@cunrun @jorge-gbs any init errors in dom0 /var/log/kern.log re. GIM driver? Also, if you search some topics here covering this specific GPU, there were mixed results booting dom0 with pci=realloc,assign-busses. Maybe it worth a try.

@sshughes My understanding of the system so far (but take that with a grain of salt, in real life I'm sort of an accountant who's only larp'ing as a sysadmin here): the system is not meant to 'run on a single host and when it dies we replace it'.

It's meant to run on three identical hosts which never all die at the same time (except for some GBU hitting their building). Therefore there is no focus on 'let's reconnect new hardware to existing SR and fire up the VMs stored on that SR'.

After planning accordingly, I can live with that. Planning accordingly in my case means: 'well, if my single host dies (running two or three isn't worth it for me), I'll take a day of down time to restore from backups.'

Yep, only one, cause one tesla onboard, no any other video devices (maybe it is a problem)

[20:53 xcp ~]# lspci | grep -i nvidia 05:00.0 3D controller: NVIDIA Corporation TU104GL [Tesla T4] (rev ff)

@andyhhp giving this a shot now.

Anyone else in the community with experience on this? I'm afraid my Windows knowledge isn't great to know where to dig to understand the issue.

@olivierlambert said in Same CPU XEON 4309Y but migration failed because some CPU features missing !:

It could be microcode update and BIOS update making that change. Since they are not in the same pool, this can be expected. Indeed, migrate to the more recent, upgrade the old one/reboot and that should do the trick.

Yes, the BIOS/microcode differences do sometimes change the CPU mask. They need to be identical in many cases on all hosts within a pool.

Yea, I dont think you'll have any luck im afraid.
But for testing those 15K drives will be enough 🙂

@bufanda @wtdrisco What I mean by suppression of "instruction sets" is different generations of CPUs, have different extensions to the standard 64bit ones.

As the generations change you can get sometimes some of the extensions, being dropped physically from the CPU, but also new ones being added.

Since pools are supposed to all be the same, in order to cope with this the hypervisor software stack suppresses (removes or hides), the extensions to instruction sets which aren't common across other pool members.

So for instance if the majority of the pool has this https://www.intel.com/content/www/us/en/products/sku/237569/intel-xeon-gold-6544y-processor-45m-cache-3-60-ghz/specifications.html, while others of the same pool has https://www.intel.com/content/www/us/en/products/sku/139940/intel-xeon-gold-6138p-processor-27-5m-cache-2-00-ghz/specifications.html.

If you look at the instruction set extensions see which ones are, on both (these will be preserved and usable). Then which ones are not, these will be suppressed.

\o/ perfect!!

I believe @Andrew is correct here, if you need that probably grab a USB one.

@Danp There is a folder in /var/crash of the time of the crash with these files:

