That's a click bait title IMHO. Sure with some hardware changes you can get different tradeoffs with regards to performance, but that does not solve the distributed transactions problem completely. E.g. What about availability?
The end of a myth: Distributed transactions can scale
31–40 of 95 posts
Re: The end of a myth: Distributed transactions can scale
#32Earlier quoted context omitted.
What kind of hardware features are we missing on cloud?
The atomic clock is the key to enable distributed transactions and Google has a proprietary lock on their atomic clocks for Spanner.
You need this for global consistency, but for logical local (like a single entity) this is unnecessary.
Re: The end of a myth: Distributed transactions can scale
#33Something like Oracle Exadata perhaps?
Re: The end of a myth: Distributed transactions can scale
#34Earlier quoted context omitted.
What kind of hardware features are we missing on cloud?
The atomic clock is the key to enable distributed transactions and Google has a proprietary lock on their atomic clocks for Spanner.
Do you know what is exactly proprietary in spanner? AFAIK most (all?) of the ideas existed before in the theoretical clock synchronization literature.
Re: The end of a myth: Distributed transactions can scale
#35IBM IMS DB
Everything is direct memory access.
SNA protocol, No TCP. This is used since the 70s by many banks to process high volume transactions
Re: The end of a myth: Distributed transactions can scale
#36RDMA, sounds unsafe by design
What seems unsafe about it? Are you worried about auth? There’s sRDMA?
Re: The end of a myth: Distributed transactions can scale
#37This is impressive, but won't have huge impact, IMO. Way back in 2015, MySQL Cluster (NDB Cluster engine) benchmarked 200m transactions/second on commodity hardware [1]. It was read-committed transactions, not snapshot isolation, but still impressive. NDB (or RonDB, the new DB by its author) uses a non-blocking 2-phase commit protocol (failed transaction coordinators are failed over) and is even open-source. Still, i…
How many machines was that? This is doing it across ~35.
105 machines with 28 cores each, says the presentation, and over infiniband. Looks like RonDB is quite impressive.
Re: The end of a myth: Distributed transactions can scale
#38Ethereum rollups have proven that transactions can scale
Re: The end of a myth: Distributed transactions can scale
#39Re: The end of a myth: Distributed transactions can scale
#40If we're bypassing TCP/IP, does that mean we need to build our own protocol on top of this to achieve the reliability guarantees etc provided by the TCP stack?