per file descriptor device callbacks ?

2012-08-27 Thread Luigi Rizzo
Hi, in netmap, i am using a single name (/dev/netmap) to create multiple independent file descriptors bound to different devices/queues, and eventually I would like to mmap() each file descriptor to a different kernel memory region. This requires to track calls to open/ioctl/poll/mmap/close. The

Re: less aggressive contigmalloc ?

2012-08-27 Thread Alan Cox
On 08/26/2012 12:11, Luigi Rizzo wrote: On Fri, Aug 24, 2012 at 11:56:06AM -0500, Alan Cox wrote: On 08/24/2012 11:54, Luigi Rizzo wrote: On Fri, Aug 24, 2012 at 11:12:51AM -0500, Alan Cox wrote: On 08/24/2012 09:57, Luigi Rizzo wrote: On Fri, Aug 24, 2012 at 12:43:33AM -0500, Alan Cox

Re: per file descriptor device callbacks ?

2012-08-27 Thread Andriy Gapon
on 27/08/2012 10:34 Luigi Rizzo said the following: This requires to track calls to open/ioctl/poll/mmap/close. The difficulty i have is with mmap() and close(), because FreeBSD seems to handle these calls per-cdev rather than per-file-descriptor (for instance, no 'struct file' argument is

Re: Time to bump default VM_SWZONE_SIZE_MAX?

2012-08-27 Thread Dag-Erling Smørgrav
Dag-Erling Smørgrav d...@des.no writes: (or we could increase the limit to 72351744 bytes, which is the precise amount required to support 16 GB) Correction, 36175872 - there are actually 32 pages per entry, not 16. DES -- Dag-Erling Smørgrav - d...@des.no

Re: less aggressive contigmalloc ?

2012-08-27 Thread Luigi Rizzo
On Mon, Aug 27, 2012 at 02:42:28AM -0500, Alan Cox wrote: ... this is dmesg when I add kdb_backtrace() at the start of vm_pageout_oom() The '... netmap_finalize_obj_allocator... are from my calls to contigmalloc, each one doing one-page allocations. These calls are made with M_WAITOK? no

Re: pkgng suggestion: renaming /usr/sbin/pkg to /usr/sbin/pkg-bootstrap

2012-08-27 Thread Olivier Smedts
2012/8/26 Baptiste Daroussin b...@freebsd.org: I received more feedback about keep pkg and changing it to pkg-bootstrap, so what should I do, changing it because you are asking for it? So, just a me too for renaming pkg, for consistency. I don't mind the new name... -- Olivier Smedts

What is Fast task queue? (Was: How to understand what `swi5' kernel thread does?)

2012-08-27 Thread Lev Serebryakov
Hello, Lev. You wrote 27 августа 2012 г., 6:19:57: I've found (with help of debug printing added to kernel), that swi5 has only one handler Fast task queue (name is too long to be seen in `top' output, may be, rename it to fast tqueue?) What fast tasks are performed via this queue? Under

Re: make package fails in chroot: tar: getvfsbyname failed: No such file or directory

2012-08-27 Thread Bernhard Fröhlich
On Mon, Aug 20, 2012 at 2:31 PM, Konstantin Belousov kostik...@gmail.com wrote: On Mon, Aug 20, 2012 at 01:42:31PM +0200, Bernhard Fr?hlich wrote: On Sun, Aug 19, 2012 at 10:01 PM, Tim Kientzle t...@kientzle.com wrote: On Aug 19, 2012, at 12:17 PM, Garrett Cooper wrote: On Sun, Aug 19,

Re: make package fails in chroot: tar: getvfsbyname failed: No such file or directory

2012-08-27 Thread Konstantin Belousov
On Mon, Aug 27, 2012 at 05:28:09PM +0200, Bernhard Fr?hlich wrote: On Mon, Aug 20, 2012 at 2:31 PM, Konstantin Belousov kostik...@gmail.com wrote: On Mon, Aug 20, 2012 at 01:42:31PM +0200, Bernhard Fr?hlich wrote: On Sun, Aug 19, 2012 at 10:01 PM, Tim Kientzle t...@kientzle.com wrote:

Re: per file descriptor device callbacks ?

2012-08-27 Thread John Baldwin
On Monday, August 27, 2012 3:55:47 am Andriy Gapon wrote: on 27/08/2012 10:34 Luigi Rizzo said the following: This requires to track calls to open/ioctl/poll/mmap/close. The difficulty i have is with mmap() and close(), because FreeBSD seems to handle these calls per-cdev rather than

Re: pkgng suggestion: renaming /usr/sbin/pkg to /usr/sbin/pkg-bootstrap

2012-08-27 Thread John Baldwin
On Sunday, August 26, 2012 4:37:53 pm Doug Barton wrote: The problem is that we don't really support the idea of things in the base magically deleting themselves. As I have said in previous messages, the bootstrapping problem is being overblown by several orders of magnitude. For newly

Re: What is Fast task queue? (Was: How to understand what `swi5' kernel thread does?)

2012-08-27 Thread John Baldwin
On Monday, August 27, 2012 8:46:46 am Lev Serebryakov wrote: Hello, Lev. You wrote 27 августа 2012 г., 6:19:57: I've found (with help of debug printing added to kernel), that swi5 has only one handler Fast task queue (name is too long to be seen in `top' output, may be, rename it to fast

Panic on use of deleted route.

2012-08-27 Thread Ian FREISLICH
Hi I was wondering if anyone else is seeing this... I get a panic shortly after ppp(8) exits. I haven't been able to get a crashdump from a recent -CURRENT system, so in that absence, I'll include output from an older system. Interestingly, the route partially persists past the destruction of

Re: What is Fast task queue? (Was: How to understand what `swi5' kernel thread does?)

2012-08-27 Thread Lev Serebryakov
Hello, John. You wrote 27 августа 2012 г., 20:26:03: What fast tasks are performed via this queue? Under network load it is main consumer of CPU. JB Certain NIC drivers perform much of their interrupt handling in that thread. Yep, I've found, that my if_vr uses it. One more question: does

Mellanox Technologies : ConnectX-3 VPI

2012-08-27 Thread Daichi GOTO
I am wondering if FreeBSD 10-CURRNET could use Mellanox Technologies's ConnectX-3 VPI infiniband devices. Is there anyone who are using ConnectX-3 VPI with FreeBSD? -- Daichi GOTO (daichi) FreeBSD Committer, http://www.FreeBSD.org The Power To Serve