Patent Troll Kills Open Source Project On Speeding Up The Computation Of Erasure Codes

from the promoting-the-progress dept

Wed, Nov 19th 2014 9:02am — Mike Masnick

Via James Bessen, we learn of how a patent trolling operation by StreamScale has resulted in an open source project completely shutting down, despite the fact that the patent in question (US Patent 8,683,296 for an "Accelerated erasure coding system and method") is almost certainly ineligible for patent protection as an abstract idea, following the Supreme Court's Alice ruling and plenty of prior art. Erasure codes are used regularly today in cloud computing data storage and are considered to be rather important. Not surprisingly, companies and lawyers are starting to pop out of the woodwork to claim patents on key pieces. I won't pretend to understand the fundamental details of erasure codes, but the link above provides all the details. It goes through the specific claims in the patents, breaking down what they actually say (basically an erasure code on a computer using SIMD instructions), and how that's clearly an abstract idea and thus not patent-eligible. Furthermore, it details the relevant prior art:

The most prominent prior art invalidating this patent is the RAID6 (one of the most commonly used Erasure Code) implementation of the linux kernel. In an article dated 2004 (i.e. ten years before the patent was granted to StreamScale) it is described to be optimized as follows : For additional speed improvements, it is desirable to use any integer vector instruction set that happens to be available on the machine, such as MMX or SSE-2 on x86, AltiVec on PowerPC, etc. Where SSE2 is the acronym of Streaming SIMD Extensions 2. The patent cites Anvin aticle’s but only to state the problem and does not acknowledge it also contains the solution.

Even so, StreamScale apparently bullied the open source project's creator, Professor James Plank, into removing his repositories and saying he is no longer working on the software project. No lawsuit was filed, but Plank posted a statement that makes it clear he was threatened by StreamScale and agreed to do this to avoid a lawsuit. Apparently, StreamScale also threatened USENIX for merely publishing a paper by Plank detailing the concepts in his software.

After a failed attempt to bully USENIX, StreamScale intimidated (i.e. there was no lawsuit and therefore no ruling) James Plank, a known researcher in the field, also author of widely used Free Software libraries using the same techniques as those described in the linux kernel. James Plank agreed to publish the following on his web site as part of a settlement, presumably in exchange for a promise from StreamScale to not threaten to sue him in the future.

On this page I (James Plank) am providing notice that:

GF-Complete and Jerasure versions 2.0 and later are no longer supported.

StreamScale, Inc. offers a similar solution for commercial purposes.

I offer no representations or warranties in general about StreamScale’s products.

I have verified that StreamScale’s solution is faster than GF-Complete or Jerasure in at least some respects.

StreamScale, Inc. asserts that the use of GF-Complete (particularly as part of Jerasure 2.0 or later) or any similar software, method or code for erasure coding infringes StreamScale’s issued United States Patent No. 8,683,296.

I express no opinion on StreamScale’s claims, but I believe that parties should be aware that StreamScale asserts such claims.

The repositories on which James Plank published the software implementing the ideas from his research papers ( gf-complete and jerasure ) have been removed the same day, meaning James Plank had to agree to never work on implementing erasure coded software in the future.

There is the only marginally complicating factor that Plank, apparently, was a consultant for StreamScale a few years ago -- leading the company to argue that his research, publications and code pulled from information he had learned while working with the company. But, again, these ideas both have clear and known prior art and do not appear to be patentable subject matter. And the end result: less ability to innovate (or even research!) these sorts of things, and some important open source code no longer being supported.

Thank you for reading this Techdirt post. With so many things competing for everyone’s attention these days, we really appreciate you giving us your time. We work hard every day to put quality content out there for our community.

Techdirt is one of the few remaining truly independent media outlets. We do not have a giant corporation behind us, and we rely heavily on our community to support us, in an age when advertisers are increasingly uninterested in sponsoring small, independent sites — especially a site like ours that is unwilling to pull punches in its reporting and analysis.

While other websites have resorted to paywalls, registration requirements, and increasingly annoying/intrusive advertising, we have always kept Techdirt open and available to anyone. But in order to continue doing so, we need your support. We offer a variety of ways for our readers to support us, from direct donations to special subscriptions and cool merchandise — and every little bit helps. Thank you.

–The Techdirt Team

Filed Under: abstract ideas, erasure codes, james plank, patent troll, patentable subject matter, patents, prior art
Companies: streamscale

28 Comments

If you liked this post, you may also be interested in...

