Re: [PATCH v2] libnvdimm: check and clear poison before writing to pmem

2016-11-10 Thread Dan Williams
Williams >> Cc: linux-nvdimm@lists.01.org >> Subject: Re: [PATCH v2] libnvdimm: check and clear poison before >> writing to pmem >> > ... >> > >> > This feels like over-engineering a still not perfect solution to a >> > rare problem.

RE: [PATCH v2] libnvdimm: check and clear poison before writing to pmem

2016-11-10 Thread Elliott, Robert (Persistent Memory)
> -Original Message- > From: Linux-nvdimm [mailto:linux-nvdimm-boun...@lists.01.org] On > Behalf Of Vishal Verma > Sent: Thursday, November 10, 2016 3:56 PM > To: Dan Williams > Cc: linux-nvdimm@lists.01.org > Subject: Re: [PATCH v2] libnvdimm: check and clear poiso

Re: [PATCH v2] libnvdimm: check and clear poison before writing to pmem

2016-11-10 Thread Vishal Verma
On 11/10, Dave Jiang wrote: > On 11/10/2016 03:04 PM, Vishal Verma wrote: > > On 11/10, Dan Williams wrote: > >> On Thu, Nov 10, 2016 at 1:56 PM, Vishal Verma > >> wrote: > >>> On 11/10, Dan Williams wrote: > On Thu, Nov 10, 2016 at 11:17 AM, Vishal Verma > wrote: > > On 11/10, Da

Re: [PATCH v2] libnvdimm: check and clear poison before writing to pmem

2016-11-10 Thread Dave Jiang
On 11/10/2016 03:04 PM, Vishal Verma wrote: > On 11/10, Dan Williams wrote: >> On Thu, Nov 10, 2016 at 1:56 PM, Vishal Verma >> wrote: >>> On 11/10, Dan Williams wrote: On Thu, Nov 10, 2016 at 11:17 AM, Vishal Verma wrote: > On 11/10, Dave Jiang wrote: >> We need to clear any

Re: [PATCH v2] libnvdimm: check and clear poison before writing to pmem

2016-11-10 Thread Vishal Verma
On 11/10, Dan Williams wrote: > On Thu, Nov 10, 2016 at 1:56 PM, Vishal Verma > wrote: > > On 11/10, Dan Williams wrote: > >> On Thu, Nov 10, 2016 at 11:17 AM, Vishal Verma > >> wrote: > >> > On 11/10, Dave Jiang wrote: > >> >> We need to clear any poison when we are writing to pmem. The granul

Re: [PATCH v2] libnvdimm: check and clear poison before writing to pmem

2016-11-10 Thread Kani, Toshimitsu
On Thu, 2016-11-10 at 14:56 -0700, Vishal Verma wrote: > On 11/10, Dan Williams wrote:  : > > This feels like over-engineering a still not perfect solution to a > > rare problem.  Outside of atomic-write-and-clear we should just > > keep the code best effort and simple. > > Fair enough :) In that

Re: [PATCH v2] libnvdimm: check and clear poison before writing to pmem

2016-11-10 Thread Dan Williams
On Thu, Nov 10, 2016 at 1:56 PM, Vishal Verma wrote: > On 11/10, Dan Williams wrote: >> On Thu, Nov 10, 2016 at 11:17 AM, Vishal Verma >> wrote: >> > On 11/10, Dave Jiang wrote: >> >> We need to clear any poison when we are writing to pmem. The granularity >> >> will be sector size. If it's less

Re: [PATCH v2] libnvdimm: check and clear poison before writing to pmem

2016-11-10 Thread Vishal Verma
On 11/10, Dan Williams wrote: > On Thu, Nov 10, 2016 at 11:17 AM, Vishal Verma > wrote: > > On 11/10, Dave Jiang wrote: > >> We need to clear any poison when we are writing to pmem. The granularity > >> will be sector size. If it's less then we can't do anything about it > >> barring corruption.

Re: [PATCH v2] libnvdimm: check and clear poison before writing to pmem

2016-11-10 Thread Dan Williams
On Thu, Nov 10, 2016 at 11:17 AM, Vishal Verma wrote: > On 11/10, Dave Jiang wrote: >> We need to clear any poison when we are writing to pmem. The granularity >> will be sector size. If it's less then we can't do anything about it >> barring corruption. >> >> Signed-off-by: Dave Jiang >> --- >>

Re: [PATCH v2] libnvdimm: check and clear poison before writing to pmem

2016-11-10 Thread Vishal Verma
On 11/10, Dave Jiang wrote: > We need to clear any poison when we are writing to pmem. The granularity > will be sector size. If it's less then we can't do anything about it > barring corruption. > > Signed-off-by: Dave Jiang > --- > drivers/nvdimm/claim.c | 24 +--- > 1 fi

[PATCH v2] libnvdimm: check and clear poison before writing to pmem

2016-11-10 Thread Dave Jiang
We need to clear any poison when we are writing to pmem. The granularity will be sector size. If it's less then we can't do anything about it barring corruption. Signed-off-by: Dave Jiang --- drivers/nvdimm/claim.c | 24 +--- 1 file changed, 21 insertions(+), 3 deletions(-)