[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Bug#796742: marked as done (general: system takes a hit when encryption used)

Your message dated Sun, 23 Aug 2015 21:37:07 +0100
with message-id <1440362227.2526.1.camel@decadent.org.uk>
and subject line Re: Bug#796742: general: system takes a hit when encryption used
has caused the Debian Bug report #796742,
regarding general: system takes a hit when encryption used
to be marked as done.

This means that you claim that the problem has been dealt with.
If this is not the case it is now your responsibility to reopen the
Bug report if necessary, and/or fix the problem forthwith.

(NB: If you are a system administrator and have no idea what this
message is talking about, this may indicate a serious mail system
misconfiguration somewhere. Please contact owner@bugs.debian.org
immediately.)


-- 
796742: http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=796742
Debian Bug Tracking System
Contact owner@bugs.debian.org with problems
--- Begin Message --- 
Package: general
Severity: important
Tags: lfs

modern day systems have 6GB/sec connections and GBs of RAM and Ghz of speed.
There is simply no reason that ANY cipher algorithm should slow a system to a
crawl.

Cached data or not.

Yet this is clearly the case.I tried both EncFS and GostCrypt(whole volume
encryption) and am getting the same results here on SATA 6GB/sec connection
with drives that support such speeds.

I am lucky to get ~100MB/sec throughput rates, and they are limited further
when using encryption by a factor of 4-5X.

This simply should NOT BE. The data can be encrypted in RAM or through a disk
buffer in such a case as a disk-to-disk copy.There is no need for excessive
disk writes during the encryption process, especially when using ext3+ as a
base filesystem. Ext3+ systems are known for error and power loss/reset
resiliency. Am I missing something here or did I find a major bug?

AES and SHA can be enhanced even further by use of OpenCL and SSE special
operations that newer CPUs have.And surely the TPM chip has some input here as
well.Or at least it SHOULD.



-- System Information:
Debian Release: stretch/sid
  APT prefers testing
  APT policy: (500, 'testing')
Architecture: amd64 (x86_64)
Foreign Architectures: i386

Kernel: Linux 4.0.0-2-amd64 (SMP w/4 CPU cores)
Locale: LANG=en_US.UTF-8, LC_CTYPE=en_US.UTF-8 (charmap=UTF-8)
Shell: /bin/sh linked to /bin/dash
Init: systemd (via /run/systemd/system)

--- End Message ---
--- Begin Message --- 
This is a complaint, not an actionable bug report.

Ben.

-- 
Ben Hutchings
You can't have everything.  Where would you put it?

Attachment: signature.asc
Description: This is a digitally signed message part


--- End Message ---
Reply to: