Søren Schmidt wrote: >> Anton Yuzhaninov has mentioned in the top of this thread that >> this bug may be easy reproduced by using external PCI-X card. >> He tried use PCI-X Marvell card and got lots of corruptions on >> the integrated HT1000. Can you or Soren try the same way to >> reproduce? > As I told earlier the fileserver I have here with the HT1000 chip also > has a marvel 6081 and it is on PCI-X. There are 4 disks on each and it > moves lots of data around on a daily basis, no problems whatsoever. I > have planned downtime today on it and will experiment with it, but I > can't hold it off for too long... May be here is different HW revisions? You have an old revision and now people with this bug have a new revision? I don't see in the this thread any verbose dmesg or pciconf outputs. So, people, who have problems and who don't have it, can you show your `pciconf -l`? -- WBR, Andrey V. ElsukovReceived on Thu Nov 29 2007 - 06:26:54 UTC
This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:39:23 UTC