Is this server strategy reckless and/or insane?
-
@dashrender said in Is this server strategy reckless and/or insane?:
@creayt said in Is this server strategy reckless and/or insane?:
@dustinb3403 said in Is this server strategy reckless and/or insane?:
@creayt said in Is this server strategy reckless and/or insane?:
These servers are 100% SSD, fortunately/unfortunately?
Ok than OBR5 the entire thing, and install Hyper-V to the array. . .
Read an article, I think by Scott, a few years ago that said OBR10 was the OB way to go in almost all cases, may be remembering that wrong. Scott/all, if I'm going to OBR the entire box, is 5 a better option than 10?
Because math - you can use RAID 5 on SSD and be fine. OBR10 is mostly meant for spinning drives due to failure situations.
Gotcha, thank you!
-
A good option here might be to remove the two 256 GB drives and replace them with one or two 1 TB drives. Replacing them with one, will mean you can get OBR5 and loose no space from that array, but you will have to give up some of that space, probably around 100 GB to Hyper-V and the OS install for your VM. If you can afford to loose that from your storage capacity (you would still have 5 TB - 100 GB = 4.9 TB for storage).
-
@dashrender said in Is this server strategy reckless and/or insane?:
Because math - you can use RAID 5 on SSD and be fine. OBR10 is mostly meant for spinning drives due to failure situations.
Not really.... sort of.
RAID10 came into existence because of drive failures. But it does offer performance benefits as well. So based on the requirements of Storage vs Performance does this need to be considered.
-
@dustinb3403 said in Is this server strategy reckless and/or insane?:
@dashrender said in Is this server strategy reckless and/or insane?:
Because math - you can use RAID 5 on SSD and be fine. OBR10 is mostly meant for spinning drives due to failure situations.
Not really.... sort of.
RAID10 came into existence because of drive failures. But it does offer performance benefits as well. So based on the requirements of Storage vs Performance does this need to be considered.
updated post
-
@dashrender said in Is this server strategy reckless and/or insane?:
@creayt said in Is this server strategy reckless and/or insane?:
@dustinb3403 said in Is this server strategy reckless and/or insane?:
@creayt said in Is this server strategy reckless and/or insane?:
These servers are 100% SSD, fortunately/unfortunately?
Ok than OBR5 the entire thing, and install Hyper-V to the array. . .
Read an article, I think by Scott, a few years ago that said OBR10 was the OB way to go in almost all cases, may be remembering that wrong. Scott/all, if I'm going to OBR the entire box, is 5 a better option than 10?
Because math - you can use RAID 5 on SSD and be fine. OBR10 is mostly meant for spinning drives due to failure situations, large storage pools, and performance.
Are sequential reads WAY, WAY, WAY slower w/ Raid 5 than Raid 0 and Raid 10 though? That's what it's looking like in my initial benchmarking ( still underway ).
Looks like things are more than twice as fast w/ 0 and 10 in the first test using Crystal DiskMark.
-
@creayt said in Is this server strategy reckless and/or insane?:
@dashrender said in Is this server strategy reckless and/or insane?:
@creayt said in Is this server strategy reckless and/or insane?:
@dustinb3403 said in Is this server strategy reckless and/or insane?:
@creayt said in Is this server strategy reckless and/or insane?:
These servers are 100% SSD, fortunately/unfortunately?
Ok than OBR5 the entire thing, and install Hyper-V to the array. . .
Read an article, I think by Scott, a few years ago that said OBR10 was the OB way to go in almost all cases, may be remembering that wrong. Scott/all, if I'm going to OBR the entire box, is 5 a better option than 10?
Because math - you can use RAID 5 on SSD and be fine. OBR10 is mostly meant for spinning drives due to failure situations, large storage pools, and performance.
Are sequential reads WAY, WAY, WAY slower w/ Raid 5 than Raid 0 and Raid 10 though? That's what it's looking like in my initial benchmarking ( still underway ).
Looks like things are more than twice as fast w/ 0 and 10 in the first test.
RAID0 gives you N-Drives as much read and write performance, and sacrifices no storage amount for it.
RIAD10 gives you N-Drives Read performance and N/2 Write performance.
-
RAID 5 gives you N-1 Read and worse for write.
-
@dashrender said in Is this server strategy reckless and/or insane?:
RAID 5 gives you N-1 Read and worse for write.
No, all RAID gives you N reads.
-
@scottalanmiller said in Is this server strategy reckless and/or insane?:
@dashrender said in Is this server strategy reckless and/or insane?:
RAID 5 gives you N-1 Read and worse for write.
No, all RAID gives you N reads.
Is the explanation for slower reads for Raid 5 because it's doing other stuff on the drives while trying to read ( like writing the parity data ), or should it be simliar to a Raid 0 of the same number of drives?
-
@creayt said in Is this server strategy reckless and/or insane?:
@scottalanmiller said in Is this server strategy reckless and/or insane?:
@dashrender said in Is this server strategy reckless and/or insane?:
RAID 5 gives you N-1 Read and worse for write.
No, all RAID gives you N reads.
Is the explanation for slower reads for Raid 5 because it's doing other stuff on the drives while trying to read ( like writing the parity data ), or should it be simliar to a Raid 0 of the same number of drives?
Strangely enough on this hardware a Raid 0 of just 2 of these SSDs dramatically outperforms a Raid 5 of 5 of the same drives for reads in my first test ( 500 MiB ), as in 1 GB/s faster Seq Q32TI and almost 3 times faster Seq in Crystal, will post the full results in a sec.