Reader Comments

Subscribe: RSS

View by: Time | Thread

Ninja (profile), 19 Nov 2014 @ 7:21am

Open source eh? So the code is available in the wild? Development will continue despite the patent system actively preventing progress.
[ link to this | view in thread ]
Michael, 19 Nov 2014 @ 9:12am

I am not sure why anyone would want to stymie the Worderland of Erasure research. Sometimes, we really need to take a hard look at The Circus that allows this kind of thing to happen. It Doesn't Have to Be this way guys. The Innocents that could be harmed by these kinds of actions just turn the whole world into a Ship of Fools. A Little Respect for open source projects like this could go a long way.
[ link to this | view in thread ]
Gumnos (profile), 19 Nov 2014 @ 9:24am

Re: Touche
I was about to make a similar comment but you beat me to it. Nice.
[ link to this | view in thread ]
That Anonymous Coward (profile), 19 Nov 2014 @ 9:33am

Yay, more patents making the world a better place. /s
[ link to this | view in thread ]
JoeT, 19 Nov 2014 @ 9:41am

Fortunately the code has been picked up by others
It is very unfortunate that Jim had to cave. He doesn't have any backing, and the cost of handling the threats was getting to be prohibitive (much less what the costs of an actual lawsuit would have been). StreamScale has apparently tried to shake down many companies who use erasure codes; basically anyone with any pockets whatsoever have told StramScale to f off. But since Jim is stuck on his own, he can't afford to.

The community of people who work on this type of thing is fairly small, and Jim was known as essentially *the* expert in high-speed erasure coding. A decade ago Jim used to license his code for commercial use; fortunately he started releasing it under a BSD license some years back (well before StreamScale's patents were filed). Now the bulk of the storage software community uses Jim's code in one form or another. I mean, what's not to like: it's blazing fast and it's free.

Since the developers of Ceph keep a copy of both Jerasure and GF-Complete the code isn't going away:

https://github.com/ceph/gf-complete

https://github.com/ceph/jerasure

They're backed by RedHat, who have at least a little money. Jim's coauthors on the academic paper also have backing, and so you can find that on their web pages as well:

http://www.ssrc.ucsc.edu/Papers/plank-fast13.pdf
[ link to this | view in thread ]
Anonymous Coward, 19 Nov 2014 @ 9:43am

so why doesn't someone come forward, assuming no-one did prior to him stopping the project, to back him? is it too late for this to happen, stating how he had no financial backing to compete against the bully?
[ link to this | view in thread ]
OldMugwump (profile), 19 Nov 2014 @ 9:50am

People need to show some backbone
I gather from your comments he's a good guy and all, but people need to show a little backbone and not cave at the first threat.

If we make it easy for the trolls to roll over people, that's what they'll do.

The proper thing is to say "see you in court, asshole" and then call the EFF.

If the case is really as clear-cut as people here think, he can even represent himself - and win.

But we all - as citizens - have a responsibility to be a little bit tough.
[ link to this | view in thread ]
Anonymous Coward, 19 Nov 2014 @ 10:22am

Re: People need to show some backbone
I'll show all the backbone you want. You're going to bankroll the whole thing, I'm assuming.
[ link to this | view in thread ]
OldMugwump (profile), 19 Nov 2014 @ 10:25am

Re: Re: People need to show some backbone
I'll chip in, yes.

But even if I didn't - we don't always get to choose our battles; sometimes the battles come to us.

As citizens we have a responsibility to do our share. Yes, sometimes it hurts.

People volunteer for worse things than lawsuits to protect their societies, you know.
[ link to this | view in thread ]
Anonymous Coward, 19 Nov 2014 @ 10:28am

Re: People need to show some backbone
and I think that's kinda the whole point of even having organizations like the ACLU and EFF. So that individuals that don't have the money to defend themselves in court but do have a solid case can have good representation.

Then again the very need to have these organizations shows a failure in our legal system. These organizations aren't tax funded but they're funded by donations. IOW, the only way the poor/middle class can get good representation when they're right without being driven into (worse) poverty in the process is to have organizations that the private sector/individuals voluntarily fund. The private sector and a separate system of donations has to make up for the shortcomings of our legal system.
[ link to this | view in thread ]
Anonymous Coward, 19 Nov 2014 @ 10:37am

Re: Re: People need to show some backbone
Justice and equality should originate from our legal system itself, it shouldn't come from a separate private entity that's funded through voluntary donations (ie: the EFF, ACLU, etc...).
[ link to this | view in thread ]
Nom du Clavier (profile), 19 Nov 2014 @ 10:37am

Not a failed attempt at bullying USENIX
After a failed attempt to bully USENIX, StreamScale intimidated (i.e. there was no lawsuit and therefore no ruling) James Plank, a known researcher in the field, also author of widely used Free Software libraries using the same techniques as those described in the linux kernel.

