Reputation
211
Top tag
Next privilege 250 Rep.
View close votes
Badges
2 9
Newest
 Informed
Impact
~3k people reached

  • 0 posts edited
  • 0 helpful flags
  • 15 votes cast
Mar
19
comment Redundancy level on a per file basis with BTRFS?
“Raid5 for metadata of course.” – Metadata is important and relatively small. It would have a very high importance/size ratio so wouldn't you want RAID 1 for metadata?
Mar
18
awarded  Informed
Mar
18
awarded  Yearling
Mar
18
revised Why is RAID 1+6 not a more common layout?
Further to my previous edit, there are some subtle variations when degraded; pinned-down the ranges to specific values; tried to further clarify some other points.
Mar
17
comment What’s the point in having “www” in a URL?
http://example.com/ is fully qualified whereas www.example.com is not. I prefer the fully qualified approach because it is always recognisable as a URL regardless of whether it's https://example.uk/ or https://blog.example.eu/ or whatever. It is consistent with specifying the protocol of a secure site as HTTPS; www.example.com is just a domain and says nothing about which protocol one should use to access it.
Mar
15
comment Why is RAID 1+6 not a more common layout?
@JamesRyan: Please could you give more details on what implementation you used, what drives you used, in which configurations, with what benchmarking methods? Did you try both a RAID 6 array of 6 RAID 1 pairs and a RAID 0 array of 4 RAID 1 triples with the same 12 drives and chunk size? Was it a software RAID?
Mar
15
comment Why is RAID 1+6 not a more common layout?
@JamesRyan: This is not second-hand information. The theoretical outcomes are derived from the fundamentals of how standard RAID levels work. All that's needed for the theory is an understanding of how RAID works and an understanding of logic and mathematical derivation. If these calculations were done by someone else then I would of-course state this and provide links for reference if possible. Note that there are many ways in which a practical RAID 1+6 implementation can be suboptimal, but different implementations will vary. What I'd like to know is why your practical test doesn't concur.
Mar
15
comment Why is RAID 1+6 not a more common layout?
“For 4, 3, 2, 1 chunks-worth respectively, the write amplification factors are (6×2)/4 = 3, (5×2)/3 = 3.33̰, (4×2)/2 = 4, (3×2)/1 = 6, giv…” – Correction: This was forgetting reads; taking the reads into consideration, the write throughput amplification factors are (6×2 + 0)/4 = 3, (5×2 + 1)/3 = 3.67̰, (4×2 + 2)/2 = 5, (3×2 + 2)/1 = 8, giving maximum write throughputs of 4×, 3.27̰×, 2.4×, 1.5×. I derive the general RAID 1+6 write throughput amplification factor formula to be ((v + 2)n₁ + min [2, n₆ - (v + 2)])/v where v is the virtual number of chunks, and n₆×n₁ is the RAID 1+6 layout (6×2).
Mar
14
revised Why is RAID 1+6 not a more common layout?
Corrected that the reads aren't multiplied by n₁ like the writes are; squeezed tables into 80 character width.
Mar
14
comment Why is RAID 1+6 not a more common layout?
@JamesRyan: “no that is incorrect.” – Actually we were both incorrect, but there's some truth in what we both say. It turns out that write amplification is far more complicated when considering chunk and write sizes. I was talking solely about write throughput amplification (regarding large writes) whereas you may be talking about write seek amplification (significant for small writes). Sorry for the confusion! I hadn't noticed 'til now that these 2 things behave very differently mathematically – see my answer for details.
Mar
14
awarded  Teacher
Mar
14
revised Why is RAID 1+6 not a more common layout?
The 2 normal RAID 1 pairs, of-course, also have a total of 4 drives, so it's actually 50–50.
Mar
14
answered Why is RAID 1+6 not a more common layout?
Mar
12
awarded  Notable Question
Mar
12
comment Why is RAID 1+6 not a more common layout?
So synonymous with write amplification. Please see my comments in the question's main comment section about that. Particularly this one, i.e. when writing a full stripe you can just clobber the whole stripe, including the parity.
Mar
12
comment Why is RAID 1+6 not a more common layout?
If a RAID 6 array of 6 identical 1TB drives is unable to write all 4TB of storage data in the time that it takes for the slowest drive to write its 6th of the array data, then this is not a theoretical limitation but a limitation in the implementation. Maybe the RAID controller is the write throughput bottleneck due to not computing parity fast enough. Software RAID on a slow processor would also incur this write penalty. This is a different matter because not all implementations will have a processing bottleneck (especially if the parity computations are done on a dedicated ASIC).
Mar
12
revised Why is RAID 1+6 not a more common layout?
Completed calculations for the splitting-off scenario; 2 minor corrections.
Mar
12
revised Why is RAID 1+6 not a more common layout?
Extended the 12-drive example to evaluate using triple mirroring for backups.
Mar
12
comment Why is RAID 1+6 not a more common layout?
I've just realised that RAID 1+6 also allows you to split-off for backup, simply by freezing and removing 1 of each drive of all but 2 of the RAID 1 pairs, and while doing so, it still has far better reliability when degraded than the degraded RAID 1+0 array! :-D (Also, I've just noticed and read your edit.)
Mar
12
comment Why is RAID 1+6 not a more common layout?
Oh, I see what you mean. The triple mirrors allow you to simply remove a clone and do a backup. Okay, I didn't think of that. I was only thinking about backups done at a higher level such as taking an atomic snapshot on a copy-on-write filesystem then copying that snapshot elsewhere. Can you not use RAID 1+6 for multisite mirroring in the same way that you did for RAID 6+1? I.e. have multisite RAID 1 arrays in a RAID 6 array. (Btw., I've been interpreting ‘DR’ as ‘disaster recovery’, but it could be a couple of other things. I take it that by ‘RG’ you mean ‘RAID group’. Can you confirm these?)