8k to 32k block size

Hello Everyone,
I have a project coming up where I need to upgrade
from 8k to 32k block size. I am on database version
10.2.0.3. Database is on raw devices. Size of the
database is 2TB. I need to know is there any docs on
how to upgrade block size or anything that is useful
(scripts,suggestion) etc .You don't mention WHY. It would be interesting to know.
1) Database block size is locked in at database create time. TO change that you have the opportunity to rebuild the database from scratch.
2) Tablespace block size is locked in at tablespace create time. TO change that you have the opportunity to create a replacement tablespace from scratch.
3) Be sure to quantify your benefits in a test environment before jumping to a new block size. Several discussions have indicated that block size does not really matter [in terms of general performance] ... other than some very specialized situations. The major benefit in general seems to be the opportunity to visit some block size related bugs.

Similar Messages

32k block size

hi all,
TOday i was not able to create tablespace with 32k block size when i was in office.
I have oracle 10gR2 with Windows 2003 32bit.
I interacted with friend as per him we cannt create 32k block size on 32bit windows...
IS HE RIGHT ABOUT THIS???
Thanks,
Neerav

Neerav999 wrote:
hi all,
TOday i was not able to create tablespace with 32k block size when i was in office.
I have oracle 10gR2 with Windows 2003 32bit.
I interacted with friend as per him we cannt create 32k block size on 32bit windows...
IS HE RIGHT ABOUT THIS???Yes. (http://download.oracle.com/docs/cd/B19306_01/win.102/b14304/specs.htm#sthref641)
Platform specific limits are provided in platform specific docs. Refer to the 'Master List' of docs for the version of Oracle you use - in this case http://www.oracle.com/pls/db102/portal.portal_db?selected=3
For Windows, these docs are
Platform Guide for Microsoft Windows (32-Bit)
Platform Guide for Microsoft Windows (64-Bit) on Intel Itanium
Platform Guide for Microsoft Windows x64
For OpenVMS, Unix and Linux, and others the docs include
Administrator's Reference for hp OpenVMS
Administrator's Reference for UNIX-Based Operating Systems
System Administration Guide for IBM z/OS (OS/390)

Mac Pro RAID block size recommendations for working with audio in Logic Pro

I have recently ordered a Mac Pro and plan to do a RAID configuration across 3 HDD's
The RAID type i am going to do is a RAID 0 striped.
The computer is going to be used primarily for audio post production and working with 20+ 24-Bit audio files at any one time within a Logic project.
I want to know what is the best block size i should use when configuring the RAID.
I understand that using a higher block size is best for working with large files but do i need to do this in my case or will the default 32k block size be enough?
Thanks in advance

Use 64k. Things like databases like having 32k blocks because of all the small files. Audio files are pretty small even at 24-bit 192KHz. Go to 128k if all you are doing is streaming and no samples. But 20+ 24-bit is really not too large anyway considering most modern HDD's can stream 100MB/s off one spindle. You'll probably be fine regardless of the block size you choose. But most audio pro's choose 64k.

RAID, ASM, and Block Size

* This was posted in the "Installation" Thread, but I copied it here to see if I can get more responses, Thank you.*
Hello,
I am about to set up a new Oracle 10.2 Database server. In the past, I used RAID5 since 1) it was a fairly small database 2) there were not alot of writes 3) high availability 4) wasted less space compared to other RAID techniques.
However, even though our database is still small (around 100GB), we are noticing that when we update our data, the time it takes is starting to grow to a point whereby the update that used to take about an hour, now takes 10-12 hours or more. One thing we noticed that if we created another tablespace which had a block size of 16KB versus our normal tablespace which had a block size of 8KB, we almost cut the update time in half.
So, we decided that we should really start from scratch on a new server and tune it optimally. Here are some questions I have:
1) Our server is a DELL PowerEdge 2850 with 4x146GB Hard Drives (584GB total). What is the best way to set up the disks? Should I use RAID 1+0 for everything? Should I use ASM? If I use ASM, how is the RAID configured? Do I use RAID0 for ASM since ASM handles mirroring and striping? How should I setup the directory structure? How about partitioning?
2) I am installing this on Linux and when I tried on my old system to use 32K block size, it said I could only use 16K due to my OS. Is there a way to use a 32K block size with Linux? Should I use a 32K block size?
Thanks!

