* ecryptfs with aes-ni slower bug
@ 2012-02-15 10:43 Stefan Dröge
2012-02-15 10:48 ` Tyler Hicks
0 siblings, 1 reply; 3+ messages in thread
From: Stefan Dröge @ 2012-02-15 10:43 UTC (permalink / raw)
To: ecryptfs
Hi all,
A while ago I read at phoronix, that ecryptfs is actually slower when
having loaded the aesni-intel kernel module.
Out of curiosiy I checked whether this problem still exists in the
Ubuntu 12.04 alpha2, and it does.
I tried to find infos to this in the mailing list archive, but I found nothing.
So my question: Is somebody working on this?
Regards, Stefan
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: ecryptfs with aes-ni slower bug
2012-02-15 10:43 ecryptfs with aes-ni slower bug Stefan Dröge
@ 2012-02-15 10:48 ` Tyler Hicks
2012-02-15 16:16 ` Dustin Kirkland
0 siblings, 1 reply; 3+ messages in thread
From: Tyler Hicks @ 2012-02-15 10:48 UTC (permalink / raw)
To: Stefan Dröge; +Cc: ecryptfs
[-- Attachment #1: Type: text/plain, Size: 680 bytes --]
On 2012-02-15 11:43:21, Stefan Dröge wrote:
> Hi all,
> A while ago I read at phoronix, that ecryptfs is actually slower when
> having loaded the aesni-intel kernel module.
> Out of curiosiy I checked whether this problem still exists in the
> Ubuntu 12.04 alpha2, and it does.
> I tried to find infos to this in the mailing list archive, but I found nothing.
>
> So my question: Is somebody working on this?
No, not currently. I've been focusing on stability rather than
performance.
I'd love for someone else to become interested in the problem and dig
in. Otherwise, it will have to wait a while longer until I get some free
cycles to look into it.
Tyler
[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: ecryptfs with aes-ni slower bug
2012-02-15 10:48 ` Tyler Hicks
@ 2012-02-15 16:16 ` Dustin Kirkland
0 siblings, 0 replies; 3+ messages in thread
From: Dustin Kirkland @ 2012-02-15 16:16 UTC (permalink / raw)
To: Tyler Hicks; +Cc: Stefan Dröge, ecryptfs
On Wed, Feb 15, 2012 at 4:48 AM, Tyler Hicks <tyhicks@canonical.com> wrote:
> On 2012-02-15 11:43:21, Stefan Dröge wrote:
>> Hi all,
>> A while ago I read at phoronix, that ecryptfs is actually slower when
>> having loaded the aesni-intel kernel module.
>> Out of curiosiy I checked whether this problem still exists in the
>> Ubuntu 12.04 alpha2, and it does.
>> I tried to find infos to this in the mailing list archive, but I found nothing.
>>
>> So my question: Is somebody working on this?
>
> No, not currently. I've been focusing on stability rather than
> performance.
>
> I'd love for someone else to become interested in the problem and dig
> in. Otherwise, it will have to wait a while longer until I get some free
> cycles to look into it.
I have made contact with an engineer at Intel working on AES-NI who
agreed to take a look at this. That was several weeks ago. I'll
check in with them and report back if there's any progress.
--
:-Dustin
Dustin Kirkland
Chief Architect
Gazzang, Inc.
www.gazzang.com
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2012-02-15 16:16 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2012-02-15 10:43 ecryptfs with aes-ni slower bug Stefan Dröge
2012-02-15 10:48 ` Tyler Hicks
2012-02-15 16:16 ` Dustin Kirkland
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox