[Paper review] TaxDC: A Taxonomy of nondeterministic concurrency bugs in datacenter distributed systems

-
This paper appeared in ASPLOS 2016 and the authors are Leesatapornwongsa, Lukman, Lu, and Gunawi.

The paper provides a comprehensive study on real-world distributed concurrency bugs and is a good complement to the paper I reviewed before: "Why does cloud stop computing". While the previous paper looked at all possible bugs that lead to service outages, this paper focuses only on distributed concurrency (DC) bugs. This type of bug happens to be my favorite kind of bug. I am fascinated with "failures", and with DC bugs doubly so. DC bugs are execution timing/ordering/scheduling related, they occur nondeterministically, and are extremely difficult to detect, diagnose, and fix in production systems. I love seeing those long traces of improbable DC bugs surface when I model check distributed algorithms in TLA+. The experience keeps me humble.

The paper presents analysis of 104 DC bugs from Cassandra, HBase, Hadoop MapReduce, and ZooKeeper. These bugs are categorized and studied according to the triggering timing condition and input preconditions, error and failure symptoms, and fix strategies, as shown in Table 1. The bug taxonomy database is available here.

Trigger warning

More than 60% of DC bugs are triggered by a single untimely message delivery that commits order violation or atomicity violation, with regard to other messages or computation. Figure 1 shows possible triggering patterns.

This sounds like a very striking and surprising finding. How is it that simple? How do we reduce most DC bugs to untimely message delivery? If you think about it, it is actually not very surprising. What is a DC bug? It is a state inconsistency across processes. What makes the state inconsistency into a bug? A communication/message-exchange between the two inconsistent processes.

Of course the root cause leading to the state inconsistency can be pretty complex. Figure 3 shows that many DC bugs need complex input preconditions, such as faults (63% in Figure 3.b), multiple protocols (80% in Figure 3.f), and background protocols (81% in Figure 3g). As an example, consider the juicy bug described in Figure 4.


Can we fix it? Yes, we can!

The paper analyzes bug patches to understand developers' fix strategies for DC bugs. They find that DC bugs can be fixed by either disabling the triggering timing by adding extra synchronization, or by changing the system's handling logic by ignoring/neutralizing the untimely message.

Yes, this sounds very simple. But what this perspective hides is that you first need to figure out the bugs before you can fix them. And identifying the DC bugs is the hard question as they occur nondeterministically and are extremely difficulty to detect and diagnose. For example, Figure 3 shows 47% of DC bugs lead to silent failures and hare hard to detect and debug in production and reproduce offline.

This is also a losing game, as you always need to play catch up with the new corner cases arising and haunting your system. Instead of doing a case-by-case fixing of the systems, it is better to fix our misconceptions and approach to designing these distributed protocols.

I like the section on Root Causes, which talks about developers misconceptions about distributed systems that leads to these bugs. These misconceptions are simple to correct, and doing so can eradicate many DC bugs.

  • One hop is faster than two hops.
  • No hop is faster than one hop.
  • Atomic blocks cannot be broken.
  • Interactions between multiple protocols seem to be safe.
  • Enough states are maintained to detect/handle problems. (Upon observing that some fixes add new in-memory/on-disk state variables to handle untimely message and fault timings.)

Another thing to improve would be to use better testing tools. Recall that 63% of DC bugs surface in the presence of hardware faults such as machine crashes (and reboots), network delay and partition (timeouts), and disk errors. The paper doesn't mention the Jepsen testing tool, but it would be a good fit to detect many DC bugs mentioned in this study.

And finally ounce of prevention is worth a pound of cure. Design your distributed protocols right in the first place. You can use TLA+ to specify and model-check your distributed protocols/algorithms before you start implementing them.

In the lessons learned section the paper discusses about what can be done to detect/prevent DC bugs, and says that "No matter how sophisticated the tools are, they are ineffective without accurate specifications. This motivates the creation or inference of local specifications that can show early errors or symptoms of DC bugs." The implication is that since the protocols do not come with good formal specifications, the tool support for testing, checking, detection, etc. becomes ineffective. This point further motivates that it is important to get the distributed protocol right first, and the specification should accompany the protocol so that the implementation can be made reliable. TLA+ provides support for writing the specifications. You can see my previous posts on TLA+ below.

