Re: [PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-20 Thread Michel Lespinasse
On Wed, Feb 20, 2013 at 4:50 PM, Alex Shi wrote: > I did a quick review on the patchset and tested the patches 1~3, and 1~3 > plus 4th, my patch plus 4th. > > The patch looks much complicated, and also goes writing slow path to > steal locking. My patch looks quite straight and simple. > > This

Re: [PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-20 Thread Ingo Molnar
* Alex Shi wrote: > > Alex, could you go through my patch and see if there is > > anything you find objectionable ? (if not about the details, > > at least about the general approach of enabling writer lock > > stealing on the fast path) > > I did a quick review on the patchset and tested

Re: [PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-20 Thread Alex Shi
> > Alex, could you go through my patch and see if there is anything you > find objectionable ? (if not about the details, at least about the > general approach of enabling writer lock stealing on the fast path) > I did a quick review on the patchset and tested the patches 1~3, and 1~3 plus

Re: [PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-20 Thread Alex Shi
Alex, could you go through my patch and see if there is anything you find objectionable ? (if not about the details, at least about the general approach of enabling writer lock stealing on the fast path) I did a quick review on the patchset and tested the patches 1~3, and 1~3 plus 4th, my

Re: [PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-20 Thread Ingo Molnar
* Alex Shi alex@intel.com wrote: Alex, could you go through my patch and see if there is anything you find objectionable ? (if not about the details, at least about the general approach of enabling writer lock stealing on the fast path) I did a quick review on the patchset and

Re: [PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-20 Thread Michel Lespinasse
On Wed, Feb 20, 2013 at 4:50 PM, Alex Shi alex@intel.com wrote: I did a quick review on the patchset and tested the patches 1~3, and 1~3 plus 4th, my patch plus 4th. The patch looks much complicated, and also goes writing slow path to steal locking. My patch looks quite straight and

Re: [PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-14 Thread Alex Shi
On 02/14/2013 09:31 AM, Michel Lespinasse wrote: > Alex, could you go through my patch and see if there is anything you > find objectionable ? (if not about the details, at least about the > general approach of enabling writer lock stealing on the fast path) I am still in my lunar new year

Re: [PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-14 Thread Alex Shi
On 02/14/2013 09:31 AM, Michel Lespinasse wrote: Alex, could you go through my patch and see if there is anything you find objectionable ? (if not about the details, at least about the general approach of enabling writer lock stealing on the fast path) I am still in my lunar new year vacation.

Re: [PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-13 Thread Michel Lespinasse
On Wed, Feb 13, 2013 at 6:49 AM, Ingo Molnar wrote: > > * Alex Shi wrote: > >> On 02/09/2013 10:45 AM, Michel Lespinasse wrote: >> > This proposal implements writer lock stealing in lib/rwsem.c, just as >> > Alex Shi's earlier proposal did for the simpler lib/rwsem-spinlock.c >> >> Ops, my patch

Re: [PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-13 Thread Ingo Molnar
* Alex Shi wrote: > On 02/09/2013 10:45 AM, Michel Lespinasse wrote: > > This proposal implements writer lock stealing in lib/rwsem.c, just as > > Alex Shi's earlier proposal did for the simpler lib/rwsem-spinlock.c > > Ops, my patch in tip/urgent is for rwsem. Yuanhan's patch is > for

Re: [PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-13 Thread Alex Shi
On 02/09/2013 10:45 AM, Michel Lespinasse wrote: > This proposal implements writer lock stealing in lib/rwsem.c, just as > Alex Shi's earlier proposal did for the simpler lib/rwsem-spinlock.c Ops, my patch in tip/urgent is for rwsem. Yuanhan's patch is for rwsem-spinlock. Thanks Alex -- To

Re: [PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-13 Thread Alex Shi
On 02/09/2013 10:45 AM, Michel Lespinasse wrote: This proposal implements writer lock stealing in lib/rwsem.c, just as Alex Shi's earlier proposal did for the simpler lib/rwsem-spinlock.c Ops, my patch in tip/urgent is for rwsem. Yuanhan's patch is for rwsem-spinlock. Thanks Alex -- To

Re: [PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-13 Thread Ingo Molnar
* Alex Shi alex@intel.com wrote: On 02/09/2013 10:45 AM, Michel Lespinasse wrote: This proposal implements writer lock stealing in lib/rwsem.c, just as Alex Shi's earlier proposal did for the simpler lib/rwsem-spinlock.c Ops, my patch in tip/urgent is for rwsem. Yuanhan's patch is

Re: [PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-13 Thread Michel Lespinasse
On Wed, Feb 13, 2013 at 6:49 AM, Ingo Molnar mi...@kernel.org wrote: * Alex Shi alex@intel.com wrote: On 02/09/2013 10:45 AM, Michel Lespinasse wrote: This proposal implements writer lock stealing in lib/rwsem.c, just as Alex Shi's earlier proposal did for the simpler

[PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-08 Thread Michel Lespinasse
This proposal implements writer lock stealing in lib/rwsem.c, just as Alex Shi's earlier proposal did for the simpler lib/rwsem-spinlock.c Patches 1 and 2 are small cleanups that I thought I should separate from the bulk of the changes; Patch 3 is the generic support for write lock stealing;

[PATCH 0/4] rwsem: Implement writer lock-stealing

2013-02-08 Thread Michel Lespinasse
This proposal implements writer lock stealing in lib/rwsem.c, just as Alex Shi's earlier proposal did for the simpler lib/rwsem-spinlock.c Patches 1 and 2 are small cleanups that I thought I should separate from the bulk of the changes; Patch 3 is the generic support for write lock stealing;