drwxr-xr-x 2 root root 4096 Apr 29 23:06 . drwxr-xr-x 3 root root 4096 Apr 29 23:07 .. -rw-r--r-- 1 root root 54527 Apr 29 23:06 dmesg.kexec.log -rw-r--r-- 1 root root 162936 Apr 29 23:06 dom0.log -rw-r--r-- 1 root root 337722 Apr 29 23:06 dom0.structures.log -rw-r--r-- 1 root root 1430 Apr 29 23:06 dom1.log -rw-r--r-- 1 root root 116088 Apr 29 23:06 dom1.structures.log -rw-r--r-- 1 root root 2610 Apr 29 23:06 dom46.log -rw-r--r-- 1 root root 189965 Apr 29 23:06 dom46.structures.log -rw-r--r-- 1 root root 2601 Apr 29 23:06 dom47.log -rw-r--r-- 1 root root 189965 Apr 29 23:06 dom47.structures.log -rw-r--r-- 1 root root 846 Apr 29 23:06 dom75.log -rw-r--r-- 1 root root 79151 Apr 29 23:06 dom75.structures.log -rw-r--r-- 1 root root 1131 Apr 29 23:06 lspci-tv.out -rw-r--r-- 1 root root 50179 Apr 29 23:06 lspci-vv.out -rw-r--r-- 1 root root 211731 Apr 29 23:06 lspci-vvxxxx.out -rw-r--r-- 1 root root 846 Apr 29 23:06 readelf-Wl.out -rw-r--r-- 1 root root 2912 Apr 29 23:06 readelf-Wn.out -rw-r--r-- 1 root root 921 Apr 29 23:06 time-v.out -rw-r--r-- 1 root root 20580 Apr 29 23:06 xen-crashdump-analyser.log -rw-r--r-- 1 root root 169234 Apr 29 23:06 xen.log -rw-r--r-- 1 root root 64834 Apr 29 23:06 xen.pcpu0.stack.log -rw-r--r-- 1 root root 157119 Apr 29 23:06 xen.pcpu1.stack.log -rw-r--r-- 1 root root 157006 Apr 29 23:06 xen.pcpu10.stack.log -rw-r--r-- 1 root root 157013 Apr 29 23:06 xen.pcpu11.stack.log -rw-r--r-- 1 root root 157031 Apr 29 23:06 xen.pcpu12.stack.log -rw-r--r-- 1 root root 157214 Apr 29 23:06 xen.pcpu13.stack.log -rw-r--r-- 1 root root 157180 Apr 29 23:06 xen.pcpu14.stack.log -rw-r--r-- 1 root root 156994 Apr 29 23:06 xen.pcpu15.stack.log -rw-r--r-- 1 root root 157403 Apr 29 23:06 xen.pcpu16.stack.log -rw-r--r-- 1 root root 157182 Apr 29 23:06 xen.pcpu17.stack.log -rw-r--r-- 1 root root 156992 Apr 29 23:06 xen.pcpu18.stack.log -rw-r--r-- 1 root root 157628 Apr 29 23:06 xen.pcpu19.stack.log -rw-r--r-- 1 root root 156934 Apr 29 23:06 xen.pcpu2.stack.log -rw-r--r-- 1 root root 157127 Apr 29 23:06 xen.pcpu3.stack.log -rw-r--r-- 1 root root 157134 Apr 29 23:06 xen.pcpu4.stack.log -rw-r--r-- 1 root root 157090 Apr 29 23:06 xen.pcpu5.stack.log -rw-r--r-- 1 root root 157116 Apr 29 23:06 xen.pcpu6.stack.log -rw-r--r-- 1 root root 156973 Apr 29 23:06 xen.pcpu7.stack.log -rw-r--r-- 1 root root 157405 Apr 29 23:06 xen.pcpu8.stack.log -rw-r--r-- 1 root root 156773 Apr 29 23:06 xen.pcpu9.stack.log

Here is the content of xen-crashdump-analyser.log
If there is another one which you would like to see tell me please.
The host was being backed up by XO running on another host when this happened. There was on "Importing..." VM left over after the crash. So this happened in the middle of a healthcheck.

