Re: 1 processor vs. 2
On Thu, 4 Mar 2004, Chuck Swiger wrote: The parity calculations for RAID-5 are a lot of work and that work scales linearly with the number of drives in the array. The longer you make the array, the worse the performance becomes for small writes in particular. How did you come to this conclusion? For a RAID 5 with a single parity drive, the reason you zero the disks out completely on initialisation is to set up the integrity of the parity check. Then any update to any RAID5 with single parity requires a read of two drives (the target sector and the corresponding parity drive), an in-memory exclusive or against the new data, and two writes. Reads and writes can be in parallel. The work for parity updates only scales linearly with number of disks if you use a naive parity algorithm. Or, obviously, if a drive fails. -- jan grant, ILRT, University of Bristol. http://www.ilrt.bris.ac.uk/ Tel +44(0)117 9287088 Fax +44 (0)117 9287112 http://ioctl.org/jan/ There's no convincing English-language argument that this sentence is true. ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: RAID1 vs RAID5 [ was Re: 1 processor vs. 2]
On Thu, 4 Mar 2004, Chuck Swiger wrote: Also, RAID-5 performance degrades horribly if a drive is down, whereas RAID-1 does fine... Using the algorithm you indicate below, RAID-5 performance would not degrade on the loss of a drive, it's start out that badly. A five-disk RAID-5 array has to read 4 sectors and write five sectors if you change one byte. Wrong; see previous response. -- jan grant, ILRT, University of Bristol. http://www.ilrt.bris.ac.uk/ Tel +44(0)117 9287088 Fax +44 (0)117 9287112 http://ioctl.org/jan/ Q: What's yellow and equivalent to the axiom of choice? A: Zorn's lemon. ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
On Mar 5, 2004, at 5:57 AM, Jan Grant wrote: How did you come to this conclusion? For a RAID 5 with a single parity drive, the reason you zero the disks out completely on initialisation is to set up the integrity of the parity check. Then any update to any RAID5 with single parity requires a read of two drives (the target sector and the corresponding parity drive), an in-memory exclusive or against the new data, and two writes. Reads and writes can be in parallel. You're right, which means I came to my conclusion wrongly, I guess. :-) Part of this was because I was also thinking about how the array behaves after a failure, as you mention next: The work for parity updates only scales linearly with number of disks if you use a naive parity algorithm. Or, obviously, if a drive fails. Even using a non-naive :-) algorithm, RAID-5 writes still take somewhat more work than RAID-1 writes do in terms of I/O ops. -- -Chuck ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
On Thu, 4 Mar 2004 05:09, Chuck McManis wrote: At 05:53 AM 3/3/2004, Danny Pansters wrote: RAID5 on 3 disks? That's useless. Its only mostly useless. You can't mirror (RAID-1) three drives, so if you want some resiliency you can use RAID-5 and give up one disk to parity and get two disks worth of data. You can certainly run RAID-1 across 3 disks leading to three copies of data and still a pretty solid system after one goes down. However I'm not sure if it is valid to call it a mirror system ;-) Malcolm You could even do RAID4 on three disks. 'course 4 disks is generally the minimum most people talk about, but its not completely useless. --Chuck ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED] ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
Danny Pansters wrote: [ ... ] Physical disks are your unit of failure or of resilliance if you like. Absolutely--- understanding RAID properly requires understanding the division of data onto the physical disks. This is an important concept. That's why you need 5+ drives for RAID5 to be any real fun. A three-disk RAID-5 array is a devolved case, but it will function usefully. I don't disagree: RAID-5 is best suited for 5 to 7 disks, but is okay with 4. You want your data to be present at least twice on different physical drives. You want the same for your parity info. You're actually describing RAID-1 or RAID-51 here. The mere fact that you stripe everything out with RAID5 doesn't change your physical unit which is one disk. Resilliance means: what happens if a random drive fails. RAID5 on 3 disks defeats the purpose of RAID5 IMHO. RAID-5 means stripe set with rotating parity, and it is the usage of parity information that provides redundancy (what you call resilliance). A 3-disk RAID-5 array will still function without data loss even if any of the physical disks fails. RAID-5 will not survive a two-disk failure, whereas some RAID-1 or RAID-10 arrays can survive