mfi driver performance

2012-09-10 Thread Achim Patzner
Hi! We’re testing a new Intel S2600GL-based server with their recommended RAID adapter (Intel(R) Integrated RAID Module RMS25CB080”) which is identified as mfi0: ThunderBolt port 0x2000-0x20ff mem 0xd0c6-0xd0c63fff,0xd0c0-0xd0c3 irq 34 at device 0.0 on pci5 mfi0: Using MSI mfi0:

Re: mfi driver performance

2012-09-10 Thread Steven Hartland
How are you intending to use the controller? If you're looking to put a load of disk in for say ZFS have you tried flashing to a none RAID firmware so it uses mps instead of mfi? Regards Steve - Original Message - From: Achim Patzner a...@bnc.net To:

Re: mfi driver performance

2012-09-10 Thread Achim Patzner
Am 10.09.2012 um 14:57 schrieb Steven Hartland: How are you intending to use the controller? As a “launch-and-forget” RAID 1+0 sub-system using UFS (which reminds me to complain about sysinstall on volumes 2 TB later). If you're looking to put a load of disk in for say ZFS have you tried

Re: mfi driver performance

2012-09-10 Thread Steven Hartland
Might be worth testing anyway, as that would help prove controller or driver issue. - Original Message - From: Achim Patzner a...@bnc.net To: Steven Hartland kill...@multiplay.co.uk Cc: freebsd-current@freebsd.org Sent: Monday, September 10, 2012 2:19 PM Subject: Re: mfi driver

Raspberry PI gets USB support [FreeBSD 10 current]

2012-09-10 Thread Hans Petter Selasky
Hi, For those that want to try the Raspberry PI and its USB ports: Add this to sys/conf/files: dev/usb/controller/dwc_otg.coptional dwcotg arm/broadcom/bcm2835/dwc_otg_brcm.c optional dwcotg And add this to RPI-B: device dwcotg device usb device umass Open ISSUE: External

buildworld after r240303 wants make cleandepend if -DNOCLEAN used

2012-09-10 Thread David Wolfskill
In case others want to save a bit of time by using -DNOCLEAN for buildworld, I found that after r240303 if make cleandepend isn't done, src/cddl/lib/libnvpair build fails with a whine: make: don't know how to make /usr/src/cddl/lib/libnvpair/../../../sys/cddl/compat/opensolaris/sys/debug.h.

Re: mfi driver performance

2012-09-10 Thread matt
On 09/10/12 05:38, Achim Patzner wrote: Hi! We’re testing a new Intel S2600GL-based server with their recommended RAID adapter (Intel(R) Integrated RAID Module RMS25CB080”) which is identified as mfi0: ThunderBolt port 0x2000-0x20ff mem 0xd0c6-0xd0c63fff,0xd0c0-0xd0c3 irq 34

Re: mfi driver performance

2012-09-10 Thread Andrey Zonov
On 9/10/12 9:14 PM, matt wrote: On 09/10/12 05:38, Achim Patzner wrote: Hi! We’re testing a new Intel S2600GL-based server with their recommended RAID adapter (Intel(R) Integrated RAID Module RMS25CB080”) which is identified as mfi0: ThunderBolt port 0x2000-0x20ff mem

Re: mfi driver performance

2012-09-10 Thread matt
On 09/10/12 11:35, Andrey Zonov wrote: On 9/10/12 9:14 PM, matt wrote: On 09/10/12 05:38, Achim Patzner wrote: Hi! We’re testing a new Intel S2600GL-based server with their recommended RAID adapter (Intel(R) Integrated RAID Module RMS25CB080”) which is identified as mfi0: ThunderBolt

Clang as default compiler November 4th

2012-09-10 Thread Brooks Davis
[Please confine your replies to toolch...@freebsd.org to keep the thread on the most relevant list.] For the past several years we've been working towards migrating from GCC to Clang/LLVM as our default compiler. We intend to ship FreeBSD 10.0 with Clang as the default compiler on i386 and amd64

Re: Clang as default compiler November 4th

2012-09-10 Thread Daniel Eischen
On Mon, 10 Sep 2012, Brooks Davis wrote: [Please confine your replies to toolch...@freebsd.org to keep the thread on the most relevant list.] For the past several years we've been working towards migrating from GCC to Clang/LLVM as our default compiler. We intend to ship FreeBSD 10.0 with

Re: Clang as default compiler November 4th

2012-09-10 Thread Brooks Davis
On Mon, Sep 10, 2012 at 05:22:37PM -0400, Daniel Eischen wrote: On Mon, 10 Sep 2012, Brooks Davis wrote: [Please confine your replies to toolch...@freebsd.org to keep the thread on the most relevant list.] For the past several years we've been working towards migrating from GCC to

Re: mfi driver performance

2012-09-10 Thread matt
On 09/10/12 11:35, Andrey Zonov wrote: On 9/10/12 9:14 PM, matt wrote: On 09/10/12 05:38, Achim Patzner wrote: Hi! We’re testing a new Intel S2600GL-based server with their recommended RAID adapter (Intel(R) Integrated RAID Module RMS25CB080”) which is identified as mfi0: ThunderBolt port

Re: Clang as default compiler November 4th

2012-09-10 Thread matt
On 09/10/12 14:22, Daniel Eischen wrote: On Mon, 10 Sep 2012, Brooks Davis wrote: [Please confine your replies to toolch...@freebsd.org to keep the thread on the most relevant list.] For the past several years we've been working towards migrating from GCC to Clang/LLVM as our default

Re: mfi driver performance

2012-09-10 Thread Garrett Cooper
On Mon, Sep 10, 2012 at 7:15 PM, matt sendtom...@gmail.com wrote: ... mfip was necessary, and allowed smartctl to work with '-d sat' bonnie++ comparison. Run with no options immediately after system boot. In both cases the same disks are used, two Seagate Barracuda 1TB 3G/S (twin platter)

Re: Clang as default compiler November 4th

2012-09-10 Thread Doug Barton
-BEGIN PGP SIGNED MESSAGE- Hash: SHA256 As of last week, 4,680 ports out of 23,857 failed to build with clang on 9-amd64. That's almost a 20% failure rate. Until we have better support for either building ports with clang, or have better support for the idea of a ports compiler, this