Can you explain PCI DMA latency please ?

2008-02-26 Thread CHAVENT Paul
Hi everyone. You write (and we can read on some docs) that DMA an PCI acess can cause long-latency. I don't understand why. I'am not a guru and knwo perfectly how the dma work but i thought that the cpu ask for a dma to a device. The device is then autonomous for acessing the memory. I wonder

Re: 2.6.24.2-rt2

2008-02-26 Thread Jan Kiszka
Steven Rostedt wrote: We are pleased to announce the 2.6.24.2-rt2 tree, which can be downloaded from the location: http://rt.et.redhat.com/download/ Information on the RT patch can be found at: http://rt.wiki.kernel.org/index.php/Main_Page Changes since 2.6.24-rt1 - ported

Re: 2.6.24.2-rt2

2008-02-26 Thread Jan Kiszka
Jan Kiszka wrote: At this chance: We still see the same unbalanced sched-other load on our NUMA box as Gernot once reported [1]: top - 11:19:20 up 4 min, 1 user, load average: 29.52, 9.54, 3.37 Tasks: 502 total, 41 running, 461 sleeping, 0 stopped, 0 zombie Cpu0 :100.0%us, 0.0%sy,

Re: [(RT RFC) PATCH v2 5/9] adaptive real-time lock support

2008-02-26 Thread Gregory Haskins
On Mon, Feb 25, 2008 at 5:03 PM, in message [EMAIL PROTECTED], Pavel Machek [EMAIL PROTECTED] wrote: +static inline void +prepare_adaptive_wait(struct rt_mutex *lock, struct adaptive_waiter *adaptive) ... +#define prepare_adaptive_wait(lock, busy) {} This is evil. Use empty inline

Re: [(RT RFC) PATCH v2 6/9] add a loop counter based timeout mechanism

2008-02-26 Thread Gregory Haskins
On Mon, Feb 25, 2008 at 5:06 PM, in message [EMAIL PROTECTED], Pavel Machek [EMAIL PROTECTED] wrote: I believe you have _way_ too many config variables. If this can be set at runtime, does it need a config option, too? Generally speaking, I think until this algorithm has an

Re: 2.6.24.2-rt2

2008-02-26 Thread Steven Rostedt
On Tue, 26 Feb 2008, Jan Kiszka wrote: Jan Kiszka wrote: At this chance: We still see the same unbalanced sched-other load on our NUMA box as Gernot once reported [1]: top - 11:19:20 up 4 min, 1 user, load average: 29.52, 9.54, 3.37 Tasks: 502 total, 41 running, 461 sleeping, 0

Re: 2.6.24.2-rt2

2008-02-26 Thread Steven Rostedt
On Tue, 26 Feb 2008, Jan Kiszka wrote: What's the NUMA topology? 4 nodes. I'm not sure if it is really NUMA related, but the same kernel runs that test as expected on a non-NUMA 2x2 box. What tasks are running, and at what priorities? 40 pthreads, created with default parameters

Re: 2.6.24.2-rt2

2008-02-26 Thread Jan Kiszka
Steven Rostedt wrote: On Tue, 26 Feb 2008, Jan Kiszka wrote: What's the NUMA topology? 4 nodes. I'm not sure if it is really NUMA related, but the same kernel runs that test as expected on a non-NUMA 2x2 box. What tasks are running, and at what priorities? 40 pthreads, created with

Re: [(RT RFC) PATCH v2 5/9] adaptive real-time lock support

2008-02-26 Thread Pavel Machek
On Tue 2008-02-26 08:03:43, Gregory Haskins wrote: On Mon, Feb 25, 2008 at 5:03 PM, in message [EMAIL PROTECTED], Pavel Machek [EMAIL PROTECTED] wrote: +static inline void +prepare_adaptive_wait(struct rt_mutex *lock, struct adaptive_waiter *adaptive) ... +#define

Re: [(RT RFC) PATCH v2 5/9] adaptive real-time lock support

2008-02-26 Thread Gregory Haskins
On Tue, Feb 26, 2008 at 1:06 PM, in message [EMAIL PROTECTED], Pavel Machek [EMAIL PROTECTED] wrote: On Tue 2008-02-26 08:03:43, Gregory Haskins wrote: On Mon, Feb 25, 2008 at 5:03 PM, in message [EMAIL PROTECTED], Pavel Machek [EMAIL PROTECTED] wrote: +static inline void