Hi
RAID 0 does indeed offer best performance, however if any one drive of the striped set fails you will lose all your data. If you have not considered a backup strategy now would be the time to do so. For redundancy RAID 1 Mirror might be a better option as this will offer a safety net in case of a single drive failure. A RAID is not a backup and you should always consider a workable backup strategy.
Purchase another 2x1TB drives and you could consider a RAID 10? Two Stripes mirrored.
Not all your files will be large ones as I'm guessing you'll be using this workstation for the usual mundane matters such as email etc? Selecting a larger block size with small file sizes usually decreases performance. You have to consider all applications and file sizes, in which case the best block size would be 32k.
My 2p
Tony

Install Recommendations (RAID, ASM, Block Size etc)

Hello,
I am about to set up a new Oracle 10.2 Database server. In the past, I used RAID5 since 1) it was a fairly small database 2) there were not alot of writes 3) high availability 4) wasted less space compared to other RAID techniques.
However, even though our database is still small (around 100GB), we are noticing that when we update our data, the time it takes is starting to grow to a point whereby the update that used to take about an hour, now takes 10-12 hours or more. One thing we noticed that if we created another tablespace which had a block size of 16KB versus our normal tablespace which had a block size of 8KB, we almost cut the update time in half.
So, we decided that we should really start from scratch on a new server and tune it optimally. Here are some questions I have:
1) Our server is a DELL PowerEdge 2850 with 4x146GB Hard Drives (584GB total). What is the best way to set up the disks? Should I use RAID 1+0 for everything? Should I use ASM? If I use ASM, how is the RAID configured? Do I use RAID0 for ASM since ASM handles mirroring and striping? How should I setup the directory structure? How about partitioning?
2) I am installing this on Linux and when I tried on my old system to use 32K block size, it said I could only use 16K due to my OS. Is there a way to use a 32K block size with Linux? Should I use a 32K block size?
Thanks!

The way I usually handle databases of that size if you don't feel like migrating to ASM redundancy is to use RAID-10. RAID5 is HORRIBLY slow (your redo logs will hate you) and if your controller is any good, a RAID-10 will be the same speed as a RAID-0 on reads, and almost as fast on writes. Also, when you create your array, make the stripe blocks as close to 1MB as you can. Modern disks can usually cache 1MB pretty easily, and that will speed the performance of your array by a lot.
I just never got into ASM, not sure why. But I'd say build your array as a RAID-10 (you have the capacity) and you'll notice a huge difference.
16k block size should be good enough. If you have recordsets that are that large, you might want to consider tweaking your multiblock read count.
~Jer

How to change existing database block size in all tablespaces

Hi,
Need Help to change block size for my existing database which is in 8kb of block size.
I have read that we can only change block size during database creation, but i want to change it after database installation.
because for some reason i dont want to change the database installation script.
Can any one list the steps to change database block size for all existing table space (except system, temp ).
want to change it to 32kb.
Thank you for you time.
-Rushang Kansara

> We are facing more and more physical reads, I thought by using 32K block size
we would resolve that..
A physical read reported by Oracle may not be - it could well be a logical read from the o/s file system cache and not a true physical read. With raw devices for example, a physical I/O reported by Oracle is indeed one as there is no o/s cache for raw devices. So one needs to be careful how aone interprets number like physical reads.
Lots of physical reads may not necessarily be a bad thing. In contrast, a high percentage of "good/fast" logical reads (i.e. a high % buffer cache hit ratio) may indicate a serious problem with application design - as the application is churning through the exact same data again and again and again. Applications should typically only make a single pass through a data set.
The best way to deal with physical reads is to make them less. Simple example. A database deals with a lot of inserts. Some bright developer decided to over-index a table. Numerous indexes for the same columns exist in difference physical column orders.
Oracle now spends a lot of time dealing (reading) with these indexes when inserting (or updating a row). A single write I/O may incur a 100 read I/Os as a result of these indexes needing to be maintained.
The bottom line is that "more and more physical I/O" is merely a symptom of a problem. Trying to speed these up could well be a wasted exercise. Besides, the most optimal approach to "lots of I/O" is to tune it to make less I/O.
I/O is the most expensive operation for a RDBMS. It is very difficult to make this expense less (i.e. make I/Os faster). It is more effective to make sure that you use this expensive resource in an optimal way.
Simple example. Single very large table with 4 indexes. Not very efficient design I/O wise. Single very large partitioned table with local indexes. This can reduce I/O on that table by up to 80% in my experience.