loss of multiple disks. (As might RAID-51...) Theoretically the more drives, the better RAID5 gets, so that might say something about Veritas if they warned against using more than 7 drives. Perhaps grog can be the final referee here, not my turf ;-) The parity calculations for RAID-5 are a lot of work and that work scales linearly with the number of drives in the array. The longer you make the array, the worse the performance becomes for small writes in particular. Very long RAID-arrays also tend to encounter bottlenecks with the system bus or the transport bus rather than being bottlenecked by the drives themselves. I just kinda fell back into the developed thread, hope you don't mind me adding a general remark: One doesn't do RAID to increase performance. Period. Sorry, but wrong. The only purpose of pure RAID-0 is to increase performance by distributing I/O between more than one device. Modes using RAID-1 mirroring will also show a significant improvement to read performance. There are three factors involved in deciding how to utilize RAID: reliability, performance, and cost. One can choose to prioritize one or two of these factors, at the expense of the third; which factors are chosen determine which RAID configuration is appropriate. RAID-5 does not increase performance because the priorities are improving reliability (ie, gaining fault-tolerance) and minimizing cost (ie, getting [n-1] available storage from n drives, rather than [n/2] as per mirroring). -- -Chuck ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: RAID1 vs RAID5 [ was Re: 1 processor vs. 2]
Danny Pansters wrote: So statistically and theoreticaly RAID1 compares to no RAID at all as 2x read speed, 1x write speed (it needs to be written twice but through two heads on two drives seperately and assume they react and move at the same speed). That's about right, but you should be aware of the fact that you are only considering a single transaction. When you think about a stream of I/O requests, either round-robin or geometric division of read access can perform better depending on whether you are moving lots or data (few big requests) or doing many small reads and being bound by seek times. Because the heads may be in different places do to distribution of reads, the heads don't end up writing data out at the exact same time; allowing write to be asyncronous rather than requiring both drives to complete a write operation can speed things up, particularly if geometric distribution of reads is being used. Take a RAID5 with 5 drives that would in terms of data resiliance compare with a RAID1 of 3 drives at best (right?). No. A three-disk RAID-1 arry can retain data even if two drives fail. The RAID-5 array will lose data if two drives fail. In more complicated cases (RAID-10 and RAID-50), RAID-1 has significantly greater reliability than RAID-5. Also, RAID-5 performance degrades horribly if a drive is down, whereas RAID-1 does fine... Change the above numbers for a RAID1 to 3 drives and you have a 3x read and a 1x write speed. With the hypothetical RAID5 as above we have 3x read and 1x write speed for data plus 2x read and 1x write for parity info which will usually be smaller in size. Let's assume they're of comparative sizes, to make things simple, then we have 5/2x reads and 1x writes to compare. For your analysis to be valid, you need to consider the size of I/O requests and the stripe or interleave size of the RAID arrays. For example: A five-disk RAID-5 array has to read 4 sectors and write five sectors if you change one byte. 9 I/O ops compared with either 2 or 3, depending on whether one has a two-disk or three-disk RAID-1 mirror. In other words, RAID-1 small writes are often a factor of four times faster than RAID-5 writes for data much smaller than stripe size. Likewise, your analysis of RAID-5 read performance neglects to consider the fact that data is only available on one drive, whereas will be available on two (or more) drives for RAID-1. For small reads, seek performance is critical and RAID-1 performance is close to n times that of a bare drive, where n is number of drives in array, and can sometimes even be slightly higher than n. RAID-5 performance can at best be (n - 1) and is usually closer half that because the I/O distribution potential of mirroring means you can't choose to utilize a drive that's free. Perhaps a better way of putting it is that RAID-1 can decrease response latency by handling reads in parallel, whereas a RAID-5 array cannot because a particular set of data is only available from one place. -- -Chuck ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
