[jeffbee]

I don't think that's really a position that can be defended. Both jemalloc and tcmalloc evolved and were refined in antagonistic multitenant environments without one overwhelming application. They are optimal for that exact thing.

[lmm]

> Both jemalloc and tcmalloc evolved and were refined in antagonistic multitenant environments without one overwhelming application. They are optimal for that exact thing.

They were mostly optimised on Facebook/Google server-side systems, which were likely one application per VM, no? (Unlike desktop usage where users want several applications to run cooperatively). Firefox is a different case but apparently mainline jemalloc never matched Firefox jemalloc, and even then it's entirely plausible that Firefox benefitted from a "selfish" allocator.

[jeffbee]

Google runs dozens to hundreds of unrelated workloads in lightweight containers on a single machine, in "borg". Facebook has a thing called "tupperware" with the same property.

[nixgeek]

I think Tupperware was rebranded to Twine sometime about 6-7 years ago.

[favorited]

It's possible that they were referring to something specific about their platform and its system allocator, but like I said it was an anecdote about one engineer's statement. I just remember thinking it sounded fair at the time.

[vlovich123]

The “system” allocator is managing memory within a process boundary. The kernel is responsible for managing it across processes. Claiming that a user space allocator is greedily inefficient is voodoo reasoning that suggests the person making the claim has a poor grasp of architecture.

[jeffbee]

There are shared resources involved though, for example one process can cause a lot of traffic in khugepaged. However I would point out that is an endemic risk of Linux's overall architecture. Any process can cause chaos by dirtying pages, or otherwise triggering reclaim.

[vlovich123]

That’s generally true of any allocator and assuming glibc’s behavior would help mitigate this is critically not something kernel engineers design around nor something glibc allocator is trying to achieve as a design goal.

[favorited]

For context, the "allocator engineer" I was talking to was a kernel engineer - they have an extremely solid grasp of their platform's architecture.

The whole advantage of being the platform's system allocator is that you can have a tighter relationship between the library function and the kernel implementation.

[vlovich123]

I’m not generally aware of any system allocator that’s written hand in glove with the kernel’s allocator or somehow interops better for overall system efficiency at the cost of behavior in-app. Care to provide an example?

[jdsully]

The "greedy" part is likely not releasing pages back to the OS in a timely manner.

[nicoburns]

That seems odd though, seeing as this is one of the main criticisms of glibc's allocator.

[jeffbee]

In the containerized environments where these allocators were mainly developed, it is all but totally pointless to return memory to the kernel. You might as well keep everything your container is entitled to use, because it's not like the other containers can use it. Someone or some automatic system has written down how much memory the container is going to use.

[toast0]

Returning no longer used anonymous memory is not without benefits.

Returning pages allows them to be used for disk cache. They can be zeroed in the background by the kernel which may save time when they're needed again, or zeroing can be avoided if the kernel uses them as the destination of a full page DMA write.

Also, returning no longer used pages helps get closer to a useful memory used measurement. Measuring memory usage is pretty difficult of course, but making the numbers a little more accurate helps.

[atombender]

I know Google has good engineering, but I find this a bit implausible?

For most applications, especially request/response type apps like web servers, "right sizing" truly correctly while accounting for spikes takes a lot of engineering effort to fully account for how much allocation a single request will need, then ensuring the maximum concurrent requests never go beyond that so you never risk OOMs.

I can see this being fine-tuned for extremely high-scale, core services like load balancers, SDNs, file systems etc., where you probably want to allocate all your data structures at startup time and never actually allocate anything after that, and you probably have whole teams of engineers devoted to just single services. But not most apps?

Surely it's better for containers to share system memory, and rely on limits and resource-driven autoscaling to make the system resilient?

[vlovich123]

glibc is not written in a containerized environment and I personally think it’s telling that a core feature of the more recent tcmalloc Google open sourced is that it returns memory efficiently, so clearly even in containerized environments it’s important. The reason for this is how kernels deal with compressing pages and pages released to the kernel are explicitly zeroed (unlike the user space allocator) which aids in the efficiency of the compression even in a containerized workload because those pages can just be skipped since they’re unused and the kernel can share the reference zeroed page for lazy allocations.

Also the kernel itself has memory needs for lots of things and it not having memory or having to go on a hunt to find contiguous pages is not good. Additionally in a VM or container environment there’s other containers and VMs running on that machine so the memory will also eventually get percolated up to the hyper visor to rebalance. None of this happens if the user space allocator hangs on to memory needlessly in a greedy fashion and indeed such an application would be more subject to the OOM killer.