fdb-nbd
Infrastructure
network block device
SHOW HN2018
192points
33comments
#192of 2,155 in 2018
Top 9%of 2018 by points
How HN took it
CuriousMostly questions and neutral comments
4 positive, 19 neutral or asking, 1 mixed, 1 critical, out of 25 comments about the project. Thread score +0.12.
Idea: 4 for, 0 againstExecution: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Fault tolerance for legacy applications via block storage over FDB
From 2 comments
Awesome. I actually think that there is a lot of potential for using block storage over FDB to bring extreme fault tolerance to legacy applications without rearchitecting them.…
voidmain on HNI think the biggest feature is that you get (up to) linearizable consistency while still being FAST, meaning you can rest assured that any writes are actually permanent, even if…
haneefmubarak on HN
Simple NBD protocol is useful for building new things
From 1 comment
It's not really "better" or "worse". NBD is an extremely simple protocol. Read range, write range, delete range, sync -- that's it. If you want to implement an NBD server from…
kentonv on HN
Objections
Python backend on same machine risks memory deadlocks
From 2 comments
Very cute. For a production system, you do not want an NBD device backed by Python code on the same machine. That way lies nasty memory allocation deadlocks.
amluto on HNSuppose you've filled up most of your memory and that some of that memory contains data that you've written to an NBD-backed device but that hasn't been flushed out yet. The…
amluto on HN
Ad hoc locking across etcd and Ceph is hard to get right
From 1 comment
Unless you have serious simulation or model checking tools, your ad hoc combination of etcd and ceph will almost certainly be buggy. I'm not 100% positive it is even possible in…
voidmain on HN
Requests
Support for multiple simultaneous clients on the same volume
From 2 comments
Could you mount this on multiple machines and do simultaneous reads and writes?
ryanworl on HNHow do you handle resilience? if FDB is multi-node, do you run a copy on each node? If so, how is failure detected / client traffic redirected, and what protects against…
scoot on HN
Failover to an alternate node when the connected node fails
From 1 comment
Thanks for the reply. Don't know if you will see this, but I was also interested in how the NBD client fails over to an alternate node if the one it's connected to fails.…
scoot on HN
Questions
How is resilience and failover handled
From 2 comments
How do you handle resilience? if FDB is multi-node, do you run a copy on each node? If so, how is failure detected / client traffic redirected, and what protects against…
scoot on HNThanks for the reply. Don't know if you will see this, but I was also interested in how the NBD client fails over to an alternate node if the one it's connected to fails.…
scoot on HN
What prevents concurrent clients on one volume
From 3 comments
How do you handle resilience? if FDB is multi-node, do you run a copy on each node? If so, how is failure detected / client traffic redirected, and what protects against…
scoot on HNSee https://www.foundationdb.org for information on FDB but in short it is a distributed database that is auto-scaling, auto-healing, auto-sharding and ACID. You do need a…
spullara on HNThanks for the reply. Don't know if you will see this, but I was also interested in how the NBD client fails over to an alternate node if the one it's connected to fails.…
scoot on HN
Does zlib compression make it faster or slower
From 1 comment
does the zlib compression in python make it faster or slower?
0x006A on HN
Alternatives named
Ceph RBD
From 2 comments
Would this provide additional benefits over Ceph, which does no-single-point-of-failure networked block storage and is already a production-ready system? It wouldn't get you the…
geofft on HNRBD (Ceph block devices) supports exclusive locking. The RBD kernel client has support for that since kernel 4.9. Older kernels can use rbd-nbd to use the user space…
emmericp on HN
iSCSI
From 2 comments
Could someone explain why/how NBD is better than just using a linux host as an iscsi target? Googling NBD vs iSCSI shows old articles with no real solid conclusion.
CaseFlatline on HNIt's not really "better" or "worse". NBD is an extremely simple protocol. Read range, write range, delete range, sync -- that's it. If you want to implement an NBD server from…
kentonv on HN
Java NBD server by spullara
From 1 comment
Cool! Here is my java version that I wrote back in the day. Recently updated to 5.1. https://github.com/spullara/nbd
spullara on HN