Hi! Following up on this I'm also looking into buying some servers and have the almost the same scenario, a MySQL DB together with apache with mod_perl and embperl, (alot of SQL and dynamic content). Would we be better off with: Dual Xeon, 2.4 GHZ with 2GB of RAM or Xeon 3.0 GHZ with 2GB of RAM and RAID-1 on three disks or RAID-5 on three disks. Will the difference between 2.4 and 3.0 really do that much ? Isn't the SMP system better. Kind Regards, Stefan Cars On Tue, 2 Mar 2004, Scott W wrote: Joseph Koenig wrote: I'm putting together a system that will host a relatively small database (around 20,000 records), as well as run Apache / PHP to search that database. I have the option in front of me to use a P III dual 1GHz machine with a SCSI Raid 5, or to use a single P4 2.8 GHz with a SCSI Raid 1. Both have 1GB RAM. I'm looking to use MySQL as the DB. The site that this machine will host gets about 2 million hits per months (yes, hits, not pageviews or visitors) from about 21,000 unique visitors. Does anyone have an opinion as to which machine will perform best under this scenario? Obviously, both would run FreeBSD. Thanks, Joe Koenig Production Manager jWeb New Media Design [EMAIL PROTECTED] http://www.jwebmedia.com/ 636.928.3162 ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED] Someone else already mentioned this, but RAID-1 will be faster than the RAID-5 at the storage level, if the RAID-5 array is a relatively small # of drives. If you're talking about 2 disk RAID-1 versus 10 disks RAID-5, those numbers may change. If the drives are integrated into the systems, it's also possible the RAID-1 disks are faster drives than the RAID-5 drives... If you're going to run the DB and web server on the same system with a high percentage of static pages, the SMP system may help out. If you have almost all dynamic content is full of complex DB queries, the P4 would do better based solely on CPU speed. How about RAID-1 on the dual PIII and keep the P4 as a workstation? :-) The PIII is likely up to the task, but it really depends on the type of content (is _everything_ PHP generating dynamic content, every page hitting the DB etc?) Scott ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED] -- Stefan Cars Snowfall Communications Tel: +46 (0)18 430 80 50 - Direct: +46 (0)18 430 80 51 Mobile: +46 (0)708 44 36 00 - Fax: +46 (0)708 44 36 04 __ SNOWFALL DISCLAIMER: The information contained in this email and in any attachments is confidential and may be privileged. If you are not the intended recipient, please destroy this message and notify the sender immediately. You should not retain, copy or use this email for any purpose, nor disclose all or any part of its content to any other person. Any views expressed in this message are those of the individual sender, except where the sender specifically states them to be the views of Snowfall Communications. Snowfall Communications monitors the content of emails sent and received via its network for unauthorised use and for other lawful business purposes. The contents of an attachment to this email may contain viruses which could damage your computer system. While Snowfall Communications has taken every reasonable precaution to minimise this risk, we cannot accept liability for any damage which you sustain as a result of software viruses. You should carry out your own virus checks before opening the attachment. ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
On Wednesday 03 March 2004 14:05, Stefan Cars wrote: Dual Xeon, 2.4 GHZ with 2GB of RAM or Xeon 3.0 GHZ with 2GB of RAM and RAID-1 on three disks or RAID-5 on three disks. RAID5 on 3 disks? That's useless. HTH, Dan ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
On Wed, Mar 03, 2004 at 02:53:49PM +0100, Danny Pansters wrote: On Wednesday 03 March 2004 14:05, Stefan Cars wrote: Dual Xeon, 2.4 GHZ with 2GB of RAM or Xeon 3.0 GHZ with 2GB of RAM and RAID-1 on three disks or RAID-5 on three disks. RAID5 on 3 disks? That's useless. 3 disks is the minimum quantity for RAID5: it's certainly not ideal, but it is by no means useless. RAID5 setups can span 3 or more drives -- I don't know what the practical limit is for Vinum or typical PC raid controller cards, but the last time I used it (which I admit was some years ago) Veritas Volumne Manager under Solaris made the strong suggestion that no more than 7 drives be put into one RAID5 group. Cheers, Matthew -- Dr Matthew J Seaman MA, D.Phil. 26 The Paddocks Savill Way PGP: http://www.infracaninophile.co.uk/pgpkey Marlow Tel: +44 1628 476614 Bucks., SL7 1TH UK pgp0.pgp Description: PGP signature
Re: 1 processor vs. 2
