The mm people are increasingly hostile to any method of handling OOMs (like, just failing the allocation) besides the OOM killer - it's become very dominated by the hyperscalars and cloud vendors.
Working around mm nuttiness is a frequent source of frustration.
I agree with the blog post's technical contents, but I feel we came across too strong in the title. For Ubicloud as a managed Postgres provider, we use strict memory overcommit. Our experience with operating Postgres at scale taught us that it's better to enable this than going with the defaults.
However, I can see many other scenarios, where using strict memory overcommit would have unanticipated side-effects. That's why Linux doesn't go with strict memory commit as its default.
(previous title was "PostgreSQL and the OOM Killer: Why You Must Use Strict Memory Overcommit", if anyone is wondering.) Thanks for updating it here as well!
They allude to this in the article but I would emphasize caution when using mode 2 especially if one has already adjusted overcommit ratios as one can prevent forks. Test this in a QA/Perf environment first, also testing the restart of all applications. Load test and do full QA tests before deploying to Production and even then when deploying to production I would just dynamically change the setting via app deployment scripts until confidence is high instead of putting it in the sysctl config files.
I've gone through this exercise in the past on much older kernels which they cover as well and just me personally I ran into less issues by leaving overcommit to 0 and just dropping the overcommit ratio to 0 and setting the oom_score_adj for programs as high as 1000 if I wanted vmscan to leave them alone and of course using the Redhat formulas for setting vm.min_free_kbytes, vm.admin_reserve_kbytes, vm.user_reserve_kbytes. And of course be vigilant in disallowing app owners from using every last bit of memory.
Correcting a rather significant typo: setting the oom_score_adj for programs as high as 1000 should be -1000 to be left alone. 1000 would make it a prime candidate for an OOM kill. Positive integers should be used on sacrificial superfluous programs. [1] As an example OpenSSH sets the sshd to -1000 by default.
This has bitten me multiple times. The problem I have is that at work we deploy the application (written in Go) and PostgreSQL on the same machine. The backend app allocates a lot of virtual memory, and initially we had overcommit to 0 (heuristic). This caused crashes on big queries in PostgreSQL and we set it to 2. The whole system became a bit unstable because the backend would still allocate a lot of virtual memory and at some point we ran into errors when allocating.
For now, we have overcommit_ratio set to a value that is stable from experience, but there really seems to be no silver lining. Go is very happy to allocate a lot of virtual memory, but so are most managed languages. The best solution would probably be to host the backend and the database on separate servers.
I'm not sure if you are aware but there are relatively recent environment variables you can set to help contain Go memory to a fixed size.
GOMEMLIMIT works very well if you set it to around 90% of available memory as a rough heuristic. You should definitely profile your application to fine tune this number (e.g. if you link with C libraries that hold large memory pools then Go doesn't account for that) but also to identify sources of spikey/leaky allocations. For example, encoding/json is notorious for it's inner sync.Pool hanging on to outsized buffers. There's usually a lot of low hanging fruit.
In my experience Go can be extremely stable in terms of memory footprint at both small (~O(1MiB)) and large (~O(256GiB)) scales, and it takes only a small amount of effort.
As far as GC languages go, it is by far the easiest to work with.
I was aware of GOMEMLIMIT, but it didn't cross my mind in this case, thanks for pointing it out. It could be really useful! I'll have to check our specific use case
Yes, it would. Basically every serious database tries to allocate everything and more - back in the day we'd just allocate VMs on the machine even with the overhead because knowing it cannot leave its constraints and would work within them was worth the cost.
There are many reasons to use a dedicated host (or VM) for a DB server, but if only the accessible memory needs to be limited a container is the simpler, more efficient tool. Said that, I would expect to be able to configure how much memory a DB process is allowed to allocate. I remember distinctly that PostgreSQL allows such. But of course both can be configured simultaneously, a belts&suspenders approach if you will.
Whether failed transactions are actually so much more desirable than a OOM-killed process isn't quite obvious, but it might be easier to troubleshoot.
cgroups have nothing to do with overcommit and memory allocation. They limit actual memory usage for a specific program or group of programs. If this program tries to use more memory than the cgroup memory limit, the program gets OOM killed.
Mode 0 (Heuristic) is described incorrectly. All this complex heuristic was removed almost a decade ago. Currently, the kernel refuses a single allocation that exceeds the physical memory. That is all.
The article ignores the proper modern solution to prevent OOM killing of critical processes - OOM Score Adjust.
