similar to: questions from a 10GbE driver author

In crossbow, each mac_srs has a kernel thread called "mac_rx_srs_poll_ring" to poll the hardware and crossbow will wakeup this thread to poll packets from the hardware automatically. Does crossbow provide any method to disable the polling mechanism, for example disabling the this kernel thread? Thanks Zhihui -------------- next part -------------- An HTML attachment was scrubbed... URL:

Recently I found that the mac_srs_rx_poll_ring thread may never stop in kernel, please see the following mpstat, cpu 2 is in 100% kernel usage, but no syscalls and no interrupts. CPU minf mjf xcal intr ithr csw icsw migr smtx srw syscl usr sys wt idl 0 0 0 0 300 100 0 0 1 0 0 0 0 0 0 100 1 14 0 0 134 68 134 1

Team, We are trying to install Crossbow on VirtualBox. Siva first tried it on Linux and reported it in Hyderabad Open Solaris User Group alias. http://opensolaris.org/os/project/hosug/ Today both of us tried it on VirtualBox running on OpenSolaris. Both attempts have the same results. a. Selecting Solaris Developer Express during boot process exits the installation. See this picture:

Hi. After running with the crossbow bits for a while, I discovered that the network management port on my T1000 wasn''t working properly (no link light). When logging in on the serial management port and running "resetsc", I got this: --->8--- ALOM POST 1.0 Dual Port Memory Test, PASSED. TTY External - Internal Loopback Test TTY External - Internal Loopback Test, PASSED.

Howdy, I just finished reading through the Crossbow presentation: http://blogs.sun.com/sunay/resource/crossbow.pdf And have one question. If you create a virtual NIC with dladm: $ dladm create-vnic -d bge0 -m 0:1:2:3:4:5 -b 10000 1 Can you then add vnic1 directly to the zone? e.g.: zonecfg -z zone1 zonecfg:zone1> create zonecfg:zone1> set zonepath=/zones/zone1 zonecfg:zone1> add net

I''ve been thinking about hardware that has multiple transmit rings ("tx resources"). We really should have a way to expose this up to the stack. And ideally, the stack should guarantee that a given flow will always be sent down using the same hardware tx resource. I''ve heard that crossbow will deliver this, but I can''t find evidence of it in the crossbow

Howdy, I just installed the crossbow snapshot from opensolaris.org, and bumped into an issue when attempting to create a virtual nic: $ dladm create-vnic -i 192.168.1.101 -d ni0 2 dladm: VNIC creation failed: No such file or directory (unknown diagnostic) When I truss the process, it looks like it''s failing when attempting to open the vnic pseudo-device: 100878/1:

Hi everyone, I''m Ezequiel from Buenos Aires. I''m new in this list, so please forgive me if my questions are not the correct one''s fro this alias. I''m working as a campus ambassador in Sun, while finishing my engineer degree, creating communities around opensolaris in Argentina. I discovered this project, and this group, looking for something that I could

Hi All, I have bfu''ed to net-virt_xb-21_snv_81_021308. The dladm command on my machine does not have create-etherstub option. Please let me know what could be the issue. Thanks Khushal

got a problem with b75 that the zone with ip-exclusive just takes the identity of the global zone. For the primary nic there is no option to set its ip and hostname. When i change the host name and ip the hostname does not change and the networking goes weird for both the zone and global zone. sparc eri qfe There any bugs about or should this work fine? This message posted from

I decided to take a stab at 6601421 dladm set-linkprop should support multiple -p options along with some related linkprop fixes, but when I looked into dladm.c, was surprised to find that "dladm_parse_props()" is called from do_create_aggr and do_create_vlan in addition to the expected (by me, at least) do_create_vnic *linkprop functions. What happened here? Why do we pass in

Hi, netvirt-src-20080310.tar.bz2 appears to the last beta release. Is this synced against Build 81 ? Also when is the next beta expected ? Regards, Moinak.

Crossbow team, The following is of interest to the Crossbow project. Since a large chunk of these changes also exist in the Crossbow gate, the delivery of this wad will result in fewer lines of changes for Crossbow''s delivery. If someone on Crossbow could participate in this review, that would be a bonus (Eric Cheng made original changes in the Crossbow gate at some point last year).

Guys, OK, now that we have the new core contributors squared away, we can go back to finishing the contributors list. There were some people who got added and then there is existing contributors list. I think Darren''s suggestion to wait to add new core contributors is fine (let the new constitution settle down and we can in the meanwhile have a more inclusive look at both rather than

Hi, I''m trying to BFU my own build of ON onto a snv_104 installation and I''m hitting problems with bnx driver; which is coming from a set of snv_105 closed bins: WARNING: bnx0: Failed to allocate GLD MAC memory. I believe bnx is a closed source GLDv3 driver. Were there any incompatible changes due to the crossbow integration that went in after snv_105?

Hello, I am a rather new user to OpenSolaris and I have been loving every minute of it. I have spent quite a lot of time looking around for bandwidth management features and Project Crossbow is just amazing. It is truly amazing compared to what Linux has to offer. I would like to use flowadm to do some bandwidth management on a tun interface. The problem is that it is not recognized by the dladm

Hi. I tried to send this to the mailing list, but it never showed up in the archives, so I''m trying the forum instead... I recently installed the Crossbow Beta October 31 2008 on my SunFire T1000, and let me first say that I''m very pleased with the functionality it provides. What''s not so pleasing is the fact that after installing this, the computer now get very

How do I create a vnic that represents the factory assigned MAC address of my physical nic? The bge device in my system (x2100) appears to support 4 MAC addresses. The driver reserves the first as the ''primary/default'' address and allows manipulation of the other three via the MAC_CAPAB_MULTIADDRESS interface. I''d like to use vnics on this system, as I have Xen guest

Hi. Can a virtual switch have more than one physical NIC? Or, can a VNIC have more than one NIC? (this is the same question, I think)? emike

So, just to play with vnics with 106, I have... e1000g2 plumb''d with 192.168.85.10 vnic0 is created on top of e1000g2 with 192.168.85.22 I snoop on e1000g2 to see the traffic. I ping 192.168.85.22 and it works. I stop the snoop on e1000g2. I ping 192.168.85.22 and it doesn''t work. I start the snoop on e1000g2. I ping 192.168.85.22 and ping works. Is this a new feature with