At 05:53 AM 3/3/2004, Danny Pansters wrote: RAID5 on 3 disks? That's useless. Its only mostly useless. You can't mirror (RAID-1) three drives, so if you want some resiliency you can use RAID-5 and give up one disk to parity and get two disks worth of data. You could even do RAID4 on three disks. 'course 4 disks is generally the minimum most people talk about, but its not completely useless. --Chuck ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
Okey, but if you would compare RAID-1 on two disks compared to RAID-5 on three disks then ? What would be the faster ? / Stefan On Wed, 3 Mar 2004, Matthew Seaman wrote: On Wed, Mar 03, 2004 at 02:53:49PM +0100, Danny Pansters wrote: On Wednesday 03 March 2004 14:05, Stefan Cars wrote: Dual Xeon, 2.4 GHZ with 2GB of RAM or Xeon 3.0 GHZ with 2GB of RAM and RAID-1 on three disks or RAID-5 on three disks. RAID5 on 3 disks? That's useless. 3 disks is the minimum quantity for RAID5: it's certainly not ideal, but it is by no means useless. RAID5 setups can span 3 or more drives -- I don't know what the practical limit is for Vinum or typical PC raid controller cards, but the last time I used it (which I admit was some years ago) Veritas Volumne Manager under Solaris made the strong suggestion that no more than 7 drives be put into one RAID5 group. Cheers, Matthew -- Dr Matthew J Seaman MA, D.Phil. 26 The Paddocks Savill Way PGP: http://www.infracaninophile.co.uk/pgpkey Marlow Tel: +44 1628 476614 Bucks., SL7 1TH UK -- Stefan Cars Snowfall Communications Tel: +46 (0)18 430 80 50 - Direct: +46 (0)18 430 80 51 Mobile: +46 (0)708 44 36 00 - Fax: +46 (0)708 44 36 04 __ SNOWFALL DISCLAIMER: The information contained in this email and in any attachments is confidential and may be privileged. If you are not the intended recipient, please destroy this message and notify the sender immediately. You should not retain, copy or use this email for any purpose, nor disclose all or any part of its content to any other person. Any views expressed in this message are those of the individual sender, except where the sender specifically states them to be the views of Snowfall Communications. Snowfall Communications monitors the content of emails sent and received via its network for unauthorised use and for other lawful business purposes. The contents of an attachment to this email may contain viruses which could damage your computer system. While Snowfall Communications has taken every reasonable precaution to minimise this risk, we cannot accept liability for any damage which you sustain as a result of software viruses. You should carry out your own virus checks before opening the attachment. ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
On Wed, Mar 03, 2004 at 10:26:43PM +0100, Stefan Cars wrote: Okey, but if you would compare RAID-1 on two disks compared to RAID-5 on three disks then ? What would be the faster ? RAID1 is going to be faster, both reading and writing, but it will take a lot more raw disk space to provide the required usable space. Cheers, Matthew -- Dr Matthew J Seaman MA, D.Phil. 26 The Paddocks Savill Way PGP: http://www.infracaninophile.co.uk/pgpkey Marlow Tel: +44 1628 476614 Bucks., SL7 1TH UK pgp0.pgp Description: PGP signature
Re: 1 processor vs. 2
Ok. In this case the costs isn't really a problem, so both read and write will be faster with two disks in a RAID1 vs. three disks in a RAID 5 ? I've read that RAID5 would be faster in read ? / Stefan On Wed, 3 Mar 2004, Matthew Seaman wrote: On Wed, Mar 03, 2004 at 10:26:43PM +0100, Stefan Cars wrote: Okey, but if you would compare RAID-1 on two disks compared to RAID-5 on three disks then ? What would be the faster ? RAID1 is going to be faster, both reading and writing, but it will take a lot more raw disk space to provide the required usable space. Cheers, Matthew -- Dr Matthew J Seaman MA, D.Phil. 26 The Paddocks Savill Way PGP: http://www.infracaninophile.co.uk/pgpkey Marlow Tel: +44 1628 476614 Bucks., SL7 1TH UK -- Stefan Cars Snowfall Communications Tel: +46 (0)18 430 80 50 - Direct: +46 (0)18 430 80 51 Mobile: +46 (0)708 44 36 00 - Fax: +46 (0)708 44 36 04 __ SNOWFALL DISCLAIMER: The information contained in this email and in any attachments is confidential and may be privileged. If you are not the intended recipient, please destroy this message and notify the sender immediately. You should not retain, copy or use this email for any purpose, nor disclose all or any part of its content to any other person. Any views expressed in this message are those of the individual sender, except where the sender specifically states them to be the views of Snowfall Communications. Snowfall Communications monitors the content of emails sent and received via its network for unauthorised use and for other lawful business purposes. The contents of an attachment to this email may contain viruses which could damage your computer system. While Snowfall Communications has taken every reasonable precaution to minimise this risk, we cannot accept liability for any damage which you sustain as a result of software viruses. You should carry out your own virus checks before opening the attachment. ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