-
@creayt said in Is this server strategy reckless and/or insane?:
@creayt said in Is this server strategy reckless and/or insane?:
@scottalanmiller said in Is this server strategy reckless and/or insane?:
@dashrender said in Is this server strategy reckless and/or insane?:
RAID 5 gives you N-1 Read and worse for write.
No, all RAID gives you N reads.
Is the explanation for slower reads for Raid 5 because it's doing other stuff on the drives while trying to read ( like writing the parity data ), or should it be simliar to a Raid 0 of the same number of drives?
Strangely enough on this hardware a Raid 0 of just 2 of these SSDs dramatically outperforms a Raid 5 of 5 of the same drives for reads, as in 1 GB/s faster Seq Q32TI and almost 3 times faster Seq in Crystal, will post the full results in a sec.
THat's a controller problem, not a RAID problem. That means that the controller is oversaturated.
-
RAID is RAID, the math is trivial. What gets hard is figuring out what is wrong with a controller, when a RAID implementation is bad, when a cache is kicking in and so forth.
-
Ok these aren't apples to apples, some of the numbers are from the previous config so I'm not saying the Raid 5 to Raid 0 / 10 differences are exactly what they'd be w/ the same number of drives, but the single drive and 2 drive Raid 0 are hopefully helpful in predicting the performance characteristics of 0 at each quantity.
-
We all understand that there are differences with different RAID types.
The point of the matter is you opt'd for RAID0 because you believe you have a need for all of the IOPS in the world, yet don't care about backups.
But you are missing critical pieces of this design like virtualization, ram cache etc to get better, safer results.
-
@dustinb3403 said in Is this server strategy reckless and/or insane?:
We all understand that there are differences with different RAID types.
The point of the matter is you opt'd for RAID0 because you believe you have a need for all of the IOPS in the world, yet don't care about backups.
But you are missing critical pieces of this design like virtualization, ram cache etc to get better, safer results.
Are IOPS what you want for heavy duty users are making database writes concurrently all day long? I don't know much about drive characteristics/performance other than the basic throughput stuff. Because backup is streamed out in realtime that's taken care of as far as I'm concerned, part of what makes Raid 0 a candidate at least.
-
@creayt said in Is this server strategy reckless and/or insane?:
@dustinb3403 said in Is this server strategy reckless and/or insane?:
We all understand that there are differences with different RAID types.
The point of the matter is you opt'd for RAID0 because you believe you have a need for all of the IOPS in the world, yet don't care about backups.
But you are missing critical pieces of this design like virtualization, ram cache etc to get better, safer results.
Are IOPS what you want for heavy duty users are making database writes concurrently all day long? I don't know much about drive characteristics/performance other than the basic throughput stuff. Because backup is streamed out in realtime that's taken care of as far as I'm concerned, part of what makes Raid 0 a candidate at least.
Yes IOPS are the consideration you need to be looking at. What has yet to be answered is how active is this database going to actually be?
Will you have 10,000 people/processes constantly making changes?
-
@dustinb3403 said in Is this server strategy reckless and/or insane?:
@creayt said in Is this server strategy reckless and/or insane?:
@dustinb3403 said in Is this server strategy reckless and/or insane?:
We all understand that there are differences with different RAID types.
The point of the matter is you opt'd for RAID0 because you believe you have a need for all of the IOPS in the world, yet don't care about backups.
But you are missing critical pieces of this design like virtualization, ram cache etc to get better, safer results.
Are IOPS what you want for heavy duty users are making database writes concurrently all day long? I don't know much about drive characteristics/performance other than the basic throughput stuff. Because backup is streamed out in realtime that's taken care of as far as I'm concerned, part of what makes Raid 0 a candidate at least.
Yes IOPS are the consideration you need to be looking at. What has yet to be answered is how active is this database going to actually be?
Will you have 10,000 people/processes constantly making changes?
Ideally more than that, but it'll be a gradual climb. Right now it's in private alpha w/ ~ 100 users and they post stuff all the time. Once I make it public I imagine the content volume will skyrocket.
-
@dustinb3403 said in Is this server strategy reckless and/or insane?:
We all understand that there are differences with different RAID types.
The point of the matter is you opt'd for RAID0 because you believe you have a need for all of the IOPS in the world, yet don't care about backups.
But you are missing critical pieces of this design like virtualization, ram cache etc to get better, safer results.
He's got backups of the data. He's doing devops style backups.
-
@creayt said in Is this server strategy reckless and/or insane?:
@dustinb3403 said in Is this server strategy reckless and/or insane?:
@creayt said in Is this server strategy reckless and/or insane?:
@dustinb3403 said in Is this server strategy reckless and/or insane?:
We all understand that there are differences with different RAID types.
The point of the matter is you opt'd for RAID0 because you believe you have a need for all of the IOPS in the world, yet don't care about backups.
But you are missing critical pieces of this design like virtualization, ram cache etc to get better, safer results.
Are IOPS what you want for heavy duty users are making database writes concurrently all day long? I don't know much about drive characteristics/performance other than the basic throughput stuff. Because backup is streamed out in realtime that's taken care of as far as I'm concerned, part of what makes Raid 0 a candidate at least.
Yes IOPS are the consideration you need to be looking at. What has yet to be answered is how active is this database going to actually be?
Will you have 10,000 people/processes constantly making changes?
Ideally more than that, but it'll be a gradual climb. Right now it's in private alpha w/ ~ 100 users and they post stuff all the time. Once I make it public I imagine the content volume will skyrocket.
MySQL is likely your performance bottleneck there.
-
How is your internet going to serve up all this RAID0 SSD awesomeness?? Do you really have the bandwidth to allow the hardware to be the bottleneck?
