The image didn't show up for me, here is a direct link for anyone with the same problem: https://lh6.googleusercontent.com/MwzsHRXQLVbmJ3pusNuGwn0ZQV...
Sorry to ask, but does anyone have a third mirror? Neither are working for me and I really am interested in seeing this image.
CPU Usage Differences After Applying Meltdown Patch at Epic Games
121–130 of 296 posts
Re: CPU Usage Differences After Applying Meltdown Patch at Epic Games
#122Maybe off-topic: Is formal verification viable anywhere in CPU logic design? Also, could any existing "CPU static analyzers" have caught the issue that caused Meltdown? Edit: It looks like the answer to the first is a definite yes.
CPU design is in a large part an exercise in formal verification. On the other hand it does not help you much when the bug in question is in the specification that you verify against in the first place or, as is almost certainly this case, is based on some behavior that is not specified by the specification at all.
Re: CPU Usage Differences After Applying Meltdown Patch at Epic Games
#123Pretty much what I predicted here: https://news.ycombinator.com/item?id=16054674 > Sounds like servers handling lots of small UDP packets would be hit pretty hard.
I wonder if this means Google's QUIC protocol is dead in the water, since it works over UDP.
Re: CPU Usage Differences After Applying Meltdown Patch at Epic Games
#124Graph says pretty clearly the patch is 60-70% slower! or 2.5-3x hardware costs. I wonder which CPU family this is?
This surprised me a lot. I thought 30-50% would be worst case and then with additive effects from both Spectre and Meltdown fixes. Not sure how it can be this bad. I imagine it could get even worse if you are running in a virtualized environment on top where the server is affected in turn, but I figure thst wouldn’t show in a CPU graph like this..
Re: CPU Usage Differences After Applying Meltdown Patch at Epic Games
#125Pretty much what I predicted here: https://news.ycombinator.com/item?id=16054674 > Sounds like servers handling lots of small UDP packets would be hit pretty hard.
I wonder if this means Google's QUIC protocol is dead in the water, since it works over UDP.
You can basically have bigger UDP packets, that will get fragmented and may not make it to their end.
As far as I know, in Linux there is no support for multi-packet UDP vectored I/O. I wonder if it would be possible to "simulate" that with a raw socket....
Re: CPU Usage Differences After Applying Meltdown Patch at Epic Games
#126Earlier quoted context omitted.
> which unfortunately seems to be getting rarer and rarer on this forum. If this isn't unnecessarily "snarky" itself, then what is it? snarky : (of a person, words, or a mood) sharply critical; cutting; snide.
That wasn't snarky because it was only mildly critical. Since it was mild, it also wasn't cutting. Lastly, it was not derogatory or mocking in an indirect way and so it was not snide either.
I disagree. Aside from the sarcastic "buffer overflow" comment, his comment was far more snide than any of the replies he seemed to be complaining about.
Since you take a different view though, as I asked in my post, if it's not "snarky" then what was it?
Re: CPU Usage Differences After Applying Meltdown Patch at Epic Games
#127If it's helpful, Our Node.js, MongoDB, Python servers all with significant network traffic didn't have any measurable impact after KPTI patches on Amazon Linux on T2.medium(burst), M4.large, T2.large(burst) respectively. Our impact is lesser than the figures suggested by redhat's advisory - https://access.redhat.com/articles/3307751
Would you be able to post some ballpark figures, please?
Re: CPU Usage Differences After Applying Meltdown Patch at Epic Games
#128Earlier quoted context omitted.
That wasn't snarky because it was only mildly critical. Since it was mild, it also wasn't cutting. Lastly, it was not derogatory or mocking in an indirect way and so it was not snide either.
I disagree. Aside from the sarcastic "buffer overflow" comment, his comment was far more snide than any of the replies he seemed to be complaining about. Since you take a different view though, as I asked in my post, if it's not "snarky" then what was it?
hey what d'you know, snarky
Re: CPU Usage Differences After Applying Meltdown Patch at Epic Games
#129I have turned windows updates off so I don’t have to deal with this crap. Screw you intel + Microsoft.
Whilst I sympathise with your frustration, at least with Intel, I can't help feeling like you might be storing up bigger problems for yourself with this course of action.
Re: CPU Usage Differences After Applying Meltdown Patch at Epic Games
#130Looks like it may be time for Epic Games to consider switching to AMD Ryzen/EPYC.