RE: 1 processor vs. 2
RAID-1 will be about 50% faster than RAID-5 doing reads regardless of size, and will also be *much* faster doing small writes-- by a factor of 4, perhaps. The abovementioned figures seem more like comparing RAID-0 (striping) to RAID-5 (striping with ECC) than RAID-5 to RAID-1 (mirroring). In my experience mirroring is always the slowest RAID in terms of retrieving data, writes might be quite comparable with RAID-1 and RAID-5 though. -Reko ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
On Mar 3, 2004, at 5:20 PM, Reko Turja wrote: RAID-1 will be about 50% faster than RAID-5 doing reads regardless of size, and will also be *much* faster doing small writes-- by a factor of 4, perhaps. The abovementioned figures seem more like comparing RAID-0 (striping) to RAID-5 (striping with ECC) than RAID-5 to RAID-1 (mirroring). In my experience mirroring is always the slowest RAID in terms of retrieving data, writes might be quite comparable with RAID-1 and RAID-5 though. Your mileage may vary. :-) However, consider that RAID-1 (mirroring) read performance should always be better than RAID-0 (striping) because you can get the data you want using a single read from either device regardless of size, and you can do things like distribute reads geometrically to reduce head motion for the RAID-1 case-- whereas with reads above the stripe size, the RAID-0 case requires you to access both devices and glue the results together. -- -Chuck ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
(enough CCing, back to list only) On Wednesday 03 March 2004 22:36, Matthew Seaman wrote: On Wed, Mar 03, 2004 at 10:26:43PM +0100, Stefan Cars wrote: Okey, but if you would compare RAID-1 on two disks compared to RAID-5 on three disks then ? What would be the faster ? RAID1 is going to be faster, both reading and writing, but it will take a lot more raw disk space to provide the required usable space. No, it would require 2 identical disks, whereas RAID5 with 3 disks would require 3 of those disks ;-) Physical disks are your unit of failure or of resilliance if you like. That's why you need 5+ drives for RAID5 to be any real fun. You want your data to be present at least twice on different physical drives. You want the same for your parity info. The mere fact that you stripe everything out with RAID5 doesn't change your physical unit which is one disk. Resilliance means: what happens if a random drive fails. RAID5 on 3 disks defeats the purpose of RAID5 IMHO. Theoretically the more drives, the better RAID5 gets, so that might say something about Veritas if they warned against using more than 7 drives. Perhaps grog can be the final referee here, not my turf ;-) Having said that I don't have a RAID5, but I would recommend OP to use RAID1 and use the 3rd drive as a (semi) hot spare for extra sleep security and less spending. It's much more interesting if you can (un)plug a spare on the fly BTW. I just kinda fell back into the developed thread, hope you don't mind me adding a general remark: One doesn't do RAID to increase performance. Period. If budget is no problem, buy spare boxen and use them secondary, always nominated to become primary at any time. That's better insurance against (any) hardware failure than mere RAID can ever be IMHO. Greets, Dan ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
RAID1 vs RAID5 [ was Re: 1 processor vs. 2]
On Wednesday 03 March 2004 23:20, Reko Turja wrote: RAID-1 will be about 50% faster than RAID-5 doing reads regardless of size, and will also be *much* faster doing small writes-- by a factor of 4, perhaps. The abovementioned figures seem more like comparing RAID-0 (striping) to RAID-5 (striping with ECC) than RAID-5 to RAID-1 (mirroring). In my experience mirroring is always the slowest RAID in terms of retrieving data, writes might be quite comparable with RAID-1 and RAID-5 though. That makes sense. With more disks you have more disk heads to read with. So statistically and theoreticaly RAID1 compares to no RAID at all as 2x read speed, 1x write speed (it needs to be written twice but through two heads on two drives seperately and assume they react and move at the same speed). Take a RAID5 with 5 drives that would in terms of data resiliance compare with a RAID1 of 3 drives at best (right?). Change the above numbers for a RAID1 to 3 drives and you have a 3x read and a 1x write speed. With