Commit a5fd2858 authored by Sumit.Saxena@avagotech.com's avatar Sumit.Saxena@avagotech.com Committed by Christoph Hellwig

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

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: default avatarSumit Saxena <sumit.saxena@avagotech.com>
Signed-off-by: default avatarKashyap Desai <kashyap.desai@avagotech.com>
Reviewed-by: default avatarTomas Henzl <thenzl@redhat.com>
Signed-off-by: default avatarChristoph Hellwig <hch@lst.de>
parent fb1a24ff
...@@ -1001,8 +1001,8 @@ megasas_init_adapter_fusion(struct megasas_instance *instance) ...@@ -1001,8 +1001,8 @@ megasas_init_adapter_fusion(struct megasas_instance *instance)
fusion->max_sge_in_chain = fusion->max_sge_in_chain =
MEGASAS_MAX_SZ_CHAIN_FRAME / sizeof(union MPI2_SGE_IO_UNION); MEGASAS_MAX_SZ_CHAIN_FRAME / sizeof(union MPI2_SGE_IO_UNION);
instance->max_num_sge = fusion->max_sge_in_main_msg + instance->max_num_sge = rounddown_pow_of_two(
fusion->max_sge_in_chain - 2; fusion->max_sge_in_main_msg + fusion->max_sge_in_chain - 2);
/* Used for pass thru MFI frame (DCMD) */ /* Used for pass thru MFI frame (DCMD) */
fusion->chain_offset_mfi_pthru = fusion->chain_offset_mfi_pthru =
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment