diff mbox

[v3] mmc: documentation of mmc non-blocking request usage and design.

Message ID 1309895008-2587-2-git-send-email-per.forlin@linaro.org (mailing list archive)
State New, archived
Headers show

Commit Message

Per Forlin July 5, 2011, 7:43 p.m. UTC
Documentation about the background and the design of mmc non-blocking.
Host driver guidelines to minimize request preparation overhead.

Signed-off-by: Per Forlin <per.forlin@linaro.org>
---
 Documentation/mmc/00-INDEX          |    2 +
 Documentation/mmc/mmc-async-req.txt |   86 +++++++++++++++++++++++++++++++++++
 2 files changed, 88 insertions(+), 0 deletions(-)
 create mode 100644 Documentation/mmc/mmc-async-req.txt

Comments

Randy Dunlap July 5, 2011, 8:27 p.m. UTC | #1
On Tue,  5 Jul 2011 21:43:28 +0200 Per Forlin wrote:

> Documentation about the background and the design of mmc non-blocking.
> Host driver guidelines to minimize request preparation overhead.
> 
> Signed-off-by: Per Forlin <per.forlin@linaro.org>
> ---

It would be better to omit the introductory email and put all of its comments
in this one [PATCH] email.


>  Documentation/mmc/00-INDEX          |    2 +
>  Documentation/mmc/mmc-async-req.txt |   86 +++++++++++++++++++++++++++++++++++
>  2 files changed, 88 insertions(+), 0 deletions(-)
>  create mode 100644 Documentation/mmc/mmc-async-req.txt
> 
> diff --git a/Documentation/mmc/00-INDEX b/Documentation/mmc/00-INDEX
> index 93dd7a7..11bc2cf 100644
> --- a/Documentation/mmc/00-INDEX
> +++ b/Documentation/mmc/00-INDEX
> @@ -4,3 +4,5 @@ mmc-dev-attrs.txt
>          - info on SD and MMC device attributes
>  mmc-dev-parts.txt
>          - info on SD and MMC device partitions
> +mmc-async-req.txt
> +        - info on mmc asynchronous request

                                      requests


> diff --git a/Documentation/mmc/mmc-async-req.txt b/Documentation/mmc/mmc-async-req.txt
> new file mode 100644
> index 0000000..d7e7698
> --- /dev/null
> +++ b/Documentation/mmc/mmc-async-req.txt
> @@ -0,0 +1,86 @@
> +Rationale
> +=========
> +
> +How significant is the cache maintenance overhead?
> +It depends, fast eMMC and multiple cache levels with speculative cache

   It depends:
or
   It depends. Fast

> +pre-fetch makes the cache overhead relatively significant. If the DMA
> +preparations for the next request are done in parallel to the current

                                                          with the current

> +transfer the DMA preparation overhead would not affect the MMC performance.

   transfer,

> +The intention of non-blocking (asynchronous) mmc requests is to minimize the
> +time between when an mmc request ends and another mmc request begins.
> +Using mmc_wait_for_req() the MMC controller is idle while dma_map_sg and

         mmc_wait_for_req(),

> +dma_unmap_sg is processing. Using non-blocking mmc requests makes it

                are processing.

> +possible to prepare the caches for next job in parallel to an active

                                                           with an active

> +mmc request.
> +
> +MMC block driver
> +================
> +
> +The issue_rw_rq() in the mmc block driver is made non-blocking.

preferably:                 MMC
throughout the file (when not a function or data name, etc.)

> +The increase in throughput is proportional to the time it takes to
> +prepare (major part of preparations is dma_map_sg and dma_unmap_sg)

                                       are

> +a request and how fast the memory is. The faster the MMC/SD is
> +the more significant the prepare request time becomes. Roughly the expected
> +performance gain is 5% for large writes and 10% on large reads on a L2 cache
> +platform. In power save mode, when clocks run on a lower frequency, the DMA
> +preparation may cost even more. As long as these slower preparations are run
> +in parallel to the transfer performance wont be affected.

               with                        won't

> +
> +Details on measurements from IOZone and mmc_test
> +================================================
> +
> +https://wiki.linaro.org/WorkingGroups/Kernel/Specs/StoragePerfMMC-async-req
> +
> +MMC core API extension
> +======================
> +
> +There is one new public function mmc_start_req()

                                    mmc_start_req().

