Messages in this thread | | | Date | Fri, 6 Jun 2014 10:02:08 -0400 | From | Konrad Rzeszutek Wilk <> | Subject | Re: Backport request to stable of two performance related fixes for xen-blkfront (3.13 fixes to earlier trees) |
| |
On Fri, Jun 06, 2014 at 06:56:57AM -0700, Greg KH wrote: > On Fri, Jun 06, 2014 at 12:47:07PM +0200, Jiri Slaby wrote: > > On 06/04/2014 07:48 AM, Greg KH wrote: > > > On Wed, May 14, 2014 at 03:11:22PM -0400, Konrad Rzeszutek Wilk wrote: > > >> Hey Greg > > >> > > >> This email is in regards to backporting two patches to stable that > > >> fall under the 'performance' rule: > > >> > > >> bfe11d6de1c416cea4f3f0f35f864162063ce3fa > > >> fbe363c476afe8ec992d3baf682670a4bd1b6ce6 > > > > > > Now queued up, thanks. > > > > AFAIU, they introduce a performance regression. > > That "regression" is also in mainline, right? As Konrad doesn't seem to > think it matters, I'm deferring to the maintainer here.
Hehe.
Greg is correct - the performance regression with tmpfs/ramfs does exist upstream and once a fix has been established will be dealt with. Right now we are fousing on the 99% usage models which is solid state, rotational, and flash (just got one of those) and the two patches outlined above are needed for the stable trees.
Thank you.
Hopefully I haven't confused the issue here. > > thanks, > > greg k-h
| |