just one of five disks detected at arcmsr(4) since upgrade to NetBSD 10
Hi, This morning I upgraded a box from 9.3_STABLE to NetBSD 10.0. With NetBSD 9.3 it probed five disks at the Areca ARC-1222 RAID controller, now just one. A powercycle and "scsictl scsibus0 scan all all" did not help. NetBSD 9.3: Apr 18 12:22:20 janeway /netbsd: [ 1.0262686] arcmsr0 at pci1 dev 0 function 0 Apr 18 12:22:20 janeway /netbsd: [ 1.0262686] arcmsr0: interrupting at ioapic0 pin 16 Apr 18 12:22:20 janeway /netbsd: [ 1.0262686] arcmsr0: Areca ARC-1222 Host Adapter RAID controller Apr 18 12:22:20 janeway /netbsd: [ 1.0262686] arcmsr0: 8 ports, 256MB SDRAM, firmware Apr 18 12:22:20 janeway /netbsd: [ 1.0262686] scsibus0 at arcmsr0: 16 targets, 8 luns per target ... Apr 18 12:22:20 janeway /netbsd: [ 1.2718484] sd0 at scsibus0 target 0 lun 0: disk fixed Apr 18 12:22:20 janeway /netbsd: [ 1.2718484] sd0: 3726 GB, 64600 cyl, 252 head, 480 sec, 512 bytes/sect x 7814037168 sectors Apr 18 12:22:20 janeway /netbsd: [ 1.2718484] sd1 at scsibus0 target 0 lun 1: disk fixed Apr 18 12:22:20 janeway /netbsd: [ 1.2718484] sd1: 3726 GB, 64600 cyl, 252 head, 480 sec, 512 bytes/sect x 7814037168 sectors Apr 18 12:22:20 janeway /netbsd: [ 1.2718484] sd2 at scsibus0 target 0 lun 2: disk fixed Apr 18 12:22:20 janeway /netbsd: [ 1.2718484] sd2: 3726 GB, 64600 cyl, 252 head, 480 sec, 512 bytes/sect x 7814037168 sectors Apr 18 12:22:20 janeway /netbsd: [ 1.2718484] sd3 at scsibus0 target 0 lun 3: disk fixed Apr 18 12:22:20 janeway /netbsd: [ 1.2718484] sd3: 3726 GB, 64600 cyl, 252 head, 480 sec, 512 bytes/sect x 7814037168 sectors Apr 18 12:22:20 janeway /netbsd: [ 1.2718484] sd4 at scsibus0 target 0 lun 4: disk fixed Apr 18 12:22:20 janeway /netbsd: [ 1.2718484] sd4: 3726 GB, 64600 cyl, 252 head, 480 sec, 512 bytes/sect x 7814037168 sectors Apr 18 12:22:20 janeway /netbsd: [ 1.2811828] autoconfiguration error: arcmsr0: unable to query firmware for sensor info NetBSD 10.0: Apr 18 14:08:20 janeway /netbsd: [ 1.0299139] arcmsr0 at pci1 dev 0 function 0 Apr 18 14:08:20 janeway /netbsd: [ 1.0299139] arcmsr0: interrupting at ioapic0 pin 16 Apr 18 14:08:20 janeway /netbsd: [ 1.0299139] arcmsr0: Areca ARC-1222 Host Adapter RAID controller Apr 18 14:08:20 janeway /netbsd: [ 1.0299139] arcmsr0: 8 ports, 256MB SDRAM, firmware Apr 18 14:08:20 janeway /netbsd: [ 1.0299139] scsibus0 at arcmsr0: 16 targets, 8 luns per target ... Apr 18 14:08:20 janeway /netbsd: [ 1.0700815] sd0 at scsibus0 target 0 lun 0: disk fixed Apr 18 14:08:20 janeway /netbsd: [ 1.0700815] sd0: 3726 GB, 64600 cyl, 252 head, 480 sec, 512 bytes/sect x 7814037168 sectors ... Apr 18 14:08:20 janeway /netbsd: [ 1.0765269] autoconfiguration error: arcmsr0: unable to query firmware for sensor info root@janeway:/home/kiers# sysctl hw.disknames hw.disknames = sd0 wd0 wd1 The card has ethernet with a webinterface and everything is fine there. The five disks are a zpool, but that seems irrelevant. Any ideas before I send-pr? Thanks, Bert
Re: IIs factible to implement full writes of strips to raid using NVRAM memory in LFS?