INFO Logging level is DEBUG INFO Command line: /usr/lib64/xen/bin/xen-crashdump-analyser --outdir /var/crash/20240429-230637-WEST --xen-symtab /var/lib/kdump/xen-4.17.3-4.map --dom0-symtab /var/lib/kdump/System.map-4.19.0+1 -v --dump-structures INFO Xen Crashdump Analyser version 2.6.1 DEBUG Opened log file 'xen-crashdump-analyser.log' INFO Output directory: /var/crash/20240429-230637-WEST/ INFO Xen symbol table: /var/lib/kdump/xen-4.17.3-4.map DEBUG text section limits: 0xffff82d040200000->0xffff82d040357f4b DEBUG init section limits: 0xffff82d040600000->0xffff82d04064bbdc DEBUG Got Xen virtual address information. Will validate Xen pointers INFO Dom0 symbol table: /var/lib/kdump/System.map-4.19.0+1 INFO CPU vendor is Intel DEBUG maxphysaddr = 39, mask = 0x0000007fffffffff DEBUG text section limits: 0xffffffff81000000->0xffffffff81a031d1 DEBUG init section limits: 0xffffffff8242b000->0xffffffff82490b2a DEBUG hypercall page: 0xffffffff81001000->0xffffffff81002000 INFO Elf CORE crash file: /proc/vmcore DEBUG Found 0 section headers of size 0 bytes at offset 0 DEBUG Found 7 program headers of size 56 bytes at offset 0x40 INFO Decoding physical CPU information. 20 PCPUs DEBUG Reading per-pcpu information DEBUG Reading PCPUs vcpus INFO Processor ID 0 DEBUG Current vcpu 0xffff8310840a2000, per-cpu vcpu 0xffff8310840a2000 (per-cpu offset 0x0000000000000000) INFO Current vcpu was RUNNING. Guest context on stack INFO Processor ID 1 DEBUG Current vcpu 0xffff83108409e000, per-cpu vcpu 0xffff83108409e000 (per-cpu offset 0x0000004043a2d000) INFO Current vcpu was RUNNING. Guest context on stack INFO Processor ID 2 DEBUG Current vcpu 0xffff8310841fa000 (IDLE), per-cpu vcpu 0xffff8310ada64000 (per-cpu offset 0x000000404387d000) INFO Current vcpu is IDLE. Guest context on stack. WARN Cannot get kernel page table address - VCPU assumed down WARN Failed to decode extended state for pcpu2 INFO Processor ID 3 DEBUG Current vcpu 0xffff8310841ed000 (IDLE), per-cpu vcpu 0xffff831084086000 (per-cpu offset 0x0000004043869000) INFO Current vcpu is IDLE. Guest context on stack. INFO Processor ID 4 DEBUG Current vcpu 0xffff8310841dc000 (IDLE), per-cpu vcpu 0xffff831084076000 (per-cpu offset 0x0000004043859000) INFO Current vcpu is IDLE. Guest context on stack. INFO Processor ID 5 DEBUG Current vcpu 0xffff8310841c7000 (IDLE), per-cpu vcpu 0xffff831084092000 (per-cpu offset 0x0000004043851000) INFO Current vcpu is IDLE. Guest context on stack. INFO Processor ID 6 DEBUG Current vcpu 0xffff8310841c2000 (IDLE), per-cpu vcpu 0xffff83108408a000 (per-cpu offset 0x0000004043835000) INFO Current vcpu is IDLE. Guest context on stack. INFO Processor ID 7 DEBUG Current vcpu 0xffff8310841b1000 (IDLE), per-cpu vcpu 0xffff831084096000 (per-cpu offset 0x0000004043825000) INFO Current vcpu is IDLE. Guest context on stack. INFO Processor ID 8 DEBUG Current vcpu 0xffff831084082000, per-cpu vcpu 0xffff831084082000 (per-cpu offset 0x0000004043815000) INFO Current vcpu was RUNNING. Guest context on stack INFO Processor ID 9 DEBUG Current vcpu 0xffff831084183000 (IDLE), per-cpu vcpu 0xffff83108407a000 (per-cpu offset 0x0000004043805000) INFO Current vcpu is IDLE. Guest context on stack. INFO Processor ID 10 DEBUG Current vcpu 0xffff831084176000 (IDLE), per-cpu vcpu 0xffff8310840a6000 (per-cpu offset 0x00000040437f1000) INFO Current vcpu is IDLE. Guest context on stack. INFO