We have 2 and 4 hw.ncpu NFS servers with 70+ disks, so there may be
cases, where even the default maximum of 256 threads is not enough to
feed the -otherwise slow- disks.
I guess the real solution here is to change the nfsd worker model to async.
(adapting to top poster)
On 01/09/14 18:14, Adr
On 04/12/2010 06:37 PM, Luigi Rizzo wrote:
Bring in geom_sched, support for scheduling disk I/O requests
in a device independent manner. Also include an example anticipatory
scheduler, gsched_rr, which gives very nice performance improvements
in presence of competing random access pat
Xin LI wrote:
> On Mon, Mar 8, 2010 at 10:14 AM, Ivan Voras wrote:
>
>> On 8 March 2010 16:01, Nathan Whitehorn wrote:
>>
>>> Author: nwhitehorn
>>> Date: Mon Mar 8 15:01:08 2010
>>> New Revision: 204870
>>> URL: http://svn.freebsd.org/changeset/base/204870
>>>
>>> Log:
>>> Enable tmpfs
Alexander Motin wrote:
> Scott Long wrote:
>
>> On Mar 3, 2010, at 1:43 PM, Alexander Motin wrote:
>>
>>> Attila Nagy wrote:
>>>
>>>> Alexander Motin wrote:
>>>>
>>>>> Author: mav
>
Alexander Motin wrote:
> Attila Nagy wrote:
>
>> Alexander Motin wrote:
>>
>>> Author: mav
>>> Date: Wed Mar 3 17:58:41 2010
>>> New Revision: 204648
>>> URL: http://svn.freebsd.org/changeset/base/204648
>>>
>>> L
Alexander Motin wrote:
> Author: mav
> Date: Wed Mar 3 17:58:41 2010
> New Revision: 204648
> URL: http://svn.freebsd.org/changeset/base/204648
>
> Log:
> Several changes to fix livelock under high load, introduced by r203489:
> - change the way in which command queue overflow is handled;
>