the hypothetical RAID5 as above we have 3x read and 1x write speed for data plus 2x read and 1x write for parity info which will usually be smaller in size. Let's assume they're of comparative sizes, to make things simple, then we have 5/2x reads and 1x writes to compare. Therefore reads are poorer and there's more overall CPU/RAM overhead (with hardware RAID this depends on how you look at it, all RAID is essentially software RAID be it on your PC on on a chip inside it). This simplified approach would indicate that 6 or more drives might be a nice thing for RAID5. I thought this over more often when thinking of how to deploy vinum and recently about whether to buy a RAID1 (cheap) or RAID5 ($$) ATA card and always thought this was the correct way to consider performance (resilliance is another thing). Do people agree on this? I often wondered because most of the meta-information around doesn't go into specifics like this. I think the above scenario applies only when there's a reasonable amount of I/O going on concurrently rather than if nothing ever happens but that lone write or read. That would change the assumption that more heads == more reads equal writes (not rights ;-). Sorry to divert a bit. What can I say, I like having a (somewhat informed) discussion... And this is still relevant to OP. Greets, Dan ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
Stefan Cars wrote: Ok. In this case the costs isn't really a problem, so both read and write will be faster with two disks in a RAID1 vs. three disks in a RAID 5 ? I've read that RAID5 would be faster in read ? Short answer- it depends. Bear in mind that there are some controllers that will do RAID-0(striping) or RAID-1(mirroring)- these generally come without cache on the controller, which is a huge hit for most cases, especially if you enable write-back cache, which will return from the write operation(s) once it's commited to _cache_ and not nescessarily to disk. If you're talking similar number of disks versus previous example of simple 2 disk mirror versus 10-disk RAID-5, reads will become signficantly faster due to the increased number of spindles in the array. I've done a fair amount of testing here- stripe size and cache size can be important, but disk I/O is ultimately limited by a large factor to the number of drive spindles in use. In theory, and for a low amount of writes, the overhead for RAID-1/mirroring is relatively low, but may increase under high load with a large amount of data being written. For the same number of _useable_ disks, RAID-5 is slower due to having to calculate parity (read useable disks as using the same hard drives, same capacity and specs, to wind up at the same amount of useable storage). Scott / Stefan On Wed, 3 Mar 2004, Matthew Seaman wrote: On Wed, Mar 03, 2004 at 10:26:43PM +0100, Stefan Cars wrote: Okey, but if you would compare RAID-1 on two disks compared to RAID-5 on three disks then ? What would be the faster ? RAID1 is going to be faster, both reading and writing, but it will take a lot more raw disk space to provide the required usable space. Cheers, Matthew -- Dr Matthew J Seaman MA, D.Phil. 26 The Paddocks Savill Way PGP: http://www.infracaninophile.co.uk/pgpkey Marlow Tel: +44 1628 476614 Bucks., SL7 1TH UK -- Stefan Cars Snowfall Communications Tel: +46 (0)18 430 80 50 - Direct: +46 (0)18 430 80 51 Mobile: +46 (0)708 44 36 00 - Fax: +46 (0)708 44 36 04 ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
Stefan Cars wrote: Hi! Following up on this I'm also looking into buying some servers and have the almost the same scenario, a MySQL DB together with apache with mod_perl and embperl, (alot of SQL and dynamic content). Would we be better off with: Dual Xeon, 2.4 GHZ with 2GB of RAM or Xeon 3.0 GHZ with 2GB of RAM and RAID-1 on three disks or RAID-5 on three disks. Will the difference between 2.4 and 3.0 really do that much ? Isn't the SMP system better. Kind Regards, Stefan Cars With that small a difference in CPU speed for the purpose you state, I'd definitely go with the dual 2.4 Xeon setup. Unless the FreeHSD SMP implemetation is _really_ bad, which I haven't seen any indication of at all, the SMP system will perform better when you're going to have multiple relatively heavy duty processes and threads running at once, as in the case of a web server with dynamic content hitting a database. Someone commented on RAID-5 with 3 disks being useless- it isn't, but most setups have at least a hot spare designated, and some vendors (IBM, unsure of others offhand) also 'extend' RAID-5 to include the hot spare in different methods (ie RAID-5E, RAID-5EE). Some relatively experienced comments on your config- Add more disk if possible. A