Re: block: optionally snapshot page contents to provide stable pages during write

2013-01-26 Thread Darrick J. Wong
On Sat, Jan 26, 2013 at 01:39:46PM +0100, Sedat Dilek wrote: > Hi Darrick, > > can you tell me why you do not put your help text where it normally > belongs ("help" Kconfig item)? Sure -- the non-ISA bounce pool is only used by a small number of specific parts of the kernel that require it. If t

Re: [PATCH 4/6] block: Optionally snapshot page contents to provide stable pages during write

2013-01-21 Thread Jan Kara
On Fri 18-01-13 17:13:01, Darrick J. Wong wrote: > This provides a band-aid to provide stable page writes on jbd without needing > to backport the fixed locking and page writeback bit handling schemes of jbd2. > The band-aid works by using bounce buffers to snapshot page contents instead > of > wa

[PATCH 4/6] block: Optionally snapshot page contents to provide stable pages during write

2013-01-18 Thread Darrick J. Wong
This provides a band-aid to provide stable page writes on jbd without needing to backport the fixed locking and page writeback bit handling schemes of jbd2. The band-aid works by using bounce buffers to snapshot page contents instead of waiting. For those wondering about the ext3 bandage -- fixing

Re: [PATCH 4/6] block: Optionally snapshot page contents to provide stable pages during write

2013-01-17 Thread Jan Kara
On Wed 16-01-13 19:01:32, Darrick J. Wong wrote: > > > diff --git a/block/blk-core.c b/block/blk-core.c > > > index c973249..277134c 100644 > > > --- a/block/blk-core.c > > > +++ b/block/blk-core.c > > > @@ -1474,6 +1474,11 @@ void blk_queue_bio(struct request_queue *q, struct > > > bio *bio) > >

Re: [PATCH 4/6] block: Optionally snapshot page contents to provide stable pages during write

2013-01-16 Thread Martin K. Petersen
> "Darrick" == Darrick J Wong writes: >> Umm, why did you move this hunk? Darrick> I moved it so that the integrity data are generated against the Darrick> contents of the bounce buffer because the write paths don't Darrick> wait for writeback to finish if the snapshotting mode is Darrick> e

Re: [PATCH 4/6] block: Optionally snapshot page contents to provide stable pages during write

2013-01-16 Thread Darrick J. Wong
On Wed, Jan 16, 2013 at 03:00:00AM +0100, Jan Kara wrote: > On Mon 14-01-13 21:43:05, Darrick J. Wong wrote: > > This provides a band-aid to provide stable page writes on jbd without > > needing > > to backport the fixed locking and page writeback bit handling schemes of > > jbd2. > > The band-ai

Re: [PATCH 4/6] block: Optionally snapshot page contents to provide stable pages during write

2013-01-15 Thread Jan Kara
On Mon 14-01-13 21:43:05, Darrick J. Wong wrote: > This provides a band-aid to provide stable page writes on jbd without needing > to backport the fixed locking and page writeback bit handling schemes of jbd2. > The band-aid works by using bounce buffers to snapshot page contents instead > of > wa

[PATCH 4/6] block: Optionally snapshot page contents to provide stable pages during write

2013-01-14 Thread Darrick J. Wong
This provides a band-aid to provide stable page writes on jbd without needing to backport the fixed locking and page writeback bit handling schemes of jbd2. The band-aid works by using bounce buffers to snapshot page contents instead of waiting. For those wondering about the ext3 bandage -- fixing

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2013-01-08 Thread OGAWA Hirofumi
"Darrick J. Wong" writes: > On Fri, Dec 28, 2012 at 06:48:35AM +0900, OGAWA Hirofumi wrote: >> "Darrick J. Wong" writes: >> >> >> I think this flag should be separated into "FS provide stable page" and >> >> "FS needs bounce buffer for stable page". >> >> >> >> My fs (I guess btrfs also) provi

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2013-01-07 Thread Darrick J. Wong
On Fri, Dec 28, 2012 at 06:48:35AM +0900, OGAWA Hirofumi wrote: > "Darrick J. Wong" writes: > > >> I think this flag should be separated into "FS provide stable page" and > >> "FS needs bounce buffer for stable page". > >> > >> My fs (I guess btrfs also) provides stable page by better way, and >

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-27 Thread OGAWA Hirofumi
"Darrick J. Wong" writes: >> I think this flag should be separated into "FS provide stable page" and >> "FS needs bounce buffer for stable page". >> >> My fs (I guess btrfs also) provides stable page by better way, and >> doesn't need to wait writeback flags too. What needs is just to avoid >> t

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-27 Thread Darrick J. Wong
On Fri, Dec 28, 2012 at 04:14:49AM +0900, OGAWA Hirofumi wrote: > "Darrick J. Wong" writes: > > > diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h > > index 780d4c6..0144fbb 100644 > > --- a/include/uapi/linux/fs.h > > +++ b/include/uapi/linux/fs.h > > @@ -69,6 +69,7 @@ struct inode

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-27 Thread OGAWA Hirofumi
"Darrick J. Wong" writes: > diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h > index 780d4c6..0144fbb 100644 > --- a/include/uapi/linux/fs.h > +++ b/include/uapi/linux/fs.h > @@ -69,6 +69,7 @@ struct inodes_stat_t { > #define MS_REMOUNT 32 /* Alter flags of a mounted FS */ >

