|
|
Sponsored Content
Operating Systems
AIX
Cannot extend logical volume
Post 302986498 by Scrutinizer on Saturday 26th of November 2016 03:09:17 AM
11-26-2016
Moderator
Indeed as a rule the combination of lvm striping with high end SAN storage (double or triple striping) is to be avoided, both for reasons of simplicity and performance.
Remarkably perhaps, I have come across situations, where lvm striping actually did make a serious performance difference (improvement) with high end SAN Storage and sequential read IO, but only with a narrow width (say 4-8) at small stripe sizes (128KiB-256KiB).
This was because there was a front-end bottle neck and at the same it was difficult to increase IO queue sizes, which is extra important because of the serial nature of Fibre Channel SANs (the bottle neck could even be observed when the cache-hit ratio was at 100% at the front-end storage level).
By using narrow striping it was possible to increase the effective IO queue size, while at the same time not confusing the prefetch algorithms of the SAN storage. The LUN's in the LVM narrow stripe had to be from different physical disk sets in the backend SAN Storage level, in case of a storage array architecture where this would make a difference). At the SAN storage, this translated in a nice even spread of backend usage, without hot spots.
Situations where this mattered was with databases with quite a bit of sequential read IO. This happened with Oracle databases that were never fully optimized, because the standard query specifications kept changing, which in my experience is the situation that occurs often. Another situation is when out of necessity reports or other batches need to run during on-line usage.
Conversely, I have come across a situation where a large stripe size was used (4 MiB) with a large stripe width (16) and that really confused storage, thwarting the prefetch algorithms, and all IO was done with small sizes, bringing sequential read IO to a crawl, while the storage processors were working overtime.
So as usual in performance tuning: "it depends...."
Remarkably perhaps, I have come across situations, where lvm striping actually did make a serious performance difference (improvement) with high end SAN Storage and sequential read IO, but only with a narrow width (say 4-8) at small stripe sizes (128KiB-256KiB).
This was because there was a front-end bottle neck and at the same it was difficult to increase IO queue sizes, which is extra important because of the serial nature of Fibre Channel SANs (the bottle neck could even be observed when the cache-hit ratio was at 100% at the front-end storage level).
By using narrow striping it was possible to increase the effective IO queue size, while at the same time not confusing the prefetch algorithms of the SAN storage. The LUN's in the LVM narrow stripe had to be from different physical disk sets in the backend SAN Storage level, in case of a storage array architecture where this would make a difference). At the SAN storage, this translated in a nice even spread of backend usage, without hot spots.
Situations where this mattered was with databases with quite a bit of sequential read IO. This happened with Oracle databases that were never fully optimized, because the standard query specifications kept changing, which in my experience is the situation that occurs often. Another situation is when out of necessity reports or other batches need to run during on-line usage.
Conversely, I have come across a situation where a large stripe size was used (4 MiB) with a large stripe width (16) and that really confused storage, thwarting the prefetch algorithms, and all IO was done with small sizes, bringing sequential read IO to a crawl, while the storage processors were working overtime.
So as usual in performance tuning: "it depends...."
Last edited by Scrutinizer; 11-26-2016 at 08:19 AM..
|
|
10 More Discussions You Might Find Interesting
1. AIX
Hi All,
I am new to AIX.
I need to extend one Logical Volume it is jfs type on On AIX 5.1.
I have enough free space on the volume group for this extension
Can I use smitty chjfs , will this do it without interruptions to the application that is using this Logical Volume.
Thanks
Scampi (1 Reply)
Discussion started by: scampi
1 Replies
2. UNIX for Advanced & Expert Users
Hello,
I have logical volume group of 50GB, in which I have 2 logical volumes, LogVol01 and LogVol02, both are of 10GB.
If I extend LogVol01 further by 10GB, then it keeps the extended copy after logical volume 2. I want to know where it keeps this information
Regards
Himanshu (3 Replies)
Discussion started by: ghimanshu
3 Replies
3. AIX
Hi,
Smit "Increase the Size of a Logical Volume" command failed. Output:
----------------------------------------------------------
Command: failed stdout: yes stderr: no
Before command completion, additional instructions may appear below.
The distribution of this command (111) failed on... (2 Replies)
Discussion started by: vilius
2 Replies
4. AIX
Hi!
