Re: Max seep of the SD slot?
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Somebody in the thread at some point said: | I've upgraded to the current kernel. TTFF-issue is solved by the last | kernel-patch. Congratulations! | | Now I'm testing the inteferences while accessing data from the sd-card. | On the current default clock of 16MHz I see heavy GPS-signal breach-ins | in a pulsing manner, if I do some continuous access with 'dd' to the | card. If I stop dd the perception signal stabilizes. Okay, this was to | expect. | | According to the statement below, the clock rate on the SD-card side is | far above the effective data-rate on the CPU side. We do 16MHz on one | and something around 2MHz on the other. That makes no sense to me. | What about fixing the rate on the sd-card side to far lower level, not | only while ideling, even if accessing? Lets say 5MHz. Would it make any | sense and would it decrase the clock noise significally enough, to be | able to just ignore the hardware patch? It's not a crazy way to look at it, but the latencies add together currently. So we have to sit it out while the Glamo independently grabs the bulk data from the card, then when it completes we get an interrupt and basically memcpy it to the requested place. So we delay the overall action by slowing the SD clock. It's worth a try using sd_max_clk if you can see the effect of SD traffic on GPS still. | I haven't found the file to place any permanent kernel opts yet, to test | this. No grub, no lilo :-) thats beyond my knowledge about the FR | booting internals. Any hints? Kernel commandline lives in the twilight world of U-Boot environment. - -Andy -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.9 (GNU/Linux) Comment: Using GnuPG with Fedora - http://enigmail.mozdev.org iEYEARECAAYFAkiJjBwACgkQOjLpvpq7dMpe0QCgjYbDV2kCTQ+j4kwDZJ9/KOLY rNEAnRaLpkkpVHpqemSWg3jrK8+3GFN0 =EYsI -END PGP SIGNATURE- ___ Openmoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community
Re: Max seep of the SD slot?
On Thu, Jul 24, 2008 at 08:49, Andy Green [EMAIL PROTECTED] wrote: Well, a good rule of thumb for generic 1-bit transfer is divide by 10 for the max speed in Bytes/sec you could expect, here we have 4-bit so the peak raw trasfer speed is ~10MBytes/sec *BUT* after Glamo pulls the data from the card, we have to sit there dragging it into the CPU memory, on top of card latencies and command setup the speed is way slower, still a decent ~2MBytes/sec each way IIRC. - -Andy Thanks. This is something I also wanted to know for the choice of a new card. So we may say that up to 10MBytes/s, max speed of the microSD matters. After it should not much. (?) (and looks like 10Mbytes/s is currently what offer rather high end microSD) One more question though : if the card is slow, throughput will be lower, but will the CPU / glamo graphic bus be able to benefit of more resources while the card transfer occur ? Or does it just had to time to wait and CPU / glamo bus are as much busy (or waiting) ? Same question if we lower the SD clock rate. Is it equivalent to having a slower card ? ___ Openmoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community
Re: Max seep of the SD slot?
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Somebody in the thread at some point said: | On Thu, Jul 24, 2008 at 08:49, Andy Green [EMAIL PROTECTED] wrote: | Well, a good rule of thumb for generic 1-bit transfer is divide by 10 | for the max speed in Bytes/sec you could expect, here we have 4-bit so | the peak raw trasfer speed is ~10MBytes/sec *BUT* after Glamo pulls the | data from the card, we have to sit there dragging it into the CPU | memory, on top of card latencies and command setup the speed is way | slower, still a decent ~2MBytes/sec each way IIRC. | | - -Andy | | | Thanks. | | This is something I also wanted to know for the choice of a new card. | | So we may say that up to 10MBytes/s, max speed of the microSD matters. | After it should not much. (?) | (and looks like 10Mbytes/s is currently what offer rather high end microSD) The MCI / MMC stack in Linux negotiates the clock speed with the card, all the microSD cards I saw say they can handle 16MHz and that's what they get. We can't sustain the actual throughput that implies right now, although soon we might be able to get a little better in the driver. | One more question though : if the card is slow, throughput will be | lower, but will the CPU / glamo graphic bus be able to benefit of more | resources while the card transfer occur ? | Or does it just had to time to wait and CPU / glamo bus are as much | busy (or waiting) ? Have to make clear what we mean by slow, it means latency to NAND inside card as I understand it. So every time you ask for some data it is slower to start sending it and chokes more often waiting on getting next block from NAND. --- | Same question if we lower the SD clock rate. Is it equivalent to | having a slower card ? If it's slow at the card it will block Glamo memory less (probably... arbitrator in Glamo might mess that assumption up) and definitely block the CPU bus less. - -Andy -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.9 (GNU/Linux) Comment: Using GnuPG with Fedora - http://enigmail.mozdev.org iEYEARECAAYFAkiJrHgACgkQOjLpvpq7dMqLWwCfUyta7nEdXK5JXOdEkMYAoJBz 5dMAoJPdUCGq0xBpbDRCoDLp2wkR6EOT =k1zT -END PGP SIGNATURE- ___ Openmoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community
Re: Max seep of the SD slot?
Am Fr 25. Juli 2008 schrieb BlueStar88: What about fixing the rate on the sd-card side to far lower level, not only while ideling, even if accessing? Lets say 5MHz. Would it make any sense and would it decrase the clock noise significally enough, to be able to just ignore the hardware patch? To add to Andy's prev comment, the noise isn't exactly relating to clock-*speed* but rather to signal rise- and fall-time of the low-high-low transitions. Those aren't affected by mere closck-speed, but actually are by adding caps or changing drive-power. Think of it like hitting a bell once a second or every 3 seconds doesn't change the frequency or amplitude of the bell's tone itself. Anyway fiddling with sd-clock-freq won't hurt, just report your results. Maybe we find something unexpected ;-) cheers jOERG signature.asc Description: This is a digitally signed message part. ___ Openmoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community
Re: Max seep of the SD slot?
