Justin,
How would I go about benchmarking that?
Eric,
Sorry, but I'm not quite an expert on the internals of Linux. What are
4k stacks and how do I know if I have them. If it helps, I am using
Ubuntu with a custom compiled Linux kernel. (This xfs/raid problem was
also occured on the default Ubuntu server kernel...)
Also, if that trace from /var/log/messages isn't of any use do you
know where I can look to find more information on this? Is it possible
that this is being caused b the cheap PCI SATA controller card that I
am using? (It's the Rosewill RC-209)
- Ian
On 10/11/06, Justin Piszcz <jpiszcz@xxxxxxxxxxxxxxx> wrote:
Also, quick question-- What type of speed do you get with 4 drives
connected to 1 card vs. I have 8 drives connected to 3-4 cards.
What speed write/read?
Justin.
On Wed, 11 Oct 2006, Ian Williamson wrote:
> Eric,
> That's all I have for the event in /var/log/messages..
>
> For the raid configuration I have the following:
> ian@ionlinux:~$ sudo mdadm --detail /dev/md0
> Password:
> /dev/md0:
> Version : 00.90.03
> Creation Time : Wed Sep 13 22:04:11 2006
> Raid Level : raid5
> Array Size : 732587712 (698.65 GiB 750.17 GB)
> Device Size : 244195904 (232.88 GiB 250.06 GB)
> Raid Devices : 4
> Total Devices : 4
> Preferred Minor : 0
> Persistence : Superblock is persistent
>
> Update Time : Mon Oct 9 00:02:30 2006
> State : clean
> Active Devices : 4
> Working Devices : 4
> Failed Devices : 0
> Spare Devices : 0
>
> Layout : left-symmetric
> Chunk Size : 64K
>
> UUID : 86770f56:8e4f51e5:fd754630:f1c65359
> Events : 0.54082
>
> Number Major Minor RaidDevice State
> 0 8 1 0 active sync /dev/sda1
> 1 8 17 1 active sync /dev/sdb1
> 2 8 33 2 active sync /dev/sdc1
> 3 8 49 3 active sync /dev/sdd1
>
> I really have no idea what could be causing this. Sometimes after
> restart it still won't work through Samba, and I can never perform
> massive local reads and writes, i.e. a recursive copy off of the raid.
>
> On 10/11/06, Eric Sandeen <sandeen@xxxxxxxxxxx> wrote:
> > Ian Williamson wrote:
> > > I am running XFS on a software raid 5. I am doing this with a PCI
> > > controller with 4 SATA drives attached to it.
> > >
> > > When I play my music over the network through Samba from the raid
> > > volume my audio client will often loose the connection. This isn't
> > > remediated until I restart the machine with the raid controller or
> > > wait for an unknown amount of time. Either way, the problem still
> > > persists.
> > >
> > > Initially I though that this was Samba's fault, but I think it may be
> > > xfs related due to what was in /var/log/messages:
> > >
> > > Oct 9 22:37:33 ionlinux kernel: [105657.982701] Modules linked in:
> > > serio_raw i2c_nforce2 pcspkr forcedeth r8169 nvidia_agp agpgart
> > > i2c_core psmouse sg evdev xfs dm_mod sd_mod generic sata_nv ide_disk
> > > ehci_hcd ide_cd cdrom sata_sil ohci_hcd usbcore libata scsi_mod
> > > ide_generic processor
> > > Oct 9 22:37:33 ionlinux kernel: [105657.982985] EIP:
> > > 0060:[<f8a1353e>] Not tainted VLI
> > > Oct 9 22:37:33 ionlinux kernel: [105657.982986] EFLAGS: 00010246
> > > (2.6.18 #1)
> >
> > It looks like you've edited this a bit too much, what came before this in
> > the logs?
> >
> > Are you running on 4k stacks, out of curiosity?
> >
> > -Eric
> >
>
>
> --
> Ian Williamson
>
>
--
Ian Williamson
|