Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

24-core CPU and I can’t move my mouse

randomascii.wordpress.com

Post reply on HN
Print view View original

91–100 of 509 posts

Re: 24-core CPU and I can’t move my mouse

#91

Post by agumonkey »

weinzierl wrote: post #16

I grew up on the Commodore 64 (1 Core, 1 hyper-thread :-), almost 1 MHz clock freq, almost 64 K usable RAM). The machine was usually pretty responsive, but when I typed too quickly in my word processor it sometimes got stuck and ate a few characters. I used to think: "If computers were only fast enough so I could type without interruption...". If you'd asked me back then for a top ten list what I wished computers cou…

way more naive but my first own desktop was a P75, a few years down a friend of a friend got his hand on a batch of P233MMX and I started to fantasize that these could be so fast, the menus may appear before you even finished clicking. I didn't know how non linear computers were at the time.

Few things also, I'm often surprised how fixed is the responsiveness of systems, hardware grew 3-4 orders of magnitude but the cruft and chaos plus the change of resolutions keep latency around the same value. It's sometimes even worse. Psychologically when I boot a 64MB windows machine and can enjoy word / IE / winamp I feel very weird (video could be offloaded to a chromecast for that matter).

Re: 24-core CPU and I can’t move my mouse

#92

Post by simias »

anigbrowl wrote: post #47
fredley wrote: post #20

Earlier quoted context omitted.

It's all just trade offs. However fast or powerful your machine is, software will use as much of that resource as possible, up to the point where it occasionally interferes with input (but not too much or you'll switch to something else).

But why? What good is an operating system on a multi-core device that allows anything to get that close to the performance envelope? This is a fine example of competition driving change for change's sake rather than real innovation and everything ending up worse as a result. I like new features as much as the next person, but not when they compromise core functionality. Not being able to type is inexcusable .

You have alternatives though. I've been using basically the same linux environment for about a decade now.

I don't have a proper desktop environment like Gnome or KDE, just Xorg and StumpWM as a window manager. Then I have Firefox, Emacs and urxvt running tmux. I use a handful of GTK applications when the need arises like Gimp, Inkscape, Evince and maybe a couple others. Done.

It boots up in a few seconds from a SSD, it's always snappy. It worked fine on a core2duo and HDD 10 years ago, it works even better on an i5 and SSD now.

Re: 24-core CPU and I can’t move my mouse

#93

Post by lucian1900 »

vidarh wrote: post #61
titzer wrote: post #45

Full disclosure: I work for Google on Chrome. A Chrome build is truly a computational load to be reckoned with. Without the distributed build, a from-scratch build of Chrome will take at least 30 minutes on a Macbook Pro--maybe an hour(!). TBH I don't remember toughing out a full build without resorting to goma. Even on a hefty workstation, a full build is a go-for-lunch kind of interruption. It will absolutely own a…

> Damn, are we doing this wrong? Yes: Not isolating different modules sufficiently to allow you to avoid including most headers when compiling most modules. Patterns to do this in C++ has been well understood for two decades: Strict separation of concerns coupled with facades at the boundaries that let all the implementation details of the modules remain hidden. Yes, it has a cost: You're incurring extra call overhea…

Unfortunately that's not feasible for highly performance-sensitive projects like browsers or games.

Re: 24-core CPU and I can’t move my mouse

#94

Post by href »

hoodoof wrote: post #53

Saw the headline and thought "must be Windows". I'm not a Windows hater, but one of my long standing gripes about Windows is that it just seems to have terrible multitasking compared to OSX. I'm sure there are reasons but it just seems utterly symbolic of Microsoft that they never managed to get Windows to multitask in a rock solid, smooth and reliable way like OSX.

I'm reading your comment while upgrading brew. This prevents me from working because typing in Sublime Text slows down to a crawl during brew's compilations ;)

Re: 24-core CPU and I can’t move my mouse

#95

Post by chemmail »

gambiting wrote: post #58
hoodoof wrote: post #53

Saw the headline and thought "must be Windows". I'm not a Windows hater, but one of my long standing gripes about Windows is that it just seems to have terrible multitasking compared to OSX. I'm sure there are reasons but it just seems utterly symbolic of Microsoft that they never managed to get Windows to multitask in a rock solid, smooth and reliable way like OSX.