Can anyone help me on how I can do a basic check on the Unix filesystems / physical volumes and logical volumes?
What items should I check, like where do I look at in smit? Or are there commands that I should execute?
I need to do this as I was informed by IBM that there seems to be... (1 Reply)
Discussion started by: chipahoys
1 Replies
5. AIX
Hello,
I am a french computer technician, and i speak English just a little.
On Aix 5.3, I encounter a name conflict logical volume on two volume group.
The first volume lvnode01 is OK in rootvg and mounted. It is also consistent in the ODM
root # lsvg -l rootvg |grep lvnode01 ... (10 Replies)
Discussion started by: dantares
10 Replies
6. HP-UX
Background:
# uname -a
HP-UX deedee B.11.23 U ia64 4294967295 unlimited-user license
deedee.rsn.hp.com:/
# bdf /opt
Filesystem kbytes used avail %used Mounted on
/dev/vg00/lvol6 6553600 6394216 158144 98% /opt
/opt is almost full... (3 Replies)
Discussion started by: Rob Sandifer
3 Replies
7. UNIX for Dummies Questions & Answers
Hi,
I am new to unix. I am working on Red Hat Linux and side by side on AIX also. After reading the concepts of Storage, I am now really confused regarding the terminologies
1)Physical Volume
2)Volume Group
3)Logical Volume
4)Physical Partition
Please help me to understand these concepts. (6 Replies)
Discussion started by: kashifsd17
6 Replies
8. HP-UX
Want to extend the /home filesystem:
Filesystem kbytes used avail %used Mounted on
/dev/vg00/lvol4 262144 260088 2056 99% /home
root@server:./root # vgdisplay vg00
--- Volume groups ---
VG Name /dev/vg00
VG Write Access read/write
VG Status available
Max LV 255
Cur LV 11
Open... (4 Replies)
Discussion started by: proactiveaditya
4 Replies
9. AIX
Hello everyone,
I just read that while creating a logical volume(LV) we can choose the region of the physical volume (PV) in which the LV should be created.
When I say region I mean: outer edge - outer middle - center - inner middle and inner edge.
Can anyone help me understand the utility... (11 Replies)
Discussion started by: adilyos
11 Replies
10. Red Hat
Hello Guys,
I want to create a file system dedicated for an application installation. But there is no space in volume group to create a new logical volume. There is enough space in other logical volume which is being mounted on /var.
I know we can use that logical volume and create a virtual... (2 Replies)
Discussion started by: vamshigvk475
2 Replies
LEARN ABOUT OSF1
stripe
stripe(8) System Manager's Manual stripe(8) NAME
stripe - Stripes a file across several volumes in a file domain SYNOPSIS
/usr/sbin/stripe -n volume_count filename OPTIONS
Specifies the number of volumes the striped file crosses. The number of volumes must be greater than one. OPERANDS
Specifies the name of the file to stripe. DESCRIPTION
The stripe utility enables you to improve the read/write performance of a file. The stripe utility directs a zero-length file (a file with no data written to it yet) to be spread evenly across several volumes within a file domain. As data is appended to the file, the data is spread across the volumes. AdvFS determines the number of pages per stripe segment and alternates the segments among the disks in a sequen- tial pattern. Existing, nonzero-length files cannot be striped using the stripe utility. To stripe an existing file, create a new file, use the stripe utility to stripe the new file, and copy the contents of the file you want to stripe into the new striped file. After copying the file, delete the nonstriped file. Once a file is striped, you cannot use the stripe utility to modify the number of disks that a striped file crosses. To change the volume count of a striped file, you can create a second file with a new volume count, and then copy the contents of the first file into the second file. After copying the file, delete the first file. RESTRICTIONS
You cannot stripe a nonzero-length file or a file that is already striped. EXAMPLES
The following example stripes the file abc across three volumes in the same file domain: # stripe -n 3 abc The following example stripes an existing, nonzero-length file, foo, across three volumes in the same domain. First a new file, newfoo, is created and striped. Then, the contents of file foo are copied to the new, striped file: # touch newfoo # stripe -n 3 newfoo # cp foo newfoo SEE ALSO
advfs(4), showfile(8) stripe(8)