TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

RAMCloud Project

129 点作者 monort超过 6 年前

16 条评论

erwan超过 6 年前
A cool tiny bit of trivia about RAMCloud: that&#x27;s from this project that the Raft consensus algorithm emerged! (<a href="https:&#x2F;&#x2F;raft.github.io&#x2F;raft.pdf" rel="nofollow">https:&#x2F;&#x2F;raft.github.io&#x2F;raft.pdf</a>)<p>Right now, I think that the algo is used in RAMCloud via LogCabin (<a href="https:&#x2F;&#x2F;github.com&#x2F;logcabin&#x2F;logcabin" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;logcabin&#x2F;logcabin</a>).<p>Raft is more practical (as in &quot;well specified&quot;) than Paxos and closest to its lesser known cousin, VR (<i>Viewstamped Replication</i>). Beyond the academic genealogy of the project, what is interesting here is the fact that usability is a first-class concern. Clearly the fact that it was born out of a real&#x2F;breathing project was a driving factor.<p>It wasn&#x27;t just an academic being creative. To pick a notorious example, have a quick look at Leslie Lamport&#x27;s paper on Paxos: you are never quite sure whether what you are reading is a distributed systems paper or a vintage edition of the Holy Bible.<p>So Raft had great timing too. It came after decades of clumsy (because novel!) systems research on consensus algos and from a laboratory of practitioners, hence its designers knew exactly how previous attempts were deficient with respect to their own needs. And it turns out these overlapped with a lot of people&#x27;s. There is wisdom to be learnt from this.<p>Also, on another note I think that&#x27;s funny because this narrative reads exactly like a startup-story!
评论 #18442917 未加载
dugluak超过 6 年前
RAMCloud sounds cool and superfast, but why is the documentation so slow? Why does it need to be a site with heavy javascript with 482 ajax requests instead of plain old HTML?
评论 #18444164 未加载
评论 #18444442 未加载
评论 #18445194 未加载
godelmachine超过 6 年前
Excellent review by Adrian Colyer -<p><a href="https:&#x2F;&#x2F;blog.acolyer.org&#x2F;2016&#x2F;01&#x2F;18&#x2F;ramcloud&#x2F;" rel="nofollow">https:&#x2F;&#x2F;blog.acolyer.org&#x2F;2016&#x2F;01&#x2F;18&#x2F;ramcloud&#x2F;</a>
jmiserez超过 6 年前
Is this still maintained? It&#x27;s a really cool project, it&#x27;s just so insanely fast.<p>I once implemented a MariaDB storage engine that used RAMCloud for storage, and it was an eye-opening experience. With blazingly fast reads and writes, latency was the number one performance issue for us.
评论 #18441148 未加载
评论 #18440877 未加载
michaelmior超过 6 年前
Calling RAMCloud &quot;new&quot; seems a bit disingenuous since the first paper came out around 7 years ago.<p><a href="https:&#x2F;&#x2F;dl.acm.org&#x2F;citation.cfm?id=2043560" rel="nofollow">https:&#x2F;&#x2F;dl.acm.org&#x2F;citation.cfm?id=2043560</a>
评论 #18440151 未加载
byte1918超过 6 年前
&gt; Durability: RAMCloud replicates all data on nonvolatile secondary storage such as disk or flash, so no data is lost if servers crash or the power fails.<p>How does this work if someone is doing multiple sequential writes? Doesn&#x27;t backup-ing to disk take a lot longer than writing to _RAM_ meaning some writes could get lost?
评论 #18441112 未加载
kijin超过 6 年前
How does it replicate all the data on disk or flash while maintaining the write latency of DRAM?<p>I&#x27;m thinking there must be a delay during which loss of power will result in loss of data that was acknowledged as written. Is this something that RAMCloud overcomes in a novel way, or is the answer simply that the data is replicated across many nodes?<p>How about the problem of raw bandwidth? If you keep sending writes to a node that exceeds the bandwidth of the persistent storage medium but is well within the capabilities of DRAM, the storage medium will never be able to catch up even if we allow a generous delay. Maybe this is a non-issue right now because you can&#x27;t send more than a few dozen Gbps over the network anyway, and we just need to hope that flash performance will improve faster than 100GbE goes mainstream.
评论 #18441213 未加载
评论 #18440081 未加载
评论 #18441296 未加载
评论 #18440148 未加载
newaccoutnas超过 6 年前
Does this mean Atlassian products will be quick(er)? Perhaps they should concentrate there if not.
评论 #18440548 未加载
AndrewDucker超过 6 年前
What would be the difference between this and an SSD-based keystore and an instance of memcached with as much RAM as was necessary to hold the whole dataset?
评论 #18443899 未加载
评论 #18440532 未加载
justinholmes超过 6 年前
I worked on this a couple of years ago to make it easier to create deb packages.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;ticketscale&#x2F;ramcloud-deb-packaging" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;ticketscale&#x2F;ramcloud-deb-packaging</a>
manigandham超过 6 年前
I would recommend Apache Ignite if you want a similar production-ready system today, along with extending datasets automatically to disk, built-in messaging and distributed data structures, and read&#x2F;write-thru cache options.
macca321超过 6 年前
Would be interesting to know how this compares&#x2F;contrasts with Apache Ignite.
chrisweekly超过 6 年前
Mods please update title to reflect year (2009). Thanks!
评论 #18441144 未加载
continuations超过 6 年前
Does this remain a research project or can it be used in production?
beamatronic超过 6 年前
You could accomplish at least 99% of this by using a properly sized Couchbase cluster
zygotic12超过 6 年前
Regardless - RAM disks have been sexy since the 80&#x27;s. Love it. Let&#x27;s go extreme!<p>Domain.com: Congratulations! your domain is available. l1cache.net $12.99
评论 #18506344 未加载