1 |
Rich Freeman wrote: |
2 |
> On Mon, Aug 3, 2020 at 1:30 AM Dale <rdalek1967@×××××.com> wrote: |
3 |
>> Little update here. Rich, I think you mentioned it would slow down when it ran out of PMR space while trying to redo the shingled part. Up until now, I hadn't ran into that issue. It seems the PMR section for this drive is somewhere around 40 or 50GBs, maybe 60GBs. I hadn't had time for backups in over a week so it was a good bit larger than usual. It was around 70GBs, maybe 75. When it got close to the end of the rsync process, I noticed it slowed down quite a bit. I'd guess about half or so. Usually it runs at around 180 to 190MBs/sec for larger files. Pretty close to the end, rsync was showing around 100MBs/sec at best. It was a little over on some but mostly a little below that. Earlier in the process, it was the normal speed. |
4 |
> I doubt this particular drop is the result of SMR, assuming 100MB/s is |
5 |
> the instantaneous speed. 100MB/s is still reasonable for a hard drive |
6 |
> - on newer CMR drives I've seen the speed of dd drop from 200MB/s to |
7 |
> 100MB/s for sequential writes as the heads move from one end of the |
8 |
> drive to the other, and then it goes back up to 200MB/s if you start |
9 |
> over at the beginning (badblocks testing and so on). |
10 |
> |
11 |
> That level of drop is probably more likely to be due to filesystem |
12 |
> overhead and so on - fragmentation/etc. When SMR buffer overrun |
13 |
> occurs you REALLY hit a wall and the rates drop quite a bit more than |
14 |
> that. If it were a difference of only 50% most would probably |
15 |
> tolerate it. |
16 |
> |
17 |
> Now, if 100MB/s were an updating average across the entire run then |
18 |
> that would be a different matter, because that would mean that it was |
19 |
> running at 200MB/s for most of the run, and then probably dropping |
20 |
> much closer to 0 for a while so as to drive the overall average down |
21 |
> to 100MB/s. I'm not sure where you're getting those numbers from so I |
22 |
> don't know what period that 100MB/s reflects. For an instantaneous |
23 |
> speed I'd consider it a completely reasonable performance for a |
24 |
> typical hard drive when you're writing to a filesystem. If you were |
25 |
> using dd or maybe copies of very large files on an efficient |
26 |
> filesystem you would get better results. |
27 |
> |
28 |
|
29 |
|
30 |
I use the --progress option with rsync. It shows the copy speed, |
31 |
elapsed time etc for each file. Some files are small and the speed it |
32 |
shows isn't accurate at all because the files are just to tiny to get a |
33 |
accurate measure. I ignore that info on the smaller files. Videos |
34 |
however are larger files and sometimes can take a lot longer to copy |
35 |
over. Those tend to be more accurate. Anyway, that is where the |
36 |
numbers came from. I wish I had saved the output but sadly I had |
37 |
finished my OS updates and needed to logout and back in again. |
38 |
|
39 |
In the past, I've never seen the drive on the larger files be that slow |
40 |
even toward the end. Generally, it stays pretty close to 180MBs/sec or |
41 |
so which is what I usually get with PMR drives. Of course, the PMR |
42 |
drives don't keep doing the bumpy thing for a while when it is done |
43 |
either. Maybe it is something else but it sure did the bumpy thing a |
44 |
lot longer this time. |
45 |
|
46 |
Either way, just wanted to update that a large copy made it slow down. |
47 |
Other than the initial copy, this is the largest rsync I've ever done to |
48 |
that drive. Most are around 20, maybe 25GBs. |
49 |
|
50 |
Dale |
51 |
|
52 |
:-) :-) |