On Tue, Nov 6, 2012 at 8:49 AM, Andrew Deason wrote:
> On Tue, 6 Nov 2012 00:06:53 -0800
> Timothy Balcer wrote:
>
> > I have a need to think about replicating large volumes (multigigabyte)
> > of large number (many terabytes of data total), to at least two other
> > servers besides the read writ
Hi Dan, thanks for your efforts in researching this problem and
posting it. And thanks to Arne for his response as well.
Renata
On Thu, 8 Nov 2012, Dan Van Der Ster wrote:
>Just run
>
>ulimit -Hn
>
>If it says 4096 your AFS will probably crash. If it says 1024 you are safe (as
>far as we'
Hi Dan,
On Nov 8, 2012, at 16:41 , Dan Van Der Ster wrote:
[...]
> All of the nasty details of this incident here:
>https://afs.web.cern.ch/afs/reports/html/afs200SegFaults.html
>
> We're now running with a workaround,
> ulimit -Hn 1024; ulimit -Sn 1024
> in our init scripts until we manag
>From what I see on our most recent RHEL derived SLC kernels this change
is only in 6.
Cheers,
Arne
On Nov 8, 2012, at 5:46 PM, Renata Maria Dart
wrote:
> Hi, does this issue apply to both rhel5 and 6?
>
> Thanks,
>
> Renata
>
>
>> Unless you manually set HAVE_POLL, you may not have it
Just run
ulimit -Hn
If it says 4096 your AFS will probably crash. If it says 1024 you are safe (as
far as we've seen).
Cheers, Dan
From: Renata Maria Dart [ren...@slac.stanford.edu]
Sent: 08 November 2012 17:46
To: Derrick Brashear
Cc: Dan Van De
Hi, does this issue apply to both rhel5 and 6?
Thanks,
Renata
>Unless you manually set HAVE_POLL, you may not have it enabled in 1.6:
>we didn't actually do the configure test for it. It will be fixed in 1.6.2.
>
>Incidentally, of note, currently salvsync unlike fssync doesn't ever try
>poll()
On Thu, 8 Nov 2012 15:41:57 +
Dan Van Der Ster wrote:
> Finally we realised this was due to fssync.c in 1.4's use of
> select()/FD_SET and the corrupting behaviour of those functions when
> using >1024 file descriptors per process. Until quite recently this
> hadn't been a problem, since RHEL
On Thu, Nov 8, 2012 at 10:41 AM, Dan Van Der Ster
wrote:
> Dear OpenAFS 1.4.x Users,
>
> At CERN we just suffered from a confusing problem where the fileserver
> process would regularly segfault (on only one new server just put into
> production). Since a gdb of the fileserver core file was show
Dear OpenAFS 1.4.x Users,
At CERN we just suffered from a confusing problem where the fileserver process
would regularly segfault (on only one new server just put into production).
Since a gdb of the fileserver core file was showing random bit flips here and
there, we initially suspected a bad
On Thursday, November 08, 2012 10:11:24 AM, Steve Simmons wrote:
> I have no clue how much work that would be, but it's a helluva idea.
Start by porting RX to C#.
signature.asc
Description: OpenPGP digital signature
On Nov 6, 2012, at 2:26 PM, Gary Buhrmaster wrote:
> On Mon, Nov 5, 2012 at 1:32 PM, Jeffrey Altman wrote:
>> OpenAFS 1.7.18 is the next a series of OpenAFS clients for the Microsoft
>> Windows platform that is implemented as a native file system.
>
> I am not asking for it, just curious if Ope
11 matches
Mail list logo