Processor ID 11 DEBUG Current vcpu 0xffff831084165000 (IDLE), per-cpu vcpu 0xffff830bf4249000 (per-cpu offset 0x00000040437e1000) INFO Current vcpu is IDLE. Guest context on stack. WARN Cannot get kernel page table address - VCPU assumed down WARN Failed to decode extended state for pcpu11 INFO Processor ID 12 DEBUG Current vcpu 0xffff831084154000 (IDLE), per-cpu vcpu 0xffff830bf423f000 (per-cpu offset 0x00000040437d1000) INFO Current vcpu is IDLE. Guest context on stack. WARN Cannot get kernel page table address - VCPU assumed down WARN Failed to decode extended state for pcpu12 INFO Processor ID 13 DEBUG Current vcpu 0xffff83108413f000 (IDLE), per-cpu vcpu 0xffff8310840b3000 (per-cpu offset 0x00000040437c1000) INFO Current vcpu is IDLE. Guest context on stack. INFO Processor ID 14 DEBUG Current vcpu 0xffff83108413a000 (IDLE), per-cpu vcpu 0xffff83108407e000 (per-cpu offset 0x00000040437ad000) INFO Current vcpu is IDLE. Guest context on stack. INFO Processor ID 15 DEBUG Current vcpu 0xffff831084129000 (IDLE), per-cpu vcpu 0xffff83108409a000 (per-cpu offset 0x000000404379d000) INFO Current vcpu is IDLE. Guest context on stack. INFO Processor ID 16 DEBUG Current vcpu 0xffff83108408e000, per-cpu vcpu 0xffff83108408e000 (per-cpu offset 0x000000404378d000) INFO Current vcpu was RUNNING. Guest context on stack INFO Processor ID 17 DEBUG Current vcpu 0xffff831084108000 (IDLE), per-cpu vcpu 0xffff830bf425d000 (per-cpu offset 0x000000404377d000) INFO Current vcpu is IDLE. Guest context on stack. WARN Cannot get kernel page table address - VCPU assumed down WARN Failed to decode extended state for pcpu17 INFO Processor ID 18 DEBUG Current vcpu 0xffff8310840eb000 (IDLE), per-cpu vcpu 0xffff8310840ae000 (per-cpu offset 0x000000404376d000) INFO Current vcpu is IDLE. Guest context on stack. INFO Processor ID 19 DEBUG Current vcpu 0xffff8310840aa000, per-cpu vcpu 0xffff8310840aa000 (per-cpu offset 0x0000004043759000) INFO Current vcpu was RUNNING. Guest context on stack DEBUG Generating active vcpu list INFO Opened for host information DEBUG Console ring: 131072 bytes at 0xffff831084380000, prod 98136, cons 0 DEBUG Correcting for passing page boundary (vaddr ffff831084380000, maddr 0000001084380000, end ffff831084380fff, n 98136) DEBUG Subwrite (vaddr ffff831084380000, maddr 0000001084380000, end ffff831084380fff, index 0, nr 4096, n 98136) DEBUG Subwrite (vaddr ffff831084381000, maddr 0000001084381000, end ffff831084381fff, index 4096, nr 4096, n 94040) DEBUG Subwrite (vaddr ffff831084382000, maddr 0000001084382000, end ffff831084382fff, index 8192, nr 4096, n 89944) DEBUG Subwrite (vaddr ffff831084383000, maddr 0000001084383000, end ffff831084383fff, index 12288, nr 4096, n 85848) DEBUG Subwrite (vaddr ffff831084384000, maddr 0000001084384000, end ffff831084384fff, index 16384, nr 4096, n 81752) DEBUG Subwrite (vaddr ffff831084385000, maddr 0000001084385000, end ffff831084385fff, index 20480, nr 4096, n 77656) DEBUG Subwrite (vaddr ffff831084386000, maddr 0000001084386000, end ffff831084386fff, index 24576, nr 4096, n 73560) DEBUG Subwrite (vaddr ffff831084387000, maddr 0000001084387000, end ffff831084387fff, index 28672, nr 4096, n 69464) DEBUG Subwrite (vaddr ffff831084388000, maddr 0000001084388000, end ffff831084388fff, index 32768, nr 4096, n 65368) DEBUG Subwrite (vaddr ffff831084389000, maddr 0000001084389000, end ffff831084389fff, index 