[jacquesm]

The last time that I've been actively involved with the development of real time control of time critical hardware on linux was about 2007 (very high speed stepper motor driven plasmacutter, slow down in a curve and you've ruined the workpiece), so for sure I'm out of the loop but I do have a fairly large Linux audio setup with all of the real time patches installed and clearly if it is possible to run with 64 sample buffers I have not been able to do so on my hardware, 1K really is the minimum before I get - inevitably, unfortunately - dropouts under relatively light load.

It might be worth documenting my setup (reproduced across three different machines, a laptop, an 'all-in-one' and a very beefy desktop), to see what could be improved because that difference is substantial.

[jcelerier]

> but I do have a fairly large Linux audio setup with all of the real time patches installed and clearly if it is possible to run with 64 sample buffers I have not been able to do so on my hardware, 1K really is the minimum before I get - inevitably, unfortunately - dropouts under relatively light load.

that sounds very weird, I don't even run a RT kernel and I have no trouble running at 64 with a fair amount of plug-ins and even 32 samples when I just want some live guitar effects (i7 6900k, RME multiface 2). My only configuration is installing this AUR package: https://archlinux.org/packages/community/any/realtime-privil...

[PaulDavisThe1st]

I've linked to it elsewhere in these comments, but this tries to describe in broad terms why any given x86* computer may not be able to meet your latency goals:

https://manual.ardour.org/setting-up-your-system/the-right-c...

There's a wide variety of reasons, all of which can interact. It's one of the few good arguments for buying Apple hardware, where this is not an issue.

Over the years I've been working on pro-audio/music creation on Linux (22+ years), I've had a couple of systems that could perform reliably at 64 samples/buffer. My current, based on a Ryzen Threadripper 2950X, can get down to 256 but not 128 or 64.

[jacquesm]

Ok, so at a guess then that 64 is an optimum configured set of hardware bought specifically with the goal of reaching that minimum, and for more realistic 'run of the mill' hardware it would be 256 and up?

If someone were to put together a guaranteed low latency config and keep it patched using a custom distro (assuming say 'Ubuntu Studio' would not be up to the task, would there be a market for that? Are there such suppliers? What specifically is different in Apple hardware that it works there?

I read that page earlier, its helpful, but more helpful would be a shopping list that says 'get this: it will work, assuming you install this particular distro'. And after independent verification you could then add alternatives for each slot. For me for instance a big question would if NVidia video cards would break the latency guarantees (their driver is pretty opaque) by keeping interrupts masked for too long in their drivers. If that would be a deal breaker then I'd have to set up a system only for studio use.

[PaulDavisThe1st]

The problem with "shopping lists" is that, at least in the past, it's turned out that companies like e.g. mobo manufacturers change the chipsets in the corners of these devices without even changing the product ID. If I told you a mobo to buy, there's no guarantee that you'll actually get what I was recommending.

Lots of efforts have been made over the years to create "audio PC" companies. Even with the Windows market within their intent, I don't know of a single one that has lasted more than a year or two. How much of that is a market problem and how much of it is a problem of actually sourcing reliable components, I don't know. I do know that when large scale mixing console companies find mobos that work for them, they buy dozens of them, just to ensure they don't get switched out by the manufacturer.

Apple stuff works because Apple sort of has to care about this workflow functioning correctly. There's no magic beyond careful selection of components and then rigorously sourcing them for the duration of a given Apple product's lifetime.

I have no actual evidence on the video adapter front, but my limited experience would keep me aware from NVidia if I was trying to build a low latency audio workstation. Back in the olden days (say, 2002), there were companies like Matrox who deliberately made video adapters that were "2D only, targetting audio professionals". These cards were properly engineered to get the hell off the bus ASAP, and didn't have of the 3D capabilities that audio professionals (while wearing that hat) really don't tend to need.