striped (2x disk) OS dedicated disk will improve performance a bit, but you'd probably do better using seperate physical disks (or logical RAID volumes but comprised of different physical disks) between the database and the web content, resulting in less I/O contention between the two (web server and DB). RAID-1 across 3 disks is a bit of overkill IMHO, as you're still limited to a bit less than the throughput for a single disk. Use a single disk (or striped pair) for the OS (seperate disk for swap if you anticipate heavy swapping), a RAID-1 mirror for the Database data/files, and another disk for web content. If the content is reasonably unchanging, (the HTML), or you have the content in a source control or content management system, then the DB data is arguably more important so should get the RAID redundancy...then just back up the HTML and web content regularly, or perhaps snapshot it to spare space on the RAID volume nightly. That woould be something along the lines of: Vol 1 (non-RAID or RAID-0 striped of $ allows, so single or dual disks)- FreeBSD Vol 2 - web content. Single disk or RAID-1 mirror, again depending on $ Vol 3 - DB content. RAID-1 mirror, only for DB use. If heavy swapping is expected, then allocate swap space on one of the other disks, but it will obviously affect performance. Do NOT use a single RAID-5 for both web and DB, unless performance is secondary- you _will_ see high amounts of I/O wait states as the server becomes more loaded. If $ allowed, making each RAID-5 or RAID-1 but using seperate physical disks for each volume would be ideal..some RAID hardware and/or software allow you to span different types of RAID configurations across the same disks, which is great for the budget (ie 3 physical disks, but having a RAID-1 volume across _parts_ of two physical disks, and the rest being a RAID-5 volume), but again, you'll eventually run into disk seek and I/O issues... Scott On Tue, 2 Mar 2004, Scott W wrote: Joseph Koenig wrote: I'm putting together a system that will host a relatively small database (around 20,000 records), as well as run Apache / PHP to search that database. I have the option in front of me to use a P III dual 1GHz machine with a SCSI Raid 5, or to use a single P4 2.8 GHz with a SCSI Raid 1. Both have 1GB RAM. I'm looking to use MySQL as the DB. The site that this machine will host gets about 2 million hits per months (yes, hits, not pageviews or visitors) from about 21,000 unique visitors. Does anyone have an opinion as to which machine will perform best under this scenario? Obviously, both would run FreeBSD. Thanks, Joe Koenig Production Manager jWeb New Media Design [EMAIL PROTECTED] http://www.jwebmedia.com/ 636.928.3162 ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED] Someone else already mentioned this, but RAID-1 will be faster than the RAID-5 at the storage level, if the RAID-5 array is a relatively small # of drives. If you're talking about 2 disk RAID-1 versus 10 disks RAID-5, those numbers may change. If the drives are integrated into the systems, it's also possible the RAID-1 disks are faster drives than the RAID-5 drives... If you're going to run the DB and web server on the same system with a high percentage of static pages, the SMP system may help out. If you have almost all dynamic content is full of complex DB queries, the P4 would do better based solely on CPU speed. How about RAID-1 on the dual PIII and keep the P4 as a workstation? :-) The PIII is likely up to the task, but it really depends on the type of content (is
1 processor vs. 2
I'm putting together a system that will host a relatively small database (around 20,000 records), as well as run Apache / PHP to search that database. I have the option in front of me to use a P III dual 1GHz machine with a SCSI Raid 5, or to use a single P4 2.8 GHz with a SCSI Raid 1. Both have 1GB RAM. I'm looking to use MySQL as the DB. The site that this machine will host gets about 2 million hits per months (yes, hits, not pageviews or visitors) from about 21,000 unique visitors. Does anyone have an opinion as to which machine will perform best under this scenario? Obviously, both would run FreeBSD. Thanks, Joe Koenig Production Manager jWeb New Media Design [EMAIL PROTECTED] http://www.jwebmedia.com/ 636.928.3162 ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