36864, nr 4096, n 61272) DEBUG Subwrite (vaddr ffff83108438a000, maddr 000000108438a000, end ffff83108438afff, index 40960, nr 4096, n 57176) DEBUG Subwrite (vaddr ffff83108438b000, maddr 000000108438b000, end ffff83108438bfff, index 45056, nr 4096, n 53080) DEBUG Subwrite (vaddr ffff83108438c000, maddr 000000108438c000, end ffff83108438cfff, index 49152, nr 4096, n 48984) DEBUG Subwrite (vaddr ffff83108438d000, maddr 000000108438d000, end ffff83108438dfff, index 53248, nr 4096, n 44888) DEBUG Subwrite (vaddr ffff83108438e000, maddr 000000108438e000, end ffff83108438efff, index 57344, nr 4096, n 40792) DEBUG Subwrite (vaddr ffff83108438f000, maddr 000000108438f000, end ffff83108438ffff, index 61440, nr 4096, n 36696) DEBUG Subwrite (vaddr ffff831084390000, maddr 0000001084390000, end ffff831084390fff, index 65536, nr 4096, n 32600) DEBUG Subwrite (vaddr ffff831084391000, maddr 0000001084391000, end ffff831084391fff, index 69632, nr 4096, n 28504) DEBUG Subwrite (vaddr ffff831084392000, maddr 0000001084392000, end ffff831084392fff, index 73728, nr 4096, n 24408) DEBUG Subwrite (vaddr ffff831084393000, maddr 0000001084393000, end ffff831084393fff, index 77824, nr 4096, n 20312) DEBUG Subwrite (vaddr ffff831084394000, maddr 0000001084394000, end ffff831084394fff, index 81920, nr 4096, n 16216) DEBUG Subwrite (vaddr ffff831084395000, maddr 0000001084395000, end ffff831084395fff, index 86016, nr 4096, n 12120) DEBUG Subwrite (vaddr ffff831084396000, maddr 0000001084396000, end ffff831084396fff, index 90112, nr 4096, n 8024) DEBUG Subwrite (vaddr ffff831084397000, maddr 0000001084397000, end ffff831084397fff, index 94208, nr 3928, n 3928) INFO Decoding Domains DEBUG Domain pointer = 0xffff8310840c3000 INFO Found domain 0 DEBUG Logging to 'dom0.log' INFO 16 VCPUs DEBUG Vcpu0 pointer = 0xffff8310840b3000 DEBUG Vcpu1 pointer = 0xffff8310840ae000 DEBUG Vcpu2 pointer = 0xffff8310840aa000 DEBUG Vcpu3 pointer = 0xffff8310840a6000 DEBUG Vcpu4 pointer = 0xffff8310840a2000 DEBUG Vcpu5 pointer = 0xffff83108409e000 DEBUG Vcpu6 pointer = 0xffff83108409a000 DEBUG Vcpu7 pointer = 0xffff831084096000 DEBUG Vcpu8 pointer = 0xffff831084092000 DEBUG Vcpu9 pointer = 0xffff83108408e000 DEBUG Vcpu10 pointer = 0xffff83108408a000 DEBUG Vcpu11 pointer = 0xffff831084086000 DEBUG Vcpu12 pointer = 0xffff831084082000 DEBUG Vcpu13 pointer = 0xffff83108407e000 DEBUG Vcpu14 pointer = 0xffff83108407a000 DEBUG Vcpu15 pointer = 0xffff831084076000 DEBUG Dom0 vcpu0 was active on pcpu13 DEBUG Dom0 vcpu1 was active on pcpu18 DEBUG Dom0 vcpu2 was active on pcpu19 DEBUG Dom0 vcpu3 was active on pcpu10 DEBUG Dom0 vcpu4 was active on pcpu0 DEBUG Dom0 vcpu5 was active on pcpu1 DEBUG Dom0 vcpu6 was active on pcpu15 DEBUG Dom0 vcpu7 was active on pcpu7 DEBUG Dom0 vcpu8 was active on pcpu5 DEBUG Dom0 vcpu9 was active on pcpu16 DEBUG Dom0 vcpu10 was active on pcpu6 DEBUG Dom0 vcpu11 was active on pcpu3 DEBUG Dom0 vcpu12 was active on pcpu8 DEBUG Dom0 vcpu13 was active on pcpu14 DEBUG Dom0 vcpu14 was active on pcpu9 DEBUG Dom0 vcpu15 was active on pcpu4 DEBUG Correcting for passing page boundary (vaddr ffff8881dc16be80, maddr 000000093a493e80, end ffff8881dc16bfff, n 2047) DEBUG Subread (vaddr ffff8881dc16be80, maddr 000000093a493e80, end ffff8881dc16bfff, index 0, nr 384, n 2047) DEBUG Subread (vaddr ffff8881dc16c000, maddr 000000093a494000, end ffff8881dc16cfff, index 384, nr 