search for: hejtmanek

Hello, is there any reason why even permissive devices cannot write some areas in the PCI config space? The PCI_COMMAND is handled in special way so that the device is enabled/disabled properly, am I right? Why is PCI_INTERRUPT_LINE read from dev->irq and not from the config space? Why the PCI address bars are handled in very different way? And it seems that writing these bars is never

...ffffba809010>] vfs_write+0xb0/0x190 [<ffffffffba80a452>] SyS_write+0x52/0xc0 [<ffffffffba603b7d>] do_syscall_64+0x8d/0xf0 [<ffffffffbac15c4e>] entry_SYSCALL_64_after_swapgs+0x58/0xc6 [<ffffffffffffffff>] 0xffffffffffffffff On Fri, Sep 14, 2018 at 03:36:59PM +0200, Lukas Hejtmanek wrote: > Hello, > > ok, I found that cpu pinning was wrong, so I corrected it to be 1:1. The issue > with iozone remains the same. > > The spec is running, however, it runs slower than 1-NUMA case. > > The corrected XML looks like follows: > <cpu mode='host-pas...

On 09/14/2018 03:36 PM, Lukas Hejtmanek wrote: > Hello, > > ok, I found that cpu pinning was wrong, so I corrected it to be 1:1. The issue > with iozone remains the same. > > The spec is running, however, it runs slower than 1-NUMA case. > > The corrected XML looks like follows: [Reformated XML for better read...

On Tue, Jun 16, 2015 at 07:37:39PM +0200, Lukas Hejtmanek wrote: > On Tue, Jun 16, 2015 at 09:12:24AM -0700, Jeremy Allison wrote: > > Not that I know of. Can you run winbindd under valgrind ? > > Should help debug this. > > this is the only waring regardless read/write that valgrind reports: > > ==16475== Syscall param writev...

On Tue, Jun 16, 2015 at 08:13:25PM +0200, Lukas Hejtmanek wrote: > On Tue, Jun 16, 2015 at 11:01:32AM -0700, Jeremy Allison wrote: > > OK, that's simply padding I think - nothing that would cause a crash. > > so, any idea how to debug this? Ensure you have symbols installed, then set: panic action = /bin/sleep 9999999 crash the bina...

Hello, I'm using sama 3.0.24 on linux machine that serves a share for a windows client. When editing a file on samba, using MS Word I can see there are severals (probably) backup files. ls looks like this: Dotaznik1.doc ~$taznik1.doc ~WRD0000.tmp ~WRD0001.tmp ~WRD0002.tmp ~WRD0003.tmp ~WRD0004.tmp These files do not disappear after I quit the Word. This does not happen if I edit

Hello, I'm facing a bug with winbind. If I request groups for particular domain user, winbind cache gets corrupted. My winbind version is 4.1.12-23.el7_1 (Centos 7.1, x86_64). 1) this is correct UID to SID mapping: wbinfo -U 100152 S-1-5-21-3451901064-902568176-4053310204-180212 2) I request groups info for a user: id -G -n 209459 [reply with 33 groups] 3) I request UID to SID mapping

On Tue, Jun 16, 2015 at 09:12:24AM -0700, Jeremy Allison wrote: > Not that I know of. Can you run winbindd under valgrind ? > Should help debug this. this is the only waring regardless read/write that valgrind reports: ==16475== Syscall param writev(vector[...]) points to uninitialised byte(s) ==16475== at 0xBB32337: writev (in /usr/lib64/libc-2.17.so) ==16475== by 0xA4AC8E4:

Hello, I'm using the Samba server 3.0.33 that exports volume from a GPFS. The GPFS strongly dislikes unlinking files that are locked (resulting in permission denied) using fcntl F_SETLEASE. It seems that the Samba *sometimes* tries to unlink a file that is oplocked. Why? Is this a bug? Why it does not happen always but only sometimes? I have strace logs showing: Wrong case: 8711

On 09/17/2018 04:59 PM, Lukas Hejtmanek wrote: > Hello, > > so the current domain configuration: > <cpu mode='host-passthrough'><topology sockets='8' cores='4' threads='1'/><numa><cell cpus='0-3' memory='62000000' /><cell cpus='4-7' memory=...

Hello, I have cluster with AMD EPYC 7351 cpu. Two CPUs per node. I have performance 8-NUMA configuration: This is from hypervizor: [root@hde10 ~]# lscpu Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian CPU(s): 64 On-line CPU(s) list: 0-63 Thread(s) per core: 2 Core(s) per socket: 16 Socket(s): 2 NUMA

Hello, I''m trying to get working infiniband device in Xen. I have Xen v3 with 2.6.18 kernel. I export PCI device from Dom0 into DomU. I''ve enabled permisive device in Dom0. However, inserting infiniband module results in the following messages (with little more verbosity which I have added): pcifront pci-0: Installing PCI frontend pcifront pci-0: Creating PCI Frontend Bus

...free shared buff/cache available Mem: 5857 75 5746 0 35 5768 ... NUMA node47 CPU(s): 376-383 this it not virtualized though :) On Mon, Sep 17, 2018 at 03:08:34PM +0200, Michal Privoznik wrote: > On 09/14/2018 03:36 PM, Lukas Hejtmanek wrote: > > Hello, > > > > ok, I found that cpu pinning was wrong, so I corrected it to be 1:1. The issue > > with iozone remains the same. > > > > The spec is running, however, it runs slower than 1-NUMA case. > > > > The corrected XML looks like...

...#39;0-7'/></numatune> In this case, the first part took more than 1700 seconds. 1-NUMA config finishes in 1646 seconds. Hypervisor with 1-NUMA config finishes in 1470 seconds, the hypervisor with 8-NUMA config finishes in 900 seconds. On Fri, Sep 14, 2018 at 02:06:26PM +0200, Lukas Hejtmanek wrote: > Hello, > > I have cluster with AMD EPYC 7351 cpu. Two CPUs per node. I have performance > 8-NUMA configuration: > > This is from hypervizor: > [root@hde10 ~]# lscpu > Architecture: x86_64 > CPU op-mode(s): 32-bit, 64-bit > Byte Order:...

Patch allowing drivers in DomU to restore address bars if needed. Signed-off-by: xhejtman@ics.muni.cz -- Lukáš Hejtmánek _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel

Hello, I''m trying to get to work InfiniBand card in DomU via exporting PCI device. How does the export works internally? I guess that pci frontend forwards stuff like pci_read_config_dword and pci_write_config_dword to pci backend that actually does it. Am I right? So if the driver of InfiniBand writes some config values to PCI config space and these values are not applied actually,