On Thu, Aug 18, 2016 at 07:58:53PM +0200, Jose Luis Rodriguez Garcia wrote: Hi, > As I understand LFS needs to do synchronous writes when there is > metadata operations (directories)/fsync operations involved. Instead > of writting a full segment (1 MB per default), it writes a "small > segment". It kills performance in RAID 5/6, because the write isn't a > full stripe: you have to read all the disks, for calculate the new > parity 1 write on raid of x disks= x reads + 2 writes (data + parity). > > The NVRAM memory solves this problem as buffer/ write cache. Sounds like WAFL https://en.wikipedia.org/wiki/Write_Anywhere_File_Layout Even though that article doesn't mention NVRAM, all Netapp filers have a (fixed) amount of NVRAM. Our big FAS8080 has 16384 MB NVRAM, the small FAS2554 has 2 GB NVRAM. Writes are very fast. Grtnx, -- B*E*R*T
Re: Tester(s) needed: ixv(4)
On Thu, Aug 20, 2015 at 12:31:27PM +0200, Bert Kiers wrote: > So I guess it is a NetBSD driver problem. After playing with some Linux setting, the MAC-addres I set with ifconfig sticks between reboots and I can think of no other place where that can ben than in the NIC. The link is also up after "ifconfig ixv0 up", but most of the time the system panics immediately after "ifconfig ixv0 194.109.43.124/27". Even when it does not panic, there is no traffic. It does not panic when I start Qemu with 1 cpu, but I noticed "affinity to cpu 1 ", so I tried with more than 1. shell# ifconfig ixv0 194.109.43.124/27 shell# fatal page fault in supervisor mode trap type 6 code 0 rip 8022fca8 cs 8 rflags 10202 cr2 89fc3e00 i level 2 rsp fe8002206ed8 curlwp 0xfe801fe93860 pid 0.5 lowest kstack 0xfe80022032c0 kernel: page fault trap, code=0 Stopped in pid 0.5 (system) at netbsd:bus_space_read_4+0x8:movl 0(%rdx), %eax db{0}> bt bus_space_read_4() at netbsd:bus_space_read_4+0x8 callout_softclock() at netbsd:callout_softclock+0x392 softint_dispatch() at netbsd:softint_dispatch+0xd3 DDB lost frame for netbsd:Xsoftintr+0x4f, trying 0xfe8002206ff0 Xsoftintr() at netbsd:Xsoftintr+0x4f --- interrupt --- 0: db{0}> -- B*E*R*T
Re: Tester(s) needed: ixv(4)
On Tue, Aug 18, 2015 at 02:03:04PM +0200, Bert Kiers wrote: > On Tue, Aug 18, 2015 at 04:39:57AM -0700, Masanobu SAITOH wrote: > > > Both MAC address and link status use communication between PF and > > VF. I suspect that communication is broken. > > Is this a bug in my linux/kvm/qemu setup, a NetBSD driver bug or > something else? FreeBSD 10.1 works, but I have to set a MAC-address manually in the VM. root@cristalle:~ # dmesg | grep ix ix0: mem 0xfe00-0xfe003fff,0xfe004000-0xfe007fff at device 3.0 on pci0 ix0: Using MSIX interrupts with 2 vectors ix0: link state changed to UP root@cristalle:~ # ifconfig ix0 ix0: flags=8843 metric 0 mtu 1500 options=401bb ether aa:00:04:00:42:42 inet 194.109.43.125 netmask 0xffe0 broadcast 194.109.43.127 nd6 options=29 media: Ethernet autoselect status: active dns works, ping works, ftp works, ssh works; not tried: IPv6, larger MTU, TSO, VLAN So I guess it is a NetBSD driver problem. -- B*E*R*T
Re: Tester(s) needed: ixv(4)