1663, n 1663) WARN paging error for vaddr 0xffff8881dc16d000 - level 1 not present DEBUG Correcting for passing page boundary (vaddr ffffffff825a7f74, maddr 00000010825a7f74, end ffffffff825a7fff, n 141) DEBUG Subwrite (vaddr ffffffff825a7f74, maddr 00000010825a7f74, end ffffffff825a7fff, index 0, nr 140, n 141) DEBUG Subwrite (vaddr ffffffff825a8000, maddr 00000010825a8000, end ffffffff825a8fff, index 140, nr 1, n 1) DEBUG Correcting for passing page boundary (vaddr ffffffff825aaffc, maddr 00000010825aaffc, end ffffffff825aafff, n 144) DEBUG Subwrite (vaddr ffffffff825aaffc, maddr 00000010825aaffc, end ffffffff825aafff, index 0, nr 4, n 144) DEBUG Subwrite (vaddr ffffffff825ab000, maddr 00000010825ab000, end ffffffff825abfff, index 4, nr 140, n 140) DEBUG Correcting for passing page boundary (vaddr ffffffff825acfec, maddr 00000010825acfec, end ffffffff825acfff, n 33) DEBUG Subwrite (vaddr ffffffff825acfec, maddr 00000010825acfec, end ffffffff825acfff, index 0, nr 20, n 33) DEBUG Subwrite (vaddr ffffffff825ad000, maddr 00000010825ad000, end ffffffff825adfff, index 20, nr 13, n 13) DEBUG Correcting for passing page boundary (vaddr ffffffff825adfcc, maddr 00000010825adfcc, end ffffffff825adfff, n 54) DEBUG Subwrite (vaddr ffffffff825adfcc, maddr 00000010825adfcc, end ffffffff825adfff, index 0, nr 52, n 54) DEBUG Subwrite (vaddr ffffffff825ae000, maddr 00000010825ae000, end ffffffff825aefff, index 52, nr 2, n 2) DEBUG Correcting for passing page boundary (vaddr ffffffff825b0fd4, maddr 00000010825b0fd4, end ffffffff825b0fff, n 66) DEBUG Subwrite (vaddr ffffffff825b0fd4, maddr 00000010825b0fd4, end ffffffff825b0fff, index 0, nr 44, n 66) DEBUG Subwrite (vaddr ffffffff825b1000, maddr 00000010825b1000, end ffffffff825b1fff, index 44, nr 22, n 22) DEBUG Correcting for passing page boundary (vaddr ffffffff825b1fe8, maddr 00000010825b1fe8, end ffffffff825b1fff, n 76) DEBUG Subwrite (vaddr ffffffff825b1fe8, maddr 00000010825b1fe8, end ffffffff825b1fff, index 0, nr 24, n 76) DEBUG Subwrite (vaddr ffffffff825b2000, maddr 00000010825b2000, end ffffffff825b2fff, index 24, nr 52, n 52) DEBUG Correcting for passing page boundary (vaddr ffffffff825b2ff4, maddr 00000010825b2ff4, end ffffffff825b2fff, n 33) DEBUG Subwrite (vaddr ffffffff825b2ff4, maddr 00000010825b2ff4, end ffffffff825b2fff, index 0, nr 12, n 33) DEBUG Subwrite (vaddr ffffffff825b3000, maddr 00000010825b3000, end ffffffff825b3fff, index 12, nr 21, n 21) DEBUG Correcting for passing page boundary (vaddr ffffffff825b3ffc, maddr 00000010825b3ffc, end ffffffff825b3fff, n 8) DEBUG Subread (vaddr ffffffff825b3ffc, maddr 00000010825b3ffc, end ffffffff825b3fff, index 0, nr 4, n 8) DEBUG Subread (vaddr ffffffff825b4000, maddr 00000010825b4000, end ffffffff825b4fff, index 4, nr 4, n 4) DEBUG Correcting for passing page boundary (vaddr ffffffff825b6fcc, maddr 00000010825b6fcc, end ffffffff825b6fff, n 66) DEBUG Subwrite (vaddr ffffffff825b6fcc, maddr 00000010825b6fcc, end ffffffff825b6fff, index 0, nr 52, n 66) DEBUG Subwrite (vaddr ffffffff825b7000, maddr 00000010825b7000, end ffffffff825b7fff, index 52, nr 14, n 14) DEBUG Correcting for passing page boundary (vaddr ffffffff825b7fd0, maddr 00000010825b7fd0, end ffffffff825b7fff, n 168) DEBUG Subwrite (vaddr ffffffff825b7fd0, maddr 00000010825b7fd0, end ffffffff825b7fff, index 0, nr 48, n 168) DEBUG Subwrite (vaddr ffffffff825b8000, maddr 