evie/android_kernel_oneplus_msm8998
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

mmc: block: serialize the requests if we are scaled down

Browse source 
When in SVS2 on low load scenario and there are lots of requests
queued for CMDQ we need to wait till the queue is empty to scale
back up to Nominal even if there is a sudden increase in load.
This impacts performance where lots of IO get executed in SVS2
frequency since the queue is full. As SVS2 is a low load use case
we can serialize the requests and not queue them in parallel
without impacting other use cases. This makes sure the queue gets
empty faster and we will be able to scale up to Nominal frequency
when needed.

Change-Id: Idbe7e939e01327061dfa5de93c0eaed59b910592
Signed-off-by: Subhash Jadavani <subhashj@codeaurora.org>
Signed-off-by: Venkat Gopalakrishnan <venkatg@codeaurora.org>
This commit is contained in:
Subhash Jadavani 2015-11-18 15:39:02 -08:00
parent e974ac15b5
commit f33ab72df2
1 changed files with 15 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
drivers/mmc/card/block.c
View file

@ -2896,6 +2896,7 @@ static int mmc_blk_cmdq_issue_rw_rq(struct mmc_queue *mq, struct request *req)
struct mmc_queue_req *active_mqrq;
struct mmc_card *card = mq->card;
struct mmc_host *host = card->host;
struct mmc_cmdq_context_info *ctx = &host->cmdq_ctx;
struct mmc_cmdq_req *mc_rq;
int ret = 0;
@ -2920,6 +2921,20 @@ static int mmc_blk_cmdq_issue_rw_rq(struct mmc_queue *mq, struct request *req)
&& (rq_data_dir(req) == READ))
host->cmdq_ctx.active_small_sector_read_reqs++;
}
/*
* When in SVS2 on low load scenario and there are lots of requests
* queued for CMDQ we need to wait till the queue is empty to scale
* back up to Nominal even if there is a sudden increase in load.
* This impacts performance where lots of IO get executed in SVS2
* frequency since the queue is full. As SVS2 is a low load use case
* we can serialize the requests and not queue them in parallel
* without impacting other use cases. This makes sure the queue gets
* empty faster and we will be able to scale up to Nominal frequency
* when needed.
*/
if (!ret && (host->clk_scaling.state == MMC_LOAD_LOW))
wait_event_interruptible(ctx->queue_empty_wq,
(!ctx->active_reqs));
return ret;
}