TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

GCP, AWS, and Azure ARM-based server performance comparison

160 pointsby jjzhiyuanover 2 years ago

13 comments

adducover 2 years ago
The benchmarks appear to show AWS wins by a considerable margin in all tests, and is cheaper at all quoted price points, but is hardly above Azure in the cost performance table. This appears to be due to including Azure's reserved pricing but continuing to use AWS and GCP's on-demand pricing. This is misleading, as both GCP and AWS offer discounts for yearly commitments.
评论 #32969954 未加载
评论 #32968992 未加载
cheriooover 2 years ago
The article end up feeling rather overwhelming. The main difference and advantage AWS holds is that it uses the newer, more advanced (and more expensive) Neoverse V1 design, while GCP and Azure are based on Neoverse N1 design which is older, cheaper, and less performant. These are largely due to how these chip were designed by ARM. It may be argued that AWS also adds its secret sauce, but so far it feels unlikely. A cursory search leads to an phoronix article [0] which has a much more in depth comparison between V1 and N1 (through AWS&#x27;s c7g vs. c6g instance types.) There are also upcoming N2 and V2 design; NVIDIA&#x27;s Grace CPU is reportedly based on V2 design, which will be interesting to watch for.<p>The 41% discount thrown in at the end for Azure, without any explanation, was also jarring. Maybe there truly is promotional rate for Azure&#x27;s ARM instance, but as another poster pointed out, it&#x27;s likely reserved pricing, which is available for all the providers.<p>[0] <a href="https:&#x2F;&#x2F;www.phoronix.com&#x2F;review&#x2F;aws-graviton3-c7g" rel="nofollow">https:&#x2F;&#x2F;www.phoronix.com&#x2F;review&#x2F;aws-graviton3-c7g</a>
评论 #32975494 未加载
评论 #32970041 未加载
tanelpoderover 2 years ago
Was hoping to see the results, but the images were all blurry dummy placeholders (some sort of lazy loading for images?). The images had a text on &quot;click here for preview&quot;, but when I clicked it, nothing happened (I have ad-blockers, maybe that&#x27;s why some JS code was disabled).<p>But what the heck, this is not how wepages should work - click here to &quot;unblur&quot; the image? Why add such an extra step? To save bandwidth cost?
评论 #32968232 未加载
评论 #32970301 未加载
评论 #32968308 未加载
评论 #32968989 未加载
评论 #32969661 未加载
评论 #32968663 未加载
tbillingtonover 2 years ago
Curious how they would compare to a non-cloud option <a href="https:&#x2F;&#x2F;www.hetzner.com&#x2F;dedicated-rootserver&#x2F;matrix-rx" rel="nofollow">https:&#x2F;&#x2F;www.hetzner.com&#x2F;dedicated-rootserver&#x2F;matrix-rx</a>.
评论 #32968418 未加载
评论 #32968391 未加载
dis-sysover 2 years ago
I think the title is misleading - it is not a server performance comparison, it is just a comparison on a single application using a single kind of workload on a fixed dual core setup.<p>It also lacks basic insights into the results, e.g., when both AWS and GCP are using ARM&#x27;s Neoverse V1 design, why those two servers are having such significant performance gap? Maybe it was just caused by some bad software configuration in the stack which can void all relevant results?<p>When there are up to 64 cores available, why only 2 cores were used? Surely other 62 cores are relevant, right?
评论 #32969386 未加载
评论 #32969362 未加载
ajrossover 2 years ago
So... the news here is that GCP seems to be significantly slower in practice, where all three products are priced at the same spot.<p>But... the weird question is why are the Azure financials funny? The listed prices are about the same, but the &quot;annual cost&quot; for Azure seems to include a &quot;41% off&quot; discount that I can&#x27;t find an explanation for? And then they use the latter in the calculation of price efficiency, which seems... what? This is the kind of thing Comcast does in its marketing. What is that discount and what&#x27;s the justification for assuming that all users get it in perpetuity?
RcouF1uZ4gsCover 2 years ago
I wish Oracle Cloud was also included. The 24 GB, 4 core ARM vps you can get for free is a really nice way to try out ARM for individual developers.
评论 #32968151 未加载
评论 #32969529 未加载
评论 #32968249 未加载
m_muellerover 2 years ago
Just FYI, if I copy out the URI of the article and want to open it again (or share it with someone) it gives a 404.
philliphaydonover 2 years ago
I just ran into issues last night with t4g instances.<p>For the most part them have been great and the performance has been better for asp.net apps than Intel&#x2F;AMD.<p>But I ended up with a stack overflow exception with System.Text.Json in my personal project that only occurs on arm but not others.<p>Still love the graviton instances.
评论 #32969892 未加载
londons_exploreover 2 years ago
And how does that same benchmark run on an apple M1 chip?
评论 #32968291 未加载
perryizgr8over 2 years ago
Is there any advantage to running an ARM instance in the cloud, as opposed to a x64 one?
评论 #32968556 未加载
评论 #32969329 未加载
评论 #32968944 未加载
评论 #32969690 未加载
评论 #32968652 未加载
评论 #32969444 未加载
评论 #32969723 未加载
评论 #32968919 未加载
评论 #32970902 未加载
antifaover 2 years ago
Does GCP Cloud Run support ARM?
Shorelover 2 years ago
I have a process in AWS that can run on ARM or AMD64 machines.<p>It runs in AMD64 machines because, for some reason, the Graviton instances are killed without warning by AWS.<p>So yeah, great performance, as long as you don&#x27;t actually need it.
评论 #32970237 未加载