Jun 28, 2026

Taking "free" resources can't hurt another application, because those resources are free.

Clod must have some assumptions about how quickly it can get things, since those things are always available, apart from a disk being full. That implies a race condition.

I know that forcing the other apps into swap file on disc will hurt their performance. So it is good to leave a little of it (1~2%) free.

That of course is the fundamental job of the operating system, and it does this. I am performing a full validation sync right now on this machine. Shows 100% CPU and RAM is 116GB used and climbing. It will hit almost 256GB (the physical RAM) and the machine will continue to be responsive - less so than normal, but that's intended.

My OS is microslop indeed 😂

I'm on Windows. It's far better than macos in this regard, and much better than Linux, as it properly dynamically manages these resources.

So 64GB RAM is what is holding my machine back then.

No, I don't know what's the problem. I don't have much info. But I have < 1hr syncs on 32GB minis on Windows.

I'll share the IBD plot when it’s done syncing

64 threads, 100% CPU. 11 yo machine.

The IBD plot won't tell me what's going on.

For me RAM hits 100% and my OS drive then hits 99% usage (normal is 1%)

Normal when you aren't doing anything on a computer is almost 0 🙂

Normal when you are trying to do something as fast as possible with a scalable impl is 100%

True, but OS disc being abused as memory is not normal

It's not being "abused as memory". It's writing blocks to the disk.

Blocks go to the external SSD for me

The blocks are buffered in RAM and the oldest accessed pages of that RAM are written in bulk to the disk by the OS as necessary.

That tradeoff is entirely decided by the OS.

Yeah, it is probably the fasted way to sync still

Just a bit janky to use while syncing

With a slow (external) SSD, it will take more time to move block data to the disk to free up memory for other things. The disk becomes a bottleneck.

It is the bottleneck indeed

It's not the amount of RAM being used, it's the rate at which blocks are coming in relative to the rate at which they can go out. Your network is much faster than your disk. It's a flow problem.

You can reduce the flow coming in by just reducing the number of peers or the number of network threads.

But the default config assumes you want the sync as fast as possible.

Network peaks at 300 Mbps or so

Right, because of your disk.

That's your peak write rate.

Yep!

I'll smack down some more sats for another Samsung 990 pro

Good man.

20x higher write speeds than external SSD

will make a difference 🙂. It's a simple idea. To store the chain coming in at 2.5Gbps you have to be able to write to RAM at 2.5Gbps and when RAM is full you have to be able to write to disk at 2.5Gbps. Otherwise RAM will remain full and the backpressure hits the network.

Of course CPU has to also be able to parse and shuffle data round fast enough to maintain those rates as well, or you become CPU bound.

By moving sigs to the GPU we get a whole new resource to work with!

My CPU is bored xD

Yep, so is your network. There's always one bottleneck, and quite clearly that's presently your disk.

That's a solid machine. With a fast internal SSD and 2.5Gbps you'll milestone sync in < 1hr.

Full validation sync in the current CPU config should be 5.5-6 hrs.

With GPU sig batching I'd say ~3 hrs.