Re: New DVB-Statistics API - please vote

2010-02-03 Thread Mauro Carvalho Chehab
Mauro Carvalho Chehab wrote: after the last thread which asked about signal statistics details degenerated into a discussion about the technical possibilites for implementing an entirely new API, which lead to nothing so far, I wanted to open a new thread to bring this forward. Maybe some

Re: New DVB-Statistics API - please vote

2010-02-03 Thread Hans Verkuil
Mauro Carvalho Chehab wrote: after the last thread which asked about signal statistics details degenerated into a discussion about the technical possibilites for implementing an entirely new API, which lead to nothing so far, I wanted to open a new thread to bring this forward. Maybe some

Re: New DVB-Statistics API - please vote

2010-02-03 Thread Manu Abraham
On Wed, Feb 3, 2010 at 2:40 PM, Hans Verkuil hverk...@xs4all.nl wrote: Mauro Carvalho Chehab wrote: after the last thread which asked about signal statistics details degenerated into a discussion about the technical possibilites for implementing an entirely new API, which lead to nothing so

Re: New DVB-Statistics API

2009-12-09 Thread Manu Abraham
On Wed, Dec 9, 2009 at 3:43 AM, Mauro Carvalho Chehab mche...@redhat.com wrote: Manu Abraham wrote: Not true. As pointed at the previous answer, the difference between a new ioctl and S2API is basically the code at dtv_property_prepare_get_stats() and dtv_property_process_get(). This is a

Re: New DVB-Statistics API

2009-12-09 Thread Mauro Carvalho Chehab
Manu Abraham wrote: On Wed, Dec 9, 2009 at 3:43 AM, Mauro Carvalho Chehab mche...@redhat.com wrote: Even with STB, let's assume a very slow cpu that runs at 100 Megabytes/second. So, the clock speed is 10 nanoseconds. Assuming that this CPU doesn't have a good pipeline, being capable of

Re: New DVB-Statistics API

2009-12-09 Thread Julian Scheel
Am 09.12.09 14:02, schrieb Mauro Carvalho Chehab: Manu Abraham wrote: On Wed, Dec 9, 2009 at 3:43 AM, Mauro Carvalho Chehab mche...@redhat.com wrote: Even with STB, let's assume a very slow cpu that runs at 100 Megabytes/second. So, the clock speed is 10 nanoseconds. Assuming

Re: New DVB-Statistics API

2009-12-09 Thread Mauro Carvalho Chehab
Julian Scheel wrote: Am 09.12.09 14:02, schrieb Mauro Carvalho Chehab: Manu Abraham wrote: I don't think you can just take the average IPC rates into account for this. When doing a syscall the processors TLB cache will be cleared, which will force the CPU to go to the whole instruction

Re: New DVB(!!)-Statistics API

2009-12-08 Thread Julian Scheel
Am 08.12.09 10:16, schrieb Julian Scheel: Hello together, after the last thread which asked about signal statistics details degenerated into a discussion about the technical possibilites for implementing an entirely new API, which lead to nothing so far, I wanted to open a new thread to

Re: New DVB-Statistics API

2009-12-08 Thread Mauro Carvalho Chehab
Hi Julian, Let me add some corrections to your technical analysis. Julian Scheel wrote: Hello together, after the last thread which asked about signal statistics details degenerated into a discussion about the technical possibilites for implementing an entirely new API, which lead to

Re: New DVB-Statistics API

2009-12-08 Thread Manu Abraham
On Tue, Dec 8, 2009 at 5:22 PM, Mauro Carvalho Chehab mche...@redhat.com wrote: Hi Julian, Let me add some corrections to your technical analysis. Julian Scheel wrote: Hello together, after the last thread which asked about signal statistics details degenerated into a discussion about the

Re: New DVB-Statistics API

2009-12-08 Thread Mauro Carvalho Chehab
Manu Abraham wrote: Not true. As pointed at the previous answer, the difference between a new ioctl and S2API is basically the code at dtv_property_prepare_get_stats() and dtv_property_process_get(). This is a pure code that uses a continuous struct that will likely be at L3 cache, inside