From: Adrian Hunter <adrian.hunter@nokia.com>
To: Chris Ball <cjb@laptop.org>
Cc: Adrian Hunter <adrian.hunter@nokia.com>,
linux-mmc Mailing List <linux-mmc@vger.kernel.org>
Subject: [PATCH 1/3] mmc_test: make performance test area size about 4MiB
Date: Tue, 8 Feb 2011 13:41:01 +0200 [thread overview]
Message-ID: <1297165263-656-2-git-send-email-adrian.hunter@nokia.com> (raw)
In-Reply-To: <1297165263-656-1-git-send-email-adrian.hunter@nokia.com>
The test area size was set to the preferred erase size
but for comparison purposes it is better if it is the
same size for different devices. Make it a multiple
of preferred erase size that is greater than or equal
to 4MiB.
Signed-off-by: Adrian Hunter <adrian.hunter@nokia.com>
---
drivers/mmc/card/mmc_test.c | 25 +++++++++++++------------
1 files changed, 13 insertions(+), 12 deletions(-)
diff --git a/drivers/mmc/card/mmc_test.c b/drivers/mmc/card/mmc_test.c
index 0131c6c..ec6060c 100644
--- a/drivers/mmc/card/mmc_test.c
+++ b/drivers/mmc/card/mmc_test.c
@@ -1426,28 +1426,29 @@ static int mmc_test_area_cleanup(struct mmc_test_card *test)
}
/*
- * Initialize an area for testing large transfers. The size of the area is the
- * preferred erase size which is a good size for optimal transfer speed. Note
- * that is typically 4MiB for modern cards. The test area is set to the middle
- * of the card because cards may have different charateristics at the front
- * (for FAT file system optimization). Optionally, the area is erased (if the
- * card supports it) which may improve write performance. Optionally, the area
- * is filled with data for subsequent read tests.
+ * Initialize an area for testing large transfers. The test area is set to the
+ * middle of the card because cards may have different charateristics at the
+ * front (for FAT file system optimization). Optionally, the area is erased
+ * (if the card supports it) which may improve write performance. Optionally,
+ * the area is filled with data for subsequent read tests.
*/
static int mmc_test_area_init(struct mmc_test_card *test, int erase, int fill)
{
struct mmc_test_area *t = &test->area;
- unsigned long min_sz = 64 * 1024;
+ unsigned long min_sz = 64 * 1024, sz;
int ret;
ret = mmc_test_set_blksize(test, 512);
if (ret)
return ret;
- if (test->card->pref_erase > TEST_AREA_MAX_SIZE >> 9)
- t->max_sz = TEST_AREA_MAX_SIZE;
- else
- t->max_sz = (unsigned long)test->card->pref_erase << 9;
+ /* Make the test area size about 4MiB */
+ sz = (unsigned long)test->card->pref_erase << 9;
+ t->max_sz = sz;
+ while (t->max_sz < 4 * 1024 * 1024)
+ t->max_sz += sz;
+ while (t->max_sz > TEST_AREA_MAX_SIZE && t->max_sz > sz)
+ t->max_sz -= sz;
t->max_segs = test->card->host->max_segs;
t->max_seg_sz = test->card->host->max_seg_size;
--
1.7.0.4
next prev parent reply other threads:[~2011-02-08 11:41 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-02-08 11:41 [PATCH 0/3] mmc_test: add some tests Adrian Hunter
2011-02-08 11:41 ` Adrian Hunter [this message]
2011-02-08 11:41 ` [PATCH 2/3] mmc_test: add tests to measure random I/O operations per second Adrian Hunter
2011-03-30 10:56 ` Keshava Munegowda
2011-02-08 11:41 ` [PATCH 3/3] mmc_test: add tests to measure large sequential I/O performance Adrian Hunter
2011-03-30 10:57 ` Keshava Munegowda
2011-02-08 15:45 ` [PATCH 0/3] mmc_test: add some tests Chris Ball
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1297165263-656-2-git-send-email-adrian.hunter@nokia.com \
--to=adrian.hunter@nokia.com \
--cc=cjb@laptop.org \
--cc=linux-mmc@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.