On Tue, Aug 18, 2015 at 04:39:57AM -0700, Masanobu SAITOH wrote: > Both MAC address and link status use communication between PF and > VF. I suspect that communication is broken. Is this a bug in my linux/kvm/qemu setup, a NetBSD driver bug or something else? -- B*E*R*T
Re: Tester(s) needed: ixv(4)
On Mon, Aug 17, 2015 at 05:38:09PM +0200, Bert Kiers wrote: > # uname -a > NetBSD 7.99.21 NetBSD 7.99.21 (GENERIC) #0: Mon Aug 17 17:13:23 CEST 2015 > ki...@shell.boppelans.net:/tmp/obj25032/sys/arch/amd64/compile/GENERIC amd64 > > # dmesg|grep ixv > ixv0 at pci0 dev 3 function 0: Intel(R) PRO/10GbE Virtual Function Network > Driver, Version - 1.1.4 > ixv0: clearing prefetchable bit > ixv0: Using MSIX interrupts with 3 vectors > ixv0: for TX/RX, interrupting at msix0 vec 0, bound queue 0 to cpu 0 > ixv0: for link, interrupting at msix0 vec 1, affinity to cpu 1 > > # ifconfig ixv0 > ixv0: flags=8802 mtu 1500 > > capabilities=bff80 P4CSUM_Rx,UDP4CSUM_Tx,TCP6CSUM_Rx,TCP6CSUM_Tx,UDP6CSUM_Rx,UDP6CSUM_Tx> > enabled=0 > address: 00:00:00:00:00:00 > media: Ethernet autoselect > status: no carrier > > > no carrier is correct at the moment; but no MAC-address :( After connecting the port to a switch, ifconfig still shows no carrier. "ifconfig ixv0 up" does not help. Doing "ifconfig eth2 up" on the host does not help. It is up on the switch. Btw, this is with 6.1.5 userland. I don't think that matters. -- B*E*R*T
Re: Tester(s) needed: ixv(4)
On Mon, Aug 17, 2015 at 04:19:44PM +0200, Bert Kiers wrote: > On Fri, Aug 14, 2015 at 02:06:02AM +0900, SAITOH Masanobu wrote: > > > 6) You might have to add some other variable settings > >to your kernel's boot argument. > > Some test progress. Linux side works and old NetBSD now says > > vendor 0x8086 product 0x1515 (ethernet network, revision 0x01) at pci0 > dev 3 function 0 not configured # uname -a NetBSD 7.99.21 NetBSD 7.99.21 (GENERIC) #0: Mon Aug 17 17:13:23 CEST 2015 ki...@shell.boppelans.net:/tmp/obj25032/sys/arch/amd64/compile/GENERIC amd64 # dmesg|grep ixv ixv0 at pci0 dev 3 function 0: Intel(R) PRO/10GbE Virtual Function Network Driver, Version - 1.1.4 ixv0: clearing prefetchable bit ixv0: Using MSIX interrupts with 3 vectors ixv0: for TX/RX, interrupting at msix0 vec 0, bound queue 0 to cpu 0 ixv0: for link, interrupting at msix0 vec 1, affinity to cpu 1 # ifconfig ixv0 ixv0: flags=8802 mtu 1500 capabilities=bff80 enabled=0 address: 00:00:00:00:00:00 media: Ethernet autoselect status: no carrier no carrier is correct at the moment; but no MAC-address :( -- B*E*R*T
Re: Tester(s) needed: ixv(4)
On Fri, Aug 14, 2015 at 02:06:02AM +0900, SAITOH Masanobu wrote: > 6) You might have to add some other variable settings > to your kernel's boot argument. Some test progress. Linux side works and old NetBSD now says vendor 0x8086 product 0x1515 (ethernet network, revision 0x01) at pci0 dev 3 function 0 not configured Now building NetBSD-current -- B*E*R*T
Re: Tester(s) needed: ixv(4)
On Fri, Aug 14, 2015 at 02:06:02AM +0900, SAITOH Masanobu wrote: > To use ixv, > > 0) Add intel_iommu=on pci=assignbus to your kernel's boot argument Only been upgrading wheezy to jessie and fighting systemd, so no ixv tests yet. -- B*E*R*T
