On 5 Mar 2010, at 01:20, eric.hagb...@morganstanley.com wrote:
I've found that if you run a program to generate tokens and pags
frequently (about once per second), that fairly soon, the cpu system
time on the machine will begin to swallow performance, though it
takes a little while to
On Fri, 5 Mar 2010, Simon Wilkinson wrote:
Things are quite different in 1.5 - keyrings are the authoritative
source of PAG information. If you have time, it would be great if you
could do the same tests with 1.5, and see if you experience similar
problems.
This took a little longer to set up
On 5 Mar 2010, at 18:34, eric.hagb...@morganstanley.com wrote:
This took a little longer to set up than I'd hoped, as 1.5.72
doesn't work under RHEL4 (the platform on which I was doing most of
my tests), due to the lack of zero_user_segments and page_offset in
the compiled kernel module.
On Fri, 5 Mar 2010, Simon Wilkinson wrote:
One thing I'd noticed in RHEL4 tests (systemtap doesn't seem to give
the same result under RHEL5) is that the system time usage
corresponds to high frequencies of calling afs_ComputePAGStats.
Compiling with AFS_NOSTATS defined or commenting out the
High number of calls to afs_ComputePAGStats, resulting in system
time being consumed unreasonably, due to it and corresponding
text.lock.spinlock system calls.
I can't see a call to afs_ComputePAGStats in afs_user.c - are you
just
commenting out the body of the function, or is there a
I've found that if you run a program to generate tokens and pags
frequently (about once per second), that fairly soon, the cpu system time
on the machine will begin to swallow performance, though it takes a little
while to observe it... but if you do that long enough, the machine will
On Thu, Mar 4, 2010 at 8:20 PM, eric.hagb...@morganstanley.com wrote:
I've found that if you run a program to generate tokens and pags frequently
(about once per second), that fairly soon, the cpu system time on the
i try to generate pags less often than that.
Maybe this isn't the best fix,
On Thu, 4 Mar 2010, Derrick Brashear wrote:
On Thu, Mar 4, 2010 at 8:20 PM, eric.hagb...@morganstanley.com wrote:
I've found that if you run a program to generate tokens and pags frequently
(about once per second), that fairly soon, the cpu system time on the
i try to generate pags less
On Thu, Mar 4, 2010 at 8:35 PM, eric.hagb...@morganstanley.com wrote:
On Thu, 4 Mar 2010, Derrick Brashear wrote:
On Thu, Mar 4, 2010 at 8:20 PM, eric.hagb...@morganstanley.com wrote:
I've found that if you run a program to generate tokens and pags
frequently
(about once per second), that