Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-31 Thread Scott Feldman
On Sat, May 30, 2015 at 2:00 AM, Jiri Pirko j...@resnulli.us wrote: Fri, May 29, 2015 at 05:39:46PM CEST, sfel...@gmail.com wrote: On Fri, May 29, 2015 at 12:50 AM, Jiri Pirko j...@resnulli.us wrote: Thu, May 21, 2015 at 07:46:54AM CEST, sfel...@gmail.com wrote: On Tue, May 19, 2015 at 1:28 PM,

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-31 Thread Scott Feldman
On Sat, May 30, 2015 at 9:19 PM, John Fastabend john.fastab...@gmail.com wrote: On 05/30/2015 02:00 AM, Jiri Pirko wrote: Fri, May 29, 2015 at 05:39:46PM CEST, sfel...@gmail.com wrote: On Fri, May 29, 2015 at 12:50 AM, Jiri Pirko j...@resnulli.us wrote: Thu, May 21, 2015 at 07:46:54AM CEST,

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-30 Thread John Fastabend
On 05/30/2015 02:00 AM, Jiri Pirko wrote: Fri, May 29, 2015 at 05:39:46PM CEST, sfel...@gmail.com wrote: On Fri, May 29, 2015 at 12:50 AM, Jiri Pirko j...@resnulli.us wrote: Thu, May 21, 2015 at 07:46:54AM CEST, sfel...@gmail.com wrote: On Tue, May 19, 2015 at 1:28 PM, David Miller

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-30 Thread Jiri Pirko
Fri, May 29, 2015 at 05:39:46PM CEST, sfel...@gmail.com wrote: On Fri, May 29, 2015 at 12:50 AM, Jiri Pirko j...@resnulli.us wrote: Thu, May 21, 2015 at 07:46:54AM CEST, sfel...@gmail.com wrote: On Tue, May 19, 2015 at 1:28 PM, David Miller da...@davemloft.net wrote: From: Andy Gospodarek

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-29 Thread Jiri Pirko
Thu, May 28, 2015 at 05:35:05PM CEST, john.fastab...@gmail.com wrote: On 05/28/2015 02:42 AM, Jiri Pirko wrote: Mon, May 18, 2015 at 10:19:16PM CEST, da...@davemloft.net wrote: From: Roopa Prabhu ro...@cumulusnetworks.com Date: Sun, 17 May 2015 16:42:05 -0700 On most systems where you can offload

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-29 Thread Jiri Pirko
Thu, May 21, 2015 at 07:46:54AM CEST, sfel...@gmail.com wrote: On Tue, May 19, 2015 at 1:28 PM, David Miller da...@davemloft.net wrote: From: Andy Gospodarek go...@cumulusnetworks.com Date: Tue, 19 May 2015 15:47:32 -0400 Are you actually saying that if users complain loudly enough about the

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-29 Thread Jiri Pirko
Thu, May 28, 2015 at 05:40:11PM CEST, sfel...@gmail.com wrote: On Thu, May 28, 2015 at 2:42 AM, Jiri Pirko j...@resnulli.us wrote: Mon, May 18, 2015 at 10:19:16PM CEST, da...@davemloft.net wrote: From: Roopa Prabhu ro...@cumulusnetworks.com Date: Sun, 17 May 2015 16:42:05 -0700 On most systems

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-29 Thread Jiri Pirko
Fri, May 29, 2015 at 05:12:35PM CEST, sfel...@gmail.com wrote: On Thu, May 28, 2015 at 2:42 AM, Jiri Pirko j...@resnulli.us wrote: Mon, May 18, 2015 at 10:19:16PM CEST, da...@davemloft.net wrote: From: Roopa Prabhu ro...@cumulusnetworks.com Date: Sun, 17 May 2015 16:42:05 -0700 On most systems

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-29 Thread Scott Feldman
On Thu, May 28, 2015 at 2:42 AM, Jiri Pirko j...@resnulli.us wrote: Mon, May 18, 2015 at 10:19:16PM CEST, da...@davemloft.net wrote: From: Roopa Prabhu ro...@cumulusnetworks.com Date: Sun, 17 May 2015 16:42:05 -0700 On most systems where you can offload routes to hardware, doing routing in

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-29 Thread Scott Feldman
On Fri, May 29, 2015 at 12:50 AM, Jiri Pirko j...@resnulli.us wrote: Thu, May 21, 2015 at 07:46:54AM CEST, sfel...@gmail.com wrote: On Tue, May 19, 2015 at 1:28 PM, David Miller da...@davemloft.net wrote: From: Andy Gospodarek go...@cumulusnetworks.com Date: Tue, 19 May 2015 15:47:32 -0400

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-28 Thread Andy Gospodarek
On Thu, May 28, 2015 at 08:40:11AM -0700, Scott Feldman wrote: On Thu, May 28, 2015 at 2:42 AM, Jiri Pirko j...@resnulli.us wrote: Mon, May 18, 2015 at 10:19:16PM CEST, da...@davemloft.net wrote: From: Roopa Prabhu ro...@cumulusnetworks.com Date: Sun, 17 May 2015 16:42:05 -0700 On most