I would use the P III with the 5. branch of freebsd and the appropriate configuration of mysql. Yoan I'm putting together a system that will host a relatively small database (around 20,000 records), as well as run Apache / PHP to search that database. I have the option in front of me to use a P III dual 1GHz machine with a SCSI Raid 5, or to use a single P4 2.8 GHz with a SCSI Raid 1. Both have 1GB RAM. I'm looking to use MySQL as the DB. The site that this machine will host gets about 2 million hits per months (yes, hits, not pageviews or visitors) from about 21,000 unique visitors. Does anyone have an opinion as to which machine will perform best under this scenario? Obviously, both would run FreeBSD. Thanks, Joe Koenig Production Manager jWeb New Media Design [EMAIL PROTECTED] http://www.jwebmedia.com/ 636.928.3162 ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED] ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
Joseph Koenig wrote: I'm putting together a system that will host a relatively small database (around 20,000 records), as well as run Apache / PHP to search that database. I have the option in front of me to use a P III dual 1GHz machine with a SCSI Raid 5, or to use a single P4 2.8 GHz with a SCSI Raid 1. Both have 1GB RAM. I'm looking to use MySQL as the DB. The site that this machine will host gets about 2 million hits per months (yes, hits, not pageviews or visitors) from about 21,000 unique visitors. Does anyone have an opinion as to which machine will perform best under this scenario? Obviously, both would run FreeBSD. Thanks, Joe Koenig Production Manager jWeb New Media Design [EMAIL PROTECTED] http://www.jwebmedia.com/ 636.928.3162 Processors?? To quote Mr. Scott, the more they overthink the plumbin' the easier 'tis to stop up the drain... Plus, the math. Two PIII 1GHz shouldn't be equal to one 2.8 P4. And there's the question of how well SMP is doing these days. There was some discussion of problems for some folks using SMP on latter 4.X'es... but I think DKFS that 5.X is doing better on this? But your talking a production machine...don't you just love decisions? The only advantage I see for the dual proc solution is the RAID-5; a super-redundant storage facility sounds good for an important db. My $.02, Kevin Kinsey DaleCo, S.P. ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
Joseph Koenig wrote: I'm putting together a system that will host a relatively small database (around 20,000 records), as well as run Apache / PHP to search that database. I have the option in front of me to use a P III dual 1GHz machine with a SCSI Raid 5, or to use a single P4 2.8 GHz with a SCSI Raid 1. Both have 1GB RAM. I'm looking to use MySQL as the DB [ ... ] I'd choose the P4 machine, not because of the difference in CPUs as much as because RAID-1 is much better suited for hosting a database than RAID-5. You probably don't need the horsepower of the P4, or even a dual-P3 box unless your workload per transaction is fairly high. 2m hits per month is less than one hit per second; if you have one DB query per pageview, and ~10 hits per page, your average transaction load is going to be quite low. On the other hand, if your usage patterns are bursty, a dual-proc machine helps reduce latency better than a single-proc might... -- -Chuck ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: 1 processor vs. 2
Joseph Koenig wrote: I'm putting together a system that will host a relatively small database (around 20,000 records), as well as run Apache / PHP to search that database. I have the option in front of me to use a P III dual 1GHz machine with a SCSI Raid 5, or to use a single P4 2.8 GHz with a SCSI Raid 1. Both have 1GB RAM. I'm looking to use MySQL as the DB. The site that this machine will host gets about 2 million hits per months (yes, hits, not pageviews or visitors) from about 21,000 unique visitors. Does anyone have an opinion as to which machine will perform best under this scenario? Obviously, both would run FreeBSD. Thanks, Joe Koenig Production Manager jWeb New Media Design [EMAIL PROTECTED] http://www.jwebmedia.com/ 636.928.3162 ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED] Someone else already mentioned this, but RAID-1 will be faster than the RAID-5 at the storage level, if the RAID-5 array is a relatively small # of drives. If you're talking about 2 disk RAID-1 versus 10 disks RAID-5, those numbers may change. If the drives are integrated into the systems, it's also possible the RAID-1 disks are faster drives than the RAID-5 drives... If you're going to run the DB and web server on the same system with a high percentage of static pages, the SMP system may help out. If you have almost all dynamic content is full of complex DB queries, the P4 would do better based solely on CPU speed. How about RAID-1 on the dual PIII and keep the P4 as a workstation? :-) The PIII is likely up to the task, but it really depends on the type of content (is _everything_ PHP generating dynamic content, every page hitting the DB etc?) Scott ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]