Messages in this thread | | | Date | Tue, 30 Mar 1999 11:24:40 -0800 (PST) | From | David Lang <> | Subject | Re: multiply files in one (was GNU/Linux stance by Richard Stallman) |
| |
-----BEGIN PGP SIGNED MESSAGE-----
The point here is that even with all the readahead in the world, the disk is still the slowest part of the system. If you can reduce the about of data (number of sectors) you need to get off of the drive you win. It doesn't matter that they will then take up the same amount of space im memory becouse memory is fast.
example 512 100 byte (ave size) files
with the tarfs you have 1 inode ~50 blocks (which are probably togeather as it is one file)
with ext2fs you have 512 inodes 512 blocks (which may be scattered as they are all seperate files)
so with tarfs you are reading 51 blocks rather then 1024 blocks a 20:1 advantage! (in real life milage will vary of course)
when reading this is a hugh advantage. when writing you need support at the filesystem level (like reiserfs is doing) so that writes can be done reasonably. (probably something along the lines of treat the files in memory as normal files and they dn't get mashed back togeather until the buffers are flushed and they get written back to disk)
David Lang
On Mon, 29 Mar 1999, Larry McVoy wrote:
> Date: Mon, 29 Mar 1999 22:15:14 -0800 > From: Larry McVoy <lm@bitmover.com> > To: Richard Gooch <rgooch@atnf.csiro.au> > Cc: linux-kernel@vger.rutgers.edu > Subject: Re: multiply files in one (was GNU/Linux stance by Richard Stallman) > > : But those were just done under SunOS, right? I wonder whether your > : results reflect that tarfs is a very good idea, or that SunOS is > : slow. This reminds me of the recurrent "let's implement swapfs for > : Linux" thread. Swapfs is good for SunOS because SunOS is slow. Swapfs > : for Linux is probably pointless because ext2fs and Linux are so fast. > > Do the math. If you did the math, instead of asking me to do the math, > then you would already know the answer. I find this whole conversation > extremely frustrating. Nothing I tell you is good enough and when I > tell you to go reason it out and come up with the same (or different, > I could care less which) answers on your own, you come back and ask > me to tell you again what I've already told you. That's an endless > loop and only you can break out of it - go think about it. Model it. > Figure out exactly how long it takes to read a bunch of little files > all in their own blocks and contrast that with how long it would take > to read all those blocks in one large I/O. > > I can't think for you. Please think for yourself and then we can have > a reasonable (and very enjoyable, I might add) conversation. > > - > 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/ >
"If users are made to understand that the system administrator's job is to make computers run, and not to make them happy, they can, in fact, be made happy most of the time. If users are allowed to believe that the system administrator's job is to make them happy, they can, in fact, never be made happy." - -Paul Evans (as quoted by Barb Dijker in "Managing Support Staff", LISA '97)
-----BEGIN PGP SIGNATURE----- Version: PGP for Personal Privacy 5.0 Charset: noconv
iQEVAwUBNwEk/D7msCGEppcbAQE4WggAwkNHQUEDcWOYeLR5Pl/yFcxnsOtgyhFW URn44/5HpFhaYKRgsr08z3I2sJy5D2oE5YKjUxcGncoeNOdi5n3cPEHnpFolnpjX uuuErDBNzFqsXb0bQDnpUhzVhTg79FbvfuRELov0rHI7XU3EJ8u66QtU8a9yq/c1 qYgdSVQzALHxY/wwx6L3tTYFe3KRU9tJ8VK4e4jXnp/V25SZb3Sgvk9KXIb9VejG 26ytAE2s5PyXSGmVqFl7y8IY5G+2bsYBEgRYlCWo2M7QXPsoGAeQ+qNQ/pRY3qYz x7U4UwigvvjQ2Xt4qo2yEOKfU0s1+qSOxixaA15tiAGlO7gZaydvyA== =cXvp -----END PGP SIGNATURE-----
- 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/
| |