Messages in this thread | | | Date | Sun, 21 Mar 1999 16:40:01 -0800 (PST) | From | Matthew Jacob <> | Subject | Re: [OFFTOPIC] Re: disk head scheduling |
| |
> On Sun, Mar 21, 1999 at 12:16:40PM -0800, Matthew Jacob wrote: > > Then there was "Enriching the File System-Storage System Interface" > > work-in-progress (Drew Roselli, Jeanna Neefe Matthews, Tom Anderson > > (drew@cs.berkeley.edu) which talked about informing the storage subsystem > > with info hints as for file block lifetime, etc... I think this might have > > been what you were thinking of? > > > I think this is what Jim must have had in mind. Tell the disk drive which > blocks are related, which blocks are unlikely to be written, ... so that the > drive can optimize geometry. If I'm not mistaken, sct said that ext3 will > support this kind of thing.
Yes- if that makes sense. For a lot of data it does. But for a lot of transactions and systems, it's a little less clear. I sort of liked the speculative I/O execution thread paper of Fay Chang's which might do what this mini-paper is talking about, but at runtime. That is, dynamically generate a hint-list. That's really good for reads, and logging filesystems with offpeak garbage collection may solve a lot of the write problems?
-matt
- 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/
| |