RE: [PATCH] block: loose check on sg gap

2017-01-11 Thread Dexuan Cui
i <toshi.k...@hpe.com>; > Dan Williams <dan.j.willi...@intel.com>; Damien Le Moal > <damien.lem...@hgst.com>; KY Srinivasan <k...@microsoft.com> > Subject: Re: [PATCH] block: loose check on sg gap > > On Wed, Jan 11, 2017 at 1:10 PM, Dexuan Cui <de...@microsoft.c

RE: [PATCH] block: loose check on sg gap

2017-01-11 Thread Dexuan Cui
Mike Christie ; Martin K. > Petersen ; Toshi Kani ; > Dan Williams ; Damien Le Moal > ; KY Srinivasan > Subject: Re: [PATCH] block: loose check on sg gap > > On Wed, Jan 11, 2017 at 1:10 PM, Dexuan Cui wrote: > >> From: Dexuan Cui > >> Sent: Tuesday, December 20,

Re: [PATCH] block: loose check on sg gap

2017-01-11 Thread Ming Lei
;mchri...@redhat.com>; Martin K. Petersen <martin.peter...@oracle.com>; >> Toshi Kani <toshi.k...@hpe.com>; Dan Williams <dan.j.willi...@intel.com>; >> Damien Le Moal <damien.lem...@hgst.com> >> Subject: RE: [PATCH] block: loose check on sg gap >> >

Re: [PATCH] block: loose check on sg gap

2017-01-11 Thread Ming Lei
>> ; Hannes Reinecke ; Mike Christie >> ; Martin K. Petersen ; >> Toshi Kani ; Dan Williams ; >> Damien Le Moal >> Subject: RE: [PATCH] block: loose check on sg gap >> >> > From: Jens Axboe [mailto:ax...@fb.com] >> > Sent: Tuesday, December 20

RE: [PATCH] block: loose check on sg gap

2017-01-10 Thread Dexuan Cui
pe.com>; Dan Williams <dan.j.willi...@intel.com>; > Damien Le Moal <damien.lem...@hgst.com> > Subject: RE: [PATCH] block: loose check on sg gap > > > From: Jens Axboe [mailto:ax...@fb.com] > > Sent: Tuesday, December 20, 2016 10:31 > > To: Ming Lei <ming.

RE: [PATCH] block: loose check on sg gap

2017-01-10 Thread Dexuan Cui
Dan Williams ; > Damien Le Moal > Subject: RE: [PATCH] block: loose check on sg gap > > > From: Jens Axboe [mailto:ax...@fb.com] > > Sent: Tuesday, December 20, 2016 10:31 > > To: Ming Lei > > Cc: Linux Kernel Mailing List ; linux-block > > bl...@vger.ke

RE: [PATCH] block: loose check on sg gap

2016-12-19 Thread Dexuan Cui
Kani <toshi.k...@hpe.com>; Dan Williams <dan.j.willi...@intel.com>; > Damien Le Moal <damien.lem...@hgst.com> > Subject: Re: [PATCH] block: loose check on sg gap > > On 12/19/2016 07:07 PM, Ming Lei wrote: > > On Sun, Dec 18, 2016 at 12:49 AM, Jens Axboe <ax...@fb.

RE: [PATCH] block: loose check on sg gap

2016-12-19 Thread Dexuan Cui
e > ; Martin K. Petersen ; > Toshi Kani ; Dan Williams ; > Damien Le Moal > Subject: Re: [PATCH] block: loose check on sg gap > > On 12/19/2016 07:07 PM, Ming Lei wrote: > > On Sun, Dec 18, 2016 at 12:49 AM, Jens Axboe wrote: > >> On 12/17/2016 03:49 AM, Ming Lei

Re: [PATCH] block: loose check on sg gap

2016-12-19 Thread Jens Axboe
On 12/19/2016 07:07 PM, Ming Lei wrote: > On Sun, Dec 18, 2016 at 12:49 AM, Jens Axboe wrote: >> On 12/17/2016 03:49 AM, Ming Lei wrote: >>> If the last bvec of the 1st bio and the 1st bvec of the next >>> bio are contineous physically, and the latter can be merged >>> to last

Re: [PATCH] block: loose check on sg gap

2016-12-19 Thread Jens Axboe
On 12/19/2016 07:07 PM, Ming Lei wrote: > On Sun, Dec 18, 2016 at 12:49 AM, Jens Axboe wrote: >> On 12/17/2016 03:49 AM, Ming Lei wrote: >>> If the last bvec of the 1st bio and the 1st bvec of the next >>> bio are contineous physically, and the latter can be merged >>> to last segment of the 1st

Re: [PATCH] block: loose check on sg gap

2016-12-19 Thread Ming Lei
On Sun, Dec 18, 2016 at 12:49 AM, Jens Axboe wrote: > On 12/17/2016 03:49 AM, Ming Lei wrote: >> If the last bvec of the 1st bio and the 1st bvec of the next >> bio are contineous physically, and the latter can be merged >> to last segment of the 1st bio, we should think they don't

Re: [PATCH] block: loose check on sg gap

2016-12-19 Thread Ming Lei
On Sun, Dec 18, 2016 at 12:49 AM, Jens Axboe wrote: > On 12/17/2016 03:49 AM, Ming Lei wrote: >> If the last bvec of the 1st bio and the 1st bvec of the next >> bio are contineous physically, and the latter can be merged >> to last segment of the 1st bio, we should think they don't >> violate sg

Re: [PATCH] block: loose check on sg gap

2016-12-17 Thread Jens Axboe
On 12/17/2016 03:49 AM, Ming Lei wrote: > If the last bvec of the 1st bio and the 1st bvec of the next > bio are contineous physically, and the latter can be merged > to last segment of the 1st bio, we should think they don't > violate sg gap(or virt boundary) limit. > > Both Vitaly and Dexuan

Re: [PATCH] block: loose check on sg gap

2016-12-17 Thread Jens Axboe
On 12/17/2016 03:49 AM, Ming Lei wrote: > If the last bvec of the 1st bio and the 1st bvec of the next > bio are contineous physically, and the latter can be merged > to last segment of the 1st bio, we should think they don't > violate sg gap(or virt boundary) limit. > > Both Vitaly and Dexuan

[PATCH] block: loose check on sg gap

2016-12-17 Thread Ming Lei
If the last bvec of the 1st bio and the 1st bvec of the next bio are contineous physically, and the latter can be merged to last segment of the 1st bio, we should think they don't violate sg gap(or virt boundary) limit. Both Vitaly and Dexuan reported lots of unmergeable small bios are observed

[PATCH] block: loose check on sg gap

2016-12-17 Thread Ming Lei
If the last bvec of the 1st bio and the 1st bvec of the next bio are contineous physically, and the latter can be merged to last segment of the 1st bio, we should think they don't violate sg gap(or virt boundary) limit. Both Vitaly and Dexuan reported lots of unmergeable small bios are observed