RAID 5/6 rebuild time calculationWhat are the different widely used RAID levels and when should I consider them?Strange issues with different raid controllers. Can it be due to environmental issue?Proliant RAID 1 Rebuild QuestionsHow can a single disk in a hardware SATA RAID-10 array bring the entire array to a screeching halt?Proliant server will not accept new hard disks in RAID 1+0?How should I calculate IOPS for RAID50 & RAID60?RAID6 degraded drive during rebuildRAID-5: Two disks failed simultaneously?How to find out raid in linux: cat /sys/block/sda/device/raid_level vs dmraid -s in Redhat?Is it better practice to buy RAID disks individually vs. in bulk?RAID: Comparision of load on disks while expanding disk space or upgrading RAID level
Can my floppy disk still work without a shutter spring?
Pirate democracy at its finest
How can I tell if I'm being too picky as a referee?
Why does Mjolnir fall down in Age of Ultron but not in Endgame?
Count Even Digits In Number
The art of clickbait captions
Where's this lookout in Nova Scotia?
Specific alignment within beginalign environment
Do photons bend spacetime or not?
How did NASA Langley end up with the first 737?
Is "cool" appropriate or offensive to use in IMs?
Website returning plaintext password
Is it truly impossible to tell what a CPU is doing?
Why did the person in charge of a principality not just declare themself king?
What does $!# mean in Shell scripting?
How to deal with a colleague who is being aggressive?
Using credit/debit card details vs swiping a card in a payment (credit card) terminal
Python program to take in two strings and print the larger string
First Match - awk
Apt - strange requests to d16r8ew072anqo.cloudfront.net:80
What is the function of the corrugations on a section of the Space Shuttle's external tank?
Which European Languages are not Indo-European?
Why are GND pads often only connected by four traces?
Why didn't Thanos use the Time Stone to stop the Avengers' plan?
RAID 5/6 rebuild time calculation
What are the different widely used RAID levels and when should I consider them?Strange issues with different raid controllers. Can it be due to environmental issue?Proliant RAID 1 Rebuild QuestionsHow can a single disk in a hardware SATA RAID-10 array bring the entire array to a screeching halt?Proliant server will not accept new hard disks in RAID 1+0?How should I calculate IOPS for RAID50 & RAID60?RAID6 degraded drive during rebuildRAID-5: Two disks failed simultaneously?How to find out raid in linux: cat /sys/block/sda/device/raid_level vs dmraid -s in Redhat?Is it better practice to buy RAID disks individually vs. in bulk?RAID: Comparision of load on disks while expanding disk space or upgrading RAID level
.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty height:90px;width:728px;box-sizing:border-box;
I plan to build some storage schema but I have to anticipate downtime, maintenance and rebuild Time.
Some guys said to me that a 10 disk RAID6 of 10To (SATA) rebuild will last for about a week ! and some company policy ask for stopping activity on Array when rebuilding.
If I use RAID 5 or 6 or 5+1 or 6+1 is there an approximate formula that can give me hint on rebuild time depending on disk size and type (SAS/SATA/SSD).
something like rpm x size(Mb) x type-factor x nb-of-disk ...
I would like to be able to anticipate all rebuild time scenario depending on Size/type of RAID/type of Disk.
I know it may depend on hardware quality, but let says I am out of dedicated hardware like 3PAR / STOREWIZE / NETAPP or likes. I am using conventional servers with traditional SAS or SATA drives with software RAID.
raid hard-drive storage
asked May 19 at 1:47
dominixdominix
607
add a comment |
I plan to build some storage schema but I have to anticipate downtime, maintenance and rebuild Time.
Some guys said to me that a 10 disk RAID6 of 10To (SATA) rebuild will last for about a week ! and some company policy ask for stopping activity on Array when rebuilding.
If I use RAID 5 or 6 or 5+1 or 6+1 is there an approximate formula that can give me hint on rebuild time depending on disk size and type (SAS/SATA/SSD).
something like rpm x size(Mb) x type-factor x nb-of-disk ...
