[Ocfs2-users] debugfs.ocfs2 and Feature Incompat

Stefan Priebe - allied internet ag s.priebe at allied-internet.ag
Tue Jun 1 11:55:21 PDT 2010


Hi!

GFS2 with the same machines same interconnect same kernel... does have a 
  higher speed in creating, deleting...

with ocfs2 the value is about 1000-2000 - with GFS2 about 11000.

Stefan

Sunil Mushran schrieb:
> You'll have to dig deeper than that. As in, find the real cause of
> the slowdown. It could be many things starting with a high latency
> interconnect, slow disk, etc.
> 
> Indexed dirs allow one to support large directories efficiently. Whether
> it improves performance or not depends on whether that was the
> "bottleneck" in the first place.
> 
> On 06/01/2010 11:00 AM, Stefan Priebe - allied internet ag wrote:
>>
>> No not but bonnie is still as slow as before when creating and 
>> deleting files. I thought this should be "fixed" when using indexed-dirs.
>>
>> Stefan
>>
>> Sunil Mushran schrieb:
>>> Are you having any problems using the software?
>>>
>>> On 06/01/2010 10:55 AM, Stefan Priebe - allied internet ag wrote:
>>>> Hi!
>>>>
>>>> Thanks for your answer but i'm still a little bit confused.
>>>>
>>>> I'm running ocfs2 tools git HEAD (middle of may) on each machine 
>>>> with a 2.6.32.12 kernel. Also the disk was formatted using:
>>>> mkfs.ocfs2 --fs-feature-level=max-features -L ocfs2disk -N 10 -T 
>>>> mail -v /dev/sdb
>>>>
>>>> So i thought that i can now use features like unwritten, inline-data 
>>>> and indexed-dirs.
>>>>
>>>> Stefan
>>>>
>>>> Sunil Mushran schrieb:
>>>>> On 06/01/2010 04:06 AM, Stefan Priebe - allied internet ag wrote:
>>>>>
>>>>> <snip>
>>>>>>           Feature Compat: 3 backup-super strict-journal-super
>>>>>>           Feature Incompat: 8016 sparse extended-slotmap inline-data
>>>>>> metaecc xattr indexed-dirs refcount
>>>>>>           Tunefs Incomplete: 0
>>>>>>           Feature RO compat: 1 unwritten
>>>>>>
>>>>> <snip>
>>>>>
>>>>>> But why is inline-data, indexed-dirs and so on incompatible?
>>>>>
>>>>> incompat means that a version of the fs not aware of this feature
>>>>> should not mount the fs. And that fsck should abort. Users 
>>>>> encountering
>>>>> this error need to mount the fs with a newer version of the fs. Or, 
>>>>> use
>>>>> tunefs.ocfs2 to disable that feature.
>>>>>
>>>>> Similarly, ro compat features means that a version of the fs not aware
>>>>> of the feature can mount fs in read-only mode only.
>>>>>
>>>>> As to which feature is incompat/ro/compat is a function of the disk 
>>>>> format
>>>>> change involved. Changes that do not negatively affect the 
>>>>> functioning when
>>>>> mounted with an older version are "compat". Changes that will 
>>>>> corrupt the
>>>>> fs if mounted with an older version are "incompat". "ro compat" are 
>>>>> changes
>>>>> that will work as long as the older fs does not write to it.
>>>
> 



More information about the Ocfs2-users mailing list