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-17 Thread Darrick J. Wong
On Mon, Dec 17, 2012 at 11:23:59AM +0100, Jan Kara wrote: > On Thu 13-12-12 00:08:11, Darrick J. Wong wrote: > > Several complaints have been received regarding long file write latencies > > when > > memory pages must be held stable during writeback. Since it might not be > > acceptable to stall

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-17 Thread Darrick J. Wong
On Mon, Dec 17, 2012 at 12:13:36AM +0800, Zheng Liu wrote: > On Thu, Dec 13, 2012 at 12:08:11AM -0800, Darrick J. Wong wrote: > > diff --git a/mm/bounce.c b/mm/bounce.c > > index 0420867..fa11935 100644 > > --- a/mm/bounce.c > > +++ b/mm/bounce.c > > @@ -178,6 +178,38 @@ static void bounce_end_io_r

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-17 Thread Darrick J. Wong
On Fri, Dec 14, 2012 at 06:06:50PM -0800, Andy Lutomirski wrote: > On Fri, Dec 14, 2012 at 6:01 PM, Darrick J. Wong > wrote: > > On Fri, Dec 14, 2012 at 05:12:37PM -0800, Andy Lutomirski wrote: > >> It survived. I hit at least one mm bug, but I really don't think it's > >> a problem with your cod

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-17 Thread Jan Kara
On Thu 13-12-12 00:08:11, Darrick J. Wong wrote: > Several complaints have been received regarding long file write latencies when > memory pages must be held stable during writeback. Since it might not be > acceptable to stall programs for the entire duration of a page write (which > may > take m

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-16 Thread Zheng Liu
On Thu, Dec 13, 2012 at 12:08:11AM -0800, Darrick J. Wong wrote: > diff --git a/mm/bounce.c b/mm/bounce.c > index 0420867..fa11935 100644 > --- a/mm/bounce.c > +++ b/mm/bounce.c > @@ -178,6 +178,38 @@ static void bounce_end_io_read_isa(struct bio *bio, int > err) > __bounce_end_io_read(bio,

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-14 Thread Andy Lutomirski
On Fri, Dec 14, 2012 at 6:01 PM, Darrick J. Wong wrote: > On Fri, Dec 14, 2012 at 05:12:37PM -0800, Andy Lutomirski wrote: >> It survived. I hit at least one mm bug, but I really don't think it's >> a problem with your code. (I have not tried this workload on Linux >> 3.7 at all before. It norm

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-14 Thread Darrick J. Wong
On Fri, Dec 14, 2012 at 05:12:37PM -0800, Andy Lutomirski wrote: > On Thu, Dec 13, 2012 at 6:10 PM, Darrick J. Wong > wrote: > > On Thu, Dec 13, 2012 at 05:48:06PM -0800, Andy Lutomirski wrote: > >> On 12/13/2012 12:08 AM, Darrick J. Wong wrote: > >> > Several complaints have been received regardi

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-14 Thread Andy Lutomirski
On Thu, Dec 13, 2012 at 6:10 PM, Darrick J. Wong wrote: > On Thu, Dec 13, 2012 at 05:48:06PM -0800, Andy Lutomirski wrote: >> On 12/13/2012 12:08 AM, Darrick J. Wong wrote: >> > Several complaints have been received regarding long file write latencies >> > when >> > memory pages must be held stab

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-14 Thread Darrick J. Wong
On Fri, Dec 14, 2012 at 02:33:34PM +1100, Dave Chinner wrote: > On Thu, Dec 13, 2012 at 06:10:49PM -0800, Darrick J. Wong wrote: > > On Thu, Dec 13, 2012 at 05:48:06PM -0800, Andy Lutomirski wrote: > > > On 12/13/2012 12:08 AM, Darrick J. Wong wrote: > > > > Several complaints have been received re

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-13 Thread Dave Chinner
On Thu, Dec 13, 2012 at 06:10:49PM -0800, Darrick J. Wong wrote: > On Thu, Dec 13, 2012 at 05:48:06PM -0800, Andy Lutomirski wrote: > > On 12/13/2012 12:08 AM, Darrick J. Wong wrote: > > > Several complaints have been received regarding long file write latencies > > > when > > > memory pages must

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-13 Thread Darrick J. Wong
On Thu, Dec 13, 2012 at 05:48:06PM -0800, Andy Lutomirski wrote: > On 12/13/2012 12:08 AM, Darrick J. Wong wrote: > > Several complaints have been received regarding long file write latencies > > when > > memory pages must be held stable during writeback. Since it might not be > > acceptable to s

Re: [PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-13 Thread Andy Lutomirski
On 12/13/2012 12:08 AM, Darrick J. Wong wrote: > Several complaints have been received regarding long file write latencies when > memory pages must be held stable during writeback. Since it might not be > acceptable to stall programs for the entire duration of a page write (which > may > take man

[PATCH 4/4] block: Optionally snapshot page contents to provide stable pages during write

2012-12-13 Thread Darrick J. Wong
Several complaints have been received regarding long file write latencies when memory pages must be held stable during writeback. Since it might not be acceptable to stall programs for the entire duration of a page write (which may take many milliseconds even on good hardware), enable a second str