I would like to be able to anticipate all rebuild time scenario depending on Size/type of RAID/type of Disk.
I know it may depend on hardware quality, but let says I am out of dedicated hardware like 3PAR / STOREWIZE / NETAPP or likes. I am using conventional servers with traditional SAS or SATA drives with software RAID.
raid hard-drive storage
asked May 19 at 1:47
dominixdominix
607
Said company policy may make sense to some extent with RAID 5. But already with RAID 6, a rebuild of one failed disk, when the array would still work with two failures, it seems unnecessarily restrictive. The more disks you use, the more often there will be a disk failing, and you do not want the complete business come to halt for several hours. With hot-spares, a rebuild in the background may even have completed or almost completed before you even have the chance to communicate a company-wide shutdown of all relevant activities ...
– Hagen von Eitzen
May 19 at 10:57
PLEASE don't use R5, it's dangerous and no professional would use it for disks >1TB, you WILL lose data - this isn't option either, it's well documented fact.
– Chopper3
May 19 at 19:06
add a comment |
I plan to build some storage schema but I have to anticipate downtime, maintenance and rebuild Time.
Some guys said to me that a 10 disk RAID6 of 10To (SATA) rebuild will last for about a week ! and some company policy ask for stopping activity on Array when rebuilding.
If I use RAID 5 or 6 or 5+1 or 6+1 is there an approximate formula that can give me hint on rebuild time depending on disk size and type (SAS/SATA/SSD).
something like rpm x size(Mb) x type-factor x nb-of-disk ...
I would like to be able to anticipate all rebuild time scenario depending on Size/type of RAID/type of Disk.
I know it may depend on hardware quality, but let says I am out of dedicated hardware like 3PAR / STOREWIZE / NETAPP or likes. I am using conventional servers with traditional SAS or SATA drives with software RAID.
raid hard-drive storage
asked May 19 at 1:47
dominixdominix
607
I plan to build some storage schema but I have to anticipate downtime, maintenance and rebuild Time.
Some guys said to me that a 10 disk RAID6 of 10To (SATA) rebuild will last for about a week ! and some company policy ask for stopping activity on Array when rebuilding.
If I use RAID 5 or 6 or 5+1 or 6+1 is there an approximate formula that can give me hint on rebuild time depending on disk size and type (SAS/SATA/SSD).
something like rpm x size(Mb) x type-factor x nb-of-disk ...
I would like to be able to anticipate all rebuild time scenario depending on Size/type of RAID/type of Disk.
I know it may depend on hardware quality, but let says I am out of dedicated hardware like 3PAR / STOREWIZE / NETAPP or likes. I am using conventional servers with traditional SAS or SATA drives with software RAID.
raid hard-drive storage
raid hard-drive storage
asked May 19 at 1:47
dominixdominix
607
asked May 19 at 1:47
dominixdominix
607
edited May 19 at 18:56
dominix
asked May 19 at 1:47
dominixdominix
607
asked May 19 at 1:47
dominixdominix
607
asked May 19 at 1:47
dominixdominix
607
607
Said company policy may make sense to some extent with RAID 5. But already with RAID 6, a rebuild of one failed disk, when the array would still work with two failures, it seems unnecessarily restrictive. The more disks you use, the more often there will be a disk failing, and you do not want the complete business come to halt for several hours. With hot-spares, a rebuild in the background may even have completed or almost completed before you even have the chance to communicate a company-wide shutdown of all relevant activities ...
– Hagen von Eitzen
May 19 at 10:57
PLEASE don't use R5, it's dangerous and no professional would use it for disks >1TB, you WILL lose data - this isn't option either, it's well documented fact.
– Chopper3
May 19 at 19:06
add a comment |
Said company policy may make sense to some extent with RAID 5. But already with RAID 6, a rebuild of one failed disk, when the array would still work with two failures, it seems unnecessarily restrictive. The more disks you use, the more often there will be a disk failing, and you do not want the complete business come to halt for several hours. With hot-spares, a rebuild in the background may even have completed or almost completed before you even have the chance to communicate a company-wide shutdown of all relevant activities ...
