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。

ZFS: Apple's new filesystem that wasn't (2016)

205 点作者 jitl13 天前

16 条评论

ahl13 天前
Back in 2016, Ars Technica picked up this piece from my blog [1] as well as a longer piece reviewing the newly announced APFS [2] [3]. Glad it&#x27;s still finding an audience!<p>[1]: <a href="https:&#x2F;&#x2F;arstechnica.com&#x2F;gadgets&#x2F;2016&#x2F;06&#x2F;zfs-the-other-new-apple-file-system-that-almost-was-until-it-wasnt&#x2F;" rel="nofollow">https:&#x2F;&#x2F;arstechnica.com&#x2F;gadgets&#x2F;2016&#x2F;06&#x2F;zfs-the-other-new-ap...</a><p>[2]: <a href="https:&#x2F;&#x2F;ahl.dtrace.org&#x2F;2016&#x2F;06&#x2F;19&#x2F;apfs-part1&#x2F;" rel="nofollow">https:&#x2F;&#x2F;ahl.dtrace.org&#x2F;2016&#x2F;06&#x2F;19&#x2F;apfs-part1&#x2F;</a><p>[3]: <a href="https:&#x2F;&#x2F;arstechnica.com&#x2F;gadgets&#x2F;2016&#x2F;06&#x2F;a-zfs-developers-analysis-of-the-good-and-bad-in-apples-new-apfs-file-system&#x2F;" rel="nofollow">https:&#x2F;&#x2F;arstechnica.com&#x2F;gadgets&#x2F;2016&#x2F;06&#x2F;a-zfs-developers-ana...</a>
whartung13 天前
As a desktop user, I am content with APFS. The only feature from ZFS that I would like, is the corruption detection. I honestly don&#x27;t know how robust the image and video formats are to bit corruption. On the one hand, potentially, &quot;very&quot; robust. But on the other, I would think that there are some very special bits that if toggled can potentially &quot;ruin&quot; the entire file. But I don&#x27;t know.<p>However, I can say, every time I&#x27;ve tried ZFS on my iMac, it was simply a disaster.<p>Just trying to set it up on a single USB drive, or setting it up to mirror a pair. The net effect was that it CRUSHED the performance on my machine. It became unusable. We&#x27;re talking &quot;move the mouse, watch the pointer crawl behind&quot; unusable. &quot;Let&#x27;s type at 300 baud&quot; unusable. Interactive performance was shot.<p>After I remove it, all is right again.
评论 #43821639 未加载
评论 #43813194 未加载
评论 #43813176 未加载
评论 #43831370 未加载
评论 #43821951 未加载
评论 #43813976 未加载
jFriedensreich13 天前
The death of ZFS in macOS was a huge shift in the industry. This has to be seen in the context of microsoft killed their largely ambitious WinFS which felt like the death of desktop innovation in combination.
评论 #43812242 未加载
评论 #43814442 未加载
danudey12 天前
Not to pointlessly nitpick, but:<p>&gt; HFS improved upon the Macintosh File System by adding—wait for it—hierarchy! No longer would files accumulate in a single pile; you could organize them in folders.<p>MFS <i>did</i> allow you to organize your files into folders, but on-disk they were represented as a single list of files with unique filenames - meaning you could have &#x27;resume.txt&#x27; in a folder called &#x27;Jan&#x27;s Docs&#x27; but you couldn&#x27;t also have &#x27;resume.txt&#x27; in a folder called &#x27;Jake&#x27;s Docs&#x27; - every file on the disk needed to have a unique filename.<p>Not so much an issue in the days of 400KB floppy drives, but once people started getting 20 MB hard drives that was going to be an unacceptable limitation.<p>The other major benefit of HFS was that it stored file data in a B-tree, which allowed directory information to be stored effectively hierarchically, meaning you could find a directory&#x27;s contents very quickly. With MFS, every file being stored in a single list meant that any time you wanted to get a directory&#x27;s contents you had to read through that list of every file on the disk to see which ones were stored in that directory, so every listing of any directory was O(n) for the total number of files on the disk.
jitl13 天前
Besides the licensing issue, I wonder if optimizing ZFS for low latency + low RAM + low power on iPhone was an uphill battle or if it’s easy. My experiencing running ZFS years ago was poor latency and large RAM use with my NAS, but that hardware and drive configuration was optimized for low $ per gb stored and used parity stuff.
评论 #43811724 未加载
评论 #43811704 未加载
评论 #43811335 未加载
评论 #43812978 未加载
评论 #43811781 未加载
评论 #43813520 未加载
krupan12 天前
