RE: RAID5 question, take 2
This actually depends on the drives, if they are cheetahs, yeah you will be pinched. But if it is anything but perhaps not. I would hope they would be, but very possible they are not. "Walking on water and developing software from a specification are easy if both are frozen." Christopher R. Spence Oracle DBA Fuelspot -Original Message- Sent: Monday, June 11, 2001 12:20 AM To: Multiple recipients of list ORACLE-L Gary, Here is where we have to know more details. a 9 drive array on a single channel sounds like your peak I/O rate for reads would be throttled by the controller channel speed. Now, if the SCSI interface is ultra 160/m, and the drive support a sustained rate of 20 MB/sec - you're not pinched. But if the RAID controller interface is FC - and only 100MB/sec - you're going to be seriously pinched during index range, fast full and full table scans - bulk reads. Are you using fine-grained striping - such that a FTS will be using the multiblock_read_count and will hit all 8 drives (net)? what's your: db_block_size multiblock_read_count OS I/O size If your OS I/O size is 128 KB and your db_block_size is 16 KB then a multiblock_read_count = 8 and a stripe size of 128 KB - or 16 KB depth per stripe member. (as the parity drive is ignored) and each member in the stripe contributes one block in each read request for a FTS. SAME methodology would imply that your OS I/O size has been cranked up to 1 MB, and that your stripe size is also 1 MB. On a FC interface - the transfer speed for a 1 MB read would be 10 ms - on par with the average seek time. But SAME is not geared for RAID 5 - as RAID 5 supports having the drive heads out of sync to satisfy mutliple independent requests concurrently. SAME is geared more for RAID 0+1 - where the drive heads in an array move in unison - with all drives returning the results of one request at a time. What do you want to return for your read requests - (1 db_block, multiblock_read_count, 1 MB)? This will depend entirely on the access paths that are used in YOUR application. Basically - a 3 drive RAID 5 array is useless. Don't even consider it. Better off to have a single RAID 1 volume with a hot spare. If I were to break the 9 drives up (it would be as a RAID 0+1 of 4 drives each) - it would be as a 5 drive and 4 drive array (assuming that 2 channels are available). if most of the read requests have been driven by an index - and only one block is being requested - the 9 disk RAID 5 config is the way to go - as seek time will dominate transfer time. just my opinion. Paul Gary Weber wrote: > > The reply below was a great post! As were replies prior to it. But, none of > the replies were for the original question. > > The issue in hand is not which raid level to use or whether to use at all. > > The question is, and I promise this is the very last time I post it: given 9 > hard drives dedicated for RAID5, should data reside on 6 drives via volume > group A and indexes on the other 3 drives via volume group B, or should data > and indexes be placed on all 9 drives via one volume group? The data is > absolutely static. > > Gary > > - Original Message - > To: "Multiple recipients of list ORACLE-L" <[EMAIL PROTECTED]> > Sent: Sunday, June 10, 2001 7:15 PM > > > Since RAID5 means that data is striped, of course read performance is OK. > As > > soon as you talk write performance, however, RAID5 becomes something of a > joke > > since it was invented back in the 70's to offer a cheap alternative to the > fast, > > extremely expensive disks offered by IBM back then. So the focus was on > limiting > > the number of disks. Today, where disks in general are cheap and caches > are > > expensive, I really have a hard time figuring out why people buy RAID5 > (few > > disks, cache required to compensate for the horrible write penalty) > instead of > > RAID1+0 (more disks, no cache required). And I have a hard time figuring > out why > > the vendors are pushing RAID5 solutions, if RAID1+0 means selling more > disks to > > the customers :-). The answer, of course, is that they are making money on > > caches, not disks. > > > > Technically speaking, RAID1+0 will always be better than RAID5, of course. > Oh, > > they will try to compensate with caches and talk of RAID3 techniques and > what > > have you. RAID1+0 is still superior to RAID5 in any techinal aspect. > > > > It becomes really absurd when you look at the SAN offerings on the market. > For > > instance, IBM's Shark only offers the customer the choice between JBOD > (Just a > > Bunch Of Disks, ie., Non-RAID) and RAID5. IBM has a red book out regarding > this > > and on page 127 out of 228 or so you can read the headline: "JBOD or > RAID5?" and > > that's when it dawns on you that Shark (which is very expensive) cannot > under > > any circumstances be configured for anything else than RAID5 or non-RAID. > > Workaround: Place a file system on top that at least can be striped > (Veritas,
