Previously, on Jepsen, we reviewed Elasticsearch’s progress in addressing data-loss bugs during network partitions. Today, we’ll see Aerospike 3.5.4, an “ACID database”, react violently to a basic partition.
[Update, 2018-03-07] See the followup analysis of 3.99.0.3
Previously, on Jepsen, we demonstrated stale and dirty reads in MongoDB. In this post, we return to Elasticsearch, which loses data when the network fails, nodes pause, or processes crash.
Nine months ago, in June 2014, we saw Elasticsearch lose both updates and inserted documents during transitive, nontransitive, and even single-node network partitions. Since then, folks continue to refer to the post, often asking whether the problems it discussed are still issues in Elasticsearch. The response from Elastic employees is often something like this:
Please note: our followup analysis of 3.4.0-rc3 revealed additional faults in MongoDB’s replication algorithms which could lead to the loss of acknowledged documents–even with Majority Write Concern, journaling, and fsynced writes.
In May of 2013, we showed that MongoDB 2.4.3 would lose acknowledged writes at all consistency levels. Every write concern less than MAJORITY loses data by design due to rollbacks–but even WriteConcern.MAJORITY lost acknowledged writes, because when the server encountered a network error, it returned a successful, not a failed, response to the client. Happily, that bug was fixed a few releases later.
I like builders and have written APIs that provide builder patterns, but I really prefer option maps where the language makes it possible. Instead of a builder like
Wizard wiz = new WizardBuilder("some string")
.withPriority(1)
.withMode(SOME_ENUM)
.enableFoo()
.disableBar()
.build();
So there’s a blog post that advises every method should, when possible, return self. I’d like to suggest you do the opposite: wherever possible, return something other than self.
Mutation is hard
Previously: Modeling.
Writing software can be an exercise in frustration. Useless error messages, difficult-to-reproduce bugs, missing stacktrace information, obscure functions without documentation, and unmaintained libraries all stand in our way. As software engineers, our most useful skill isn’t so much knowing how to solve a problem as knowing how to explore a problem that we haven’t seen before. Experience is important, but even experienced engineers face unfamiliar bugs every day. When a problem doesn’t bear a resemblance to anything we’ve seen before, we fall back on general cognitive strategies to explore–and ultimately solve–the problem.
With the language fundamentals in hand, here’s my thinking for the remainder of the Clojure from the ground up book chapters. I’m putting Jepsen on hold to work on this project for the rest of the year; hoping to get the source material complete by… January?
- Debugging and getting help
- Polymorphism
- Error Handling
- Modularization and refactoring
- It’s not at all obvious what an object is
- JVM interop
- The Clojure type system
- Compiler at runtime
- Build your own language
- Performance analysis
- Parsers and protocols
- Storage and persistence
- Networks and messaging
- Concurrency and queues
In the previous post, we discovered the potential for data loss in RabbitMQ clusters. In this oft-requested installation of the Jepsen series, we’ll look at etcd: a new contender in the CP coordination service arena. We’ll also discuss Consul’s findings with Jepsen.
Like Zookeeper, etcd is designed to store small amounts of strongly-consistent state for coordination between services. It exposes a tree of logical nodes; each identified by a string key, containing a string value, and with a version number termed an index–plus, potentially, a set of child nodes. Everything’s exposed as JSON over an HTTP API.
Earlier versions of Jepsen found glaring inconsistencies, but missed subtle ones. In particular, Jepsen was not well equipped to distinguish linearizable systems from sequentially or causally consistent ones. When people asked me to analyze systems which claimed to be linearizable, Jepsen could rule out obvious classes of behavior, like dropping writes, but couldn’t tell us much more than that. Since users and vendors are starting to rely on Jepsen as a basic check on correctness, it’s important that Jepsen be able to identify true linearization errors.
Update, 2018-08-24: For a more complete, formal discussion of consistency models, see jepsen.io.
Network partitions are going to happen. Switches, NICs, host hardware, operating systems, disks, virtualization layers, and language runtimes, not to mention program semantics themselves, all conspire to delay, drop, duplicate, or reorder our messages. In an uncertain world, we want our software to maintain some sense of intuitive correctness.