Re: ipfw port lookup table patch for review

2008-10-07 Thread Ganbold
Hi, I have just made the patches that use arrays for port entries. It is under the same directory: http://people.freebsd.org/~ganbold/ipfw_port_table/ Array version (each array can have IPFW_TABLES_MAX entries): http://people.freebsd.org/~ganbold/ipfw_port_table/ipfw_port_table_array_unsorted/

Re: kernel profiling: spinlock_exit consumes 36% CPU time.

2008-10-07 Thread John Baldwin
On Tuesday 07 October 2008 07:44:00 am 邱剑 wrote: > Hi, folks, > > I did kernel profiling when a single thread client sends UDP packets to a > single thread server on the same machine. > > In the output kernel profile, the first few kernel functions that consumes > the most CPU time are listed b

Re: kernel profiling: spinlock_exit consumes 36% CPU time.

2008-10-07 Thread Jeremy Chadwick
On Tue, Oct 07, 2008 at 07:44:00PM +0800, wrote: > Hi, folks, > > I did kernel profiling when a single thread client sends UDP packets to a > single thread server on the same machine. > > In the output kernel profile, the first few kernel functions that consumes > the most CPU time are lis

kernel profiling: spinlock_exit consumes 36% CPU time.

2008-10-07 Thread 邱剑
Hi, folks, I did kernel profiling when a single thread client sends UDP packets to a single thread server on the same machine. In the output kernel profile, the first few kernel functions that consumes the most CPU time are listed below: granularity: each sample hit covers 16 byte(s) for 0.01

Re: kernel profiling: spinlock_exit consumes 36% CPU time.

2008-10-07 Thread Julian Elischer
邱剑 wrote: > Hi, folks, [...] spinlocks disable interrupts so the profiling interrupt is held off from the moment that the spinlock is entered to the moment it is exited, and all of that time is attributed to spinlock_exit(). so that this tells you that 3% of your time is spent under spinlocks whi

How to support an Ethernet PHY without ID registers?

2008-10-07 Thread Bruce M Simpson
Hi, I have been trying to get FreeBSD onto the Freecom FSG3 Storage Gateway. It is an xScale based ARM system. Whilst the npe(4) driver appears to attach, the PHY does not. It is a Realtel RTL8305SB switch chip in dual miibus mode. Unfortunately the RTL8305SB does not have ID registers. The RT

Re: kern/127928: [tcp] [patch] TCP bandwidth gets squeezed every time tcp_xmit_bandwidth_limit() kicks in

2008-10-07 Thread linimon
Old Synopsis: The TCP bandwidth gets squeezed every time tcp_xmit_bandwidth_limit() kicks in New Synopsis: [tcp] [patch] TCP bandwidth gets squeezed every time tcp_xmit_bandwidth_limit() kicks in Responsible-Changed-From-To: freebsd-bugs->freebsd-net Responsible-Changed-By: linimon Responsible-C

Re: How to support an Ethernet PHY without ID registers?

2008-10-07 Thread Sepherosa Ziehau
On Wed, Oct 8, 2008 at 3:09 AM, Bruce M Simpson <[EMAIL PROTECTED]> wrote: > Hi, > > I have been trying to get FreeBSD onto the Freecom FSG3 Storage Gateway. > It is an xScale based ARM system. > > Whilst the npe(4) driver appears to attach, the PHY does not. It is a > Realtel RTL8305SB switch chip