FAQ Search Today's Posts Mark Forums Read
» Video Reviews

» Linux Archive

Linux-archive is a website aiming to archive linux email lists and to make them easily accessible for linux users/developers.


» Sponsor

» Partners

» Sponsor

Go Back   Linux Archive > Ubuntu > Ubuntu User

 
 
LinkBack Thread Tools
 
Old 06-19-2010, 03:59 PM
Peng Yu
 
Default current access to file systems

Hi,

I'm seeking for a solution in ubuntu to address the concurrent disk
access problem that are described below. I did a google search but
there are just too many information out there and I don't which is the
best for my situation.

I have one machine (8 CPUs and 40GB RAM) with 4 slots that can be
plugged in 4 local disks. Right now, there is one 2T disk (xfs
filesystem) and a 140GB disk plugged in. I run a speed test using the
gnu coreutils split command to split 8 500MB files (each into 10
smaller files), either in serial or in parallel (8 process running
simultaneously). Both run finish in about 15 sec, which indicates a
speed of about 270MB/s (read and write the same disk). The test is
performed on both on 2T and on 140GB disks.

However, I run 6 other 3rd party program simultaneously (I don't know
how the program handle disk buffering), iotop tells me that each
consume a bandwidth of only a few handred KB/s (both read and write on
2T disk). The 6 processes takes 100% CPU time each, which means that
they are CPU bound rather than disk bound. While they are running, I
start the split test program on the 2T disk. The speed now drops to
only a MB/sec. But if I run the split test program on 140GB disk. the
speed is about 80-90MB/sec.

This clearly indicated that the main bottleneck is on the 2T disk. So
far, I think of 2 solutions.

1. increase the buffers, which involves changing the kernel.
2. using a cluster filesystem, which has several disks to balance the
load on each disk.

But I'm not sure how much performance gain I can get from either
solutions? And how much time it need for a novice administrator? If
one or both solutions are viable, what detailed steps I need to do?

NOTE, in the future I may need to expand the system from just one
machine to multiples machines, which all access the same storage
space. When all the machines with many processes on each machine
access the same storage simultaneously, I'd think that cluster file
system probably is the solution that need to be adopt. But please let
me know if you have any better solutions.


--
Regards,
Peng

--
ubuntu-users mailing list
ubuntu-users@lists.ubuntu.com
Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/ubuntu-users
 
Old 06-20-2010, 02:41 AM
Sandy Harris
 
Default current access to file systems

On 6/19/10, Peng Yu <pengyu.ut@gmail.com> wrote:

> I'm seeking for a solution in ubuntu to address the concurrent disk
> access problem that are described below. ...
>
> I have one machine (8 CPUs and 40GB RAM) ...
> I run a speed test ... (8 process running simultaneously) ...

> NOTE, in the future I may need to expand the system from just one
> machine to multiples machines, which all access the same storage
> space.

I would be looking at a hardware RAID controller. They are not cheap,
but not out of proportion relative to your CPU & RAM costs. Better
reliability which is probably important if many things depend on the
storage. Reduced CPU load, caching, ...

--
ubuntu-users mailing list
ubuntu-users@lists.ubuntu.com
Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/ubuntu-users
 
Old 07-21-2010, 10:30 PM
Peng Yu
 
Default current access to file systems

On Sat, Jun 19, 2010 at 9:41 PM, Sandy Harris <sandyinchina@gmail.com> wrote:
> On 6/19/10, Peng Yu <pengyu.ut@gmail.com> wrote:
>
>> *I'm seeking for a solution in ubuntu to address the concurrent disk
>> *access problem that are described below. ...
>>
>> *I have one machine (8 CPUs and 40GB RAM) ...
>> I run a speed test ... (8 process running simultaneously) ...
>
>> *NOTE, in the future I may need to expand the system from just one
>> *machine to multiples machines, which all access the same storage
>> *space.
>
> I would be looking at a hardware RAID controller. They are not cheap,
> but not out of proportion relative to your CPU & RAM costs. Better
> reliability which is probably important if many things depend on the
> storage. Reduced CPU load, caching, ...