00000010825b8000, end ffffffff825b8fff, index 48, nr 120, n 120) DEBUG Correcting for passing page boundary (vaddr ffffffff825b9fd0, maddr 00000010825b9fd0, end ffffffff825b9fff, n 50) DEBUG Subwrite (vaddr ffffffff825b9fd0, maddr 00000010825b9fd0, end ffffffff825b9fff, index 0, nr 48, n 50) DEBUG Subwrite (vaddr ffffffff825ba000, maddr 00000010825ba000, end ffffffff825bafff, index 48, nr 2, n 2) DEBUG Correcting for passing page boundary (vaddr ffffffff825baff0, maddr 00000010825baff0, end ffffffff825bafff, n 50) DEBUG Subwrite (vaddr ffffffff825baff0, maddr 00000010825baff0, end ffffffff825bafff, index 0, nr 16, n 50) DEBUG Subwrite (vaddr ffffffff825bb000, maddr 00000010825bb000, end ffffffff825bbfff, index 16, nr 34, n 34) DEBUG Correcting for passing page boundary (vaddr ffffffff825bbfdc, maddr 00000010825bbfdc, end ffffffff825bbfff, n 62) DEBUG Subwrite (vaddr ffffffff825bbfdc, maddr 00000010825bbfdc, end ffffffff825bbfff, index 0, nr 36, n 62) DEBUG Subwrite (vaddr ffffffff825bc000, maddr 00000010825bc000, end ffffffff825bcfff, index 36, nr 26, n 26) DEBUG Correcting for passing page boundary (vaddr ffffffff825beff8, maddr 00000010825beff8, end ffffffff825befff, n 50) DEBUG Subwrite (vaddr ffffffff825beff8, maddr 00000010825beff8, end ffffffff825befff, index 0, nr 8, n 50) DEBUG Subwrite (vaddr ffffffff825bf000, maddr 00000010825bf000, end ffffffff825bffff, index 8, nr 42, n 42) DEBUG Correcting for passing page boundary (vaddr ffffffff825c0fd8, maddr 00000010825c0fd8, end ffffffff825c0fff, n 51) DEBUG Subwrite (vaddr ffffffff825c0fd8, maddr 00000010825c0fd8, end ffffffff825c0fff, index 0, nr 40, n 51) DEBUG Subwrite (vaddr ffffffff825c1000, maddr 00000010825c1000, end ffffffff825c1fff, index 40, nr 11, n 11) DEBUG Correcting for passing page boundary (vaddr ffffffff825c1ff8, maddr 00000010825c1ff8, end ffffffff825c1fff, n 51) DEBUG Subwrite (vaddr ffffffff825c1ff8, maddr 00000010825c1ff8, end ffffffff825c1fff, index 0, nr 8, n 51) DEBUG Subwrite (vaddr ffffffff825c2000, maddr 00000010825c2000, end ffffffff825c2fff, index 8, nr 43, n 43) DEBUG Correcting for passing page boundary (vaddr ffffffff825c4fec, maddr 00000010825c4fec, end ffffffff825c4fff, n 74) DEBUG Subwrite (vaddr ffffffff825c4fec, maddr 00000010825c4fec, end ffffffff825c4fff, index 0, nr 20, n 74) DEBUG Subwrite (vaddr ffffffff825c5000, maddr 00000010825c5000, end ffffffff825c5fff, index 20, nr 54, n 54) DEBUG Correcting for passing page boundary (vaddr ffffffff825c5fc8, maddr 00000010825c5fc8, end ffffffff825c5fff, n 65) DEBUG Subwrite (vaddr ffffffff825c5fc8, maddr 00000010825c5fc8, end ffffffff825c5fff, index 0, nr 56, n 65) DEBUG Subwrite (vaddr ffffffff825c6000, maddr 00000010825c6000, end ffffffff825c6fff, index 56, nr 9, n 9) DEBUG Dumping structures to 'dom0.structures.log' INFO Found domain 1 DEBUG Logging to 'dom1.log' INFO 4 VCPUs DEBUG Vcpu0 pointer = 0xffff8310ada84000 DEBUG Vcpu1 pointer = 0xffff8310ada78000 DEBUG Vcpu2 pointer = 0xffff8310ada6e000 DEBUG Vcpu3 pointer = 0xffff8310ada64000 DEBUG Dom1 vcpu0 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom1 vcpu1 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom1 vcpu2 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom1 vcpu3 was active on pcpu2 WARN Cannot get kernel page table address from active VCPU DEBUG Dumping structures to 'dom1.structures.log' INFO Found domain 46 DEBUG