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Somebody in the thread at some point said: | | access let me know what the max speed of the Glamo's MicroSD card | | controller is? looking for MB/s, or something like that. | | It's just slightly under 25MHz SD Clock, we round it up and call it 25MHz. | What is that in MB/s? Well, a good rule of thumb for generic 1-bit transfer is divide by 10 for the max speed in Bytes/sec you could expect, here we have 4-bit so the peak raw trasfer speed is ~10MBytes/sec *BUT* after Glamo pulls the data from the card, we have to sit there dragging it into the CPU memory, on top of card latencies and command setup the speed is way slower, still a decent ~2MBytes/sec each way IIRC. - -Andy -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.9 (GNU/Linux) Comment: Using GnuPG with Fedora - http://enigmail.mozdev.org iEYEARECAAYFAkiIJfYACgkQOjLpvpq7dMq4pgCghgrmfW/rgPdMCgmnJssxnB10 rsAAni9A9EOVbDS9zwa51rj3CLqWCbOK =PhsH -END PGP SIGNATURE- ___ Openmoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community
Re: Max seep of the SD slot?
I've upgraded to the current kernel. TTFF-issue is solved by the last kernel-patch. Congratulations! Now I'm testing the inteferences while accessing data from the sd-card. On the current default clock of 16MHz I see heavy GPS-signal breach-ins in a pulsing manner, if I do some continuous access with 'dd' to the card. If I stop dd the perception signal stabilizes. Okay, this was to expect. According to the statement below, the clock rate on the SD-card side is far above the effective data-rate on the CPU side. We do 16MHz on one and something around 2MHz on the other. That makes no sense to me. What about fixing the rate on the sd-card side to far lower level, not only while ideling, even if accessing? Lets say 5MHz. Would it make any sense and would it decrase the clock noise significally enough, to be able to just ignore the hardware patch? I haven't found the file to place any permanent kernel opts yet, to test this. No grub, no lilo :-) thats beyond my knowledge about the FR booting internals. Any hints? Andy Green schrieb: Somebody in the thread at some point said: | | access let me know what the max speed of the Glamo's MicroSD card | | controller is? looking for MB/s, or something like that. | | It's just slightly under 25MHz SD Clock, we round it up and call it 25MHz. | What is that in MB/s? Well, a good rule of thumb for generic 1-bit transfer is divide by 10 for the max speed in Bytes/sec you could expect, here we have 4-bit so the peak raw trasfer speed is ~10MBytes/sec *BUT* after Glamo pulls the data from the card, we have to sit there dragging it into the CPU memory, on top of card latencies and command setup the speed is way slower, still a decent ~2MBytes/sec each way IIRC. -Andy ___ Openmoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community -- BlueStar88 PGPID: 0x36150C86 PGPFP: E9AE 667C 4A2E 3F46 9B69 9BB2 FC63 8933 3615 0C86 signature.asc Description: OpenPGP digital signature ___ Openmoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community
Max seep of the SD slot?
I can see that the MicroSD card is hooked it through the Glamo. http://wiki.openmoko.org/wiki/Image:SimpleComponentDiagram.jpg I do not have the data sheets for the Glamo 3362, can some one, who has access let me know what the max speed of the Glamo's MicroSD card controller is? looking for MB/s, or something like that. -Adam ___ Openmoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community
Re: Max seep of the SD slot?
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Somebody in the thread at some point said: | I can see that the MicroSD card is hooked it through the Glamo. | http://wiki.openmoko.org/wiki/Image:SimpleComponentDiagram.jpg | I do not have the data sheets for the Glamo 3362, can some one, who has | access let me know what the max speed of the Glamo's MicroSD card | controller is? looking for MB/s, or something like that. It's just slightly under 25MHz SD Clock, we round it up and call it 25MHz. You can read about how to change the clock here: http://git.openmoko.org/?p=kernel.git;a=commit;h=ef2376d29e996d9d21a9e5798cb88aa73f734c83 - -Andy -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.9 (GNU/Linux) Comment: Using GnuPG with Fedora - http://enigmail.mozdev.org iEYEARECAAYFAkiHjxkACgkQOjLpvpq7dMqphwCfc+JqlPzDfV1mnN4Th+rmSwb0 mHoAnjxnjhpKyL8rmhltkN2G5C/cZCRQ =pc3e -END PGP SIGNATURE- ___ Openmoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community
Re: Max seep of the SD slot?
What is that in MB/s? On Wed, 2008-07-23 at 21:05 +0100, Andy Green wrote: -BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Somebody in the thread at some point said: | I can see that the MicroSD card is hooked it through the Glamo. | http://wiki.openmoko.org/wiki/Image:SimpleComponentDiagram.jpg | I do not have the data sheets for the Glamo 3362, can some one, who has | access let me know what the max speed of the Glamo's MicroSD card | controller is? looking for MB/s, or something like that. It's just slightly under 25MHz SD Clock, we round it up and call it 25MHz. You can read about how to change the clock here: http://git.openmoko.org/?p=kernel.git;a=commit;h=ef2376d29e996d9d21a9e5798cb88aa73f734c83 - -Andy -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.9 (GNU/Linux) Comment: Using GnuPG with Fedora - http://enigmail.mozdev.org iEYEARECAAYFAkiHjxkACgkQOjLpvpq7dMqphwCfc+JqlPzDfV1mnN4Th+rmSwb0 mHoAnjxnjhpKyL8rmhltkN2G5C/cZCRQ =pc3e -END PGP SIGNATURE- ___ Openmoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community ___ Openmoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community
