Messages in this thread | | | Subject | Re: PATCH: Raw device IO for 2.1.131 | Date | Wed, 16 Dec 1998 17:15:50 -0800 | From | Stephen Williams <> |
| |
[1] > > There is also the fact that raw io for databases IS faster. Whatever type > > filesystem you design, doesn't matter since we know which blocks to write
[2] > Well from Linus' comments it sounds like raw devices won't be appearing in > 2.3, or indeed, ever.
mingo@chiara.csoma.elte.hu said: > well, my interpretation is that [2] was said only because [1] is > false. So the rest of your conclusions are false too.
Has anybody actually *measured* this? Do we know that the cache does not get polluted by doubly-cached data (once by DBMS once by linux)? Someone needs to write a benchmark that simulates the access patterns (including memory use) of a DBMS in order to prove a point, one way or the other.
And what about the case the Oracle guy pointed out where they share a SCSI disk between two hosts? Can that be made to work under Linux? -- Steve Williams "The woods are lovely, dark and deep. steve@icarus.com But I have promises to keep, steve@picturel.com and lines to code before I sleep, http://www.picturel.com And lines to code before I sleep."
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |