Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 01 Mar 2004 17:13:09 -0500
From:      Forrest Aldrich <forrie@forrie.com>
To:        Derrick Ryalls <ryallsd@datasphereweb.com>
Cc:        freebsd-questions@freebsd.org
Subject:   Re: FreeBSD filesystem performance in Enterprise
Message-ID:  <4043B575.6040400@forrie.com>
In-Reply-To: <A99A5AC30F74624388EE5F757BA58A20D7A23A@RED-MSG-50.redmond.corp.microsoft.com>
References:  <A99A5AC30F74624388EE5F757BA58A20D7A23A@RED-MSG-50.redmond.corp.microsoft.com>

next in thread | previous in thread | raw e-mail | index | archive | help
Not trying to start a holy war -  just  looking into hard facts to 
support some systems I'm designing.   FFS will either work, or it 
won't.  Black or white.

The type of I/O I'm talking about will be in the 100's of thousands of 
email messages (probably more) per day... obviously the underlying OS, 
filesystem tuning, hardware are also an issue.  I'm simply trying to 
gain some insight into other's experience with FFS, etc.


Thanks.


Derrick Ryalls wrote:

>>Curious how FreeBSD ffs performs in Enterprise-level 
>>environments (ie: 
>>email stores that send 100's of thousands of messages per  
>>day) versus 
>>other filesystems like XFS (I heard thre's a port going on for 
>>FreeBSD..?), ReiserFS, et al.   Is there a FAQ that covers 
>>some of this 
>>and the various tuning issues one might consider (filesystem and 
>>kernel).   This applies either disk-alone or across a raid array, 
>>etc.    I'm interested in hearing others experiences (good and bad).
>>
>>
>>    
>>
>
>You are almost starting a holy war  :)
>
>I believe hotmail used to be hosted on FreeBSD until it was bought out by
>MS, that should be a decent volume indicator.
>
>I run a very small email list server and it works fine on a p200.  I did see
>a noticable jump in speed when I switched the mail service from sendmail to
>qmail, so it is also dependant on what you will run.
>
>  
>



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4043B575.6040400>