all was never a solution.
One of the best parts about GC languages is they tend to have much more efficient allocation/freeing because the cost is much more lumped together so it shows up better in a profile.
Agreed, however there is also a reason why the best ones also pack multiple GC algorithms, like in Java and .NET, because one approach doesn't fit all workloads.
14 replies →
Any extra throughput is far overshadowed by trying to control pauses and too much heap allocations happening because too much gets put on the heap. For anything interactive the options are usually fighting the gc or avoiding gc.
When it works. Many programs in GC language end up fighting the GC by allocating a large buffer and managing it by hand anyway because when performance counts you can't have allocation time in there at all. (you see this in C all the time as well)
9 replies →
I remember in the early days of web services, using the apache portable runtime, specifically memory pools.
If you got a web request, you could allocate a memory pool for it, then you would do all your memory allocations from that pool. And when your web request ended - either cleanly or with a hundred different kinds of errors, you could just free the entire pool.
it was nice and made an impression on me.
I think the lowly malloc probably has lots of interesting ways of growing and changing.
This is called “an arena” more generally, and it is in wide use across many forms of servers, compilers, and others.
Look into talloc, used inside Samba (and other FLOSS projects like sssd). Exactly this.
In many cases you can also do better than using malloc e.g. if you know you need a huge page, map a huge page directly with mmap
Yes, if you want to use huge pages with arbitrary alloc/free, then use a third-party malloc. If your alloc/free patterns are not arbitrary, you can do even better. We treat malloc as a magic black box but it's actually not very good.
I think some operating system improvements could get people motivated to use huge pages a lot better. In particular make them less fragile on linux and make them not need admin rights on windows. The biggest factor causing problems there is that neither OS can swap a 2MB page. So someone needs to care enough to fix that.
I've been using jemalloc for over 10 years and don't really see a need for it to be updated. It always holds up in benchmarks against any new flavor of the month malloc that comes out.
Last time I checked mimalloc which was admittedly a while ago, probably 5 years, it was noticebly worse and I saw a lot of people on their github issues agreeing with me so I just never looked at it again.
Mimalloc v3 has just come out (about a month ago) and is a significant improvement over both v2 and v1 (what you likely last tested)
Benchmarks age fast. Treating a ten-year-old allocator as done just because it still wins old tests is tempting fate, since distros, glibc, kernel VM behavior, and high-core alloc patterns keep moving and the failures usually show up as weird regressions in production, not as a clean loss on someone's benchmark chart.
7 replies →
I used mimalloc to run zenlisp under OpenBSD as it would clash with the paranoid malloc of base.
I feel like the real thing that needs to change is we need a more expressive allocation interface than just malloc/realloc. I'm sure that memory allocators could do a significantly better job if they had more information about what the program was intending to do.
There are, look no further than jemalloc API surface itself:
https://jemalloc.net/jemalloc.3.html
One thing to call out: sdallocx integrates well with C++'s sized delete semantics: https://isocpp.org/files/papers/n3778.html
1 reply →
Just out of curiosity are you getting 1GB huge pages on Xeon or some other platform? I always thought this class of page is the hardest to exploit, considering that the machine only has, if I recall correctly, one TLB slot for those.
Modern x86_64 has supported multiple page sizes for a long time. I'm on commodity Zen 5 hardware (9900X) with 128 GiB of RAM. Linux will still use a base page size of 4kb but also supports both 2 MiB and 1 GiB huge pages. You can pass something like `default_hugepagesz=2M hugepagesz=1G hugepages=16` to your kernel on boot to use 2 MiB pages but reserve 16 1 GiB pages for later use.
The nice thing about mimalloc is that there are a ton of configurable knobs available via env vars. I'm able to hand those 16 1 GiB pages to the program at launch via `MIMALLOC_RESERVE_HUGE_OS_PAGES=16`.
EDIT: after re-reading your comment a few times, I apologize if you already knew this (which it sounds like you did).
3 replies →
If there is so much performance difference among generic allocators, it means you need semantic optimized allocators (unless performance is actually not that much important in the end).
You are not wrong and this is indeed what zig is trying to push by making all std functions that allocate take a allocator parameter.
Agreed mostly. Going from standard library to something like jemalloc or tcmalloc will give you around 5-10% wins which can be significant, but the difference between those generic allocators seem small. I just made a slab allocator recently for a custom data type and got speedups of 100% over malloc.
1 reply →
Related. Others?
Jemalloc Postmortem - https://news.ycombinator.com/item?id=44161128 - June 2025 (7 comments)
One has to wonder if this due to the global memory shortage. ("Oh - changing our memory allocator to be more efficient will yield $XXM dollar savings over the next year").
Facebook had talks already years ago (10+) - nobody was allowed to share real numbers, but several facebook employed where allowed to share that the company has measured savings from optimizations. Reading between the lines, a 0.1% efficiency improvement to some parts of Facebook would save them $100,000 a month (again real numbers were never publicly shared so there is a range - it can't be less than $20,000), and so they had teams of people whose job it was to find those improvements.
Most of the savings seemed to come from HVAC costs, followed by buying less computers and in turn less data centers. I'm sure these days saving memory is also a big deal but it doesn't seem to have been then.
