------------------------------------------------------------------------------
Kamal R. Prasad
AIX Support & Test, IBM India Software Labs
Golden Enclave, Airport Road, Bangalore-560017, India
Phone : +91-80-5094963,  Internal Ext   : 2963






Bill Studenmund <wrstuden@netbsd.org>
05/13/2003 05:43 PM
 
        To:     Kamal R Prasad/India/IBM@IBMIN
        cc:     Roland Dowdeswell <elric@imrryr.org>, BokLM 
<boklm@mars-attacks.org>, <tech-kern@netbsd.org>, Thomas Klausner 
<wiz@netbsd.org>
        Subject:        Re: is there an sshfs for NetBSD ?

 

On Tue, 13 May 2003, Kamal R Prasad wrote:

> On 1052687897 seconds since the Beginning of the UNIX epoch
> Bill Studenmund wrote:

>1% or 2% is costly? See either my USENIX DMFS papaer or any of the UCLA
>work. While some ops were as bad as 4%, in general, it was hard to notice
>the layered file system. In my tests, I found (for reads & writes)  that
>on-disk layout was a more dominant performance term than layering. Plus,
>we're talking about an encrypting file system. The encryption/decryption
>will be the big performance bottleneck.

It sounded costly in terms of extra LOC that need to be executed per 
read/write operation. but maybe as you point out the overhead associated 
with disk I/O is many times more than the overhead of the layered fs.

re:- Thor,
permissions have nothing to do with the encryption mechanism. the binary 
is stored on flashdisk as an encrypted file. when the pagedaemon reads in 
a text page from the binary, it is decrypted inside the kernel. so without 
knowing the decryption key, the binary is just not usable on another 
kernel.
regards
-kamal