> +It starts a new MMC command request for a host. The function isn't
> +truly non-blocking. If there is on ongoing async request it waits
> +for completion of that request and starts the new one and returns. It
> +doesn't wait for the new request to complete. If there is no ongoing
> +request it starts the new request and returns immediately.
> +
> +MMC host extensions
> +===================
> +
> +There are two optional hooks pre_req() and post_req() that the host driver

                          hooks -- pre_req() and post_req() -- that

> +may implement in order to move work to before and after the actual
> +mmc_request function is called. In the DMA case pre_req() may do
> +dma_map_sg() and prepare the dma descriptor, and post_req runs

                                DMA

> +the dma_unmap_sg.
> +
> +Optimize for the first request
> +==============================
> +
> +The first request in a series of requests can't be prepared in parallel to

                                                                           with

> +the previous transfer, since there is no previous request.
> +The argument is_first_req in pre_req() indicates that there is no previous
> +request. The host driver may optimize for this scenario to minimize
> +the performance loss. A way to optimize for this is to split the current
> +request in two chunks, prepare the first chunk and start the request,
> +and finally prepare the second chunk and start the transfer.
> +
> +Pseudocode to handle is_first_req scenario with minimal prepare overhead:
> +if (is_first_req && req->size > threshold)
> +   /* start MMC transfer for the complete transfer size */
> +   mmc_start_command(MMC_CMD_TRANSFER_FULL_SIZE)

      Please use ';' at the end of each pseudo-call.

> +
> +   /*
> +    * Begin to prepare DMA while cmd is being processed by MMC.
> +    * The first chunk of the request should take the same time
> +    * to prepare as the "MMC process command time".
> +    * If prepare time exceeds MMC cmd time
> +    * the transfer is delayed, guesstimate max 4k as first chunk size.
> +    */
> +    prepare_1st_chunk_for_dma(req)
> +    /* flush pending desc to the DMAC (dmaengine.h) */
> +    dma_issue_pending(req->dma_desc)
> +
> +    prepare_2nd_chunk_for_dma(req)
> +    /*
> +     * The second issue_pending should be called before MMC runs out
> +     * of the first chunk. If the MMC runs out of the first data chunk
> +     * before this call, the transfer is delayed.
> +     */
> +    dma_issue_pending(req->dma_desc)
> -- 


---
~Randy
*** Remember to use Documentation/SubmitChecklist when testing your code ***
--
To unsubscribe from this list: send the line "unsubscribe linux-mmc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Per Forlin July 5, 2011, 9:31 p.m. UTC | #2
On 5 July 2011 22:27, Randy Dunlap <rdunlap@xenotime.net> wrote:
> On Tue,  5 Jul 2011 21:43:28 +0200 Per Forlin wrote:
>
>> Documentation about the background and the design of mmc non-blocking.
>> Host driver guidelines to minimize request preparation overhead.
>>
>> Signed-off-by: Per Forlin <per.forlin@linaro.org>
>> ---
>
> It would be better to omit the introductory email and put all of its comments
> in this one [PATCH] email.
>
I agree. I'll put the changelog after "--" to exclude it from the
commit message.
All of your comments will be updated in v4.