– Hagen von Eitzen
May 19 at 10:57
PLEASE don't use R5, it's dangerous and no professional would use it for disks >1TB, you WILL lose data - this isn't option either, it's well documented fact.
– Chopper3
May 19 at 19:06
Said company policy may make sense to some extent with RAID 5. But already with RAID 6, a rebuild of one failed disk, when the array would still work with two failures, it seems unnecessarily restrictive. The more disks you use, the more often there will be a disk failing, and you do not want the complete business come to halt for several hours. With hot-spares, a rebuild in the background may even have completed or almost completed before you even have the chance to communicate a company-wide shutdown of all relevant activities ...
– Hagen von Eitzen
May 19 at 10:57
Said company policy may make sense to some extent with RAID 5. But already with RAID 6, a rebuild of one failed disk, when the array would still work with two failures, it seems unnecessarily restrictive. The more disks you use, the more often there will be a disk failing, and you do not want the complete business come to halt for several hours. With hot-spares, a rebuild in the background may even have completed or almost completed before you even have the chance to communicate a company-wide shutdown of all relevant activities ...
– Hagen von Eitzen
May 19 at 10:57
PLEASE don't use R5, it's dangerous and no professional would use it for disks >1TB, you WILL lose data - this isn't option either, it's well documented fact.
– Chopper3
May 19 at 19:06
PLEASE don't use R5, it's dangerous and no professional would use it for disks >1TB, you WILL lose data - this isn't option either, it's well documented fact.
– Chopper3
May 19 at 19:06
add a comment |
2 Answers
2
active
oldest
votes
You can calculate the best-case rebuild rate fairly simply: as rebuild is sequential, the needed time is capacity / transfer rate. For example, rebuilding a 10 TB disk with a 200 MB/s transfer rate needs at least 10000000 / 200 = 50000s = ~14h.
Now take this result and trow it away, as it is an overly optimistic scenario: it suppose 100% disk availability for the rebuild operation and totally sequential reads/writes. Toss in the mix some non-rebuild (ie: application) load, cap the rebuild itself to 30% (to not grind other applications to an halt) and you are suddenly in the 10x (eg: a week) rebuild time.
These long rebuild times are the reason while I avoid RAID5/6 in many system, favoring mirroring instead. Anyway, with such big drives, absolutely avoid RAID5, which is moo much exposed to double failure and/or URE issues.
If you want to play with the number, give a look here
answered May 19 at 5:46
shodanshokshodanshok
27.8k35192
OP said he'd (have to) stop other activity on the array ...
– Hagen von Eitzen
May 19 at 10:49
add a comment |
The theoretical absolute minimum rebuild time is the time needed to write a complete disk worth of data : the capacity of a disk divided by the average sustained write speed a disk can maintain without cache.
(Note: that average sustained write speed will probably be not even near the performance numbers quoted in the specs.)
Larger disks take longer.
Slower disks take longer.
Parity calculations take extra time.
Real world numbers will vary but will certainly be (much) larger and depend on your RAID level , the number of remaining disks, load on the system while the array rebuild takes place, the controller etc.
Also see What are the different widely used RAID levels and when should I consider them?
answered May 19 at 6:04
HBruijnHBruijn
58.2k1191155
add a comment |
Your Answer
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "2"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);
else
createEditor();
);
function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);
);
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fserverfault.com%2fquestions%2f967930%2fraid-5-6-rebuild-time-calculation%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
2 Answers
2
active
oldest
votes
2 Answers
2
active
oldest
votes
active
oldest
votes
active
oldest
votes
You can calculate the best-case rebuild rate fairly simply: as rebuild is sequential, the needed time is capacity / transfer rate. For example, rebuilding a 10 TB disk with a 200 MB/s transfer rate needs at least 10000000 / 200 = 50000s = ~14h.
