Slower performance with ext4

[Christopher Chan]

>   
>> Did you miss my remarks about when you are not using hardware raid + bbu 
>> cache? You do know that such hardware covers for any short comings in 
>> filesystems with regards to data consistency and that that is the reason 
>> for the existence of such hardware?
>>
>>   
>>     
>
> It is (or should be) widely known that cheap (s)ata drives do not honor 
> fsync requests (*many* google links).
>
>   

Too bad I got the same problem with scsi drives. There were no sata 
drives given to me during my four years as a MTA admin in Outblaze Ltd. 
(2002 - 2004) and with server boards from Supermicro.

>> A server motherboard that uses ECC RAM and SAS/SCSI hard drives and 
>> software raid will suffer the same results. You have been spouting 
>> inaccurate information about filesystem behaviour that will affect those 
>> who do not have the means to purchase your uber hardware that covers for 
>> any filesystem's shortcomings with respects to data integrity. Others 
>> make do with less by having a full understanding of the behaviour of the 
>> operating systems they run whether it is FreeBSD and softupdates or 
>> Linux and its various filesystems that support journaling. You can get 
>> the same data integrity on lesser hardware (motherboards supporting 
>> ECC-RAM are no longer the realm of 'server' grade motherboards) if 
>> configured properly.
>>
>>   
>>     
> No it will not. I've been a Freebsd server admin for the last 10 years - 
> no data loss due to power failure on any of my servers - because I've 
> used reliable hardware that honors fsync.
>
>   


Yawn. Been there and done that. Without bbu cached hardware raid. Just 
plain Linux software raid. XFS = pray for no power loss and ext3 
data=journal  =  sleep well at night (except for spammers getting 
through the developers' webmail system).


You are using hardware raid + bbu and you have no need to delve deep 
into how the filesystems work. If you do not want to take even the 
standard explanations for ext3's (which are repeated for ext4) different 
journaling modes then that is just too bad. Just stop propagating the 
myth that fsync = return after data has been written to the filesytem. 
If that was the case, there would not be large differences in filesystem 
performance