Uhm I have a 40-core machine with 256GB of ram at work and I can make it completely unresponsive without taxing either ram or the cpu to 100% - we have a certain computational load that just destroys the CPU Ram bandwidth, so cpu usage is about 30-40%, ram sits at 50%, and yet the computer is completely unresponsive. It's exactly the same on both Windows Server and Linux - we're just running into hardware limits.

Interesting. I've been CPU mining on my old IVY bridge and i don't even notice it causing much performance drop. Free coins for me!

Re: 24-core CPU and I can’t move my mouse

#96

Post by m_fayer »

nailer wrote: post #56

While the issue closing processes slowly is unique to Windows 10, I've found similar situations of not being able to control my OS on RHEL, Fedora, Ubuntu and MacOS. At this point I genuinely believe latency will be the death of general purpose computing. iOS and Android very rarely get out of control. Apple is already pushing iOS devices as laptop replacements. But we lose a lot on these devices with their locked do…

All the midrange Android devices I own get out of control all the time if you switch between heavy apps too quickly. And every once in a while while I wait for the system to become responsive again, some low level process like "Android System" will crash and restart itself. I shudder to think what will happen once we start throwing desktop-class loads at Android using it's current application stack.

Re: 24-core CPU and I can’t move my mouse

#97

Post by rurban »

titzer wrote: post #45

Full disclosure: I work for Google on Chrome. A Chrome build is truly a computational load to be reckoned with. Without the distributed build, a from-scratch build of Chrome will take at least 30 minutes on a Macbook Pro--maybe an hour(!). TBH I don't remember toughing out a full build without resorting to goma. Even on a hefty workstation, a full build is a go-for-lunch kind of interruption. It will absolutely own a…

just use zapcc, and compile-time will be down. it's basically clang-4.0 so it's safe to use.

Re: 24-core CPU and I can’t move my mouse

#98

Post by hypervis0r »

RJIb8RBYxzAMX9u wrote: post #48
weinzierl wrote: post #16

I grew up on the Commodore 64 (1 Core, 1 hyper-thread :-), almost 1 MHz clock freq, almost 64 K usable RAM). The machine was usually pretty responsive, but when I typed too quickly in my word processor it sometimes got stuck and ate a few characters. I used to think: "If computers were only fast enough so I could type without interruption...". If you'd asked me back then for a top ten list what I wished computers cou…

Except without interrupts, your computer would miss all the keystrokes. :-)

That's so deep, it hit me in the IDT

Re: 24-core CPU and I can’t move my mouse

#99

Post by pjc50 »

ori_b wrote: post #71
pjc50 wrote: post #66

Earlier quoted context omitted.

"Concatenated" builds seem to be the best band-aid for this. Concatenate as many source files as possible before compiling, #include a bunch of cpp files into one big file. It makes tracking down errors slightly harder and macros a bit more risky, but greatly improves the overall build efficiency.

And trashes incremental compilation time, which is what really matters.

Incremental compilation opportunities are rarer than we'd like on C++: as soon as you add a new class member or function, that's potentially a huge recompile.

Re: 24-core CPU and I can’t move my mouse

#100

Post by qb45 »

masklinn wrote: post #34
albertzeyer wrote: post #9

I was wondering what ETW is, and found in one of his other posts: ETW (Event Tracing for Windows). He seems to be one of the main contributors of https://github.com/google/UIforETW Seems to be quite useful. --- About the post: tl;dr: NtGdiCloseProcess has a system-wide global lock which is used quite often e.g. during a build of Chrome which spawns a lot of processes. This problem seems to be introduced between Windo…

> NtGdiCloseProcess has a system-wide global lock which is used quite often "Holds" rather than "has", and importantly that system-wide lock must be held by things like SendMessageW (which sends a message and waits for its processing before returning) which is pretty critical for UI updates. This is compounded by parallelised build processes as not only do they spawn lots of processes leading to lots of process destr…

> "Holds" rather than "has", and importantly that system-wide lock must be held by things like SendMessageW (which sends a message and waits for its processing before returning) which is pretty critical for UI updates.

Do you happen to know anything about it? I'm scratching my head how it's possible that process termination serializes with GUI... Maybe it hogs some lock on process descriptors which SendMessage also needs to grab for a moment to find the target process? I hope you didn't mean to say that every SendMessage call is completely serialized with each other.

Post reply on HN