1 |
On Fri, Jun 21, 2013 at 3:28 AM, Rich Freeman <rich0@g.o> wrote: |
2 |
> On Fri, Jun 21, 2013 at 3:31 AM, Duncan <1i5t5.duncan@×××.net> wrote: |
3 |
>> So with 4k block sizes on a 5-device raid6, you'd have 20k stripes, 12k |
4 |
>> in data across three devices, and 8k of parity across the other two |
5 |
>> devices. |
6 |
> |
7 |
> With mdadm on a 5-device raid6 with 512K chunks you have 1.5M in a |
8 |
> stripe, not 20k. If you modify one block it needs to read all 1.5M, |
9 |
> or it needs to read at least the old chunk on the single drive to be |
10 |
> modified and both old parity chunks (which on such a small array is 3 |
11 |
> disks either way). |
12 |
> |
13 |
|
14 |
Hi Rich, |
15 |
I've been rereading everyone's posts as well as trying to collect |
16 |
my own thoughts. One question I have at this point, being that you and |
17 |
I seem to be the two non-RAID1 users (but not necessarily devotees) at |
18 |
this time, is what chunk size, stride & stripe width with you are |
19 |
using? Are you currently using 512K chunks on your RAID5? If so that's |
20 |
potentially quite different than my 16K chunk RAID6. The more I read |
21 |
through this thread and other things on the web the more I am |
22 |
concerned that 16K chunks has possibly forced far more IO operations |
23 |
that really makes sense for performance. Unfortunately there's no easy |
24 |
way to me to really test this right now as the RAID6 uses the whole |
25 |
drive. However for every 512K I want to get off the drive you might |
26 |
need 1 chuck whereas I'm going to need what, 32 chunks? That's got to |
27 |
be a lot more IO operations on my machine isn't it? |
28 |
|
29 |
For clarity, I'm a 16K chunk, stride of 4K, stripe of 12K: |
30 |
|
31 |
c2RAID6 ~ # tune2fs -l /dev/md3 | grep RAID |
32 |
Filesystem volume name: RAID6root |
33 |
RAID stride: 4 |
34 |
RAID stripe width: 12 |
35 |
c2RAID6 ~ # |
36 |
|
37 |
c2RAID6 ~ # cat /proc/mdstat |
38 |
Personalities : [linear] [raid0] [raid1] [raid10] [raid6] [raid5] [raid4] |
39 |
md3 : active raid6 sdb3[9] sdf3[5] sde3[6] sdd3[7] sdc3[8] |
40 |
1452264480 blocks super 1.2 level 6, 16k chunk, algorithm 2 [5/5] [UUUUU] |
41 |
|
42 |
unused devices: <none> |
43 |
c2RAID6 ~ # |
44 |
|
45 |
As I understand one of your earlier responses I think you are using |
46 |
4K sector drives, which again has that extra level of complexity in |
47 |
terms of creating the partitions initially, but after that should be |
48 |
fairly straight forward to use. (I think) That said there are |
49 |
trade-offs between RAID5 & RAID6 but have you measured speeds using |
50 |
anything like the dd method I posted yesterday, or any other way that |
51 |
we could compare? |
52 |
|
53 |
As I think Duncan asked about storage usage requirements in another |
54 |
part of this thread I'll just document it here. The machine serves |
55 |
main 3 purposes for me: |
56 |
|
57 |
1) It's my day in, day out desktop. I run almostly totally Gentoo |
58 |
64-bit stable unless I need to keyword a package to get what I need. |
59 |
Over time I tend to let my keyworded packages go stable if they are |
60 |
working for me. The overall storage requirements for this, including |
61 |
my home directory, typically don't run over 50GB. |
62 |
|
63 |
2) The machine runs 3 Windows VMs every day - 2 Win 7 & 1 Win XP. |
64 |
Total storage for the basic VMs is about 150GB. XP is just for things |
65 |
like NetFlix. These 3 VMs typically have allocated 9 cores allocated |
66 |
to them (6+2+1) leaving 3 for Gentoo to run the hardware, etc. The 6 |
67 |
core VM is often using 80-100% of its CPUs sustained for times. (hours |
68 |
to days.) It's doing a lot of stock market math... |
69 |
|
70 |
3) More recently, and really the reason to consolidate into a single |
71 |
RAID of any type, I have about 900GB of mp4s which has been on an |
72 |
external USB drive, and backed up to a second USB drive. However this |
73 |
is mostly storage. We watch most of this video on the TV using the |
74 |
second copy drive hooked directly to the TV or copied onto Kindles. |
75 |
I've been having to keep multiple backups of this outside the machine |
76 |
(poor man's RAID1 - two separate USB drives hooked up one at a time!) |
77 |
;-) I'd rather just keep it safe on the RAID 6, That said, I've not |
78 |
yet put it on the RAID6 as I have these performance issues I'd like to |
79 |
solve first. (If possible. Duncan is making me worry that they cannot |
80 |
be solved...) |
81 |
|
82 |
Lastly, even if I completely buy into Duncan's well formed reasons |
83 |
about why RAID1 might be faster, using 500GB drives I see no single |
84 |
RAID solution for me other than RAID5/6. The real RAID1/RAID6 |
85 |
comparison from a storage standpoint would be a (conceptual) 3-drive |
86 |
RAID6 vs 3 drive RAID1. Both create 500GB of storage and can |
87 |
(conceptually) lose 2 drives and still recover data. However adding |
88 |
another drive to the RAID1 gains you more speed but no storage (buying |
89 |
into Duncan's points) vs adding storage to the RAID6 and probably |
90 |
reducing speed. As I need storage what other choices do I have? |
91 |
|
92 |
Answering myself, take the 5 drives, create two RAIDS - a 500GB |
93 |
2-drive RAID1 for the system + VMs, and then a 3-drive RAID5 for video |
94 |
data maybe? I don't know... |
95 |
|
96 |
Or buy more hardware and do a 2 drive SSD RAID1 for the system, or |
97 |
a hardware RAID controller, etc. The options explode if I start buying |
98 |
more hardware. |
99 |
|
100 |
Also, THANKS TO EVERYONE for the continued conversation. |
101 |
|
102 |
Cheers, |
103 |
Mark |