Re: [PATCH v2] sg: add SG_FLAG_Q_AT_TAIL flag

2014-06-11 Thread Mike Christie
On 06/04/2014 09:58 AM, Douglas Gilbert wrote: > When the SG_IO ioctl was copied into the block layer and > later into the bsg driver, subtle differences emerged. > > One difference is the way injected commands are queued through > the block layer (i.e. this is not SCSI device queueing nor SATA >

Re: [PATCH v2] sg: add SG_FLAG_Q_AT_TAIL flag

2014-06-11 Thread Ewan Milne
On Wed, 2014-06-04 at 10:58 -0400, Douglas Gilbert wrote: > When the SG_IO ioctl was copied into the block layer and > later into the bsg driver, subtle differences emerged. > > One difference is the way injected commands are queued through > the block layer (i.e. this is not SCSI device queueing

Re: [PATCH v2] sg: add SG_FLAG_Q_AT_TAIL flag

2014-06-05 Thread Douglas Gilbert
On 14-06-05 11:27 AM, Boaz Harrosh wrote: On 06/04/2014 05:58 PM, Douglas Gilbert wrote: When the SG_IO ioctl was copied into the block layer and later into the bsg driver, subtle differences emerged. One difference is the way injected commands are queued through the block layer (i.e. this is n

Re: [PATCH v2] sg: add SG_FLAG_Q_AT_TAIL flag

2014-06-05 Thread Jeremy Linton
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 On 6/5/2014 10:27 AM, Boaz Harrosh wrote: > 1. aio "scatter_gather" type io. (ie multiple pointers multiple length > buffers that are written / read from same linear range on device) [The > async aspect of aio can be implemented via bsg with the write

Re: [PATCH v2] sg: add SG_FLAG_Q_AT_TAIL flag

2014-06-05 Thread Boaz Harrosh
On 06/04/2014 05:58 PM, Douglas Gilbert wrote: > When the SG_IO ioctl was copied into the block layer and > later into the bsg driver, subtle differences emerged. > > One difference is the way injected commands are queued through > the block layer (i.e. this is not SCSI device queueing nor SATA >

Re: [PATCH v2] sg: add SG_FLAG_Q_AT_TAIL flag

2014-06-05 Thread Christoph Hellwig
On Wed, Jun 04, 2014 at 10:58:30AM -0400, Douglas Gilbert wrote: > When the SG_IO ioctl was copied into the block layer and > later into the bsg driver, subtle differences emerged. > > One difference is the way injected commands are queued through > the block layer (i.e. this is not SCSI device qu

[PATCH v2] sg: add SG_FLAG_Q_AT_TAIL flag

2014-06-04 Thread Douglas Gilbert
When the SG_IO ioctl was copied into the block layer and later into the bsg driver, subtle differences emerged. One difference is the way injected commands are queued through the block layer (i.e. this is not SCSI device queueing nor SATA NCQ). Summarizing: - SG_IO in the block layer: blk_exec*