On Tue, Jul 16, 2013 at 12:29:15AM +0100, Peter Robinson wrote:
> 8 socket 10 core Xeon XE (I think that's what they're now called,
> might be Xeon E7) with hyper threading are commonly available now (if
> you've got in the high tens or 100s of thousand pounds) so it might be
> a consideration
On Mon, Jul 15, 2013 at 10:49 PM, Dave Jones wrote:
> On Mon, Jul 15, 2013 at 04:25:54PM -0400, Prarit Bhargava wrote:
>
> > > 1.1M isn't small. We recently declined to build btrfs into the kernel
> > > because it increased the overall memory usage by a similar amount.
> > > Also, we regularly
On Mon, Jul 15, 2013 at 04:25:54PM -0400, Prarit Bhargava wrote:
> > 1.1M isn't small. We recently declined to build btrfs into the kernel
> > because it increased the overall memory usage by a similar amount.
> > Also, we regularly see users and bug reports still in the 2G range.
>
> OOC
On 07/15/2013 04:14 PM, Josh Boyer wrote:
> On Mon, Jul 15, 2013 at 1:21 PM, Prarit Bhargava wrote:
>> I've done some testing across various systems (both "large" and "small").
>> Increasing NR_CPUS seems to have a negligible effect. I see about a 1.1M
>> increase in memory usage when switching
On Mon, Jul 15, 2013 at 1:21 PM, Prarit Bhargava wrote:
> I've done some testing across various systems (both "large" and "small").
> Increasing NR_CPUS seems to have a negligible effect. I see about a 1.1M
> increase in memory usage when switching between 128 cpus and 5120 cpus. Since
> most sy
On Mon, 15 Jul 2013 20:30:54 +0200
Dan Horák wrote:
> - disable various drivers not relevant for s390x
> - enable kdump support
this is a first round required for having a buildable kernel in rawhide
Dan
> ---
> config-s390x | 39 ---
> 1 f
- disable various drivers not relevant for s390x
- enable kdump support
---
config-s390x | 39 ---
1 file changed, 32 insertions(+), 7 deletions(-)
diff --git a/config-s390x b/config-s390x
index ab65656..e1e06a5 100644
--- a/config-s390x
+++ b/config-s390x
@@ -
On 07/15/2013 01:33 PM, "Jóhann B. Guðmundsson" wrote:
> On 07/15/2013 05:21 PM, Prarit Bhargava wrote:
>> I've done some testing across various systems (both "large" and "small").
>> Increasing NR_CPUS seems to have a negligible effect. I see about a 1.1M
>> increase in memory usage when switchin
On 07/15/2013 05:21 PM, Prarit Bhargava wrote:
I've done some testing across various systems (both "large" and "small").
Increasing NR_CPUS seems to have a negligible effect. I see about a 1.1M
increase in memory usage when switching between 128 cpus and 5120 cpus. Since
most systems ship with
I've done some testing across various systems (both "large" and "small").
Increasing NR_CPUS seems to have a negligible effect. I see about a 1.1M
increase in memory usage when switching between 128 cpus and 5120 cpus. Since
most systems ship with 4G or more these days, I cannot see an issue with
On Mon, Jul 15, 2013 at 04:55:24PM +0200, Reindl Harald wrote:
>
>
> Am 15.07.2013 16:44, schrieb Michal Schmidt:
> > On 07/13/2013 01:44 AM, Reindl Harald wrote:
> >> please take a look at this
> >> https://bugzilla.redhat.com/show_bug.cgi?id=982740#c12
> >>
> >> what do we do in the future to d
On Mon, 2013-07-15 at 16:55 +0200, Reindl Harald wrote:
>
> Am 15.07.2013 16:44, schrieb Michal Schmidt:
> > On 07/13/2013 01:44 AM, Reindl Harald wrote:
> >> please take a look at this
> >> https://bugzilla.redhat.com/show_bug.cgi?id=982740#c12
> >>
> >> what do we do in the future to disable ipv
On 07/15/2013 02:44 PM, Michal Schmidt wrote:
On 07/13/2013 01:44 AM, Reindl Harald wrote:
please take a look at this
https://bugzilla.redhat.com/show_bug.cgi?id=982740#c12
what do we do in the future to disable ipv6 entirely
and why is "ipv6.disable=1" as kernel param at least
with 3.10.0-1.fc
On 07/13/2013 01:44 AM, Reindl Harald wrote:
please take a look at this
https://bugzilla.redhat.com/show_bug.cgi?id=982740#c12
what do we do in the future to disable ipv6 entirely
and why is "ipv6.disable=1" as kernel param at least
with 3.10.0-1.fc20.x86_64 on F19?
Back in 2011 the preferred
14 matches
Mail list logo
