Re: [PATCH 1/8] aoe: avoid running request handler on plugged queue
On 2012-11-09 01:17, Ed Cashin wrote: > Calling the request handler directly on a plugged queue defeats > the performance improvements provided by the plugging mechanism. > Use the __blk_run_queue function instead of calling the request > handler directly, so that we don't interfere with the block > layer's ability to plug the queue. Thanks Ed, applied! -- Jens Axboe -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 1/8] aoe: avoid running request handler on plugged queue
On Nov 8, 2012, at 2:26 PM, Andrew Morton wrote: > On Thu, 8 Nov 2012 11:29:32 -0500 > Ed Cashin wrote: > >> Signed-off-by: Ed Cashin > > Could you please prepare decent changelogs for the patches? Several of > these appear to be bugfixes but we have no description of the > user-visible behavioural changes. So nobody knows what the patches do, > nor which kernel version(s) they should be merged into. Yes, sure. For this one, I Cc'ed Jens Axboe in part because although I believe that it is correct to use __blk_run_queue rather than to call the request handler directly, I am going on old information. I'm not entirely sure what the user impact is when the request hander is called directly, other than perhaps a slight performance hit. But I'd like to do the right thing. Jens Axboe, if you have a comment about correctness or user impact, I'd like to include that information in the changelog for this commit. Or if the change doesn't look right to you, I'd like to know that. Thanks. -- Ed Cashin ecas...@coraid.com -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 1/8] aoe: avoid running request handler on plugged queue
On Thu, 8 Nov 2012 11:29:32 -0500 Ed Cashin wrote: > Signed-off-by: Ed Cashin Could you please prepare decent changelogs for the patches? Several of these appear to be bugfixes but we have no description of the user-visible behavioural changes. So nobody knows what the patches do, nor which kernel version(s) they should be merged into. Thanks. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 1/8] aoe: avoid running request handler on plugged queue
On Thu, 8 Nov 2012 11:29:32 -0500 Ed Cashin ecas...@coraid.com wrote: Signed-off-by: Ed Cashin ecas...@coraid.com Could you please prepare decent changelogs for the patches? Several of these appear to be bugfixes but we have no description of the user-visible behavioural changes. So nobody knows what the patches do, nor which kernel version(s) they should be merged into. Thanks. -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 1/8] aoe: avoid running request handler on plugged queue
On Nov 8, 2012, at 2:26 PM, Andrew Morton wrote: On Thu, 8 Nov 2012 11:29:32 -0500 Ed Cashin ecas...@coraid.com wrote: Signed-off-by: Ed Cashin ecas...@coraid.com Could you please prepare decent changelogs for the patches? Several of these appear to be bugfixes but we have no description of the user-visible behavioural changes. So nobody knows what the patches do, nor which kernel version(s) they should be merged into. Yes, sure. For this one, I Cc'ed Jens Axboe in part because although I believe that it is correct to use __blk_run_queue rather than to call the request handler directly, I am going on old information. I'm not entirely sure what the user impact is when the request hander is called directly, other than perhaps a slight performance hit. But I'd like to do the right thing. Jens Axboe, if you have a comment about correctness or user impact, I'd like to include that information in the changelog for this commit. Or if the change doesn't look right to you, I'd like to know that. Thanks. -- Ed Cashin ecas...@coraid.com -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH 1/8] aoe: avoid running request handler on plugged queue
On 2012-11-09 01:17, Ed Cashin wrote: Calling the request handler directly on a plugged queue defeats the performance improvements provided by the plugging mechanism. Use the __blk_run_queue function instead of calling the request handler directly, so that we don't interfere with the block layer's ability to plug the queue. Thanks Ed, applied! -- Jens Axboe -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/