Searched hist:"5 e84ea3a" (Results 1 – 4 of 4) sorted by relevance
/openbmc/linux/block/ |
H A D | elevator.c | 5e84ea3a Mon Mar 21 04:14:27 CDT 2011 Jens Axboe <jaxboe@fusionio.com> block: attempt to merge with existing requests on plug flush
One of the disadvantages of on-stack plugging is that we potentially lose out on merging since all pending IO isn't always visible to everybody. When we flush the on-stack plugs, right now we don't do any checks to see if potential merge candidates could be utilized.
Correct this by adding a new insert variant, ELEVATOR_INSERT_SORT_MERGE. It works just ELEVATOR_INSERT_SORT, but first checks whether we can merge with an existing request before doing the insertion (if we fail merging).
This fixes a regression with multiple processes issuing IO that can be merged.
Thanks to Shaohua Li <shaohua.li@intel.com> for testing and fixing an accounting bug.
Signed-off-by: Jens Axboe <jaxboe@fusionio.com> 5e84ea3a Mon Mar 21 04:14:27 CDT 2011 Jens Axboe <jaxboe@fusionio.com> block: attempt to merge with existing requests on plug flush One of the disadvantages of on-stack plugging is that we potentially lose out on merging since all pending IO isn't always visible to everybody. When we flush the on-stack plugs, right now we don't do any checks to see if potential merge candidates could be utilized. Correct this by adding a new insert variant, ELEVATOR_INSERT_SORT_MERGE. It works just ELEVATOR_INSERT_SORT, but first checks whether we can merge with an existing request before doing the insertion (if we fail merging). This fixes a regression with multiple processes issuing IO that can be merged. Thanks to Shaohua Li <shaohua.li@intel.com> for testing and fixing an accounting bug. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
|
H A D | blk-merge.c | 5e84ea3a Mon Mar 21 04:14:27 CDT 2011 Jens Axboe <jaxboe@fusionio.com> block: attempt to merge with existing requests on plug flush
One of the disadvantages of on-stack plugging is that we potentially lose out on merging since all pending IO isn't always visible to everybody. When we flush the on-stack plugs, right now we don't do any checks to see if potential merge candidates could be utilized.
Correct this by adding a new insert variant, ELEVATOR_INSERT_SORT_MERGE. It works just ELEVATOR_INSERT_SORT, but first checks whether we can merge with an existing request before doing the insertion (if we fail merging).
This fixes a regression with multiple processes issuing IO that can be merged.
Thanks to Shaohua Li <shaohua.li@intel.com> for testing and fixing an accounting bug.
Signed-off-by: Jens Axboe <jaxboe@fusionio.com> 5e84ea3a Mon Mar 21 04:14:27 CDT 2011 Jens Axboe <jaxboe@fusionio.com> block: attempt to merge with existing requests on plug flush One of the disadvantages of on-stack plugging is that we potentially lose out on merging since all pending IO isn't always visible to everybody. When we flush the on-stack plugs, right now we don't do any checks to see if potential merge candidates could be utilized. Correct this by adding a new insert variant, ELEVATOR_INSERT_SORT_MERGE. It works just ELEVATOR_INSERT_SORT, but first checks whether we can merge with an existing request before doing the insertion (if we fail merging). This fixes a regression with multiple processes issuing IO that can be merged. Thanks to Shaohua Li <shaohua.li@intel.com> for testing and fixing an accounting bug. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
|
H A D | blk.h | 5e84ea3a Mon Mar 21 04:14:27 CDT 2011 Jens Axboe <jaxboe@fusionio.com> block: attempt to merge with existing requests on plug flush
One of the disadvantages of on-stack plugging is that we potentially lose out on merging since all pending IO isn't always visible to everybody. When we flush the on-stack plugs, right now we don't do any checks to see if potential merge candidates could be utilized.
Correct this by adding a new insert variant, ELEVATOR_INSERT_SORT_MERGE. It works just ELEVATOR_INSERT_SORT, but first checks whether we can merge with an existing request before doing the insertion (if we fail merging).
This fixes a regression with multiple processes issuing IO that can be merged.
Thanks to Shaohua Li <shaohua.li@intel.com> for testing and fixing an accounting bug.
Signed-off-by: Jens Axboe <jaxboe@fusionio.com> 5e84ea3a Mon Mar 21 04:14:27 CDT 2011 Jens Axboe <jaxboe@fusionio.com> block: attempt to merge with existing requests on plug flush One of the disadvantages of on-stack plugging is that we potentially lose out on merging since all pending IO isn't always visible to everybody. When we flush the on-stack plugs, right now we don't do any checks to see if potential merge candidates could be utilized. Correct this by adding a new insert variant, ELEVATOR_INSERT_SORT_MERGE. It works just ELEVATOR_INSERT_SORT, but first checks whether we can merge with an existing request before doing the insertion (if we fail merging). This fixes a regression with multiple processes issuing IO that can be merged. Thanks to Shaohua Li <shaohua.li@intel.com> for testing and fixing an accounting bug. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
|
H A D | blk-core.c | 5e84ea3a Mon Mar 21 04:14:27 CDT 2011 Jens Axboe <jaxboe@fusionio.com> block: attempt to merge with existing requests on plug flush
One of the disadvantages of on-stack plugging is that we potentially lose out on merging since all pending IO isn't always visible to everybody. When we flush the on-stack plugs, right now we don't do any checks to see if potential merge candidates could be utilized.
Correct this by adding a new insert variant, ELEVATOR_INSERT_SORT_MERGE. It works just ELEVATOR_INSERT_SORT, but first checks whether we can merge with an existing request before doing the insertion (if we fail merging).
This fixes a regression with multiple processes issuing IO that can be merged.
Thanks to Shaohua Li <shaohua.li@intel.com> for testing and fixing an accounting bug.
Signed-off-by: Jens Axboe <jaxboe@fusionio.com> 5e84ea3a Mon Mar 21 04:14:27 CDT 2011 Jens Axboe <jaxboe@fusionio.com> block: attempt to merge with existing requests on plug flush One of the disadvantages of on-stack plugging is that we potentially lose out on merging since all pending IO isn't always visible to everybody. When we flush the on-stack plugs, right now we don't do any checks to see if potential merge candidates could be utilized. Correct this by adding a new insert variant, ELEVATOR_INSERT_SORT_MERGE. It works just ELEVATOR_INSERT_SORT, but first checks whether we can merge with an existing request before doing the insertion (if we fail merging). This fixes a regression with multiple processes issuing IO that can be merged. Thanks to Shaohua Li <shaohua.li@intel.com> for testing and fixing an accounting bug. Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
|