RE: RAID5 question, take 2
Mogens, the super-market analogy does not apply - this is for SQL Server database. I'm not sure how far I'll be able to tweak that rdbms, hence my question did not contain many details - it was simply a request for opinions. Btw, to sum up current responses: Option 1: split 9 drives to separate data/index I/O Option 2: stripe everything across 9 drives for better throughput. So, methinks the Windoz admin is going to try both ways and monitor i/o... Thanks to Paul, Jared, Christopher for great input, Gary Weber Senior DBA Charles Jones, LLC 609-530-1144, ext 5529 -Original Message- Nørgaard Sent: Monday, June 11, 2001 3:15 AM To: Multiple recipients of list ORACLE-L Indeed, Paul. Very good points. Gary - you're asking us to determine the number of bags we'll need at the supermarket without knowing what we're going to buy. If we had IO-stats for your datafiles/tablespaces, ie reads/writes and their size, and your availability requirements on the system, we could tell you more. Paul Drake wrote: > Gary, > > Here is where we have to know more details. > > a 9 drive array on a single channel sounds like your peak I/O rate for > reads would be throttled by the controller channel speed. Now, if the > SCSI interface is ultra 160/m, and the drive support a sustained rate of > 20 MB/sec - you're not pinched. But if the RAID controller interface is > FC - and only 100MB/sec - you're going to be seriously pinched during > index range, fast full and full table scans - bulk reads. > > Are you using fine-grained striping - such that a FTS will be using the > multiblock_read_count and will hit all 8 drives (net)? > what's your: > db_block_size > multiblock_read_count > OS I/O size > > If your OS I/O size is 128 KB > and your db_block_size is 16 KB > then a multiblock_read_count = 8 > and a stripe size of 128 KB - or 16 KB depth per stripe member. > (as the parity drive is ignored) > and each member in the stripe contributes one block in each read request > for a FTS. > > SAME methodology would imply that your OS I/O size has been cranked up > to 1 MB, and that your stripe size is also 1 MB. On a FC interface - the > transfer speed for a 1 MB read would be 10 ms - on par with the average > seek time. > But SAME is not geared for RAID 5 - as RAID 5 supports having the drive > heads out of sync to satisfy mutliple independent requests concurrently. > SAME is geared more for RAID 0+1 - where the drive heads in an array > move in unison - with all drives returning the results of one request at > a time. > > What do you want to return for your read requests - (1 db_block, > multiblock_read_count, 1 MB)? > This will depend entirely on the access paths that are used in YOUR > application. > > Basically - a 3 drive RAID 5 array is useless. Don't even consider it. > Better off to have a single RAID 1 volume with a hot spare. If I were to > break the 9 drives up (it would be as a RAID 0+1 of 4 drives each) > - it would be as a 5 drive and 4 drive array (assuming that 2 channels > are available). > > if most of the read requests have been driven by an index - and only one > block is being requested - the 9 disk RAID 5 config is the way to go - > as seek time will dominate transfer time. > > just my opinion. > > Paul -- Please see the official ORACLE-L FAQ: http://www.orafaq.com -- Author: Gary Weber INET: [EMAIL PROTECTED] Fat City Network Services-- (858) 538-5051 FAX: (858) 538-5051 San Diego, California-- Public Internet access / Mailing Lists To REMOVE yourself from this mailing list, send an E-Mail message to: [EMAIL PROTECTED] (note EXACT spelling of 'ListGuru') and in the message BODY, include a line containing: UNSUB ORACLE-L (or the name of mailing list you want to be removed from). You may also send the HELP command for other information (like subscribing).