Tuning CommitLimit manually is an archaic, imprecise, and error-prone way to handle memory limits, only suitable for single-process workloads that can handle ENOMEM properly. It completely ignores dynamic file page cache memory allocation. You still can get OOM if you get unusually high file activity. On the other hand, under low file activity, it wastes memory on the same page cache, because it can't be reclaimed without memory pressure, and memory pressure can't be created because workload hits ENOMEM earlier. Don't use strict overcommit.
Microsoft just followed VAX/VMS that does not overcommit. And there is a noise on Linux mail lists to implement process builder pattern which VAX had like 50 years ago…
Nothing worse than memory management on Hyperscaler VMs which do not use Swap :|
Took k8s ages to get Swap support.
We lost something when we accepted that Hyperscalers just tell you to use more moemory. It was shitty 5 years ago and today especially after the ram price increases
My guess would be: it's because memory management before MGLRU was really not good and required different userspace solutions and tinkering. You either get killed with OOM (no swap) or got into thrashing (swap).
And now, with PSI + MGLRU, situation is much better, but there are still missing features/subsystems which would be nice to have. For example there's no simple way to lock memory mlockall-style to ensure that rarely used daemon would not face long no-cache-latency upon accessing the first time after long idle time.
First, Linux's default memory management strategy is bonkers. OOM killing rarely actually works in my experience, at least on desktop. It takes ages to kick in and usually the system just freezes and you have to hard reboot. I've experienced this on every Linux system I've used, even my current one with 128GB of RAM and 64GB of swap, so don't say "it works for me". Windows and Mac do not have this issue at all, so clearly it's possible to do it better.
Has anyone tried using strict overcommit on desktop Linux?
Second, this bug is a great counterpoint to those annoying people who naysay Rust with "but not all bugs are memory safety bugs, what about logic bugs? huh?". Rust code would not have had this bug.
Does this result in programs more frequently erroring/crashing because they can't allocate? I don't know how well many of the programs I frequently use on my desktop (Firefox, GNOME desktop, JVM + IntelliJ, Slack, etc.) handle allocation failures. I'm not sure they would do much better than crash, but I know the default OOM killer settings work well for me. About once a year a real runaway process (usually a throwaway program I'm working on) gets OOM-killed, and that's fine with me.
Java allowed to handle out-of-memory rather well if one wanted to even 25 years ago. Basically one allocated a buffer on a startup taking 5% of memory that the application was supposed to use and made all threads to catch the oom exception. When handling that the buffer would be released, GC would be forced and a special flag would be set asking app to cancel any memory-intensive tasks until enough memory would be released and the buffer can be allocated again. It worked extremely well.
> Does this result in programs more frequently erroring/crashing because they can't allocate?
I run Firefox, VSCodium with LSP, Discord, Signal and there's still space left for a game like CS2. I'm not a heavy user by any means.
> I'm not sure they would do much better than crash
I have yet to see a program that silently handles allocation failures and doesn't crash. These days everything is coded to crash if no memory :(
> About once a year a real runaway process (usually a throwaway program I'm working on) gets OOM-killed
In my case it killed system critical processes with no way to recover. With disabled overcommit, it freezes for a while (usually for a minute or two), I close some random program of my choosing and then see in Resource Monitor what's eating my ram.
The reason you hear less about Window's OOM killer is simply because it works well.
The Linux Kernel OOM killer kills random things. Userspace OOM killers are meant to improve this, and they work well in a server situation when you already know in advance what is likely to go haywire and what is safe to kill. But they don't work well on desktop (some of them are improving but it doesn't seem to be a priority).
The Windows OOM killer by comparison usually kills something sensible (i.e. the program that is actually using all the memory), and asks the user for permission before killing it (when possible). You do see a lot of memes of situations where it fails.
damn, good observation, when my data analysis python script goes wrong and allocates 24 GB of RAM on a 32 GB computer, it crashes (gets killed) with "out of memory" error. I've never seen something else getting killed
Not overcommitting is Windows's default and only behavior
A memory allocator can implement overcommit, because you can separate reserving virtual memory and having it backed by physical memory into two different system calls. But from the point of view of the kernel, any time it promises to give you physical memory that memory is backed either by RAM or by space reserved in the swap file
That's disabling swap, not overcommit. Windows doesn't overcommit. It's one of the reason why it handles low memory situations so much more gracefully than Linux.
The purpose of the system commit limit and commit charge is to track all uses of these resources to ensure they are never overcommitted — that is, that there is never more virtual address space defined than there is space to store its contents, either in RAM or in backing store (on disk).
If no memory is available where a page file would make a difference, this leads to application crashes instead. A crash is (usually) worse than paging.
