Re: [casper] ROACH File I/O Bottleneck

2010-04-29 Thread Jason Manley
Yep... you can check the actual temp in linux with lmsensors, or otherwise remotely through the xport using roach_monitor.py. If they're in an air-conditioned room, it _should_ be fine. The PAPER ROACH PPCs have run at 60degC for extended periods without trouble, but much above that and

Re: [casper] ROACH File I/O Bottleneck

2010-04-29 Thread David George
Hi All. Just a few comments on bus performance. The processor bus is 16 bits at 66 MHz (or 83), so the theoretical maximum is 133 MB/s. There are 3 cycles bus overhead per transaction (for registering etc in FPGA) and an extra two or so for for accessing the register/bram. So that is roughly a

Re: [casper] ROACH File I/O Bottleneck

2010-04-28 Thread Aaron Parsons
So commenting out all the lines in /etc/syslog.conf and then rebooting seems to have done the trick. I now see ~7.8MB/s read times. Yay! Muchas gracias! On Wed, Apr 28, 2010 at 8:00 AM, Jason Manley jasonman...@gmail.com wrote: Syslog flushes all logs to disk as they happen (synchronous

Re: [casper] ROACH File I/O Bottleneck

2010-04-28 Thread David MacMahon
Hi, Jason, Glad you made it back to SA OK! On Apr 28, 2010, at 8:00 , Jason Manley wrote: The logs you're seeing are likely from the kernel itself, as BORPH logs every bus transaction. A kernel recompile is required to remove this entirely. But you can configure what is logged to disk by

Re: [casper] ROACH File I/O Bottleneck

2010-04-28 Thread David MacMahon
Hi, Mel, On Apr 28, 2010, at 9:54 , melvyn wright wrote: You should be getting around 7MegaBytes/s across that bus. 56 Mb / 16 b 4 MHz bus clock frequency Good suggestion re kernel, but don't understand the significance of the 56 Mb I omitted the /s in 56 Mb/s. 7 megabytes/s == 56

Re: [casper] ROACH File I/O Bottleneck

2010-04-28 Thread Jason Manley
ROACH bus runs at 66MHz (or 83MHz if you overclock it to boot config H). I agree that the 3.5MB/s is miserable performance considering what it should be capable of achieving. I suspect these bottlenecks are mostly BORPH related. I also recall an extended bus handshake being mentioned for

Re: [casper] ROACH File I/O Bottleneck

2010-04-28 Thread Aaron Parsons
On a semi-related note, I've notice the CPU running pretty hot when I read data fast from the FPGA and make packets out of it. Do we need heatsinks for the CPU? On Wed, Apr 28, 2010 at 10:44 PM, Jason Manley jasonman...@gmail.com wrote: ROACH bus runs at 66MHz (or 83MHz if you overclock it to