The above was already the case 10 years ago, so LLMs are at most another factor added on.
I don't have many regrets about having spent my career in (relatively) tiny companies by comparison, but it sure does sound fun to be on the other side for this kind of thing - the scale where micro-optimizations have macro impact.
In startups I've put more effort into squeezing blood from a stone for far less change; even if the change was proportionally more significant to the business. Sometimes it would be neat to say "something I did saved $X million dollars or saved Y kWh of energy" or whatever.
I've worked on optimizing systems in that ballpark range, memory is worth saving but it isn't necessarily 1:1 with increasing revenue like CPU is. For CPU we have tables to calculate the infra cost savings (we're not really going to free up the server, more like the system is self balancing so it can run harder with the freed CPU), but for memory as long as we can load in whatever we want to (rec systems or ai models) we're in the clear so the marginal headroom isn't as important. It's more of a side thing that people optimizing CPU also get wins in by chance because the skillsets are similar.
I've heard of some people getting banned from FB to save memory space? Surely that can't be the case but I swear I've seen something like that
1 reply →
> LLMs are at most another factor added on
At most... Think 10x rather than 0.1x or 1x.
On top of cost, they probably cannot get as much memory as they order in a timely fashion so offsetting that with greater efficiency matters right now.
Yeah, identifying single-digit millions of savings out of profiles is relatively common practice at Meta. It's ~easy to come up with a big number when the impact is scaled across a very large numbers of servers. There is a culture of measuring and documenting these quantified wins.
With the reputation of that company, one can wonder a lot of backstories that are even more depressing than a memory shortage.
Not just shortage, any improvements to LLMs/electricity/servers memory footprint is becoming much more valuable as the time goes. If we can get 10% faster, you can easily get a lead in the LLM race. The incentives to transparently improving performance are tremendous
Oooh maybe finally time for lovingly hand-optimized assembly to come back in fashion! (It probably has in AI workloads or so I daydream)
> changing our memory allocator
they've been using jemalloc (and employing "je") since 2009.
We migrated to jemalloc from glibc malloc two years ago and saw 15-20% memory reduction in our Python services. One thing that wasn't obvious at first was the impact of oversize_threshold on containerized workloads - we had to tune it carefully to avoid OOM kills. Has anyone benchmarked jemalloc vs mimalloc for long-running services?
As an Australian who was just made redundant from a role that involved this type of low level programming - I love working on these these kinds of challenges.
I'm saddened that the job market in Australia is largely React CRUD applications and that it's unlikely I will find a role that lets me leverage my niche skill set (which is also my hobby)
I know this isn’t who’s hiring thread, but we are hiring in AU for low-level data processing and have interesting performance challenges.
Link in bio.
Love your product!
Speaking as an Australian that works on React CRUD applications because there's nothing else in the market, I've been reading through this thread thinking the exact same thing.
Google had some position open working on the kernel for ChromeOS, and Microsoft had some positions working on data center network drivers.
I applied for both and got ghosted, haha.
I also saw a government role as a security researcher. Involves reverse engineering, ghidra and that sort of thing. Super awesome - but the pay is extremely uncompetitive. Such a shame.
Other than that, the most interesting roles are in finance (like HFT) - where you need to juggle memory allocations, threads and use C++ (hoping I can pitch Rust but unlikely).
Sadly they have a reputation of having pretty rough cultures, uncompetitive salaries and it's all in-office
1 reply →
Some of this remote stuff might interest you:
https://www.igalia.com/jobs/open/
Or https://www.fsf.org/resources/jobs/fsf-engineering-and-certi...
Not sure if it's the domain you're interested in, but there are quite a few HFT firms with offices in Australia.
The one I know of (IMC trading) does a lot of low level stuff like this and is currently hiring.
I'm actually looking at HFT companies. Hoping I find one that allows remote working - but looks like there are basically no remote roles going at the moment
I just tried to apply for IMC, the form on their careers page is broken. Looks like that's the first boss to defeat, haha
SIG is hiring for some roles in Sydney: https://careers.sig.com/global-experienced
I have a relative in Australia who was hired by some type of consultancy to work on Samba, but I don't know what work he was doing.
Which consultancy was that?
2 replies →
I remember I was a senior lead softeng of a worldbank funded startup project, and have deployed Ruby with jemalloc in prod. There's a huge noticeable speed and memory efficiency. It did saved us a lot of AWS costs, compare to just using normal Ruby. This was 8 years ago, why haven't projects adopt it yet as de facto.
Usually lack of knowledge that such a thing exists, or just plain ol' momentum. Changing something long in production at established companies, even if there is a tangible benefit, can be a real challenge.
I nice use case too
https://technology.blog.gov.uk/2015/12/11/using-jemalloc-to-...
Opening up strong with a gigantic merge of the stuff they've been working on in their own fork: https://github.com/jemalloc/jemalloc/pull/2863
Is there a concise timelime/history of this? I thought jemalloc was 100% open source, why is Meta in control of it?