Certain applications, Photoshop being the historical example, will outright fail to run with no page file present.
Typically, performance drops enough that the user kills the program or reboots before the page file expands to fill the disk. And other threads here suggest there is something that will prompt users to kill programs in states like this.
> No such problem would've ever occured if programs hadn't allocated more than they actually use.
That's part of the issue, but sometimes things do in fact use too much memory as well as allocate too much.
Another part of the issue is that few programs are built to handle allocation failures.
And then you have a metrics issue. There's not really a good metric to know when you're out of memory, other than performance collapse. If your applications don't use disk, it's not too hard; but when they do use disk, performance will collapse once there's insufficient memory to provide the disk caching needed. In my experience, adding a small swap and monitoring swap i/o can be pretty helpful, and a small swap doesn't tend to allow long thrashing when memory use grows. But that's not universal and everybody loves to hate swap these days.
> Typically, performance drops enough that the user kills the program or reboots before the page file expands to fill the disk. And other threads here suggest there is something that will prompt users to kill programs in states like this.
Not in the age of NVMe it doesn't. Swap is fast now. Plus, at least on Linux, you can put zswap in front of the regular swap and introduce an even faster level of memory hierarchy and thereby make page-outs even more profitable.
Your argument falls flat when a page file can be multi-GB and automatically grow. And if your application admin was competent, memory monitoring would be part of the application monitoring stack.
An application that grows in such a way (besides having backing stores for memory-mapped files, as well) will often perform so poorly that it requires addressing (adding RAM, looking for application faults, etc).
A page file is insurance, one that can last you much longer than available system memory.
- system dies under memory pressure (regardless of swapping, actually not having swap makes it worse which should be common knowledge by now)
- system dies under disk pressure even if there are tons of free memory (this one is fun to diagnose)
- system can technically not die, but render itself useless (or worse) under memory pressure by the oom killer
- memory compression of any sort is not enabled
- ...
Both Windows and macOS do so much better out of the box for essentially any workload.
Working around mm nuttiness is a frequent source of frustration.
I agree with the blog post's technical contents, but I feel we came across too strong in the title. For Ubicloud as a managed Postgres provider, we use strict memory overcommit. Our experience with operating Postgres at scale taught us that it's better to enable this than going with the defaults.
However, I can see many other scenarios, where using strict memory overcommit would have unanticipated side-effects. That's why Linux doesn't go with strict memory commit as its default.
I've gone through this exercise in the past on much older kernels which they cover as well and just me personally I ran into less issues by leaving overcommit to 0 and just dropping the overcommit ratio to 0 and setting the oom_score_adj for programs as high as 1000 if I wanted vmscan to leave them alone and of course using the Redhat formulas for setting vm.min_free_kbytes, vm.admin_reserve_kbytes, vm.user_reserve_kbytes. And of course be vigilant in disallowing app owners from using every last bit of memory.
[1] - https://man7.org/linux/man-pages/man5/proc_pid_oom_score_adj...
For now, we have overcommit_ratio set to a value that is stable from experience, but there really seems to be no silver lining. Go is very happy to allocate a lot of virtual memory, but so are most managed languages. The best solution would probably be to host the backend and the database on separate servers.
GOMEMLIMIT works very well if you set it to around 90% of available memory as a rough heuristic. You should definitely profile your application to fine tune this number (e.g. if you link with C libraries that hold large memory pools then Go doesn't account for that) but also to identify sources of spikey/leaky allocations. For example, encoding/json is notorious for it's inner sync.Pool hanging on to outsized buffers. There's usually a lot of low hanging fruit.
In my experience Go can be extremely stable in terms of memory footprint at both small (~O(1MiB)) and large (~O(256GiB)) scales, and it takes only a small amount of effort.
As far as GC languages go, it is by far the easiest to work with.
Whether failed transactions are actually so much more desirable than a OOM-killed process isn't quite obvious, but it might be easier to troubleshoot.
If the database requests more memory, it gets ENOMEM, but if the backend app requests more memory, it does get some more because it can overcommit?
Sounds dangerous, if the go program then writes to the overcommitted memory, you'd still trigger the OOM killer, right?
The article ignores the proper modern solution to prevent OOM killing of critical processes - OOM Score Adjust.
Tuning CommitLimit manually is an archaic, imprecise, and error-prone way to handle memory limits, only suitable for single-process workloads that can handle ENOMEM properly. It completely ignores dynamic file page cache memory allocation. You still can get OOM if you get unusually high file activity. On the other hand, under low file activity, it wastes memory on the same page cache, because it can't be reclaimed without memory pressure, and memory pressure can't be created because workload hits ENOMEM earlier. Don't use strict overcommit.