&quot;Still another version I’ve heard calls into question the veracity of their purported friendship, and has Steve instead suggesting that Larry go f*ck himself. Normally the iconoclast, that would, if true, represent Steve’s most mainstream opinion.&quot;<p>LOL!!<p>I really hope they weren&#x27;t friends, that really shatters my internal narrative (mainly because I can&#x27;t actually picture either of them having actual friends).
评论 #43821980 未加载
评论 #43819095 未加载
throw0101b13 天前
Apple and Sun couldn&#x27;t agree on a &#x27;support contract&#x27;. From Jeff Bonwick, one of the co-creators ZFS:<p>&gt;&gt; <i>Apple can currently just take the ZFS CDDL code and incorporate it (like they did with DTrace), but it may be that they wanted a &quot;private license&quot; from Sun (with appropriate technical support and indemnification), and the two entities couldn&#x27;t come to mutually agreeable terms.</i><p>&gt; <i>I cannot disclose details, but that is the essence of it.</i><p>* <a href="https:&#x2F;&#x2F;archive.is&#x2F;http:&#x2F;&#x2F;mail.opensolaris.org&#x2F;pipermail&#x2F;zfs-discuss&#x2F;2009-October&#x2F;033125.html" rel="nofollow">https:&#x2F;&#x2F;archive.is&#x2F;http:&#x2F;&#x2F;mail.opensolaris.org&#x2F;pipermail&#x2F;zfs...</a><p>Apple took DTrace, licensed via CDDL—just like ZFS—and put it into the kernel without issue. Of course a file system is much more central to an operating system, so they wanted much more of a CYA for that.
评论 #43817262 未加载
rrdharan13 天前
Kind of odd that the blog states that &quot;The architect for ZFS at Apple had left&quot; and links to the LinkedIn profile of someone who doesn&#x27;t have any Apple work experience listed on their resume. I assume the author linked to the wrong profile?
评论 #43811953 未加载
volemo13 天前
It was just yesterday I relistened to the contemporary Hypercritical episode on the topic: <a href="https:&#x2F;&#x2F;hypercritical.fireside.fm&#x2F;56" rel="nofollow">https:&#x2F;&#x2F;hypercritical.fireside.fm&#x2F;56</a>
评论 #43813381 未加载
dang12 天前
Discussed at the time:<p><i>ZFS: Apple’s New Filesystem That Wasn’t</i> - <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=11909606">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=11909606</a> - June 2016 (128 comments)
smittywerben13 天前
Thanks for sharing I was just looking for what happened to Sun. I like the second-hand quote comparing the IBM and HP as &quot;garbage trucks colliding&quot; plus the inclusion of blog posts with links to the court filings.<p>Is it fair to say ZFS made most sense on Solaris using Solaris Containers on SPARK?
评论 #43812151 未加载
评论 #43817234 未加载
secabeen13 天前
ZFS remains an excellent filesystem for bulk storage on rust, but were I Apple at the time, I would probably want to focus on something built for the coming era of flash and NVMe storage. There are a number of axioms built into ZFS that come out of the spinning disk era that still hold it back for flash-only filesystems.
评论 #43812431 未加载
jeroenhd13 天前
I wonder what ZFS in the iPhone would&#x27;ve looked like. As far as I recall, the iPhone didn&#x27;t have error correcting memory, and ZFS is notorious for corrupting itself when bit flips hit it and break the checksum on disk. ZFS&#x27; RAM-hungry nature would&#x27;ve also forced Apple to add more memory to their phone.
评论 #43812422 未加载
评论 #43811928 未加载
评论 #43812061 未加载
评论 #43812017 未加载
评论 #43811935 未加载
评论 #43816742 未加载
评论 #43817255 未加载
评论 #43811974 未加载
评论 #43811868 未加载
ein0p13 天前
ZFS sort of moved inside the NVMe controller - it also checksums and scrubs things all the time, you just don&#x27;t see it. This does not, however, support multi-device redundant storage, but that is not a concern for Apple - the vast majority of their devices have only one storage device.
评论 #43824019 未加载
water912 天前
ZFS is the king of all file systems. As someone with over a petabyte of storage across 275 drives I have never lost a single byte due to a hard drive failure or corruption thanks to ZFS
ewuhic13 天前
What&#x27;s the current state of ZFS on Macos? As far as I&#x27;m aware there&#x27;s a supported fork.
评论 #43824129 未加载