Now take this result and trow it away, as it is an overly optimistic scenario: it suppose 100% disk availability for the rebuild operation and totally sequential reads/writes. Toss in the mix some non-rebuild (ie: application) load, cap the rebuild itself to 30% (to not grind other applications to an halt) and you are suddenly in the 10x (eg: a week) rebuild time.
These long rebuild times are the reason while I avoid RAID5/6 in many system, favoring mirroring instead. Anyway, with such big drives, absolutely avoid RAID5, which is moo much exposed to double failure and/or URE issues.
If you want to play with the number, give a look here
answered May 19 at 5:46
shodanshokshodanshok
27.8k35192
OP said he'd (have to) stop other activity on the array ...
– Hagen von Eitzen
May 19 at 10:49
add a comment |
You can calculate the best-case rebuild rate fairly simply: as rebuild is sequential, the needed time is capacity / transfer rate. For example, rebuilding a 10 TB disk with a 200 MB/s transfer rate needs at least 10000000 / 200 = 50000s = ~14h.
Now take this result and trow it away, as it is an overly optimistic scenario: it suppose 100% disk availability for the rebuild operation and totally sequential reads/writes. Toss in the mix some non-rebuild (ie: application) load, cap the rebuild itself to 30% (to not grind other applications to an halt) and you are suddenly in the 10x (eg: a week) rebuild time.
These long rebuild times are the reason while I avoid RAID5/6 in many system, favoring mirroring instead. Anyway, with such big drives, absolutely avoid RAID5, which is moo much exposed to double failure and/or URE issues.
If you want to play with the number, give a look here
answered May 19 at 5:46
shodanshokshodanshok
27.8k35192
OP said he'd (have to) stop other activity on the array ...
– Hagen von Eitzen
May 19 at 10:49
add a comment |
You can calculate the best-case rebuild rate fairly simply: as rebuild is sequential, the needed time is capacity / transfer rate. For example, rebuilding a 10 TB disk with a 200 MB/s transfer rate needs at least 10000000 / 200 = 50000s = ~14h.
Now take this result and trow it away, as it is an overly optimistic scenario: it suppose 100% disk availability for the rebuild operation and totally sequential reads/writes. Toss in the mix some non-rebuild (ie: application) load, cap the rebuild itself to 30% (to not grind other applications to an halt) and you are suddenly in the 10x (eg: a week) rebuild time.
These long rebuild times are the reason while I avoid RAID5/6 in many system, favoring mirroring instead. Anyway, with such big drives, absolutely avoid RAID5, which is moo much exposed to double failure and/or URE issues.
If you want to play with the number, give a look here
answered May 19 at 5:46
shodanshokshodanshok
27.8k35192
You can calculate the best-case rebuild rate fairly simply: as rebuild is sequential, the needed time is capacity / transfer rate. For example, rebuilding a 10 TB disk with a 200 MB/s transfer rate needs at least 10000000 / 200 = 50000s = ~14h.
Now take this result and trow it away, as it is an overly optimistic scenario: it suppose 100% disk availability for the rebuild operation and totally sequential reads/writes. Toss in the mix some non-rebuild (ie: application) load, cap the rebuild itself to 30% (to not grind other applications to an halt) and you are suddenly in the 10x (eg: a week) rebuild time.
These long rebuild times are the reason while I avoid RAID5/6 in many system, favoring mirroring instead. Anyway, with such big drives, absolutely avoid RAID5, which is moo much exposed to double failure and/or URE issues.
If you want to play with the number, give a look here
answered May 19 at 5:46
shodanshokshodanshok
27.8k35192
answered May 19 at 5:46
shodanshokshodanshok
27.8k35192
answered May 19 at 5:46
shodanshokshodanshok
27.8k35192
answered May 19 at 5:46
shodanshokshodanshok
27.8k35192
27.8k35192
OP said he'd (have to) stop other activity on the array ...
