Python Sweetness
pythonsweetness.tumblr.com · Personal blog · on HN since 2013
Python Sweetness is a blog by David Wilson, the author of Mitogen, on Linux internals, Python performance, and infrastructure code.
What HN saysHN links its post on the Linux page table isolation patches, which commenters cite as informed speculation that spotted the Meltdown fix before disclosure.
42HN people shared it
17linked it in comments
34stories submitted
2.2Kstory points
9 years agolast shared
2013people per year2026
Most-shared posts
- 1The mysterious case of the Linux Page Table Isolation patches12 people · 1.0K points · first shared 2018 · 254 comments on HN
- 2How to lose $172,222 a second for 45 minutes6 people · 29 points · first shared 2015 · 3 comments on HN
- 3Quadrupling Ansible performance with Mitogen5 people · 11 points · first shared 2018 · 1 comments on HN
- 4How to lose $172,222 a second for 45 minutes2 people · 613 points · first shared 2013 · 236 comments on HN
- 5Mitogen, an infrastructure code baseline that sucks less2 people · 112 points · first shared 2017 · 23 comments on HN
- 6Pro Linux systems spelunking2 people · 20 points · first shared 2016 · 2 comments on HN
- 7I will burn your progress bar on sight2 people · 4 points · first shared 2016 · discussion on HN
- 8Much ado about latency: Mitogen and the BFG9000 of import hooks2 people · 4 points · first shared 2018 · discussion on HN
- 9Block range brin indexes in postgresql 952 people · first shared 2016
- 10Please stop serving .git to the outside world1 people · 247 points · first shared 2013 · 85 comments on HN
- 11Skip lists: fast PyPy-compatible ordered map in 89 lines of Python1 people · 77 points · first shared 2013 · 25 comments on HN
- 12Fun with BPF, or, shutting down a TCP listening socket the hard way1 people · 26 points · first shared 2015 · 7 comments on HN
- 13excellent rant on the dumbing down of data access and UIs1 people · 13 points · first shared 2013 · 2 comments on HN
- 14A plan for a completely decentralized BitTorrent index1 people · 8 points · first shared 2014 · 1 comments on HN
- 15Deploying modern Python apps to ancient infrastructure with pkgsrc1 people · 4 points · first shared 2016 · discussion on HN
What HN people wrote when they linked it
sasojaso · 2018-01-10
Does this release has anything to do with Linux P
page table isolation patches (http://pythonsweetness.tumblr.com/post/169166980422/the-mysterious-cas…
lmm · 2018-01-04
No-one necessarily broke the embargo. A blogger noticed unusual activity around a certain linux patchset and put two and two together, and the register mostly sourced from his article ( http://pythonsweetness.tumblr.com/post/169166980422/the-mysterious-cas… )
JdeBP · 2018-01-04
What alerted people that something may be up were discussions on LWN and the patch commentaries in Linux kernel code commits.
* http://pythonsweetness.tumblr.com/post/169166980422/the-mysterious-cas…
* https://news.ycombinator.com/item?id=16046636
amckenna · 2018-01-03
Here is some more context - http://pythonsweetness.tumblr.com/post/169166980422/the-mysterious-cas…
The connection between the linked article in this comment and the linked page for this post is that there is a potentially huge bug that will be made public soon and it just affects Intel processors, not AMD - hence the large sale of stock by the Intel CEO.
NelsonMinar · 2018-01-03
See this blog post, which is some very informed speculation based on public Linux kernel patch activity. http://pythonsweetness.tumblr.com/post/169166980422/the-mysterious-cas…
rst · 2018-01-02
Reports are that Windows is also getting an update for this; see refs to recent NT kernels here: http://pythonsweetness.tumblr.com/post/169166980422/the-mysterious-cas…
and the original source for that report:
https://twitter.com/aionescu/status/930412525111296000
OSX and BSD variants are an interesting question...
tambre · 2018-01-01
_wmd · 2017-10-14
I wrote http://pythonsweetness.tumblr.com/post/119568339102/block-range-brin-i… because I had the same problem, maybe see if it works for you
nl · 2017-03-15
While I agree with your point (and often use this in interview questions) that wasn't what caused the Knight Capital problem.
