[dm-devel] [RFC] dm-devel mailing list can't be joined

2017-11-23 Thread Changwei Ge
Hi, It's strange dm-devel mailing list can't be joined right now since no CAPTCHA shows up on portal website https://www.redhat.com/mailman/listinfo/dm-devel. Does anyone has any idea how to join dm-devel@redhat.com now? Thanks, Changwei -- dm-devel mailing list dm-devel@redhat.com

Re: [dm-devel] [PATCH 3/4] dm: convert dm_dev_internal.count from atomic_t to refcount_t

2017-11-23 Thread Reshetova, Elena
> On Fri, Oct 20, 2017 at 10:37:38AM +0300, Elena Reshetova wrote: > > } else if (dd->dm_dev->mode != (mode | dd->dm_dev->mode)) { > > r = upgrade_mode(dd, mode, t->md); > > if (r) > > return r; > > + refcount_inc(>count); > > } > >

Re: [dm-devel] [PATCH 2/2] dm-writecache

2017-11-23 Thread Christoph Hellwig
> +/* > + * The clflushopt instruction is very slow on Broadwell, so we use > non-temporal > + * stores instead. > + */ > +#ifdef CONFIG_X86_64 > +#define NT_STORE(dest, src) asm ("movnti %1, %0" : "=m"(dest) : "r"(src)) > +#define FLUSH_RANGE(dax, ptr, size) do { } while (0) > +#define

Re: [dm-devel] [PATCH 1/2] swait: export the symbols __prepare_to_swait and __finish_swait

2017-11-23 Thread Christoph Hellwig
Please run this past the swait authors. It is supposed to be a simple and self-contained API so I'd expect this patch to be seen critical. You might be better off to just use the normal complex waitqueues if you want to micro-optimize like this. On Wed, Nov 22, 2017 at 09:35:36PM -0500, Mikulas

Re: [dm-devel] [PATCH 4/4] dm: convert table_device.count from atomic_t to refcount_t

2017-11-23 Thread Zdenek Kabelac
Dne 20.10.2017 v 09:37 Elena Reshetova napsal(a): atomic_t variables are currently used to implement reference counters with the following properties: - counter is initialized to 1 using atomic_set() - a resource is freed upon counter reaching zero - once counter reaches zero, its further

Re: [dm-devel] [PATCH 3/4] dm: convert dm_dev_internal.count from atomic_t to refcount_t

2017-11-23 Thread Alasdair G Kergon
On Fri, Oct 20, 2017 at 10:37:38AM +0300, Elena Reshetova wrote: > } else if (dd->dm_dev->mode != (mode | dd->dm_dev->mode)) { > r = upgrade_mode(dd, mode, t->md); > if (r) > return r; > + refcount_inc(>count); > } Missing

Re: [dm-devel] [PATCH 2/2] dm-writecache

2017-11-23 Thread Dan Williams
On Thu, Nov 23, 2017 at 12:29 AM, Christoph Hellwig wrote: >> +/* >> + * The clflushopt instruction is very slow on Broadwell, so we use >> non-temporal >> + * stores instead. >> + */ >> +#ifdef CONFIG_X86_64 >> +#define NT_STORE(dest, src) asm ("movnti %1, %0" : "=m"(dest)

Re: [dm-devel] [PATCH 3/4] libmultipath: path latency: simplify getprio()

2017-11-23 Thread Martin Wilck
On Thu, 2017-11-23 at 10:20 +0800, Guan Junxiong wrote: > Hi Martin， > > Thanks for your clarification. I agree with you now in this thread. Thank you. I'd be grateful if you could give these patches a test in your environment, I believe you have better testing equipment for this stuff than I

Re: [dm-devel] [PATCH 2/2] dm-writecache

2017-11-23 Thread Mikulas Patocka
On Thu, 23 Nov 2017, Dan Williams wrote: > On Thu, Nov 23, 2017 at 12:29 AM, Christoph Hellwig > wrote: > >> +/* > >> + * The clflushopt instruction is very slow on Broadwell, so we use > >> non-temporal > >> + * stores instead. > >> + */ > >> +#ifdef CONFIG_X86_64 > >>

Re: [dm-devel] [PATCH 1/2] swait: export the symbols __prepare_to_swait and __finish_swait

2017-11-23 Thread Mikulas Patocka
On Thu, 23 Nov 2017, Christoph Hellwig wrote: > Please run this past the swait authors. It is supposed to be a simple > and self-contained API so I'd expect this patch to be seen critical. I already sent it to Peter Zijlstra and didn't get a response yet. > You might be better off to just

[dm-devel] [PATCH] dm-snapshot: use mutex instead of rw-semaphore

2017-11-23 Thread Mikulas Patocka
The rw-semaphore is acquired for read only on two places, none of them is performance-critical. So, we can replace it with a mutex. Signed-off-by: Mikulas Patocka --- drivers/md/dm-snap.c | 82 +-- 1 file changed, 41

[dm-devel] [PATCH] dm: use cloned bio as head, not remainder, in __split_and_process_bio()

2017-11-23 Thread NeilBrown
When we use bio_clone_bioset() to split off the front part of a bio and chain the two together and submit the remainder to generic_make_request(), it is important that the newly allocated bio is used as the head to be processed immediately, and the original bio gets "bio_advance()"d and sent to