On 10/17/14 12:58, Christoph Hellwig wrote:
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index cc0bf83b..224ef25 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -853,7 +853,6 @@ static int srp_alloc_req_data(struct srp_rdma_ch *ch)
goto out;
req->indirect_dma_addr = dma_addr;
- req->index = i;
list_add_tail(&req->list, &ch->free_reqs);
}
Seems like a nice optimization for the future would be to preallocate
the srp requests with the block ones and the scsi command.
Agreed. The reason why that optimization has not been included in this
patch series is because it would require more work than the optimization
in patch 10/12. The free_reqs list is namely not only used when a SCSI
command is submitted by the SCSI core but also when submitting a task
management command or when replying to a request submitted by the target
system. In other words, the free_reqs list would have to be modified
such that it is only used for the latter two purposes.
Bart.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