Apparently not a failed attempt at bullying after all.
The full FAST '13 conference proceedings (in PDF, EPUB, and MOBI) and the table of contents (in PDF), which contain papers entitled SD Codes: Erasure Codes Designed for How Storage Systems Really Fail and Screaming Fast Galois Field Arithmetic Using Intel SIMD Instructions, which were posted here, have been taken down due to a dispute over the two papers' contents. USENIX takes no position regarding the merits of the dispute. We will re-post the papers when the dispute has been resolved to our satisfaction or at such earlier time that we deem appropriate. Note that all other FAST '13 papers are available individually below

[ link to this | view in thread ]
OldMugwump (profile), 19 Nov 2014 @ 10:54am

Re: Re: Re: People need to show some backbone
Yes of course. In an ideal world, that's how it would work.

If you find one, let me know - I'd like to move there.

In the meantime, we have to do it ourselves.
[ link to this | view in thread ]
Avatar28 (profile), 19 Nov 2014 @ 11:06am

Re: Re: Touche
Ah, I don't get it. I mean, obviously there is some sort of hidden message in there but I'm not getting it. Can someone explain?
[ link to this | view in thread ]
Anonymous Coward, 19 Nov 2014 @ 11:06am

Re:
Actually, it's easier than that: this is an Open Source project, and people have the source. All that needs to happen is that someone needs to make a big public issue about the fact that they're continuing development -- and also point to the patent claims and sue the company for predation or whatever the legal term is. They could even write a nastygram to the firm's lawyers stating that there's a new understanding that unless they want their patent invalidated, they'd better grant an inclusive license immediately for it to be used in open source projects.

Anyone willing to bankroll/stick their neck out for this one?
[ link to this | view in thread ]
John Fenderson (profile), 19 Nov 2014 @ 11:10am

Re: Re: Re: Touche
The italicized phrases are the names of songs by the band Erasure.
[ link to this | view in thread ]
Anonymous Coward, 19 Nov 2014 @ 11:18am

Four words.
Open Source Defense Fund.

Is there one? Shouldn't there be one? Can someone step in for Plank regardless of his own actions? Or countersue?
[ link to this | view in thread ]
Anonymous Coward, 19 Nov 2014 @ 11:34am

Where did you get the idea that the claimed invention falls without Section 101? Just because an invention happens to involve software in some fashion by no means moves it outside the scope of Section 101, as the Supreme Court has repeatedly stated.
[ link to this | view in thread ]
Nom du Clavier (profile), 19 Nov 2014 @ 11:57am

Re:
Finite fields (like Galois Fields) have been in use for over a century. The patent claims a way of calculating them faster on a computer as claim 1. The rest are dependent claims.

"Do this general thing that's been common practice, but on a computer" is exactly what the Supreme Court rejected in Alice, unless I'm mistaken.

Something in active use for over a century can be said to be common practice.
[ link to this | view in thread ]
ltlw0lf (profile), 19 Nov 2014 @ 12:50pm

Re: Re: Re: People need to show some backbone
People volunteer for worse things than lawsuits to protect their societies, you know.

For life and death cases, yes. Other than that, I can't think of anything worse than to volunteer to pay everything you have ever or will ever own over to a lawyer with the very real probability that it won't be enough to cover the jury award that isn't in your favor.

Frankly, volunteering for carrying a gun into battle for your country is somewhat safer, since they usually have Geneva Conventions to prevent the type of abuse you will likely see in the courts. At least the worse you can get in battle is the loss of your life and/or permanent, life-changing injury.

As citizens, we should be demanding a court system that is for justice and protection of the innocents, not a private tax system for those get-rich-quick lawyers that couldn't make it chasing ambulances or working as high-priced divorce attorneys.
[ link to this | view in thread ]
alternatives(), 19 Nov 2014 @ 1:01pm

Re: Re: Re: Re: People need to show some backbone
demanding a court system that is for justice and protection of the innocents

If you are willing to fight and the other side lies while there ARE perjury laws on the books they are not enforced.

As prosecutor E. Michael McCann has concluded, "Outside of income tax evasion, perjury is…probably the most underprosecuted crime in America." From Mark Curriden, The Lies Have It, A.B.A. J., May 1995

If there is little chance of punishment for lying in Court - how honest are the proceedings going to be?
[ link to this | view in thread ]
That One Guy (profile), 19 Nov 2014 @ 1:03pm

Re: Re:
they'd better grant an inclusive license immediately for it to be used in open source projects.

