Active Topics
-
Sailfish OS for the Motorola Moto G7 Power (XT1955-5) - (ocean) (9)
to SailfishOS by biketool - 18 hrs, 1 min ago -
[Announce] coderus unrestricted system-ui (297)
to MeeGo / Harmattan by nieldk - 6 days, 23 hrs ago - more...
|
2007-08-17
, 19:23
|
|
Posts: 1 |
Thanked: 0 times |
Joined on Aug 2007
|
#2
|
0 is a Ridata 2gb labeled "PRO 150X"
1 is a 4 gig PNY that came labeled class 4 or something like that.
/dev/mmcblk1p1:
Timing cached reads: 236 MB in 2.01 seconds = 117.66 MB/sec
Timing buffered disk reads: 18 MB in 3.28 seconds = 5.48 MB/sec
/dev/mmcblk0p1:
Timing cached reads: 240 MB in 2.01 seconds = 119.69 MB/sec
Timing buffered disk reads: 18 MB in 3.15 seconds = 5.72 MB/sec
1 is a 4 gig PNY that came labeled class 4 or something like that.
/dev/mmcblk1p1:
Timing cached reads: 236 MB in 2.01 seconds = 117.66 MB/sec
Timing buffered disk reads: 18 MB in 3.28 seconds = 5.48 MB/sec
/dev/mmcblk0p1:
Timing cached reads: 240 MB in 2.01 seconds = 119.69 MB/sec
Timing buffered disk reads: 18 MB in 3.15 seconds = 5.72 MB/sec
|
|
2007-08-18
, 02:18
|
|
Posts: 3,401 |
Thanked: 1,255 times |
Joined on Nov 2005
@ London, UK
|
#3
|
joe.rock - you need to state which firmware/kernel you are using.... judging bye your slow SDHC performance it looks like stock 4.2007.26-8 but could be due to your card not supporting high speed mode.
|
|
2007-08-18
, 02:31
|
|
Posts: 3,401 |
Thanked: 1,255 times |
Joined on Nov 2005
@ London, UK
|
#4
|
Firmware: Stock 4.2007.26-8
Internal slot, Transcend 4GB Class 2 SDHC
External slot, Transcend 4GB Class 2 SDHC
Internal slot, Transcend 4GB Class 2 SDHC
Code:
/home/user # ./hdparm -Tt /dev/mmcblk0p1 /dev/mmcblk0p1: Timing cached reads: 240 MB in 2.00 seconds = 119.80 MB/sec Timing buffered disk reads: 16 MB in 3.22 seconds = 4.97 MB/sec
Code:
/home/user # ./hdparm -Tt /dev/mmcblk1p1 /dev/mmcblk1p1: Timing cached reads: 238 MB in 2.01 seconds = 118.13 MB/sec Timing buffered disk reads: 16 MB in 3.01 seconds = 5.32 MB/sec
|
|
2007-08-18
, 02:47
|
|
Posts: 3,401 |
Thanked: 1,255 times |
Joined on Nov 2005
@ London, UK
|
#5
|
Firmware: High speed community 4.2007.26-8 kernel
Internal slot, Transcend 4GB Class 2 SDHC (48Mhz, wide bus), FAT32
I have an ext2 second partition on the internal card which interestingly gives better performance:
External slot, Transcend 4GB Class 2 SDHC (48Mhz, wide bus), FAT32
Last edited by Milhouse; 2007-08-18 at 02:54.
Internal slot, Transcend 4GB Class 2 SDHC (48Mhz, wide bus), FAT32
Code:
/home/user # ./hdparm -Tt /dev/mmcblk0p1 /dev/mmcblk0p1: Timing cached reads: 228 MB in 2.00 seconds = 113.92 MB/sec Timing buffered disk reads: 24 MB in 3.21 seconds = 7.48 MB/sec
Code:
/home/user # ./hdparm -Tt /dev/mmcblk0p2 /dev/mmcblk0p2: Timing cached reads: 220 MB in 2.00 seconds = 109.73 MB/sec Timing buffered disk reads: 30 MB in 3.03 seconds = 9.91 MB/sec
Code:
/home/user # ./hdparm -Tt /dev/mmcblk1p1 /dev/mmcblk1p1: Timing cached reads: 224 MB in 2.01 seconds = 111.44 MB/sec Timing buffered disk reads: 24 MB in 3.18 seconds = 7.54 MB/sec
Last edited by Milhouse; 2007-08-18 at 02:54.
