On Thu, Nov 12, 2015 at 11:23 PM, Robert Haas <robertmh...@gmail.com> wrote: > On Mon, Nov 9, 2015 at 2:47 PM, Simon Riggs <si...@2ndquadrant.com> wrote: >> On 9 November 2015 at 18:46, Robert Haas <robertmh...@gmail.com> wrote: >>> One point I'd like to mention is that it's absolutely critical to >>> design this in a way that minimizes network roundtrips without >>> compromising correctness. XC's GTM proxy suggests that they failed to >>> do that. I think we really need to look at what's going to be on the >>> other sides of the proposed APIs and think about whether it's going to >>> be possible to have a strong local caching layer that keeps network >>> roundtrips to a minimum. We should consider whether the need for such >>> a caching layer has any impact on what the APIs should look like. >> You mean the caching layer that already exists in XL/XC? > > I don't think that's what I mean, no. If you have an external GTM > Proxy, then you have missed a trick, because whatever caching it does > could be done better inside the process that sent the request to the > proxy.
Definitely. Having a single communication channel between the backends and the centralized server that communicate with grouped messages would clearly help enhancing the scalability of the system, though this is not something the DTM should try to solve IMO. >>> For example, consider a 10-node cluster where each node has 32 cores >>> and 32 clients, and each client is running lots of short-running SQL >>> statements. The demand for snapshots will be intense. If every >>> backend separately requests a snapshot for every SQL statement from >>> the coordinator, that's probably going to be terrible. We can make it >>> the problem of the stuff behind the DTM API to figure out a way to >>> avoid that, but maybe that's going to result in every DTM needing to >>> solve the same problems. >> >> The whole purpose of that XTM API is to allow different solutions for that >> to be created. Konstantin has made a very good case for such an API to >> exist, based around 3 markedly different approaches. > > I'm not arguing with that. > >> Whether we allow the API into core to be accessible via extensions is a >> different issue, but it looks fine for its purpose. > > I'm not attacking the API. I'm trying to have a discussion about the > important design issues in this area. FWIW, I just looked at the wiki page regarding the DTM, and the set of routines GTM is actually very close to what XC/XL is doing. Where XC/XL directly forked the code of Postgres to redirect to the GTM when fetching a snapshot, TXID, whatever, DTM is using a set of generic methods to achieve this purpose and replace the in-core calls with a set of custom functions to relocate to the external instance in charge of distributing the transaction data. Other differences are that GTM is extended for global timestamps and global sequence values, but that's not really related to ACID. This just reminded me the following message where I wondered about the possibility to add hooks in those hot code paths... http://www.postgresql.org/message-id/cab7npqtdjf-58wuf-xz01nkj7wf0e+eukggqhd0igvsod4h...@mail.gmail.com -- Michael -- Sent via pgsql-hackers mailing list (firstname.lastname@example.org) To make changes to your subscription: http://www.postgresql.org/mailpref/pgsql-hackers