That was bad software engineering and deployment practices, and had nothing to do with interprability of the model (actually it had little to do with the model at all.) They repurposed a feature toggle, then misdeployed the code: http://pythonsweetness.tumblr.com/post/64740079543/how-to-lose-172222-…
I understand that this was an example, but I'm sure someone will misread it as what happened in that case.
pards · 2017-01-17
Knight Capital lost $465 million in 45 minutes caused (at least in part) by technical debt and poor development practices.
Summary: http://pythonsweetness.tumblr.com/post/64740079543/how-to-lose-172222-…
user5994461 · 2016-12-29
> When you ship every week, you can easily undo mistakes, and you're better off erring toward iteration.
Or so they thought:
http://pythonsweetness.tumblr.com/post/64740079543/how-to-lose-172222-…
gcb0 · 2016-01-08
http://pythonsweetness.tumblr.com/post/119568339102/block-range-brin-i…
the very first example points to BRIN indexes resulting in smaller index than btree but with much longer search time... so i guess the 5% time figure was very use-case specific?
pjc50 · 2015-11-22
The Knight Capital bug is probably most people's worst nightmare: http://pythonsweetness.tumblr.com/post/64740079543/how-to-lose-172222-…
p8952 · 2014-03-14
Knight Capital Group went bankrupt, it wasn't due to HFT, but was caused by bad electronic trading.
http://pythonsweetness.tumblr.com/post/64740079543/how-to-lose-172-222…
Erwin · 2013-11-02
Seccomp might be a possibility here, but will require one process per live robot (and Linux). With seccomp your process can do nothing but read/write from its file descriptors (so you have to make sure they are safe) but can do nothing more (thus you cannot import modules). So you can exchange messages via file descriptors and otherwise use any Python (or even any other language at all features). Here's one recent article about it: http://pythonsweetness.tumblr.com/post/65442885019/secure-low-overhead…
RestrictedPython, used in zope, is nice too. However it cuts you out of many Python features that it cannot statically validate.
ta_wh · 2018-01-03
See the three-year warranty here for boxed CPUs:
https://www.intel.com/content/dam/support/us/en/documents/processors/L…
Note the first bullet under "WHAT THIS LIMITED WARRANTY DOES NOT COVER":
"design defects or errors in the Product (Errata). Contact Intel for information on characterized errata."
Guess we're not covered on this one.
EDIT: That being said, given the potential scope of this issue (years of affected CPUs, massive PR hit) I'm hoping that Intel will at least offer some remedy to recent buyers. According to the article from The Register [1], OS vendors have been working on the fix since November. The blog posted over on pythonsweetness [2] posits the bug may have been identified in October. It'd be interesting to know for how long Intel has been selling Coffee Lake CPUs that are known to be vulnerable.
[1] https://www.theregister.co.uk/2018/01/02/intel_cpu_design_flaw/
[2] http://pythonsweetness.tumblr.com/post/169166980422/the-mysterious-cas…
testplzignore · 2018-01-03
I'm trying to understand the timeline of everything that is going on.
https://cyber.wtf/2017/07/28/negative-result-reading-kernel-memory-fro… was published on 2017-07-28.
The pythonsweetness.tumblr.com post talks about patches being first posted in October (anyone have a link to the first public patch?).
https://lwn.net/Articles/738975/ was published on 2017-11-15.
https://lwn.net/SubscriberLink/741878/5c019c71457e0da6/ was published on 2017-12-20.
https://lkml.org/lkml/2017/12/27/2 was published on 2017-12-27.
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/com… shows that Linus merged the patches on 2017-12-30.
https://lwn.net/Articles/742404/ was published on 2017-12-30.
http://pythonsweetness.tumblr.com/post/169166980422/the-mysterious-cas… which was the post that grabbed everyone's attention, was published on 2018-01-01.
Was the blog post on 2017-07-28 talking about the same vulnerability that has the world on fire today, or are there multiple issues going on?