Multi Block Size

Oracle 10.2.0.4:
We are creating tablespace of 32K block to place BLOB table. I needed some suggestion on the following:
1. Currently our DB_CACHE_SIZE is set to 0. Do I need to set DB_nk_CACHE_SIZE to 0? Would oracle auto tune this parameter if I set to 0? What's preferable?
2. If I enable CACHE on LOB column would it affect other online users? I am assming there will be a separate buffer pool for 32K block size and probably will not affect online users.

1. Say your DB_BLOCK_SIZE (for the LOB Segment Tablespace) is 8KB. Say your CHUNKSIZE is 32KB.
Say you insert a LOB of 10KB. Oracle's write will be 32KB.
Say you insert a LOB of 100KB. Oracle's writes will be 4 32KB chunks.
2. For a normal table, multiple rows will fit into a block. The "free" space is initial reserved based on PCTFREE. However, actual usage will vary based on the pattern of INSERTs and DELETEs. ASSM manages the candidacy of a block for new rows based on the free space.
3. Before you create a 32KB tablespace, you have to allocate a 32K CACHE. That requires a restart !
4. If you use an SPFILE , the parameter can be "unset" by using the
"ALTER SYSTEM RESET 'db_file_multiblock_read_count'; " command.
TEST TEST TEST !!
You must test the impact of 32KB on your LOBs and other issues. Note that this means that you'd be setting up a separate cache. Whatever cache space the LOB was using the DEFAULT cache earlier is now "released" to other tables/indexes etc. However, if the new 32KB CACHE is much lesser than the space it used to take in the DEFAULT, then the LOB operations may be slower !
Also, obviously your I/Os are now larger with a larger CHUNK size
TEST TEST TEST !!
Test for the impact of unsettting db_file_multiblock_read_count and relying on SYSTEM Stats.

ORA-00374 - Block Size issue

I've already searched and researched this quite a bit. I am not using 9i like the other post about this issue from many years ago. Before you ask "Why a db_block_size of 32k?", this is for a test case. Simple as that.
My system:
Quad DC Operton, 32GB RAM, 4x 15k SAS disks in hardware RAID10.
Windows Server 2008 R2 Standard 64bit (I much prefer Linux, but this test requires Win2008)
Oracle 11g R2 64-bit EE
The Disk with the O/S and ORACLE_HOME is formatted with the default 4k size allocation units.
The allocated database file storage IS formatted with 32k sized allocation units and is on a SAN.
I know it's 32k because when I presented the LUN to the server, I formatted it with 32k allocation units. See below the output paying attention to the * * section:
C:\Users\********************>fsutil fsinfo ntfsinfo o:
NTFS Volume Serial Number : 0x60d245e2d245bcd2
Version : 3.1
Number Sectors : 0x00000000397fc7ff
Total Clusters : 0x0000000000e5ff1f
Free Clusters : 0x0000000000e5f424
Total Reserved : 0x0000000000000000
Bytes Per Sector : 512
Bytes Per Cluster : 32768
Bytes Per FileRecord Segment : 1024
Clusters Per FileRecord Segment : 0
Mft Valid Data Length : 0x0000000000040000
Mft Start Lcn : 0x0000000000018000
Mft2 Start Lcn : 0x0000000000000001
Mft Zone Start : 0x0000000000018000
Mft Zone End : 0x0000000000019920
RM Identifier: 35506ECB-7F9E-11DF-99F3-001EC92FDE3F
So, my db file storage is formatted with a 32k allocation size.
My issue is this:
Oracle shows me the 32k block size when running DBCA using the Custom template. I choose it and the other required options are configured, and when it starts building the DB, I get this:
ORA:00374: parameter db_block_size = 32768 invalid ; must be a multiple of 512 in the range [2048..16384].
Other responses I've seen to this says "Windows doesn't support a allocation size above 8k or 16k" which is utterly absurd since I run SQL2008 on a few machines and it DOES support up to a 64k allocation size, which is what I run. I know this for a FACT.
Windows DOES support up to a 64k allocation size. Does anyone know why Oracle is giving me a hard time about it?
I saw Metalink note 794842.1, but I'd like to know the reasoning/logic for this limitation?
Edited by: user6517483 on Jun 24, 2010 9:21 PM