Thanks for your comments,
Per
--
To unsubscribe from this list: send the line "unsubscribe linux-mmc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/Documentation/mmc/00-INDEX b/Documentation/mmc/00-INDEX
index 93dd7a7..11bc2cf 100644
--- a/Documentation/mmc/00-INDEX
+++ b/Documentation/mmc/00-INDEX
@@ -4,3 +4,5 @@  mmc-dev-attrs.txt
         - info on SD and MMC device attributes
 mmc-dev-parts.txt
         - info on SD and MMC device partitions
+mmc-async-req.txt
+        - info on mmc asynchronous request
diff --git a/Documentation/mmc/mmc-async-req.txt b/Documentation/mmc/mmc-async-req.txt
new file mode 100644
index 0000000..d7e7698
--- /dev/null
+++ b/Documentation/mmc/mmc-async-req.txt
@@ -0,0 +1,86 @@ 
+Rationale
+=========
+
+How significant is the cache maintenance overhead?
+It depends, fast eMMC and multiple cache levels with speculative cache
+pre-fetch makes the cache overhead relatively significant. If the DMA
+preparations for the next request are done in parallel to the current
+transfer the DMA preparation overhead would not affect the MMC performance.
+The intention of non-blocking (asynchronous) mmc requests is to minimize the
+time between when an mmc request ends and another mmc request begins.
+Using mmc_wait_for_req() the MMC controller is idle while dma_map_sg and
+dma_unmap_sg is processing. Using non-blocking mmc requests makes it
+possible to prepare the caches for next job in parallel to an active
+mmc request.
+
+MMC block driver
+================
+
+The issue_rw_rq() in the mmc block driver is made non-blocking.
+The increase in throughput is proportional to the time it takes to
+prepare (major part of preparations is dma_map_sg and dma_unmap_sg)
+a request and how fast the memory is. The faster the MMC/SD is
+the more significant the prepare request time becomes. Roughly the expected
+performance gain is 5% for large writes and 10% on large reads on a L2 cache
+platform. In power save mode, when clocks run on a lower frequency, the DMA
+preparation may cost even more. As long as these slower preparations are run
+in parallel to the transfer performance wont be affected.
+
+Details on measurements from IOZone and mmc_test
+================================================
+
+https://wiki.linaro.org/WorkingGroups/Kernel/Specs/StoragePerfMMC-async-req
+
+MMC core API extension
+======================
+
+There is one new public function mmc_start_req()
+It starts a new MMC command request for a host. The function isn't
+truly non-blocking. If there is on ongoing async request it waits
+for completion of that request and starts the new one and returns. It
+doesn't wait for the new request to complete. If there is no ongoing
+request it starts the new request and returns immediately.
+
+MMC host extensions
+===================
+
+There are two optional hooks pre_req() and post_req() that the host driver
+may implement in order to move work to before and after the actual
+mmc_request function is called. In the DMA case pre_req() may do
+dma_map_sg() and prepare the dma descriptor, and post_req runs
+the dma_unmap_sg.
+
+Optimize for the first request
+==============================
+
+The first request in a series of requests can't be prepared in parallel to
+the previous transfer, since there is no previous request.
+The argument is_first_req in pre_req() indicates that there is no previous
+request. The host driver may optimize for this scenario to minimize
+the performance loss. A way to optimize for this is to split the current
+request in two chunks, prepare the first chunk and start the request,
+and finally prepare the second chunk and start the transfer.
+
+Pseudocode to handle is_first_req scenario with minimal prepare overhead:
+if (is_first_req && req->size > threshold)
+   /* start MMC transfer for the complete transfer size */
+   mmc_start_command(MMC_CMD_TRANSFER_FULL_SIZE)
+
+   /*
+    * Begin to prepare DMA while cmd is being processed by MMC.
+    * The first chunk of the request should take the same time
+    * to prepare as the "MMC process command time".
+    * If prepare time exceeds MMC cmd time
+    * the transfer is delayed, guesstimate max 4k as first chunk size.
+    */
+    prepare_1st_chunk_for_dma(req)
+    /* flush pending desc to the DMAC (dmaengine.h) */
+    dma_issue_pending(req->dma_desc)
+
+    prepare_2nd_chunk_for_dma(req)
+    /*
+     * The second issue_pending should be called before MMC runs out
+     * of the first chunk. If the MMC runs out of the first data chunk
+     * before this call, the transfer is delayed.
+     */
+    dma_issue_pending(req->dma_desc)