Using TLA+ for teaching distributed systems

My experience with using TLA+ in distributed systems class

Modeling the hygienic dining philosophers algorithm in TLA+

There is a vibrant Google Groups forum for TLA+: https://groups.google.com/forum/#!forum/tlaplus

By clicking on label "tla" at the end of the post you can reach all my posts about TLA+

Comments

Anonymous said…
This comment has been removed by a blog administrator.
November 24, 2016 at 12:46 AM
Post a Comment

Popular posts from this blog

Hints for Distributed Systems Design

-
This is with apologies to Butler Lampson, who published the " Hints for computer system design " paper 40 years ago in SOSP'83. I don't claim to match that work of course. I just thought I could draft this post to organize my thinking about designing distributed systems and get feedback from others. I start with the same  disclaimer Lampson gave. These hints are not novel, not foolproof recipes, not laws of design, not precisely formulated, and not always appropriate. They are just hints.  They are context dependent, and some of them may be controversial. That being said, I have seen these hints successfully applied in distributed systems design throughout my 25 years in the field, starting from the theory of distributed systems (98-01), immersing into the practice of wireless sensor networks (01-11), and working on cloud computing systems both in the academia and industry ever since. These heuristic principles have been applied knowingly or unknowingly and has proven
Read more >>

Learning about distributed systems: where to start?

-
This is definitely not a "learn distributed systems in 21 days" post. I recommend a principled, from the foundations-up, studying of distributed systems, which will take a good three months in the first pass, and many more months to build competence after that. If you are practical and coding oriented you may not like my advice much. You may object saying, "Shouldn't I learn distributed systems with coding and hands on? Why can I not get started by deploying a Hadoop cluster, or studying the Raft code." I think that is the wrong way to go about learning distributed systems, because seeing similar code and programming language constructs will make you think this is familiar territory, and will give you a false sense of security. But, nothing can be further from the truth. Distributed systems need radically different software than centralized systems do.  --A. Tannenbaum This quotation is literally the first sentence in my distributed systems syllabus. Inst
Read more >>

Making database systems usable

-
Image
C. J. Date's Sigmod 1983 keynote, "Database Usability", was prescient. Usability is the most important thing to the customers. They care less about impressive benchmarks or clever algorithms, and more about whether they can operate and use a database efficiently to query, update, analyze, and persist their data with minimal headache. (BTW, does anyone have a link to the contents of this Sigmod'83 talk? There is no transcript around, except for this short abstract .) The paper we cover today is from Sigmod 2007. It takes on the database usability problem raised in that 1983 keynote head-on, and calls out that the king is still naked.  Let's give some context for the year 2007. Yes, XML format was still popular then. The use-case in the paper is XQuery. The paper does not contain any  reference to json. MongoDB would be released in 2009 with the document model; and that seems to be great timing for some of the usability pains mentioned in the paper! Web 2.0 was in
Read more >>

Looming Liability Machines (LLMs)

-
As part of our zoom reading group ( wow, 4.5 years old now ), we discussed a paper that uses LLMs for automatic root cause analysis (RCA) for cloud incidents. This was a pretty straightforward application of LLMs. The proposed system employs an LLM to match incoming incidents to incident handlers based on their alert types, predicts the incident's root cause category, and provides an explanatory narrative. The only customization is through prompt-engineering. Since this is a custom domain, I think a more principled and custom-designed  machine learning system would be more appropriate rather than adopting LLMs. Anyways, the use of LLMs for RCAs spooked me vicerally. I couldn't find the exact words during the paper discussion, but I can articulate this better now. Let me explain. RCA is serious business Root cause analysis (RCA) is the process of identifying the underlying causes of a problem/incident, rather than just addressing its symptoms. One RCA heuristic is asking 5 Why&#
Read more >>

Foundational distributed systems papers

-
I talked about the importance of reading foundational papers last week. To followup, here is my compilation of foundational papers in the distributed systems area. (I focused on the core distributed systems area, and did not cover networking, security, distributed ledgers, verification work etc. I even left out distributed transactions, I hope to cover them at a later date.)  I classified the papers by subject, and listed them in chronological order. I also listed expository papers and blog posts at the end of each section. Time and State in Distributed Systems Time, Clocks, and the Ordering of Events in a Distributed System. Leslie Lamport, Commn. of the ACM,  1978. Distributed Snapshots: Determining Global States of a Distributed System. K. Mani Chandy Leslie Lamport, ACM Transactions on Computer Systems, 1985. Virtual Time and Global States of Distributed Systems.  Mattern, F. 1988. Practical uses of synchronized clocks in distributed systems. B. Liskov, 1991. Expository papers
Read more >>