Took k8s ages to get Swap support.
We lost something when we accepted that Hyperscalers just tell you to use more moemory. It was shitty 5 years ago and today especially after the ram price increases
And now, with PSI + MGLRU, situation is much better, but there are still missing features/subsystems which would be nice to have. For example there's no simple way to lock memory mlockall-style to ensure that rarely used daemon would not face long no-cache-latency upon accessing the first time after long idle time.
First, Linux's default memory management strategy is bonkers. OOM killing rarely actually works in my experience, at least on desktop. It takes ages to kick in and usually the system just freezes and you have to hard reboot. I've experienced this on every Linux system I've used, even my current one with 128GB of RAM and 64GB of swap, so don't say "it works for me". Windows and Mac do not have this issue at all, so clearly it's possible to do it better.
Has anyone tried using strict overcommit on desktop Linux?
Second, this bug is a great counterpoint to those annoying people who naysay Rust with "but not all bugs are memory safety bugs, what about logic bugs? huh?". Rust code would not have had this bug.
Unfortunately, many programs commit 2x memory than they actually use. Often I see ~32GB committed and ~16GB resident.
I run Firefox, VSCodium with LSP, Discord, Signal and there's still space left for a game like CS2. I'm not a heavy user by any means.
> I'm not sure they would do much better than crash
I have yet to see a program that silently handles allocation failures and doesn't crash. These days everything is coded to crash if no memory :(
> About once a year a real runaway process (usually a throwaway program I'm working on) gets OOM-killed
In my case it killed system critical processes with no way to recover. With disabled overcommit, it freezes for a while (usually for a minute or two), I close some random program of my choosing and then see in Resource Monitor what's eating my ram.
Postgres handles allocation failures
https://unix.stackexchange.com/questions/797835/disabling-ov...
I dont think it has an option for that.
The Linux Kernel OOM killer kills random things. Userspace OOM killers are meant to improve this, and they work well in a server situation when you already know in advance what is likely to go haywire and what is safe to kill. But they don't work well on desktop (some of them are improving but it doesn't seem to be a priority).
The Windows OOM killer by comparison usually kills something sensible (i.e. the program that is actually using all the memory), and asks the user for permission before killing it (when possible). You do see a lot of memes of situations where it fails.
By default, the Linux kernel kills the largest process in the system (unless OOM adjust was applied).
A memory allocator can implement overcommit, because you can separate reserving virtual memory and having it backed by physical memory into two different system calls. But from the point of view of the kernel, any time it promises to give you physical memory that memory is backed either by RAM or by space reserved in the swap file
If no memory is available where a page file would make a difference, this leads to application crashes instead. A crash is (usually) worse than paging.
Certain applications, Photoshop being the historical example, will outright fail to run with no page file present.
Same happens if the page file is full. In that case, why don't those programs use disk directly instead?
No such problem would've ever occured if programs hadn't allocated more than they actually use.
Typically, performance drops enough that the user kills the program or reboots before the page file expands to fill the disk. And other threads here suggest there is something that will prompt users to kill programs in states like this.
> No such problem would've ever occured if programs hadn't allocated more than they actually use.
That's part of the issue, but sometimes things do in fact use too much memory as well as allocate too much.
Another part of the issue is that few programs are built to handle allocation failures.
And then you have a metrics issue. There's not really a good metric to know when you're out of memory, other than performance collapse. If your applications don't use disk, it's not too hard; but when they do use disk, performance will collapse once there's insufficient memory to provide the disk caching needed. In my experience, adding a small swap and monitoring swap i/o can be pretty helpful, and a small swap doesn't tend to allow long thrashing when memory use grows. But that's not universal and everybody loves to hate swap these days.
Not in the age of NVMe it doesn't. Swap is fast now. Plus, at least on Linux, you can put zswap in front of the regular swap and introduce an even faster level of memory hierarchy and thereby make page-outs even more profitable.
An application that grows in such a way (besides having backing stores for memory-mapped files, as well) will often perform so poorly that it requires addressing (adding RAM, looking for application faults, etc).
A page file is insurance, one that can last you much longer than available system memory.
You don't need it if you have everything allocated upfront. TigerBeetle does this, everybody else can.
Using something like Rust is already a huge win when compared to shipping a browser or running Node.js.
> Your argument falls flat when a page file can be multi-GB and automatically grow
This doesn't solve the original issue and only masks the underlying problem.