Messages in this thread | | | Date | Mon, 19 Apr 1999 02:41:38 +0530 (IST) | From | V Ganesh <> | Subject | Re: bad lmbench numbers for mmap |
| |
> From: torvalds@transmeta.com (Linus Torvalds) [snip] > Btw, that also explains why we're twice as slow as Solaris: Solaris > probably does just one copy. Which is not very impressive either, as > the proprt (2.3.x) way to do it is to do it without a single copy at > all, and just write it out directly from the page cache page.
not likely. solaris VM is like SVR4, right ?(or rather, the other way round). their writes go through page cache. their buffer cache is usually used only for filesystem metadata. so there's no reason to do a copy. but they have other overheads like having to map the page into kernel space before doing IO (unlike linux which maps all physical mem, so this step is trivial).
ganesh
- 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/
| |