 |
|
2007-08-18
, 03:36
|
|
Posts: 3,096 |
Thanked: 1,525 times |
Joined on Jan 2006
@ Michigan, USA
|
#6
|
sdhc 8GB - Class 6 - Kingston
Code:
Nokia-N800-26:~# ./hdparm -Tt /dev/mmcblk0p1
/dev/mmcblk1p2:
Timing cached reads: 242 MB in 2.00 seconds = 120.25 MB/sec
Timing buffered disk reads: 38 MB in 3.04 seconds = 12.50 MB/sec
updated kernel listed in this post
mounted on /usr/local
Code:
Nokia-N800-26:~# ./hdparm -Tt /dev/mmcblk0p1
/dev/mmcblk1p2:
Timing cached reads: 242 MB in 2.00 seconds = 120.25 MB/sec
Timing buffered disk reads: 38 MB in 3.04 seconds = 12.50 MB/sec
updated kernel listed in this post
mounted on /usr/local
|
|
2007-08-19
, 07:28
|
|
Posts: 64 |
Thanked: 9 times |
Joined on Jun 2007
@ abuja, nigeria (currently)
|
#7
|
so seems like class 4 is worth it over class 2, if you are using the updated kernel.
rob.
rob.
 |
|
2007-08-19
, 08:39
|
|
Posts: 87 |
Thanked: 1 time |
Joined on Mar 2006
|
#8
|
Testing internal Flash gives me a respectable result.
How could that be? We all know that booting from mmc is boosting read performance.
Still on 51-6 with the SDHC kernel although I'm only running non-SDHC cards still.
Code:
/dev/mtdblock4: Timing cached reads: 206 MB in 2.00 seconds = 102.83 MB/sec Timing buffered disk reads: 42 MB in 3.08 seconds = 13.66 MB/sec
Still on 51-6 with the SDHC kernel although I'm only running non-SDHC cards still.
__________________
Naboo
__________________
Naboo
__________________
|
|
2007-08-19
, 08:46
|
|
Posts: 3,401 |
Thanked: 1,255 times |
Joined on Nov 2005
@ London, UK
|
#9
|
There's no difference between a Class 4 and a Class 6 card... perhaps the N800 becomes the bottleneck at around that speed.
Before declaring that Class 4 is faster than Class 2 I think we need to see more Class 2 results from manufacturers other than Transcend.
In previous tests with dd my Transcend 8GB SDHC C2 cards achieved a transfer rate of 11.5MB/s... I didn't bother posting the 8GB results here as when testing with hdparm, the 8GB card turned in the same results as the 4GB card which I had already posted (ie. 7.5MB/s). This surprised me, and I'm not sure why my Transcend cards are now slower than they appeared to be in the past - maybe dd isn't accurate, or maybe hdparm isn't accurate...
The fact that I obtained two different results for the same card when accessing different partitions (and filesystems) suggests that hdparm isn't testing the raw performance of the card at all. Instead it appears to be testing the performance of the filesystem. Different block sizes in a VFAT partition may thus play a role in determining the figures returned by hdparm, and I'm sceptical about it's accuracy compared to dd.
Before declaring that Class 4 is faster than Class 2 I think we need to see more Class 2 results from manufacturers other than Transcend.
In previous tests with dd my Transcend 8GB SDHC C2 cards achieved a transfer rate of 11.5MB/s... I didn't bother posting the 8GB results here as when testing with hdparm, the 8GB card turned in the same results as the 4GB card which I had already posted (ie. 7.5MB/s). This surprised me, and I'm not sure why my Transcend cards are now slower than they appeared to be in the past - maybe dd isn't accurate, or maybe hdparm isn't accurate...
The fact that I obtained two different results for the same card when accessing different partitions (and filesystems) suggests that hdparm isn't testing the raw performance of the card at all. Instead it appears to be testing the performance of the filesystem. Different block sizes in a VFAT partition may thus play a role in determining the figures returned by hdparm, and I'm sceptical about it's accuracy compared to dd.
|
|
2007-08-19
, 08:50
|
|
Posts: 2,152 |
Thanked: 1,490 times |
Joined on Jan 2006
@ Czech Republic
|
#10
|
Originally Posted by tolou
jffs2 filesystem is compressed and has big overhead. By using device you are reading compressed data blocks directly. Try to read/write files. dd and time commands may be better for this, examples can be found in this forum.
How could that be? We all know that booting from mmc is boosting read performance.
__________________
Newbies click here before posting. Thanks.
If you really need to PM me with troubleshooting question please consider posting it to the forum instead. It is OK to PM me a link to such post then. Thank you.
Newbies click here before posting. Thanks.
If you really need to PM me with troubleshooting question please consider posting it to the forum instead. It is OK to PM me a link to such post then. Thank you.
I have 2 sdhc cards purchased from www.7dayshop.com, with the following results:
sdhc 8GB - Class 6 - Kingston
please post your own card details and numbers so I can make better choices next time.
oh yes, I'm using the updated kernel from http://intr.overt.org/4.2007.26-mmc-kernel/
anyone suggest a preferred write speed tester?
rob.