Re: RAID5 question, take 2
Indeed, Paul. Very good points. Gary - you're asking us to determine the number of bags we'll need at the supermarket without knowing what we're going to buy. If we had IO-stats for your datafiles/tablespaces, ie reads/writes and their size, and your availability requirements on the system, we could tell you more. Paul Drake wrote: > Gary, > > Here is where we have to know more details. > > a 9 drive array on a single channel sounds like your peak I/O rate for > reads would be throttled by the controller channel speed. Now, if the > SCSI interface is ultra 160/m, and the drive support a sustained rate of > 20 MB/sec - you're not pinched. But if the RAID controller interface is > FC - and only 100MB/sec - you're going to be seriously pinched during > index range, fast full and full table scans - bulk reads. > > Are you using fine-grained striping - such that a FTS will be using the > multiblock_read_count and will hit all 8 drives (net)? > what's your: > db_block_size > multiblock_read_count > OS I/O size > > If your OS I/O size is 128 KB > and your db_block_size is 16 KB > then a multiblock_read_count = 8 > and a stripe size of 128 KB - or 16 KB depth per stripe member. > (as the parity drive is ignored) > and each member in the stripe contributes one block in each read request > for a FTS. > > SAME methodology would imply that your OS I/O size has been cranked up > to 1 MB, and that your stripe size is also 1 MB. On a FC interface - the > transfer speed for a 1 MB read would be 10 ms - on par with the average > seek time. > But SAME is not geared for RAID 5 - as RAID 5 supports having the drive > heads out of sync to satisfy mutliple independent requests concurrently. > SAME is geared more for RAID 0+1 - where the drive heads in an array > move in unison - with all drives returning the results of one request at > a time. > > What do you want to return for your read requests - (1 db_block, > multiblock_read_count, 1 MB)? > This will depend entirely on the access paths that are used in YOUR > application. > > Basically - a 3 drive RAID 5 array is useless. Don't even consider it. > Better off to have a single RAID 1 volume with a hot spare. If I were to > break the 9 drives up (it would be as a RAID 0+1 of 4 drives each) > - it would be as a 5 drive and 4 drive array (assuming that 2 channels > are available). > > if most of the read requests have been driven by an index - and only one > block is being requested - the 9 disk RAID 5 config is the way to go - > as seek time will dominate transfer time. > > just my opinion. > > Paul > > Gary Weber wrote: > > > > The reply below was a great post! As were replies prior to it. But, none of > > the replies were for the original question. > > > > The issue in hand is not which raid level to use or whether to use at all. > > > > The question is, and I promise this is the very last time I post it: given 9 > > hard drives dedicated for RAID5, should data reside on 6 drives via volume > > group A and indexes on the other 3 drives via volume group B, or should data > > and indexes be placed on all 9 drives via one volume group? The data is > > absolutely static. > > > > Gary > > > > - Original Message - > > To: "Multiple recipients of list ORACLE-L" <[EMAIL PROTECTED]> > > Sent: Sunday, June 10, 2001 7:15 PM > > > > > Since RAID5 means that data is striped, of course read performance is OK. > > As > > > soon as you talk write performance, however, RAID5 becomes something of a > > joke > > > since it was invented back in the 70's to offer a cheap alternative to the > > fast, > > > extremely expensive disks offered by IBM back then. So the focus was on > > limiting > > > the number of disks. Today, where disks in general are cheap and caches > > are > > > expensive, I really have a hard time figuring out why people buy RAID5 > > (few > > > disks, cache required to compensate for the horrible write penalty) > > instead of > > > RAID1+0 (more disks, no cache required). And I have a hard time figuring > > out why > > > the vendors are pushing RAID5 solutions, if RAID1+0 means selling more > > disks to > > > the customers :-). The answer, of course, is that they are making money on > > > caches, not disks. > > > > > > Technically speaking, RAID1+0 will always be better than RAID5, of course. > > Oh, > > > they will try to compensate with caches and talk of RAID3 techniques and > > what > > > have you. RAID1+0 is still superior to RAID5 in any techinal aspect. > > > > > > It becomes really absurd when you look at the SAN offerings on the market. > > For > > > instance, IBM's Shark only offers the customer the choice between JBOD > > (Just a > > > Bunch Of Disks, ie., Non-RAID) and RAID5. IBM has a red book out regarding > > this > > > and on page 127 out of 228 or so you can read the headline: "JBOD or > > RAID5?" and > > > that's when it dawns on you that Shark (which is very expensive) cannot > > under > > > any circumstances be configured for anything else
Re: RAID5 question, take 2