Re: Tester(s) needed: ixv(4)
On Thu, Aug 13, 2015 at 07:19:15PM +0900, Masanobu SAITOH wrote: > NetBSD's ixv(4) can be test with Linux KVM or VMware vSphere. > Some people other than me must be familar with them :) Ah! We have Linux boxes running KVM with network hardware: 02:00.0 Ethernet controller: Intel Corporation Ethernet Controller 10-Gigabit X540-AT2 (rev 01) But inside a VM the network shows as: 00:03.0 Ethernet controller: Red Hat, Inc Virtio network device I doubt that will be ixv when I boot NetBSD. I guess there is some form of bridging going on because there are a lot of vnet interfaces in the host. I think I need a different method of networking for ixv. Will have a look this weekend. -- B*E*R*T
Re: Tester(s) needed: ixv(4)
On Thu, Aug 13, 2015 at 02:16:27PM +0900, Masanobu SAITOH wrote: > Hi, all. > > I've commited change to support ixv(4), Intel 10G Ethernet's virtual > function. The reason why this driver had not been compilable is that > it supports MSI-X only. > > Currently, I have not environment to test this driver. Could some > people who are familiar with it test with the latest -current > (and fix bugs)? Sounds interesting, but what is it? Some advanced function of Intel X540? I have read http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/pci/ixgbe/ixv.c?only_with_tag=MAIN but http://netbsd.gw.com/cgi-bin/man-cgi?ixv++NetBSD-current is empty. I have X540 (and X710), but don't know how to test. -- B*E*R*T
Re: ixg(4) performances
On Wed, Sep 03, 2014 at 04:11:29PM +0200, Bert Kiers wrote: > NetBSD 6.1 says: > > vendor 0x8086 product 0x1528 (ethernet network, revision 0x01) at pci1 dev 0 > function 0 not configured > > Complete messages: http://netbsd.itsx.net/hw/x9drw.dmesg > > NetBSD current from today also does not configure them. Btw, FreeBSD 9.3-RELEASE says: ix0: port 0x8020-0x803f mem 0xde20-0xde3f,0xde404000-0xde407fff irq 26 at device 0.0 on pci1 ix0: Using MSIX interrupts with 9 vectors ix0: Ethernet address: 00:25:90:f9:49:20 ix0: PCI Express Bus: Speed 5.0GT/s Width x8 -- B*E*R*T
Re: ixg(4) performances
On Sat, Aug 30, 2014 at 10:24:52AM +0100, Justin Cormack wrote: > On Sat, Aug 30, 2014 at 8:22 AM, Thor Lancelot Simon wrote: > > On Fri, Aug 29, 2014 at 12:22:31PM -0400, Terry Moore wrote: > >> > >> Is the ixg in an expansion slot or integrated onto the main board? > > > > If you know where to get a mainboard with an integrated ixg, I wouldn't > > mind hearing about it. > > They are starting to appear, eg > http://www.supermicro.co.uk/products/motherboard/Xeon/C600/X9SRH-7TF.cfm We have some SuperMicro X9DRW with 10 GbE Intel NICs on board. NetBSD current does not configure them. NetBSD 6.1 says: vendor 0x8086 product 0x1528 (ethernet network, revision 0x01) at pci1 dev 0 function 0 not configured Complete messages: http://netbsd.itsx.net/hw/x9drw.dmesg NetBSD current from today also does not configure them. (I boot from an USB-stick with current kernel and 6.1 userland. It wants to mount sda0 but there is only dk0, dk1. So I end up with read/only disk. I have to sort that out before I can save kernels messages.) Grtnx, -- B*E*R*T