On 12 August 2016 at 10:01, Martin K. Petersen
wrote:
>
> Again, the point of max_hw_sectors and max_dev_sectors is to enforce the
> hard limits of controller and device respectively. Nothing else.
>
Sounds like libata-scsi is doing something wrong then. It should not
set max_hw_sectors to dev->m
On 12 August 2016 at 09:34, Martin K. Petersen
wrote:
>> "Tom," == tom ty89 writes:
>
> Tom,
>
> + put_unaligned_be64(65535 * ATA_MAX_TRIM_RNUM /
> + (sector_size / 512), &rbuf[36]);
>
> MAXIMUM WRITE SAME LENGTH is in units of the device's logic
On 12 August 2016 at 11:10, Martin K. Petersen
wrote:
>
> However, the CDB transfer length limit is really not the main issue
> here, it's bi_size that we need to enforce.
>
> After contemplating a bit I think it would be cleanest to add
> BLK_MAX_BIO_SECTORS and clamp on that in blk_queue_max_foo
> "Tom" == tom ty89 writes:
Tom,
Tom> However, SD_MAX_WS16_BLOCKS is used to check values that are, for
Tom> example, orignated from Maximum Write Same Length field on the
Tom> Block Limit VPD. Such field expresses the number of blocks in terms
Tom> of the actual logical sector size of the s
> "Tom" == Tom Yan writes:
Hey Tom,
Tom> Shouldn't we use Maximum Transfer Length to derive max_sectors (and
Tom> get rid of the almost useless max_dev_sectors)?
MAXIMUM TRANSFER LENGTH could be gigabytes. Some disks report it as the
full capacity of the device.
Again, the point of max_hw_
> "Tom," == tom ty89 writes:
Tom,
+ put_unaligned_be64(65535 * ATA_MAX_TRIM_RNUM /
+ (sector_size / 512), &rbuf[36]);
MAXIMUM WRITE SAME LENGTH is in units of the device's logical block
size.
--
Martin K. Petersen Oracle Linux Engineerin
From: Tom Yan
WRITE SAME (16) command can technically handle up to 32-bit
number of blocks. However, since 32-bit is also the limitation of
the maximum number of bytes that can be represented in the block
layer, the current SD_MAX_WS16_BLOCKS was hence derived from the
technical limit devided by
The patch isn't about how the request from the block layer will be
processed (to form the SCSI commands).
What it addresses is blk_queue_max_write_same_sectors() and
blk_queue_max_discard_sectors() that are called in the SCSI disk
driver. You can see that they are called with an input of the Maxim
On Thu, Aug 11, 2016 at 3:26 AM, wrote:
> From: Tom Yan
>
> Currently we advertise Maximum Write Same Length based on the
> maximum number of sectors that one-block TRIM payload can cover.
> The field are used to derived discard_max_bytes and
> write_same_max_bytes limits in the block layer, whi
On 08/11/2016 02:15 AM, Johannes Berg wrote:
From: Johannes Berg
Due to the (indirect) nesting of min(..., min(...)), sparse will
show a variable shadowing warning whenever bvec.h is included.
Avoid that by assigning the inner min() to a temporary variable first.
Grumble, reluctantly applied
Please just fix bcache to not submit bios larger than BIO_MAX_PAGES for
now, until we can support such callers in general and enable common
used code to do so.
--
To unsubscribe from this list: send the line "unsubscribe linux-block" in
the body of a message to majord...@vger.kernel.org
More majord
On 11 August 2016 at 11:37, Martin K. Petersen
wrote:
>> "Tom" == Tom Yan writes:
>
> I don't agree with conflating the optimal transfer size and the maximum
> supported ditto. Submitting the largest possible I/O to a device does
> not guarantee that you get the best overall performance.
>
>
From: Tom Yan
Currently we advertise Maximum Write Same Length based on the
maximum number of sectors that one-block TRIM payload can cover.
The field are used to derived discard_max_bytes and
write_same_max_bytes limits in the block layer, which currently can
at max be 0x (32-bit).
Howe
From: Johannes Berg
Due to the (indirect) nesting of min(..., min(...)), sparse will
show a variable shadowing warning whenever bvec.h is included.
Avoid that by assigning the inner min() to a temporary variable first.
Signed-off-by: Johannes Berg
---
include/linux/bvec.h | 3 ++-
1 file chan
14 matches
Mail list logo
