Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
Ok .. but here's some bad feedback ... I just took the cvs version (which is labeled 0.7-pre7) and it has the same problem I mentioned a couple of days ago where the 2nd box locks up solid as soon as it contacts the primary. This time I've written down all the trace back that I can see on the screen: (without the hex offsets) in_atomic (): 1 irqs_disabled (): 0 call trace __might_sleep +0xab/0xc9 printk profile_exit_task do_exit do_page_fault do_divide_error do_page_fault reschedule_interrupt inet_recevmsg sock_recvmsg do_page_fault error_code __wake_up_common __wake_up _drbd_process_ee default_wake_function drbd_process_ee drbd_asender drbd_thread_setup +0x79 drbd_thread_setup +0x00 kernel_thread_helper Interesting pieces in this puzzle (since timing is at the heart of all good comedy) - Gigabit ethernet connection ... things hapen quickly here - bonded ethernet interface (slightly slower ... but not much) - linux 2.6.4 stock kernel - 1Gb ram Is this enough to go by? The machine is still sitting there with the offsets on the screen and the fault is 100% reproducible. Ron Philipp Reisner wrote: >>When the 0.7 will be out? >> >> > >Hi, > >DRBD 0.7 is out today, was out yesterday :) The only thing is that >we do not believe that it is as stable as drbd-0.6.x is . > >But, Yesterday drbd-0.7-pre7 got released! >It is a very big step in DRBD-0.7's development. > >This is the request to everybody who waits for DRBD-0.7-final to >help testing DRBD-0.7-pre7. > >As with today the only open issue is that it currently does >not work with XFS. (Earlier releases already worked with XFS, >it must be something on the surface..., not a desing bug...) > >PLEASE HELP FINDING BUGS IN DRBD-0.7 > >PS: So far, this mail indicates that only posts like "bla bla > crashed my drbd-0.7 setup" are welcome. We would also enjoy > mails like, "I stress tested DRBD-0.7 for 48 hours, and > did run app-x-y-z for 48 hours, and did 2880 disconnect/reconnect > cycles in this time, and it works like a charm on my 16 processor > boxes ... " :) > >-Philipp > >