Re: Slow Performance on Encrypted svnd

2007-11-18 Thread Die Gestalt
On Nov 18, 2007 2:34 AM, Ted Unangst [EMAIL PROTECTED] wrote: On 11/17/07, Die Gestalt [EMAIL PROTECTED] wrote: I'd like to be explained why you have to do all these steps to encrypt a partition. Isn't it possible to have some sort of filter driver that simply ciphers and deciphers data as

Re: Slow Performance on Encrypted svnd

2007-11-17 Thread Jona Joachim
On Fri, 16 Nov 2007 14:34:22 -0800, Ted Unangst wrote: On 11/16/07, Nick Guenther [EMAIL PROTECTED] wrote: On 11/16/07, Ted Unangst [EMAIL PROTECTED] wrote: instead of pondering problems with using the whole disk, you could just use svnd with a file. Yeah but doesn't this hint at some

Re: Slow Performance on Encrypted svnd

2007-11-17 Thread Chris Kuethe
On Nov 17, 2007 4:24 AM, Jona Joachim [EMAIL PROTECTED] wrote: Who says the tool is used the wrong way? You? I think when OpenBSD developers go and write a howto about how to use a tool in a certain way then you can be sure it's meant to be used this way. Please refer to:

Re: Slow Performance on Encrypted svnd

2007-11-17 Thread Die Gestalt
On Nov 17, 2007 6:48 PM, Chris Kuethe [EMAIL PROTECTED] wrote: On Nov 17, 2007 4:24 AM, Jona Joachim [EMAIL PROTECTED] wrote: Who says the tool is used the wrong way? You? I think when OpenBSD developers go and write a howto about how to use a tool in a certain way then you can be sure

Re: Slow Performance on Encrypted svnd

2007-11-17 Thread Ted Unangst
On 11/17/07, Jona Joachim [EMAIL PROTECTED] wrote: On Fri, 16 Nov 2007 14:34:22 -0800, Ted Unangst wrote: it hints at using tools the wrong way leading to poor results. Who says the tool is used the wrong way? You? me.

Re: Slow Performance on Encrypted svnd

2007-11-17 Thread Ted Unangst
On 11/17/07, Die Gestalt [EMAIL PROTECTED] wrote: I'd like to be explained why you have to do all these steps to encrypt a partition. Isn't it possible to have some sort of filter driver that simply ciphers and deciphers data as it is received, a little bit like a GEOM plugin? anything is

Re: Slow Performance on Encrypted svnd

2007-11-16 Thread Ted Unangst
instead of pondering problems with using the whole disk, you could just use svnd with a file.

Re: Slow Performance on Encrypted svnd

2007-11-16 Thread Die Gestalt
On Nov 16, 2007 12:36 AM, Clint Pachl [EMAIL PROTECTED] wrote: Nonetheless, the bonnie++ results may provide some insight to the problem for an experienced guru. What I found interesting is that the CPU usage is really low for writes and rewrites when svnd is backed by the whole disk. This is

Re: Slow Performance on Encrypted svnd

2007-11-16 Thread Nick Guenther
On 11/16/07, Ted Unangst [EMAIL PROTECTED] wrote: instead of pondering problems with using the whole disk, you could just use svnd with a file. Yeah but doesn't this hint at some horrible inefficiency in the stack somewhere? -Nick

Re: Slow Performance on Encrypted svnd

2007-11-16 Thread bofh
On Nov 16, 2007 1:32 PM, Ted Unangst [EMAIL PROTECTED] wrote: instead of pondering problems with using the whole disk, you could just use svnd with a file. Well, I think he just found the itch. Now the question is whether he'll scratch it, or will someone else find it interesting enough to

Re: Slow Performance on Encrypted svnd

2007-11-16 Thread Ted Unangst
On 11/16/07, Nick Guenther [EMAIL PROTECTED] wrote: On 11/16/07, Ted Unangst [EMAIL PROTECTED] wrote: instead of pondering problems with using the whole disk, you could just use svnd with a file. Yeah but doesn't this hint at some horrible inefficiency in the stack somewhere? it hints at

Re: Slow Performance on Encrypted svnd

2007-11-15 Thread Nick Guenther
On 11/14/07, Clint Pachl [EMAIL PROTECTED] wrote: Reading through the archives I have found several people say that encrypting via an svnd device isn't much slower than writing directly to a raw unencrypted disk. While I found this to be true for svnd devices backed by files, svnd devices

Re: Slow Performance on Encrypted svnd

2007-11-15 Thread Die Gestalt
On Nov 15, 2007 3:22 PM, Nick Guenther [EMAIL PROTECTED] wrote: This is really really really weird. You'd think that files, having the filesystem to go through before getting to the disk, would necessarily be slower. There must be some kind of weirdness with the thing. I concur. My

Re: Slow Performance on Encrypted svnd

2007-11-15 Thread Clint Pachl
I experimented with a few more things, but nothing helped. Someone said run a bonnie++ benchmark to verify the performance. bonnie++ basically told me what dd did, that svnd backed by a file is slow and svnd backed by a disk or partition is floppy disk slow. Nonetheless, the bonnie++ results

Re: Slow Performance on Encrypted svnd

2007-11-14 Thread knitti
Instead of e.g. /dev/sd0a try /dev/rsd0a. I didn't try with svnd, but when copying partitions with dd I use this. --knitti

Re: Slow Performance on Encrypted svnd

2007-11-14 Thread Clint Pachl
knitti wrote: Instead of e.g. /dev/sd0a try /dev/rsd0a. I didn't try with svnd, but when copying partitions with dd I use this. I tried that, but like I said fdisk complained when the svnd device is associated with the raw direct access disk device. For example # vnconfig -k svnd0

Re: Slow Performance on Encrypted svnd

2007-11-14 Thread Clint Pachl
knitti wrote: On 11/14/07, Clint Pachl [EMAIL PROTECTED] wrote: knitti wrote: Instead of e.g. /dev/sd0a try /dev/rsd0a. I didn't try with svnd, but when copying partitions with dd I use this. I tried that, but like I said fdisk complained when the svnd device is associated

Re: Slow Performance on Encrypted svnd

2007-11-14 Thread knitti
On 11/14/07, Clint Pachl [EMAIL PROTECTED] wrote: knitti wrote: Instead of e.g. /dev/sd0a try /dev/rsd0a. I didn't try with svnd, but when copying partitions with dd I use this. I tried that, but like I said fdisk complained when the svnd device is associated with the raw direct access