Sorry for the late reply. I just saw your email. Would you please let
me know why RAID controller might help me in this case? Does RAID
controller somehow buffer the data and write them a large chunk at
once? Do you recommend any brand? What specifications of the
controller I should look at to make sure that it matches my machine?

--
Regards,
Peng

--
ubuntu-users mailing list
ubuntu-users@lists.ubuntu.com
Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/ubuntu-users
 
Old 07-22-2010, 10:04 AM
Dave Howorth
 
Default current access to file systems

Peng Yu wrote:
> On Sat, Jun 19, 2010 at 9:41 PM, Sandy Harris <sandyinchina@gmail.com> wrote:
>> On 6/19/10, Peng Yu <pengyu.ut@gmail.com> wrote:
>>
>>> I'm seeking for a solution in ubuntu to address the concurrent disk
>>> access problem that are described below. ...
>>>
>>> I have one machine (8 CPUs and 40GB RAM) ...
>>> I run a speed test ... (8 process running simultaneously) ...
>>> NOTE, in the future I may need to expand the system from just one
>>> machine to multiples machines, which all access the same storage
>>> space.
>> I would be looking at a hardware RAID controller. They are not cheap,
>> but not out of proportion relative to your CPU & RAM costs. Better
>> reliability which is probably important if many things depend on the
>> storage. Reduced CPU load, caching, ...
>
> Sorry for the late reply. I just saw your email. Would you please let
> me know why RAID controller might help me in this case? Does RAID
> controller somehow buffer the data and write them a large chunk at
> once? Do you recommend any brand? What specifications of the
> controller I should look at to make sure that it matches my machine?

Peng Yu, you can answer your questions about RAID yourself. If you don't
know what RAID does, you need to educate yourself first. Do some
browsing. For your application you're looking to get benefits from
striping and you probably don't need a special controller. You can use
Linux software RAID (google for mdadm or look at wikipedia etc).

But when you talk about multiple machines accessing the same disk
storage, when one is already saturating the disk, you're going to a
whole different level. You probably need to do a fundamental review of
your application design to see how to avoid that requirement. It sounds
to me like you need a new system architecture. But that's well outside
the scope of this list.

Cheers, Dave



--
ubuntu-users mailing list
ubuntu-users@lists.ubuntu.com
Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/ubuntu-users
 
Old 07-22-2010, 02:35 PM
Dave Howorth
 
Default current access to file systems

Peng Yu wrote:
> I agree with you that I need to understand RAID and maybe filesystem
> in general. I have read the beginning of the following webpage page.
> In particular, I read what RAID0,1,5 are, which are commonly used
> according to the page. The wiki page is rather long and couldn't
> finish all of it, and it seems to me that not all the information on
> the page are relevant to me at this moment.
>
> http://en.wikipedia.org/wiki/RAID

Yes, that's a good place to start. You won't find any page that has all
the information you need and nothing else. You need to build the
knowledge yourself by reading around.

> My lab have a CORAID

Interesting, I hadn't come across coraid before. Thanks for the paper.

> ... is something wrong with the setup of the CORAID in my system?
> ... do you know what mailing might be the most appropriate

I'd suggest two possible places to look for some help. First would be
Coraid support. They should be able to tell you what should happen and
how it should be set up and at least point you to the right place in
their manuals.

The second place I'd try would be the linux-cluster mailing list.
There'll be more people there with some knowledge and experience.

Cheers, Dave

--
ubuntu-users mailing list
ubuntu-users@lists.ubuntu.com
Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/ubuntu-users
 

Thread Tools




All times are GMT. The time now is 01:30 PM.

VBulletin, Copyright ©2000 - 2014, Jelsoft Enterprises Ltd.
Content Relevant URLs by vBSEO ©2007, Crawlability, Inc.
Copyright 2007 - 2008, www.linux-archive.org