1 |
Wols Lists wrote: |
2 |
> On 27/12/2021 13:40, Michael wrote: |
3 |
>> On Monday, 27 December 2021 11:32:39 GMT Wols Lists wrote: |
4 |
>>> On 27/12/2021 11:07, Jacques Montier wrote: |
5 |
>>>> Well, i don't know if my partitions are aligned or mis-aligned... How |
6 |
>>>> could i get it ? |
7 |
>>> |
8 |
>>> fdisk would have spewed a bunch of warnings. So you're okay. |
9 |
>>> |
10 |
>>> I'm not sure of the details, but it's the classic "off by one" |
11 |
>>> problem - |
12 |
>>> if there's a mismatch between the kernel block size and the disk block |
13 |
>>> size any writes required doing a read-update-write cycle which of |
14 |
>>> course |
15 |
>>> knackered performance. I had that hit a while back. |
16 |
>>> |
17 |
>>> But seeing as fdisk isn't moaning, that isn't the problem ... |
18 |
>>> |
19 |
>>> Cheers, |
20 |
>>> Wol |
21 |
>> |
22 |
>> I also thought of misaligned boundaries when I first saw the error, |
23 |
>> but the |
24 |
>> mention of Seagate by the OP pointed me to another edge case which |
25 |
>> crept up |
26 |
>> with zstd compression on ZFS. I'm mentioning it here in case it is |
27 |
>> relevant: |
28 |
>> |
29 |
>> https://livelace.ru/posts/2021/Jul/19/unaligned-write-command/ |
30 |
>> |
31 |
> that might be of interest to me ... I'm getting system lockups but |
32 |
> it's not an SSD. I've got two IronWolves and a Barracuda. |
33 |
> |
34 |
> But I notice the OP has a Barra*C*uda. Note the different spelling. |
35 |
> That's a shingled drive I believe, which shouldn't make a lot of |
36 |
> difference in light usage, but you don't want to hammer it! |
37 |
> |
38 |
> Cheers, |
39 |
> Wol |
40 |
> |
41 |
> |
42 |
|
43 |
I don't recall seeing this mentioned but this may be part of the issue |
44 |
unless I'm missing something that rules this out. Could it be a drive |
45 |
is a SMR drive? I recently made a new backup after wiping out the |
46 |
drive. I know the backup drive is a SMR drive. At first, it copied at |
47 |
a fairly normal speed but after a short time frame, it started slowing |
48 |
down. At times, it would do only about 50 to 60MBs/sec. It started out |
49 |
at well over 100MBs/sec which is fairly normal for this rig. I would |
50 |
stop the copy process, let it catch up and restart just to give it some |
51 |
time to process. I can't say it was any faster that way tho. |
52 |
|
53 |
The way I noticed my drive was SMR, I could feel the heads going back |
54 |
and forth by putting my hand on the enclosure. It had a bumpy feel to |
55 |
it. You can't really hear it tho. If you can feel those little bumps |
56 |
even when the drive isn't mounted, I'd be thinking it is a SMR drive. |
57 |
There are also sites that you can look this sort of thing up on too. If |
58 |
needed, I can go dig out some links. |
59 |
|
60 |
Just thought it worth a mention. |
61 |
|
62 |
Dale |
63 |
|
64 |
:-) :-) |