user6517483 wrote:
I saw Metalink note 794842.1, but I'd like to know the reasoning/logic for this limitation?
A WAG.. Oracle is written to be run on a wide variety of operating system. As operating systems differ one typically designs something that is equivalent in functionality to a Windows HAL - this provides an abstraction layer between the kernel services/calls that is needed by the s/w and the actual implementation of such by the kernel itself.
So despite the kernel supporting feature X, it could be different than similar features supported on other kernels and difficult to implement via this s/w HAL-like interface. The Windows kernel has a lot of differences from the Linux kernel for example.. and somehow Oracle needs to make the same core db s/w run on both. Not unrealistic to expect that some kernel features will be supported better than others, as there is a common denominator ito design and implementation in the core s/w.
As this is a case with block sizes... not that critical IMO. I have played with different block sizes in a 20+TB storage system and Oracle RAC (10.2g) on Linux (part of testing the combo of storage system and cluster and technologies used). Larger block sizes made zero difference to raw I/O performance. The impact was instead more a logical one. Fewer db blocks can be cached as these are larger.. more data can be written into a datablock. And as numerous experienced Oracle professionals have commented, Oracle decided that the default 8KB size is a best fit at this layer.
So extensive and very accurate testing needs to be done IMO to determine whether a larger block size is justified... and the effort to do that may just outweigh the little gains achieved by finding the "+perfect+" block size. Why not focus all that effort instead on correctly using Oracle? Application design? Data modeling? Development and coding? These are factors that play the most dominant roles at the end of day that impact and determine performance.

How to change block size 32 at installation of oracle

hey
i'm going to install aoracle on 64bit windows server 2003. but the problem i'm facing is that i dont know how to change bolck size from 8k to 32k. i usually run setup dan install oracle but during this process it not prompt to change Bolck size. plz help what step i should take in order to successful installtion of oracle 64bit with 32K block size. i tried to find dcoumnet link but every body disscuse the db block size could be change but how i did find anywhere.

yes you are right but what can i do as per my understanding about the below statement is that i should crerate DSS instead of gernal purpose database plz help what can i do now
From Bug 5141453, development indicates that DB_BLOCK_SIZE cannot be changed for the General Purpose, Transaction Procession and DataWarehouse templates as the seed database is using 8k block size.
You should create a custom database to get a different block size.
References

Need to understand the relation B/w Bigger block size like 16k or 32k

Hi
How can we determine which block size is good for the data base specially for reporting DB on which real time replication is being performed.
I will really appreciate if some one could help me in identifying this or are there any ways to find out the correct DB block size by queering any db objects.

I think that part of the decision will have to be based on knowledge of your application and how it interacts with the database. If you database does a lot of single reads/updates of records then the smaller block size will probably be more appropriate.
However if your application does bulk reads, insertions then you might benefit for larger block sizes.
There are several Thread already on this subject and references as well:
size of db_block_size
how to decide size of db_block_size of a block.
Re: DB_BLOCK_SIZE
do a search in the search field on the main thread page for more.
Regards
tim

Raid storage usage and block size

We have two XServe RAID units Raid 5 and we are adding a new 16 bay ACNC raid with 16 1.5TB drives in Raid 6 + Hot Spare. I initialized the Raid 6 with 128K block size. The total data moving from the older raid volumes is around 5.7TB, but on the new Raid it is taking around 7.4TB of space. Is this due to the 128K block size? This is a prepress server so most of the files are quite large, but there may be lots of small files as well.

Hi
RAID 0 does indeed offer best performance, however if any one drive of the striped set fails you will lose all your data. If you have not considered a backup strategy now would be the time to do so. For redundancy RAID 1 Mirror might be a better option as this will offer a safety net in case of a single drive failure. A RAID is not a backup and you should always consider a workable backup strategy.
Purchase another 2x1TB drives and you could consider a RAID 10? Two Stripes mirrored.
Not all your files will be large ones as I'm guessing you'll be using this workstation for the usual mundane matters such as email etc? Selecting a larger block size with small file sizes usually decreases performance. You have to consider all applications and file sizes, in which case the best block size would be 32k.
My 2p
Tony

RAID block size for final cut pro x

Just got one of the new late 2012 27" iMacs and a 6 TB LaCie Thunderbolt drive. Can finally edit the video I took last spring. I'll be using Final Cut Pro X, and doing a lot of multicam stuff with 4 or 5 views and a separate audio track. The LaCie came formatted as a mirrored RAID. I'm going to change that to 0 (Striped RAID set), but am wondering what block size to set. The default is 32k, but I have read that this ought to be increased to the max (256k) for video editing. I have also read it should NOT be increased. And the posts I have read have all been at least 3 years old. So let me ask you all--what block size would you recommend for my situation?
Thanks in advance!

