1 |
Grant Taylor wrote: |
2 |
> Sorry for the duplicate post. I had an email client error that |
3 |
> accidentally caused me to hit send on the window I was composing in. |
4 |
|
5 |
I figured it was something like that. ;-) |
6 |
|
7 |
> |
8 |
> On 8/20/22 1:15 PM, Dale wrote: |
9 |
>> Howdy, |
10 |
> |
11 |
> Hi, |
12 |
> |
13 |
>> Related question. Does encryption slow the read/write speeds of a |
14 |
>> drive down a fair amount? |
15 |
> |
16 |
> My experience has been the opposite. I know that it's unintuitive |
17 |
> that encryption would make things faster. But my understanding is |
18 |
> that it alters how data is read from / written to the disk such that |
19 |
> it's done in more optimized batches and / or optimized caching. |
20 |
> |
21 |
> This was so surprising that I decrypted a drive / re-encrypted a drive |
22 |
> multiple times to compare things to come to the conclusion that |
23 |
> encryption was noticeably better. |
24 |
> |
25 |
> Plus, encryption has the advantage of destroying the key rendering the |
26 |
> drive safe to use independent of the data that was on it. |
27 |
> |
28 |
> N.B. The actual encryption key is encrypted with the passphrase. The |
29 |
> passphrase isn't the encryption key itself. |
30 |
> |
31 |
>> This new 10TB drive is maxing out at about 49.51MB/s or so. |
32 |
> |
33 |
> I wonder if you are possibly running into performance issues related |
34 |
> to shingled drives. Their raw capacity comes at a performance penalty. |
35 |
|
36 |
This drive is not supposed to be SMR. It's a 10TB and according to a |
37 |
site I looked on, none of them are SMR, yet. I found another site that |
38 |
said it was CMR. So, pretty sure it isn't SMR. Nothing is 100% tho. I |
39 |
might add, it's been at about that speed since I started the backup. If |
40 |
you have a better source of info, it's a WD model WD101EDBZ-11B1DA0 drive. |
41 |
|
42 |
|
43 |
> |
44 |
>> I actually copied that from the progress of rsync and a nice sized |
45 |
>> file. It's been running over 24 hours now so I'd think buffer and |
46 |
>> cache would be well done with. LOL |
47 |
> |
48 |
> Ya, you have /probably/ exceeded the write back cache in the system's |
49 |
> memory. |
50 |
> |
51 |
>> It did pass both a short and long self test. I used cryptsetup -s 512 |
52 |
>> to encrypt with, nice password too. My rig has a FX-8350 8 core running |
53 |
>> at 4GHz CPU and 32GBs of memory. The CPU is fairly busy. A little more |
54 |
>> than normal anyway. Keep in mind, I have two encrypted drives connected |
55 |
>> right now. |
56 |
> |
57 |
> The last time I looked at cryptsetup / LUKS, I found that there was a |
58 |
> [kernel] process per encrypted block device. |
59 |
> |
60 |
> A hack that I did while testing things was to slice up a drive into |
61 |
> multiple partitions, encrypt each one, and then re-aggregate the LUKS |
62 |
> devices as PVs in LVM. This surprisingly was a worthwhile performance |
63 |
> boost. |
64 |
|
65 |
I noticed there is a kcrypt something thread running, a few actually but |
66 |
it's hard to keep up since I see it on gkrellm's top process list. The |
67 |
CPU is running at about 40% or so average but I do have mplayer, a |
68 |
couple Firefox profiles, Seamonkey and other stuff running as well. I |
69 |
still got plenty of CPU pedal left if needed. Having Ktorrent and |
70 |
qbittorrent running together isn't helping. Thinking of switching |
71 |
torrent software. Qbit does seem to use more memory tho. |
72 |
|
73 |
|
74 |
> |
75 |
>> Just curious if that speed is normal or not. |
76 |
> |
77 |
> I suspect that your drive is FAR more the bottleneck than the |
78 |
> encryption itself is. There is a chance that the encryption's access |
79 |
> pattern is exascerbating a drive performance issue. |
80 |
> |
81 |
>> Thoughts? |
82 |
> |
83 |
> Conceptually working in 512 B blocks on a drive that is natively 4 kB |
84 |
> sectors. Thus causing the drive to do lots of extra work to account |
85 |
> for the other seven 512 B blocks in a 4 kB sector. |
86 |
|
87 |
I think the 512 has something to do with key size or something. Am I |
88 |
wrong on that? If I need to use 256 or something, I can. My |
89 |
understanding was that 512 was stronger than 256 as far as the |
90 |
encryption goes. |
91 |
|
92 |
|
93 |
> |
94 |
>> P. S. The pulled drive I bought had like 60 hours on it. Dang near |
95 |
>> new. |
96 |
> |
97 |
> :-) |
98 |
|
99 |
I'm going to try some tests Rich mentioned after it is done doing its |
100 |
backup. I don't want to stop it if I can avoid it. It's about half way |
101 |
through, give or take a little. |
102 |
|
103 |
Dale |
104 |
|
105 |
:-) :-) |