Sluggish scheduling during a long disk copy

Kris Kennaway kris at
Sun Nov 9 12:56:26 PST 2008

matt donovan wrote:
> On Sun, Nov 9, 2008 at 3:32 PM, Dan <dan-freebsd-questions at>wrote:
>> Odhiambo Washington(odhiambo at 23:25:19 +0300:
>>> On Sun, Nov 9, 2008 at 11:21 PM, Dan <
>> dan-freebsd-questions at>wrote:
>>>> Hello. I am copying one 150G disk to a 3ware mirror, and the machine
>>>> becomes downright unusable. It takes seconds to switch between
>> 'konsole'
>>>> windows and it takes seconds between I type a command (ssh session to
>>>> a remote box, which I know is fast and unloaded) and see it executed.
>>>> This is 7.1-BETA2. Is this a bug or a generally-accepted performance
>>>> behavior?
>>> Bug? :-)
>>> How are you copying?
>> I am copying an 'ntfs-3g'-mounted disk to the 3ware mirror with cp -a.
>> It's around 150G of data, and it's going at about 10MB/s to the mirror.
>> The mirror uses geom journaling. The speed is fine, the disks are slow.
>> But should the copy really freeze-up the system like that?
>> _______________________________________________
>> freebsd-questions at mailing list
>> To unsubscribe, send any mail to "
>> freebsd-questions-unsubscribe at"
> could be an issue with ntfs-3g driver

Sounds like it to me.  ntfs-3g uses FUSE, which is a userland filesystem 
framework.  By design it will have poor I/O performance since every I/O 
transfer will require multiple trips into and out of the kernel.


More information about the freebsd-questions mailing list