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-28 Thread roopa
On 5/28/15, 3:35 PM, Andy Gospodarek wrote: On Thu, May 28, 2015 at 08:40:11AM -0700, Scott Feldman wrote: On Thu, May 28, 2015 at 2:42 AM, Jiri Pirko j...@resnulli.us wrote: Mon, May 18, 2015 at 10:19:16PM CEST, da...@davemloft.net wrote: From: Roopa Prabhu ro...@cumulusnetworks.com Date:

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-28 Thread roopa
On 5/28/15, 9:10 AM, John Fastabend wrote: On 05/28/2015 08:40 AM, Scott Feldman wrote: On Thu, May 28, 2015 at 2:42 AM, Jiri Pirko j...@resnulli.us wrote: Mon, May 18, 2015 at 10:19:16PM CEST, da...@davemloft.net wrote: From: Roopa Prabhu ro...@cumulusnetworks.com Date: Sun, 17 May 2015

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-28 Thread Jiri Pirko
Mon, May 18, 2015 at 10:19:16PM CEST, da...@davemloft.net wrote: From: Roopa Prabhu ro...@cumulusnetworks.com Date: Sun, 17 May 2015 16:42:05 -0700 On most systems where you can offload routes to hardware, doing routing in software is not an option (the cpu limitations make routing impossible

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-28 Thread John Fastabend
On 05/28/2015 08:40 AM, Scott Feldman wrote: On Thu, May 28, 2015 at 2:42 AM, Jiri Pirko j...@resnulli.us wrote: Mon, May 18, 2015 at 10:19:16PM CEST, da...@davemloft.net wrote: From: Roopa Prabhu ro...@cumulusnetworks.com Date: Sun, 17 May 2015 16:42:05 -0700 On most systems where you can

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-28 Thread Scott Feldman
On Thu, May 28, 2015 at 2:42 AM, Jiri Pirko j...@resnulli.us wrote: Mon, May 18, 2015 at 10:19:16PM CEST, da...@davemloft.net wrote: From: Roopa Prabhu ro...@cumulusnetworks.com Date: Sun, 17 May 2015 16:42:05 -0700 On most systems where you can offload routes to hardware, doing routing in

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-28 Thread John Fastabend
On 05/28/2015 02:42 AM, Jiri Pirko wrote: Mon, May 18, 2015 at 10:19:16PM CEST, da...@davemloft.net wrote: From: Roopa Prabhu ro...@cumulusnetworks.com Date: Sun, 17 May 2015 16:42:05 -0700 On most systems where you can offload routes to hardware, doing routing in software is not an option

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-21 Thread roopa
On 5/20/15, 10:46 PM, Scott Feldman wrote: On Tue, May 19, 2015 at 1:28 PM, David Miller da...@davemloft.net wrote: From: Andy Gospodarek go...@cumulusnetworks.com Date: Tue, 19 May 2015 15:47:32 -0400 Are you actually saying that if users complain loudly enough about the current behavior

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-20 Thread Scott Feldman
On Tue, May 19, 2015 at 1:28 PM, David Miller da...@davemloft.net wrote: From: Andy Gospodarek go...@cumulusnetworks.com Date: Tue, 19 May 2015 15:47:32 -0400 Are you actually saying that if users complain loudly enough about the current behavior (not the change Roopa has proposed) that you

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-19 Thread David Miller
From: Andy Gospodarek go...@cumulusnetworks.com Date: Tue, 19 May 2015 15:47:32 -0400 Are you actually saying that if users complain loudly enough about the current behavior (not the change Roopa has proposed) that you would be open to considering a change the current behavior? I am saying

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-19 Thread David Miller
From: roopa ro...@cumulusnetworks.com Date: Mon, 18 May 2015 22:58:54 -0700 from where I see, with the limitations on these boxes, this requires every app, every `ip route` cmd running on the box to explicitly specify offload when running on this hardware. Users know what they are doing, and

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-18 Thread roopa
On 5/18/15, 1:19 PM, David Miller wrote: From: Roopa Prabhu ro...@cumulusnetworks.com Date: Sun, 17 May 2015 16:42:05 -0700 On most systems where you can offload routes to hardware, doing routing in software is not an option (the cpu limitations make routing impossible in software). You

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-18 Thread David Miller
From: John Fastabend john.r.fastab...@intel.com Date: Mon, 18 May 2015 17:21:29 -0700 So how about having an error strategy sysctl field that we can set at provisioning time. I think this would align to Roopa's option (b). This way we can default to transparent mode and the users where this

Re: [PATCH net v2] switchdev: don't abort hardware ipv4 fib offload on failure to program fib entry in hardware

2015-05-18 Thread David Miller
From: Roopa Prabhu ro...@cumulusnetworks.com Date: Sun, 17 May 2015 16:42:05 -0700 On most systems where you can offload routes to hardware, doing routing in software is not an option (the cpu limitations make routing impossible in software). You absolutely do not get to determine this