Logging to 'dom46.log' INFO 8 VCPUs DEBUG Vcpu0 pointer = 0xffff830a67bd5000 DEBUG Vcpu1 pointer = 0xffff830a67bcb000 DEBUG Vcpu2 pointer = 0xffff830a67bc3000 DEBUG Vcpu3 pointer = 0xffff830a67bbb000 DEBUG Vcpu4 pointer = 0xffff830a67bb3000 DEBUG Vcpu5 pointer = 0xffff830a67bab000 DEBUG Vcpu6 pointer = 0xffff830a67ba3000 DEBUG Vcpu7 pointer = 0xffff830a67b99000 DEBUG Dom46 vcpu0 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom46 vcpu1 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom46 vcpu2 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom46 vcpu3 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom46 vcpu4 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom46 vcpu5 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom46 vcpu6 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom46 vcpu7 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dumping structures to 'dom46.structures.log' INFO Found domain 47 DEBUG Logging to 'dom47.log' INFO 8 VCPUs DEBUG Vcpu0 pointer = 0xffff830bf4287000 DEBUG Vcpu1 pointer = 0xffff830bf427b000 DEBUG Vcpu2 pointer = 0xffff830bf4271000 DEBUG Vcpu3 pointer = 0xffff830bf4267000 DEBUG Vcpu4 pointer = 0xffff830bf425d000 DEBUG Vcpu5 pointer = 0xffff830bf4253000 DEBUG Vcpu6 pointer = 0xffff830bf4249000 DEBUG Vcpu7 pointer = 0xffff830bf423f000 DEBUG Dom47 vcpu0 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom47 vcpu1 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom47 vcpu2 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom47 vcpu3 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom47 vcpu4 was active on pcpu17 WARN Cannot get kernel page table address from active VCPU DEBUG Dom47 vcpu5 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom47 vcpu6 was active on pcpu11 WARN Cannot get kernel page table address from active VCPU DEBUG Dom47 vcpu7 was active on pcpu12 WARN Cannot get kernel page table address from active VCPU DEBUG Dumping structures to 'dom47.structures.log' INFO Found domain 75 DEBUG Logging to 'dom75.log' INFO 2 VCPUs DEBUG Vcpu0 pointer = 0xffff830dae687000 DEBUG Vcpu1 pointer = 0xffff830dae675000 DEBUG Dom75 vcpu0 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dom75 vcpu1 was not active WARN Cannot get kernel page table address - VCPU assumed down DEBUG Dumping structures to 'dom75.structures.log' DEBUG Successfully printed 5 domains INFO COMPLETE

@stormi I’ll be back on Wednesday (just short holiday now), I’ll try your advice and see how it works

@TheRedHerring I have an HM90 that I use as a host and it worked with 8.2 out of the box except for the 2.5G NIC. I switched to 8.3 and everything worked out of the box.

As a server virtualization platform, ECC is the most common memory used by our XCP-ng deployments all around the world 🙂 It's up to the system (CPU/memory) to deal with it and correct errors on the fly, it's transparent for the hypervisor 🙂

That's weird, never heard about this option to be needed to make it work, does it ring a bell @fohdeesha ?

No worries. There's some politics involved also to be sure it will be accepted upstream, but we expect to be a matter of months (at worst) to be upstream, and then it should be straightforward to get it into 8.3 🙂

Because on XO side: it's already working! (we are using our own patched XAPI to make the tests)

Thanks everyone! I’ll let you know if we have any issues.