Gary, Here is where we have to know more details. a 9 drive array on a single channel sounds like your peak I/O rate for reads would be throttled by the controller channel speed. Now, if the SCSI interface is ultra 160/m, and the drive support a sustained rate of 20 MB/sec - you're not pinched. But if the RAID controller interface is FC - and only 100MB/sec - you're going to be seriously pinched during index range, fast full and full table scans - bulk reads. Are you using fine-grained striping - such that a FTS will be using the multiblock_read_count and will hit all 8 drives (net)? what's your: db_block_size multiblock_read_count OS I/O size If your OS I/O size is 128 KB and your db_block_size is 16 KB then a multiblock_read_count = 8 and a stripe size of 128 KB - or 16 KB depth per stripe member. (as the parity drive is ignored) and each member in the stripe contributes one block in each read request for a FTS. SAME methodology would imply that your OS I/O size has been cranked up to 1 MB, and that your stripe size is also 1 MB. On a FC interface - the transfer speed for a 1 MB read would be 10 ms - on par with the average seek time. But SAME is not geared for RAID 5 - as RAID 5 supports having the drive heads out of sync to satisfy mutliple independent requests concurrently. SAME is geared more for RAID 0+1 - where the drive heads in an array move in unison - with all drives returning the results of one request at a time. What do you want to return for your read requests - (1 db_block, multiblock_read_count, 1 MB)? This will depend entirely on the access paths that are used in YOUR application. Basically - a 3 drive RAID 5 array is useless. Don't even consider it. Better off to have a single RAID 1 volume with a hot spare. If I were to break the 9 drives up (it would be as a RAID 0+1 of 4 drives each) - it would be as a 5 drive and 4 drive array (assuming that 2 channels are available). if most of the read requests have been driven by an index - and only one block is being requested - the 9 disk RAID 5 config is the way to go - as seek time will dominate transfer time. just my opinion. Paul Gary Weber wrote: > > The reply below was a great post! As were replies prior to it. But, none of > the replies were for the original question. > > The issue in hand is not which raid level to use or whether to use at all. > > The question is, and I promise this is the very last time I post it: given 9 > hard drives dedicated for RAID5, should data reside on 6 drives via volume > group A and indexes on the other 3 drives via volume group B, or should data > and indexes be placed on all 9 drives via one volume group? The data is > absolutely static. > > Gary > > - Original Message - > To: "Multiple recipients of list ORACLE-L" <[EMAIL PROTECTED]> > Sent: Sunday, June 10, 2001 7:15 PM > > > Since RAID5 means that data is striped, of course read performance is OK. > As > > soon as you talk write performance, however, RAID5 becomes something of a > joke > > since it was invented back in the 70's to offer a cheap alternative to the > fast, > > extremely expensive disks offered by IBM back then. So the focus was on > limiting > > the number of disks. Today, where disks in general are cheap and caches > are > > expensive, I really have a hard time figuring out why people buy RAID5 > (few > > disks, cache required to compensate for the horrible write penalty) > instead of > > RAID1+0 (more disks, no cache required). And I have a hard time figuring > out why > > the vendors are pushing RAID5 solutions, if RAID1+0 means selling more > disks to > > the customers :-). The answer, of course, is that they are making money on > > caches, not disks. > > > > Technically speaking, RAID1+0 will always be better than RAID5, of course. > Oh, > > they will try to compensate with caches and talk of RAID3 techniques and > what > > have you. RAID1+0 is still superior to RAID5 in any techinal aspect. > > > > It becomes really absurd when you look at the SAN offerings on the market. > For > > instance, IBM's Shark only offers the customer the choice between JBOD > (Just a > > Bunch Of Disks, ie., Non-RAID) and RAID5. IBM has a red book out regarding > this > > and on page 127 out of 228 or so you can read the headline: "JBOD or > RAID5?" and > > that's when it dawns on you that Shark (which is very expensive) cannot > under > > any circumstances be configured for anything else than RAID5 or non-RAID. > > Workaround: Place a file system on top that at least can be striped > (Veritas, > > for instance). > > > > EMC has a standard offering where they'll suggest RAID-S (S looks a lot > like 5, > > doesn't it?) and the standard answer if write performance is not good > enough is: > > "Add more cache". Well, we had a customer who reached 32 GB of cache (not > MB, > > mind you, but GB) and write performance was still bad (of course) for > restores > > and recovery operations and file copying and all those things wh
Re: RAID5 question, take 2
On Sunday 10 June 2001 20:15, Gary Weber wrote: > The question is, and I promise this is the very last time I post it: given > 9 hard drives dedicated for RAID5, should data reside on 6 drives via > volume group A and indexes on the other 3 drives via volume group B, or > should data and indexes be placed on all 9 drives via one volume group? The > data is absolutely static. > > Gary Given the choices, I would consider whether the access is heavily weighted towards full table scans. If so, the 9 disk array would sound good. If more heavily weighted toward table access via indexes, then separating the data and indexes would get the nod. HTH Jared -- Please see the official ORACLE-L FAQ: http://www.orafaq.com -- Author: Jared Still INET: [EMAIL PROTECTED] Fat City Network Services-- (858) 538-5051 FAX: (858) 538-5051 San Diego, California-- Public Internet access / Mailing Lists To REMOVE yourself from this mailing list, send an E-Mail message to: [EMAIL PROTECTED] (note EXACT spelling of 'ListGuru') and in the message BODY, include a line containing: UNSUB ORACLE-L (or the name of mailing list you want to be removed from). You may also send the HELP command for other information (like subscribing).