Tweets
- Tweets, current page.
- Tweets & replies
- Media
You blocked @jepsen_io
Are you sure you want to view these Tweets? Viewing Tweets won't unblock @jepsen_io
-
New Jepsen analysis! We talk about etcd's kv operations, watches, and locks. KV ops look strict serializable, and watches deliver all changes in order (with a minor undocumented edge case around revision zero). As usual, distributed locks aren't real: https://jepsen.io/analyses/etcd-3.4.3 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
I'm committed to giving everyone the most accurate, rigorous reporting on database correctness that I can, and I encourage vendors to do the same. Be open, honest, and nuanced in your writing. That honesty is good for users, and it builds trust in your team.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
But still, some vendors do misrepresent the results of our work together, and this bugs me. I expected vendors to call each other out for this sort of thing, because they're more than willing to write take-downs over interpretation of benchmarks, but so far that hasn't happened.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Most vendors are telling the truth here: by the time we conclude our collaboration, the safety issues we found have usually been addressed, and the test suite often passes. Many vendors also follow up "passes" with a description of the issues we found, which I think is honest.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
In more general terms, almost every database we tested with Jepsen fails, sometimes in dozens of ways, before its test suite passes. That's how we know Jepsen is *working*! The vendor headline that comes out of that process is usually "X passes Jepsen".pic.twitter.com/bJBT3MDw74
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Crashes, unavailability, and performance problems aren't usually reported by Jepsen as "failing" results, because we're primarily concerned with checking safety, rather than liveness problems. It's hard to say how slow is too slow. We file and discuss these issues qualitatively.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
There are other issues that we found in our work, like slowly spawning an ever-increasing number of backend worker processes which eventually consume all resources and kill the machine. This one's still open too.https://github.com/YugaByte/yugabyte-db/issues/2075 …
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Because these problems involve schema changes (e.g. creating tables), they may not impact users frequently. YugaByte doesn't think they're relevant to the core transactional mechanism in YugaByte DB, which is why they're not discussing them when they say "Jepsen tests passed".
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Again, YugaByte DB's Jepsen tests did not pass. They do not currently pass. Correctness issues we identified in our collaboration, mainly due to non-transactional schema changes, are still unaddressed. YugaByte and I have talked about this. https://blog.yugabyte.com/announcing-yugabyte-db-2-0-ga-jepsen-tested-high-performance-distributed-sql/ …pic.twitter.com/lu8gwTq8re
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
An open question in my mind: can non-transactional schema changes (e.g. adding a column) result in *data-level* serializability violations? What would those anomalies look like? I'm honestly not sure, but it's something we can explore going forward!
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
So... when YugaByte says they "pass Jepsen" (https://blog.yugabyte.com/yugabyte-db-distributed-sql-api-passes-jepsen-tests/ …) they're only talking about the parts of the test suite which look at changes to data records in the absence of schema changes. We think that's most important for users, and it's the vast majority of our tests
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
The impact of this issue (like many of the problems we found in schema modification) is limited to a short time around table creation. Schema changes in general aren't transactional, so this might occur during other changes, like adding/removing columns--we haven't looked yet.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
YugaByte DB doesn't pass Jepsen presently; some of the safety issues we identified in testing are still extant. For instance, YugaByte DB has a race condition which allows `DEFAULT NOW()` columns to be initialized to `NULL`, rather than a timestamp.https://github.com/YugaByte/yugabyte-db/issues/2021 …
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
New
#Jepsen report! We worked with@YugaByte to evaluate YugaByte DB 1.3.1's beta support for serializable SQL transactions. We found 2 safety bugs including anti-dependency cycles (now fixed), and availability issues like a slow leak in backend processes. https://jepsen.io/analyses/yugabyte-db-1.3.1 …Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Jepsen 0.1.15 is out! It's a minor bugfix and ergonomics release.https://github.com/jepsen-io/jepsen/releases/tag/0.1.15 …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
And here's the video!https://www.youtube.com/watch?v=w_zYYF3-iSo&feature=youtu.be …
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
On Wednesday, August 14, I'll be giving a livestreamed talk with
@fauna, discussing various approaches for transactional isolation in globally distributed systems, including Spanner,@CockroachDB, FaunaDB, @YugaByteDB,@VoltDB, Percolator, and TiDB.http://www2.fauna.com/wcdistributedarchitectures …Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
In the latest
#Jepsen analysis, we worked with@pingcap to test TiDB 2.1.7 through 3.0.0-rc.2. Due to 2 transaction retry mechanisms, TiDB exhibited constant snapshot isolation anomalies under normal conditions. This and other bugs are fixed in 3.0.0-rc.2: https://jepsen.io/analyses/tidb-2.1.7 …Thanks. Twitter will use this to make your timeline better. UndoUndo -
Jepsen 0.1.14 is now available, featuring a bunch of bugfixes, usability improvements, and new tests.https://github.com/jepsen-io/jepsen/releases …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
Jepsen Retweeted
During
@jepsen_io testing we discovered failovers after a network partition weren't happening quick enough. Here's how we made them faster - https://bit.ly/2WIpLqB#distributedsql#postgresql#microservices#kubernetesThanks. Twitter will use this to make your timeline better. UndoUndo
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.