Jason Evans (the creator of jemalloc) recounted the entire thing last year: https://jasone.github.io/2025/06/12/jemalloc-postmortem/
"Were I to reengage, the first step would be at least hundreds of hours of refactoring to pay off accrued technical debt."
Facebook's coding AIs to the rescue, maybe? I wonder how good all these "agentic" AIs are at dreaded refactoring jobs like these.
5 replies →
If you filter the commits to the past five years, four of the top six committers are Meta employees. The other two might be as well, it just doesn't say that on their Github / personal website.
Surprised not to see any mention of the global memory supply shock. Would love to learn more about how that economic is shifting software priorities toward memory allocation for the first time in my (relatively young) career
While it may seem directly related, it's just not. These things are worked on regardless of how cheap or expensive RAM is, because optimizing memory footprint pretty much always leads to fewer machines leased, which is a worthwhile goal even for smaller shops.
That's useful to know, thank you.
There’s been shocks at hyperscaler scale, ex. this got yuge at Google for a couple years before ChatGPT
Few months back, some of the services switched to jemalloc for the Java VM. It took months (of memory dumps and tracing sys-calls) to blame the JVM, itself, for getting killed by the oom_killer.
Initially the idea was diagnostics, instead the the problem disappeared on its own.
If you changed from glibc to jemalloc and that solved your issues, then you should blame glibc, not the JVM.
Well, indeed - I thought that part was obvious reading it.
(wrong thread)
The URL of this story seems to have changed to a Meta press release. What are you quoting?
Sorry, misdirected the reply.
Large engineering orgs often underestimate how much CI pipelines amplify performance issues. Even small inefficiencies multiply when builds run hundreds of times a day.
Someone should tell Bryan Cantrill, he'd probably be ecstatic...
I used jemalloc recently for ComfyUI/Wan and it’s literally magic. I’m surprised it doesn’t come that way by default.
Allocators like that aren't the default for every process because they have higher startup costs. They are targeted to server workloads where startup cost doesn't matter, but it matters a lot if you're doing crud like starting millions of short-lived processes.
First impressions: LOL, the blunt commentary in the HN thread title compared to the PR-speak of the fb.com post.
Second thoughts: Actually the fb.com post is more transparent than I'd have predicted. Not bad at all. Of course it helps that they're delivering good news!
It’s still quite corporate-y, but other than the way of writing I agree it’s generally quite clear.
How is the original author making out in the new arrangement?
Jason Evans worked for Facebook for almost two decades, starting in 2009 - https://jasone.github.io/2025/06/12/jemalloc-postmortem/
He's doing just fine. If you're looking for a story about a FAANG company not paying engineers well for their work, this isn't it.
> Building a software system is a lot like building a skyscraper: The product everyone sees is the top, but the part that keeps it from falling over is the foundation buried in the dirt and the scaffolding hidden from sight.
They should have just called it an ivory tower, as that's what they're building whenever they're not busy destroying democracy with OS Backdoor lobbyism or Cambridge Analytica shenanigans.
Edit: If every thread about any of Elon Musk's companies can contain at least 10 comments talking about Elon's purported crimes against humanity, threads about Zuckerberg's companies can contain at least 1 comment. Without reminders like this, stories like last week's might as well remain non-consequential.
>We are committed to continuing to develop jemalloc development
From the Department of Redundancy Department.
Jemalloc also is used by android bionic libc library
scudo has been the default allocator for Android since Android 11, and we are hoping to make it mandatory for the few remaining places that don't use it. Using an allocator without memory protections in 2026 (especially after we have closed nearly all known performance gaps with jemalloc) is really not a great choice.
Doesn't it depend on vendors/customization? Default is https://llvm.org/docs/ScudoHardenedAllocator.html since Android 11 (2020).
I don't know, that is probably the case I guess?
I was recently debugging an app double-free segfault on my android 13 samsung galaxy A51 phone, and the internal stack trace pointed to jemalloc function calls (je_free).
Meta never abandoned jemalloc. https://github.com/facebook/jemalloc remained public the entire time. It's my understanding that Jason Evans, the creator of jemalloc, had ownership over the jemalloc/jemalloc repo which is why that one stopped being updated after he left.
The repo's availability isn't related to whether it's still maintained.
Meta still maintained it and actively pushed commits to it fixing bugs and adding improvements. From this blog post it sounds like they are increasing investment into it along with resurrecting the original repo. When the repo was archived Meta said that development on jemalloc would be focused towards Meta's own goals and needs as opposed to the larger ecosystem.
3 replies →
All the AI investment and their biggest news is commitment to Jemalloc
Seems like they’d want to wait to commit until after the layoffs, right?
I work in the space. This article would not have been published if the team responsible was on the chopping block
[dead]
It's just one team with like 4 people. They can layoff a lot of staff from Metaverse.
[dead]
[dead]
And the Oscar for most mealy-mouthed post of the year goes to…
We generally try to avoid corporate press releases for that reason, but is there a good third-party post to replace it with?
https://hn.algolia.com/?dateRange=all&page=0&prefix=true&sor...
If you need to optimize the allocator you are doing it wrong.
Exactly. No need to engineer an allocator. You only live once!
/s