1 |
Rich Freeman wrote: |
2 |
> On Sat, Aug 20, 2022 at 3:15 PM Dale <rdalek1967@×××××.com> wrote: |
3 |
>> Related question. Does encryption slow the read/write speeds of a drive |
4 |
>> down a fair amount? This new 10TB drive is maxing out at about |
5 |
>> 49.51MB/s or so. |
6 |
> Encryption won't impact the write speeds themselves of course, but it |
7 |
> could introduce a CPU bottleneck. If you don't have any cores pegged |
8 |
> at 100% though I'd say this isn't happening. On x86 encrypting a hard |
9 |
> drive shouldn't be a problem. I have seen it become a bottleneck on |
10 |
> something like a Pi4 if the encryption isn't directly supported in |
11 |
> hardware by the CPU. |
12 |
> |
13 |
> 50MB/s is reasonable if you have an IOPS-limited workload. It is of |
14 |
> course a bit low for something that is bandwidth-limited. If you want |
15 |
> to test that I'm not sure rsync is a great way to go. I'd pause that |
16 |
> (ctrl-z is fine), then verify that all disk IO goes to zero (might |
17 |
> take 30s to clear out the cache). Then I'd use "time dd bs=1M |
18 |
> count=20000 if=/dev/zero of=/path/to/drive/test" to measure how long |
19 |
> it takes to create a 20GB file. Oh, this assumes you're not using a |
20 |
> filesystem that can detect all-zeros and compress or make the file |
21 |
> sparse. If you get crazy-fast results then I'd do a test like copying |
22 |
> a single large file with cp and timing that. |
23 |
> |
24 |
> Make sure your disk has no IO before testing. If you have two |
25 |
> processes accessing at once then you're going to get a huge drop in |
26 |
> performance on a spinning disk. That includes one writing process and |
27 |
> one reading one, unless the reads all hit the cache. |
28 |
> |
29 |
|
30 |
Kinda picking random reply. |
31 |
|
32 |
I finally got the full backups done and have updated a couple times, new |
33 |
drive and old drives. Someone mentioned atop and I gave it a try. I |
34 |
noticed the drive parts that is either being read from or written to |
35 |
show up in red and a high amount of use. After doing some google |
36 |
searching, red means really, really busy. Makes sense. So, the drives |
37 |
are apparently just maxing out. |
38 |
|
39 |
I also noticed something else. Given that my internet is so much faster |
40 |
now, that also puts a load on disk I/O. Heck, the internet alone can |
41 |
almost max out the drive I/O. On top of that I'm watching a video on my |
42 |
TV. So, doing backups, watching TV and downloading stuff over a really |
43 |
fast internet connection, no wonder things were a little slow. |
44 |
|
45 |
I also ran this on the new 10TB drive and a older SMR 8TB drive. This |
46 |
is about normal, ish. sdl is the 8TB and sdm is the 10TB. |
47 |
|
48 |
|
49 |
root@fireball / # hdparm -tT /dev/sdl |
50 |
|
51 |
/dev/sdl: |
52 |
Timing cached reads: 8814 MB in 2.00 seconds = 4410.88 MB/sec |
53 |
Timing buffered disk reads: 558 MB in 3.00 seconds = 185.76 MB/sec |
54 |
root@fireball / # hdparm -tT /dev/sdm |
55 |
|
56 |
/dev/sdm: |
57 |
Timing cached reads: 8992 MB in 2.00 seconds = 4499.72 MB/sec |
58 |
Timing buffered disk reads: 612 MB in 3.01 seconds = 203.47 MB/sec |
59 |
root@fireball / # |
60 |
|
61 |
I have some other drives that are slower and a couple that are faster. |
62 |
So, I guess it about averages out. |
63 |
|
64 |
I have another question. I notice that the drive activity light stays |
65 |
on a lot more, downloading/uploading faster etc etc. Will that cause my |
66 |
drives to age faster or is that designed in? I try to get the higher |
67 |
grade of drives, avoid those built for light duty stuff. Of course, |
68 |
they not designed to be used by NASA either. :/ |
69 |
|
70 |
By the way, that new backup drive, filling up fast. My storage |
71 |
partition is too. This fast internet is causing, issues. ROFL Time to |
72 |
hunt up a deal on another 8TB or 10TB drive to add on. Dang, my case is |
73 |
about full. I really need a NAS or something. :-D |
74 |
|
75 |
Dale |
76 |
|
77 |
:-) :-) |