Good ideas except for that last part, asking for a license at all would just be used to defend the patent in court.

'You see your honor, they demanded a license, clearly they believed at the time that the patent was a valid one, since you don't need to license an invalid patent.'
[ link to this | view in thread ]
JoeT, 19 Nov 2014 @ 7:21pm

Re: Not a failed attempt at bullying USENIX
USENIX, although better bankrolled than Jim, has a similar problem. They're run on a shoestring. From my understanding, even just rolling over blew their yearly legal budget.

This is the real damage bad actor litigants can do; they have a button they can press where they pay their lawyer $10 and it costs you $40 to respond. Even a small player (StreamScale at this point has been reduced to more or less the founder and outside council) can effectively bully what would seem to be much larger organizations. Until the courts are much more generous in cost shifting, and until the bar association starts spanking the lawyers who go along with this, we won't really have a fair system.
[ link to this | view in thread ]
FauxReal (profile), 20 Nov 2014 @ 9:15am

Re: Re: Re: Re: People need to show some backbone
I don't know about carrying guns into being safer. The loss of life or a life changing and costly injury that can just as well bankrupt you while leaving you crippled is not a better deal in my book.
[ link to this | view in thread ]
Pragmatic, 24 Nov 2014 @ 7:52am

Re:
Promoting innovation and stuff. /s
[ link to this | view in thread ]
poeemah, 15 Dec 2014 @ 2:28am

Legally penalized regarding access to open access that is legally approved...huh-
Now that's quite the concept, who'd thought??!!? And I thought the bureaucracy surrounding this entire concept of 'Open Access' sanctioned through provisions of the Patriot Act in 2011 (perhaps even back 2001 when the Act was passed) supported these methods, and in which Technical progress heavily relied upon- as I recently discovered. Only by chance, in efforts to troubleshoot some of the peculiar security issues I'd been experiencing, but not likely- per Tech Support after constant Help request/correspondence and later advised to replicate the problem to provide a more comprehensive approach- and strangely ending on several Software Project pages/files to different sites/platforms. Surprised at the access, but shocked to have a profile. Attempts to eliminate that access, affected common use of my primary account.(where irregularities initially discovered) After reading release notes, and realizing that it was 'me' they'd refer to on comments making reference to the "client" and seeing how my activity interrupted project progress. Of not only that the working team, (trust me when I say, "I kept them working." But the users,...people. Who're like me. Lives. Work. Progress. And because I'm all for forward progress. Especially progress that could very well improve us as a society. A nation, heck-as a People. Possibilities are limitless, aside from National security- a blanket statement originally gaining approval of this Open Access concept. My concern is how it should enable Accountability. Up until reading this article, I had no clue this act was something of legal consequence. I figured it was the consensus in Tech/Dev/Software industry that I eager have spent countless hours/days/nights learning how to create applications to interpret ideas of methods/tools that could make life easier- my life easier. And concluded how helpful, it would be. The competitive aggressiveness, isn't for me. And that teaching was a more satisfying way to help/impact a more crucially vital industry essentially in need of attention. I Imperative to the future of any industry, our future- The Children. While we compete to become the leading nation in technology, our children's education is registered on carbon copy forms/applications processed on probably ancient technology compared to quickly our cell phones seem to become obsolete according to the lines to get the latest release.
Open access enables one to be effective, when Accountable access can prove to be effective. I was a 'little' more at ease when I thought it was just NSA w/granted clearances accessing my private information. Never feeling so vulnerable- I now know better. Currently researching a purchase of a personal hard drive with little to zero access to the web.
-open me
[ link to this | view in thread ]
Loic Dachary, 28 Dec 2014 @ 12:39pm

jerasure & gf-complete are very much alive
The code and documentation are now hosted at http://jerasure.org/ and ARMv8 SIMD acceleration has been added recently. StreamScale may have bullied someone out of jerasure (shame on them) but there is no way they can slow down the momentum :-)
[ link to this | view in thread ]
Dan Adkins, 12 Mar 2020 @ 9:47am

qfs: prior art from 2010
https://github.com/quantcast/qfs/tree/master/src/cc/qcrs

I wrote the preceding code in the summer of 2010, as an extension of Avind's Linux RAID-6 scheme to three parity disks, using the same SIMD tricks for fast Galois Field arithmetic. If that's not prior art, I don't what is.
[ link to this | view in thread ]