Hi Eddie...
This depends on what kind of source footage you are editing....
For compressed Video, Audio and Uncompressed audio 128k
I have only had BAD results with 256k. 64 is also weird. Whereas 32 is fine.
All my RAIDs have 128k for audio/video editing
you can go further if you editing Image Sequences.. but according to my own findings and I have been dealing with raid since years.... 128k does the job the best.
Rule of thumb.... The smaller the file sizes you are putting the RAID the smaller the block size. And vice versa.
I.e. You would cripple the raid performance if storing a database on it, having a block size of 256. In case of servers and OS 32k would be a good choice, perhaps even 16k if supported.

Best Raid Block Size for video editing

I cannot seem to get my head round about which Raid Block Size I should set my Striped Raid 50 configuration to.
There seems to be very little info about this, but what info there is seems to imply that it could seriously affect the performace of the Raid.
I have initialized two Raid array's to Raid 5 and was about to stripe them together using Disk Utility, when I decided to click on options in the bottom left of the Disk Utility window. This is where you can set the Raid Block Size.
The default is 32K, but it states that there could be 'performance benefits' if this setting is changed to better match my configuration.
What exactly does this mean?
I want do read multiple dv streams from my Raid 50 - Any ideas which Block Size I should allocate??
Should I just leave it as the default 32K??
Any help will be appreciated
Cheers
Adam

My main concern is really to have as many editors as possible reading DV footage from the Raid simultaneously (up to 5 at once).
I understand that we may struggle at times, but Xsan isn't an option and I just need to get the best out of a limited budget!
Chers
Adam

Recommended Block Size For RAID 0

I am setting up a RAID configuration (Striping, no Parity, Mac G5, OS-X) and was curious what the recommended Block Size should be. Content is primarily (but not limited to) Images created with Adobe Photoshop CS2 and range in size from 1.5MB to >20MB. The default for OS-X is 32K chunks of data.
Drives are External FW-400.
Many thanks, and Happy Holidays to all!

If it is just scratch, run some benchmarks with it set to 128k and 256k and see how it feels with each. The default is too small, though some find it acceptable for small images. For larger files you want larger - and for PS scratch you definitely want 128 or 256k.

Drives, block size and raptor300 choice

Hi,
Got MacPro2,1 (07 flavour) and was planning on upgrading some internal drives. My boot is currently using two striped WD 500G's with a block size of 16k. If i were to replace these with newer drives and changed the block size to 32k, would there be any issues to speak of ? Thinking of superduper backups, Adobe CS3 licensing, Time machine doing whole boot update etc.
Alternatively i may go for a pared-down boot and use one raptor 300GB, but which one ?
WD3000BLFS / WD3000HLFS / WD3000GLFS ? - HLFS looks like the one with regularly placed SATA connections, but unsure which fits the MacPro sleds. Also is there a link for further isolation solutions eg. vibration dampeners.
Do the Raid Edition's of WD drives still cut the mustard in terms of performance (1TB Western Digital WD1002FBYS RE3, SATA 3Gb/s, 7200 rpm, 32MB Cache, 4.20 ms).
Many thanks
J

16k use to be slightly better for boot drive. The trouble wtih Apple's, I don't know how to change it on the fly like I can with SoftRAIDs.
Okay, so you probably might want 4 WD Veloci's for scratch, or 3 SSDs.
Any WD Black or RE3 should be just fine, 500GB up to 1TB, and then you get into 2TB Green RE4, yes, an RE Green drive edition.
The other factor is you want even more than 16GB RAM to be used as cache for primary 'scratch'.
There is a guide to photoshop acceleration and optimizing up on
http://www.macgurus.com - lower left side panel of links to articles.

8k to 32k block size

Similar Messages

Maybe you are looking for