July 2003 - ixp1200 - lists.cs.princeton.edu

[Q] I have a question about IXP SDRAM mapped into PCI bus.
by Cho, joon-woo 23 Jul '03

23 Jul '03

Hello. I kwow that all region of IXP SDRAM is mapped into PCI bus. And I am curious about how do I read/write 'SDRAM mapped in PCI bus' using vera source. Is there a function to access that region? I think that 'VeraI2Oexp' function is used for reading/writing to SDRAM Am I right? If right, please give me more information. And can I access that address using 'variable' like below? example) int xx (allocated in SDRAM) write some data to xx Please answer my questions. Thanks

1 0

Inter-ME uCode communication
by Cyrus Hall 22 Jul '03

22 Jul '03

I've finally gotten to the point in my code where I need to expand to multiple microengines. I think I've figured out what changes are needed in ixconfig, but other things are now vexing me. In the count example, the dispatch loop either forwards a packet with DL_SASink[] or DL_MESink[]. From the documentation, it sounds like DL_MESink[] passes the current packet reference to the next control block (next microengine). Just like DL_SASink[] has a inverse (DL_SASource[]), I would expect the the ME version to have one, something like DL_MESource[], yet no such macro exists. So what do must of you do? Have you just written a DL_MESource, or do you use one of the many other ways to syncronize between engines (SRAM CAM locks, or some other test-set mechanism)? I'm wondering which is the best way to go from here. Thanks, Cy

3 2

Re: [ixp1200] Inter-ME uCode communication
by Shyamal Pandya 22 Jul '03

22 Jul '03

I wrote my own MESource macro and I assigned ME-to-ME queues separately. This has to be done carefully so as not to clash with the queues assigned by the resource manager, otherwise you will end up clobbering the queues already set up. I look at the resource manager source code will reveal the queues that are assigned, so that you can determine your own queues. As Abhijeet said, these are hard-coded. Also if you look at the MESink macro, you will realize that the queues in which the packets go depend on the output port, so if you want to put your packets in a different queue you will have to write a different sink macro, or you will have to manilpulate the output port register in the sending thread. -- Shyamal Pandya Arizona State University Addr: 920 S Terrace Rd #102 Tempe AZ 85281 Phone: 1-480-966-1982 >From: Cyrus Hall <hallcp(a)cs.colorado.edu> >Reply-To: ixp1200(a)CS.Princeton.EDU >To: ixp1200 List <ixp1200(a)CS.Princeton.EDU> >Subject: [ixp1200] Inter-ME uCode communication >Date: 21 Jul 2003 17:03:09 -0600 > >I've finally gotten to the point in my code where I need to expand to >multiple microengines. I think I've figured out what changes are needed >in ixconfig, but other things are now vexing me. > >In the count example, the dispatch loop either forwards a packet with >DL_SASink[] or DL_MESink[]. From the documentation, it sounds like >DL_MESink[] passes the current packet reference to the next control >block (next microengine). Just like DL_SASink[] has a inverse >(DL_SASource[]), I would expect the the ME version to have one, >something like DL_MESource[], yet no such macro exists. > >So what do must of you do? Have you just written a DL_MESource, or do >you use one of the many other ways to syncronize between engines (SRAM >CAM locks, or some other test-set mechanism)? I'm wondering which is >the best way to go from here. > >Thanks, >Cy > _________________________________________________________________ MSN 8 helps eliminate e-mail viruses. Get 2 months FREE*. http://join.msn.com/?page=features/virus

1 0

FBI error specification.
by Yannis Haritakis 17 Jul '03

17 Jul '03

Hi all, According to hardware reference manual of ixp1200, the FBI should set the SOP bit of receive control register to zero whenever a cancelled speculative request occurs. I am suspecting that this does not occur actually. Has anyone used this feature ? Thanks for your time, yannis

1 0

how to load the application developed with uC to ixp1200
by ning weng 16 Jul '03

16 Jul '03

Hi, Thanks advance if you coud provide me some hint or reference... For an application developed in Micro C code(not microcode) such as the bridging in ixp1200 programming, how do I load it to ixp1200? I guess my question is : is it same with application developed with microcode? Thanks -Ning

1 0

ENP-2505 Bootup
by Ning Weng 14 Jul '03

14 Jul '03

Greeting, Did any one have this kind of experience? Please help and give me some hints. (I do remember some people mentioned in this broadcast e-mail before: one special key to get rid of this problem.) ENP-2505 board booting up... ".... Welcome to minicom 1.83.1 OPTIONS: History Buffer, F-key Macros, Search History Buffer, I18n Compiled on Aug 28 2001, 15:09:33. Press CTRL-A Z for help on special keys cygmon> script "./.ixstart": global timeout ...." Any help is greatly appreciated!!!! Thanks a lot. -Ning

