Re:IceFireDB: Distributed disk storage database based on Raf...
by alexchamberlain on Saturday August 21, 2021 @01:33PM
(#28258858)
Each write should be fsync'd to the WAL, right?
[ Parent
| on HN ]
Re:IceFireDB: Distributed disk storage database based on Raf...
by stingraycharles on Saturday August 21, 2021 @04:02PM
(#28260068)
Yes but those can happen at the convenience of the particular node, not necessarily as a globally chrckpointed fsync()
Re:IceFireDB: Distributed disk storage database based on Raf...
by refenestrator on Saturday August 21, 2021 @04:19PM
(#28260230)
Then you're sacrificing consistency guarantees. If less than a majority have committed a write, it could be lost while the cluster still has a quorum up.
Waiting to report success until a majority have committed allows you to make guarantees with a straight face.. "it will probably be committed in the near future" is not the same thing.
Re:IceFireDB: Distributed disk storage database based on Raf...
by rubiquity on Saturday August 21, 2021 @08:07PM
(#28261755)
Not necessarily. As long as your quorums always overlap you can have weaker commit requirements. See the FPaxos paper and some of Heidi Howard’s blogs for more on this.
Re:IceFireDB: Distributed disk storage database based on Raf...
by jimsimmons on Sunday August 22, 2021 @02:33AM
(#28263397)
FPaxos requires commit quorum and subsequent promise request quorum to intersect. It doesn't bring any significant thruput benefits
Re:IceFireDB: Distributed disk storage database based on Raf...
by rubiquity on Sunday August 22, 2021 @11:50AM
(#28266447)
I didn't say FPaxos brought throughput benefits. I pointed out that you can still have a correct implementation without requiring majority quorums.
But since you brought it up, FPaxos can have both lower latency and higher throughput than MultiPaxos/Raft[0] ;)
Re:IceFireDB: Distributed disk storage database based on Raf...
by jimsimmons on Sunday August 22, 2021 @06:00PM
(#28270079)
Great link. Need to look into what WPaxos is.