Advice to the young

-
Image
I notice I haven't written any advice posts recently. Here is a collection of my advice posts pre 2020. I've been feeling all this elderly wisdom pent up in me, ready to pour at any moment. So here it goes. Get ready to quench your thirst from my fount of wisdom. No man, think for yourself, only get what works for you. It is called foundations, not theory Foundations of computer science (or rather any field of study) are the most important topics you can learn. These lay down the frame of thinking/perspective for that area of study. Yet, I am saddened to hear these called as "theory", and labeled as "unpractical". This couldn't be farther from the truth. Take a look at how I recommend studying distributed systems . Don't you dare call this "theory" and "unpractical". This lays the bedrock that you build your practice on. Don't skimp on the foundations. Don't build your home on quicksand. Keep your hands dirty, your mind cl
Read more >>

Linearizability: A Correctness Condition for Concurrent Objects

-
Image
This paper is from Herlihy and Wing appeared in ACM Transactions on Programming Languages and Systems 1990. This is the canonical reference for the linearizability definition. I had not read this paper in detail before, so I thought it would be good to go to the source to see if there are additional delightful surprises in the original text. Hence, this post. I will dive into a technical analysis of the paper first, and then discuss some of my takes toward the end. I had written an accessible explanation of linearizability earlier; you may want to read that first. I will assume an understanding of linearizability to keep this review at reasonable length. Introduction I love how the old papers just barge in with the model, without bothered by pleasantries such as motivation of the problem. These are the first two sentences of the introduction. "A concurrent system consists of a collection of sequential processes that communicate through shared typed objects . This model encompass
Read more >>

Scalable OLTP in the Cloud: What’s the BIG DEAL?

-
Image
This paper is from Pat Helland, the apostate philosopher of database systems, overall a superb person, and a good friend of mine. The paper appeared this week at CIDR'24. (Check out the program for other interesting papers). The motivating question behind this work is: " What are the asymptotic limits to scale for cloud OLTP (OnLine Transaction Processing) systems? " Pat says that the CIDR 2023 paper "Is Scalable OLTP in the Cloud a Solved Problem?" prompted this question.  The answer to the question? Pat says that the answer lies in the joint responsibility of database and the application. If you know of Pat's work, which I have summarized several in this blog , you would know that Pat has been advocating along these lines before. But this paper provides a very crisp, specific, concrete answer. Read on for my summary of the paper. Disclaimer: This is a wisdom and technical information/detail packed 13-page paper, so I will try my best to summarize the sa
Read more >>

Understanding the Performance Implications of Storage-Disaggregated Databases

-
Image
Storage-compute disaggregation in databases has emerged as a pivotal architecture in cloud environments, as evidenced by Amazon ( Aurora ), Microsoft ( Socrates ), Google (AlloyDB), Alibaba ( PolarDB ), and Huawei (Taurus). This approach decouples compute from storage, allowing for independent and elastic scaling of compute and storage resources. It provides fault-tolerance at the storage level. You can then share the storage for other services, such as adding read-only replicas for the databases. You can even use the storage level for easier sharding of your database. Finally, you can also use this for exporting a changelog asynchronously to feed into peripheral cloud services, such as analytics. Disaggregated architecture was the topic of Sigmod 23 panel . I think this quote summarizes the industry's thinking on the topic. "Disaggregated architecture is here, and is not going anywhere. In a disaggregated architecture, storage is fungible, and computing scales independently.
Read more >>

Designing Data Intensive Applications (DDIA) Book

-
Image
We started reading this book as part of Alex Petrov's book club . We just got started, so you can join us, by joining the discord channel above. We meet Wednesday's 11am Eastern Time.  Previously we had read transaction processing book by Grey and Reuters. This page links to my summaries of that book. Chp 1. Reliable, Scalable, and Maintainable Applications I love the diagrams opening each chapter. Beautiful! The first chapter consists of warm up stuff. It talks about the definitions of reliabilty, scalability, and maintainability. It is still engaging, because  it is written with an educator and technical blogger voice, rather than a dry academic voice. This book came out on 2017. Martin is working on the new version. So if you have comments for things to focus on for the new version, it would be helpful to collect them in a document and email it to Martin. For example, I am curious about how the below paragraph from the Preface will get revised with 8 more years of hindsight:
Read more >>