1 0

ix bus throughput limitations
by liam noonan 14 Jul '03

14 Jul '03

Hi, I have carried out some testing on a single thread process receiving and counting packets (code from chapter 5 from ixp 1200 book) When it runs at wire speed at 177Mhz and Ixbus at 66 Mhz it has a receive rate of 350 Mbps at the IX bus. The same rate is achieved when running at 200Mhz, Ixbus at 66Mhz. I would expect the receive rate to be faster. Does anyone have any idea as to why the receive rate isn't higher for 200MHZ? Thanks Liam Noonan Univeristy Of Limerick

2 1

can anybody make it logic??
by rodrigo ruiz 14 Jul '03

14 Jul '03

Hi.. we�ve been working about four months with the enp-2505. We followed the ixa education workstation step by step, after we corrected some poblems, everything worked just fine, except that the card didn`t give response through the serial interface. We think we might detect some hardware problems. We changed the video card (nvidia gforce, agp),for a pci one. The leds start changeing in the booting. Then we completed the instalation according to the guide and the enp-2505 got alive. We got running win 2000 in the virtual machine, Linux 7.2 and the linux in the enp-2505. So far so good. The problem now is that we gotta install the card in some clones, identical machines, and what we get is either linux 7.2 just stop working, or the card sends some lines printing the registers... We changed te hard drive (the one that was working), and didn`t work in the new pc, but the hard drive from the new, worked on the old pc. We are using three computers (exactly the same), and the same hard drive and the same enp2505 only works in one of the computers. We already checked jumpers and bios. They seems to be just the same. In could get into cygmon terminal in some of the pc, with the same hardrive, but the .bootixp doesn`t work on it, only in the only pc it worked. Does anybody knows what is happening or at least has some idea of it ???. thanks Rodrigo __________________________________ Do you Yahoo!? SBC Yahoo! DSL - Now only $29.95 per month! http://sbc.yahoo.com

1 0

The microACE "tutorial"
by Øyvind Hvamstad 11 Jul '03

11 Jul '03

Hi, I'm trying to do the "tutorial" for the ENP-2505 card. The card is up after numerous hours of compiling and tweeking. So now I am ready for some programming; I thought.. I tried to start with the Count_8_1 project. I follow the README in $IXROOT/src/microace/aces/tutorial1 and use the workbench to build the microACE. This results in a single .uof file, Count_8_1Gig.uof. I copy this to the $IXROOT/bin/arm-be directory, then I run export CONFIG=ARM_BE and make the code. I modify the ixsys.config file to use interface 0-3 and mode=0, then I copy it to $IXROOT/bin/arm-be. That's it. The output when I run ./ixstart on the board outputs: <snip> ConfigureFBusInterface: ENP has 64Bit IXbus. ConfigureFBusInterface: ENP has 64Bit IXbus. ixconfig: Initialized Resource Manager ixconfig: ix_task_init successful ixconfig: Created OSSL thread ixconfig: ix_res_open_sync successful ixconfig: ix_ns_open_sync successful ixconfig: File ./SlowIngressCount.uof doesn't Exist or doesn't have READ permission. </snip> I have searched all over for the file and the permissions are all set correctly. Now, where can I find this file? What am I doing wrong. I can't seem to run any other aces either. I tried the l3forward, but then I only get ixconfig: Invalid port number 2, even though the config file specifies the four first ports. Can anyone help? Please! I've been sitting all day. By the way sometimes the serial connection hangs during setup, after the kernel is loaded. Is there a better way for rebooting the card than rebooting the host? In advance thanks.. -- Øyvind Hvamstad

4 4

Peculiar drops. (quiz)
by Yannis Haritakis 11 Jul '03

11 Jul '03

Hi all, I ran into the following trouble recently, and the "solution" was quite surprising! Let me spend a few lines to describe the environment: I have an ENP2506 board hosted inside a Dell server. One of the Gigabit ports of the ENP2506 is connected to a transmiter, that generates large packets at a constant rate (about 600 Mbit/s). Now, I log into the linux running on the ENP2506. I use the load utility (from the ASAN drivers) to upload some simple code to the uEngines. The uploaded code simply transfers incoming packets from the gigabit port to the RFIFO and then to SDRAM. I use a simple utilitity to read the counters of the gigabit port, and see how many packets were dropped and how many packets were received correctly. This utility uses the ioctls defined in the giga_drv module. One could expect that running at 600Mbit/s should be quite ok, and never loose a single packet. Indeed, this is the case when I move packets from the buffer of the port up to the RFIFO, but not into SDRAM. That is the uploaded code has commented out the sdram2rfifo directive. Everything works fine, and whenever I run my utility it reads zero drops from the counters of the port. Now, I modify the uploaded code so as to perform the final move of data. So data move from the port to the RFIFO and then to SDRAM. In simulation the buffer of the gigabit port never exceeds 200 bytes, using 166MHz core frequence and 66MHz IX Bus frequency.-- well below the actual numbers of the ENP2506 --. And here goes the problem: One, would expect again to have zero drops. However this is not the case, and whenever I ran the utility it reports about 10 to 15 dropped packets, never more. Why ? Hint: I ran the utility again, after I finished writing this email (it took me at least 5 full minutes) and reported 11 drops... :-) yannis

2 2