Skip site navigation (1)Skip section navigation (2)
Date:      Sun, 09 Nov 2008 12:57:16 -0800
From:      Kris Kennaway <kris@FreeBSD.org>
To:        matt donovan <kitchetech@gmail.com>
Cc:        freebsd-questions@freebsd.org
Subject:   Re: Sluggish scheduling during a long disk copy
Message-ID:  <49174EAC.2070403@FreeBSD.org>
In-Reply-To: <28283d910811091235q70181b52nc4235aea61518cd@mail.gmail.com>
References:  <20081109202149.GA7091@ourbrains.org>	<991123400811091225t392bd3f3i531dbe348a13e5e4@mail.gmail.com>	<20081109203241.GB8395@ourbrains.org> <28283d910811091235q70181b52nc4235aea61518cd@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help
matt donovan wrote:
> On Sun, Nov 9, 2008 at 3:32 PM, Dan <dan-freebsd-questions@ourbrains.org>wrote:
> 
>> Odhiambo Washington(odhiambo@gmail.com)@2008.11.09 23:25:19 +0300:
>>> On Sun, Nov 9, 2008 at 11:21 PM, Dan <
>> dan-freebsd-questions@ourbrains.org>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@freebsd.org mailing list
>> http://lists.freebsd.org/mailman/listinfo/freebsd-questions
>> To unsubscribe, send any mail to "
>> freebsd-questions-unsubscribe@freebsd.org"
>>
> 
> 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.

Kris



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?49174EAC.2070403>