Re: [dm-devel] [PATCH v2 RESEND] x86: optimize memcpy_flushcache

2018-06-21 Thread Ingo Molnar
* Mikulas Patocka wrote: > On Thu, 21 Jun 2018, Ingo Molnar wrote: > > > > > * Mike Snitzer wrote: > > > > > From: Mikulas Patocka > > > Subject: [PATCH v2] x86: optimize memcpy_flushcache > > > > > > In the context of constant short length stores to persistent memory, > > > memcpy_flushc

Re: [dm-devel] [PATCH v2 RESEND] x86: optimize memcpy_flushcache

2018-06-21 Thread Mikulas Patocka
On Thu, 21 Jun 2018, Ingo Molnar wrote: > > * Mike Snitzer wrote: > > > From: Mikulas Patocka > > Subject: [PATCH v2] x86: optimize memcpy_flushcache > > > > In the context of constant short length stores to persistent memory, > > memcpy_flushcache suffers from a 2% performance degradation

Re: [dm-devel] dm bufio: Reduce dm_bufio_lock contention

2018-06-21 Thread Mikulas Patocka
On Tue, 19 Jun 2018, Michal Hocko wrote: > On Mon 18-06-18 18:11:26, Mikulas Patocka wrote: > [...] > > I grepped the kernel for __GFP_NORETRY and triaged them. I found 16 cases > > without a fallback - those are bugs that make various functions randomly > > return -ENOMEM. > > Well, maybe t

[dm-devel] [PATCH] dm cache: require io_mode cache feature selection to be mutually exclusive

2018-06-21 Thread John Pittman
Due to commit 629d0a8a1a10 ("dm cache metadata: add "metadata2" feature"), when creating a dm cache device, more than one io_mode can be selected. As the io_mode selections are incompatible with one another, we should force them to be selected exclusively. Add simple ctr to check for more than o

Re: [dm-devel] [PATCH 04/11] dm verity fec: Remove VLA usage

2018-06-21 Thread Kees Cook
On Wed, Jun 20, 2018 at 7:30 PM, Herbert Xu wrote: > On Wed, Jun 20, 2018 at 12:04:01PM -0700, Kees Cook wrote: >> In the quest to remove all stack VLA usage from the kernel[1], this >> uses the newly defined max digest size macro. Also adds a sanity-check >> at use-time. >> >> [1] >> https://lkm

Re: [dm-devel] [PATCH v2 RESEND] x86: optimize memcpy_flushcache

2018-06-21 Thread Ingo Molnar
* Mike Snitzer wrote: > From: Mikulas Patocka > Subject: [PATCH v2] x86: optimize memcpy_flushcache > > In the context of constant short length stores to persistent memory, > memcpy_flushcache suffers from a 2% performance degradation compared to > explicitly using the "movnti" instruction. >

Re: [dm-devel] [PATCH 4.17.0-rc3 1/2] dm: Reduce line length

2018-06-21 Thread Mike Snitzer
On Thu, Jun 21 2018 at 8:02am -0400, Ssemagoye Umar Munddu wrote: > Signed-off-by: Ssemagoye Umar Munddu > --- > drivers/md/dm.c | 187 > +--- > 1 file changed, 123 insertions(+), 64 deletions(-) There is absolutely no way I'm taking this.

Re: [dm-devel] [PATCH] multipath-tools: fix help for hds prio

2018-06-21 Thread Christophe Varoqui
Done, thanks. On Thu, Jun 21, 2018 at 10:59 AM Xose Vazquez Perez wrote: > Hi Christophe, > > This one is missing. > > Thank you. > > On 05/21/2018 10:03 PM, Xose Vazquez Perez wrote: > > Cc: Christophe Varoqui > > Cc: DM-DEV ML > > Signed-off-by: Xose Vazquez Perez > > --- > > multipath/mul

Re: [dm-devel] [PATCH] multipath-tools: fix help for hds prio

2018-06-21 Thread Xose Vazquez Perez
Hi Christophe, This one is missing. Thank you. On 05/21/2018 10:03 PM, Xose Vazquez Perez wrote: > Cc: Christophe Varoqui > Cc: DM-DEV ML > Signed-off-by: Xose Vazquez Perez > --- > multipath/multipath.conf.5 | 4 ++-- > 1 file changed, 2 insertions(+), 2 deletions(-) > > diff --git a/multi