– Hagen von Eitzen
May 19 at 10:49
add a comment |
OP said he'd (have to) stop other activity on the array ...
– Hagen von Eitzen
May 19 at 10:49
OP said he'd (have to) stop other activity on the array ...
– Hagen von Eitzen
May 19 at 10:49
OP said he'd (have to) stop other activity on the array ...
– Hagen von Eitzen
May 19 at 10:49
add a comment |
The theoretical absolute minimum rebuild time is the time needed to write a complete disk worth of data : the capacity of a disk divided by the average sustained write speed a disk can maintain without cache.
(Note: that average sustained write speed will probably be not even near the performance numbers quoted in the specs.)
Larger disks take longer.
Slower disks take longer.
Parity calculations take extra time.
Real world numbers will vary but will certainly be (much) larger and depend on your RAID level , the number of remaining disks, load on the system while the array rebuild takes place, the controller etc.
Also see What are the different widely used RAID levels and when should I consider them?
answered May 19 at 6:04
HBruijnHBruijn
58.2k1191155
add a comment |
The theoretical absolute minimum rebuild time is the time needed to write a complete disk worth of data : the capacity of a disk divided by the average sustained write speed a disk can maintain without cache.
(Note: that average sustained write speed will probably be not even near the performance numbers quoted in the specs.)
Larger disks take longer.
Slower disks take longer.
Parity calculations take extra time.
Real world numbers will vary but will certainly be (much) larger and depend on your RAID level , the number of remaining disks, load on the system while the array rebuild takes place, the controller etc.
Also see What are the different widely used RAID levels and when should I consider them?
answered May 19 at 6:04
HBruijnHBruijn
58.2k1191155
add a comment |
The theoretical absolute minimum rebuild time is the time needed to write a complete disk worth of data : the capacity of a disk divided by the average sustained write speed a disk can maintain without cache.
(Note: that average sustained write speed will probably be not even near the performance numbers quoted in the specs.)
Larger disks take longer.
Slower disks take longer.
Parity calculations take extra time.
Real world numbers will vary but will certainly be (much) larger and depend on your RAID level , the number of remaining disks, load on the system while the array rebuild takes place, the controller etc.
Also see What are the different widely used RAID levels and when should I consider them?
answered May 19 at 6:04
HBruijnHBruijn
58.2k1191155
The theoretical absolute minimum rebuild time is the time needed to write a complete disk worth of data : the capacity of a disk divided by the average sustained write speed a disk can maintain without cache.
(Note: that average sustained write speed will probably be not even near the performance numbers quoted in the specs.)
Larger disks take longer.
Slower disks take longer.
Parity calculations take extra time.
Real world numbers will vary but will certainly be (much) larger and depend on your RAID level , the number of remaining disks, load on the system while the array rebuild takes place, the controller etc.
Also see What are the different widely used RAID levels and when should I consider them?
answered May 19 at 6:04
HBruijnHBruijn
58.2k1191155
answered May 19 at 6:04
HBruijnHBruijn
58.2k1191155
answered May 19 at 6:04
HBruijnHBruijn
58.2k1191155
answered May 19 at 6:04
HBruijnHBruijn
58.2k1191155
58.2k1191155
add a comment |
add a comment |
Thanks for contributing an answer to Server Fault!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fserverfault.com%2fquestions%2f967930%2fraid-5-6-rebuild-time-calculation%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Said company policy may make sense to some extent with RAID 5. But already with RAID 6, a rebuild of one failed disk, when the array would still work with two failures, it seems unnecessarily restrictive. The more disks you use, the more often there will be a disk failing, and you do not want the complete business come to halt for several hours. With hot-spares, a rebuild in the background may even have completed or almost completed before you even have the chance to communicate a company-wide shutdown of all relevant activities ...
– Hagen von Eitzen
May 19 at 10:57
PLEASE don't use R5, it's dangerous and no professional would use it for disks >1TB, you WILL lose data - this isn't option either, it's well documented fact.
– Chopper3
May 19 at 19:06