leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

megaraid_sas : Round down max sge supported by controller to power of two

Browse Source 
Resending the patch. Addressed the review comments from Tomas Henzl.

Round down the max sge to power of two.

Earlier max sge limit is 70 SGE, which will allow block layer to send 280K IO frame.
It is optimal to provide max IO size aligned to the smallest possible stripe size.
E.a
Consider that we have configured RAID Volumes which does not allow Fast Path across the stripe.
Raid volume with stripe size = 256K, will have peformance hit if we get io frame of size 280K.
Driver will not send IO frame large than stripe size to the Fast Path.
Also, FW will convert 280K frame into 256K + 24K. This is an additional overhead.

Signed-off-by: Sumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: Kashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This commit is contained in:
Sumit.Saxena@avagotech.com 2014-09-12 18:57:43 +05:30 committed by Christoph Hellwig
parent fb1a24ff65
commit a5fd2858e2
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
drivers/scsi/megaraid/megaraid_sas_fusion.c
View File

@ -1001,8 +1001,8 @@ megasas_init_adapter_fusion(struct megasas_instance *instance)
fusion->max_sge_in_chain =
MEGASAS_MAX_SZ_CHAIN_FRAME / sizeof(union MPI2_SGE_IO_UNION);
instance->max_num_sge = fusion->max_sge_in_main_msg +
fusion->max_sge_in_chain - 2;
instance->max_num_sge = rounddown_pow_of_two(
fusion->max_sge_in_main_msg + fusion->max_sge_in_chain - 2);
/* Used for pass thru MFI frame (DCMD) */
fusion->chain_offset_mfi_pthru =