Re: Proposed 6.2 em RELEASE patch

At 08:47 PM 11/12/2006, Scott Long wrote:
2. Try compiling in WITNESS and running the test as before, then break
into the debugger as before. Run 'show locks'. I'm not sure how
fruitful this will be, WITNESS might make it unbearably slow.
It was in that kernel already

So you're seeing the livelock under load while also having WITNESS enabled? Have you tried your test without WITNESS? What about INVARIANTS?

Sorry, by it was in the kernel already, it was from last nights tests where you asked me to break into the debugger to see what was going on. I figured you would want it in there. My original tests were all without WITNESS and INVARIANTS and they were showing the same behaviour (locking up on the management interface) with and without WITNESS and INVARIANTS


Removing ADAPTIVE_GIANT seems to be very key in this! If I remove it, the box no longer locks up under a high packet rate! Its still a little sluggish on the bge OOB interface, but its not totally locking up like before

Running ifstat -b from the management interface, here is the traffic pattern first with one blast running and then the second kicks in. The Kbps/s out on em1 drops in half, but the box is still responsive and bge1... Certainly responsive enough to see the output of ifstat.



218028.4 0.00 0.00 216389.9 0.47 1.17
218971.2 0.00 0.00 217123.1 0.94 2.34
217754.7 0.00 0.00 215677.2 0.94 1.17
215763.1 0.00 0.00 214578.5 0.47 1.17
217850.3 0.00 0.00 216138.7 1.40 2.34
217668.0 0.00 0.00 215888.3 0.47 1.17
em0 em1 bge1
Kbps in Kbps out Kbps in Kbps out Kbps in Kbps out
217382.3 0.00 0.00 216293.8 1.26 1.59
218247.9 118916.5 234167.3 124972.1 0.47 2.17
215973.4 220459.9 393350.0 54875.64 1.40 2.34
217697.7 210984.5 398543.3 58165.20 0.94 3.09
217183.6 200424.9 399096.5 61845.74 0.94 1.17
217788.7 221212.9 400129.8 53716.38 0.47 1.17
217040.0 204934.2 396628.7 61247.34 1.40 2.34
217105.9 201295.5 399274.1 61710.76 0.94 3.09
215605.6 225012.4 397533.5 53237.31 0.94 1.17
217933.3 200346.4 395949.3 62734.52 0.47 1.17
216783.7 205114.1 395923.0 61042.17 0.94 1.17
217885.7 88513.41 159056.4 151418.9 0.47 1.17
216927.2 0.00 0.00 215450.4 0.94 1.17
217454.1 0.00 0.00 215466.6 0.47 1.17
216810.6 0.00 0.00 215564.2 1.40 1.17
217608.3 0.00 0.00 216061.8 0.47 1.17
217452.8 0.00 0.00 215627.1 0.94 1.17
217185.0 0.00 0.00 216079.7 0.47 1.17


However, if I turn on fastforwarding, its back to the old behavior with it locking up. This was with the stock driver. I will try the same test with

#define EM_FAST_INTR 1

as well as taking out the nfs option from the kernel driver. Anything else to tune with ?

---Mike





Scott

_______________________________________________
freebsd-net@xxxxxxxxxxx mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to "freebsd-net-unsubscribe@xxxxxxxxxxx"

Relevant Pages

  • Re: Proposed 6.2 em RELEASE patch
    ... So you're seeing the livelock under load while also having WITNESS enabled? ... Sorry, by it was in the kernel already, it was from last nights tests where you asked me to break into the debugger to see what was going on. ... the box no longer locks up under a high packet rate! ... Kbps in Kbps out Kbps in Kbps out Kbps in Kbps out ...
    (freebsd-stable)
  • Re: Panic on -CURRENT after LDT changes
    ... Here is a dmesg and backtrace. ... I'm stopped in the debugger now with WITNESS and friends enabled. ... Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org ...
    (freebsd-current)
  • Re: Ufs dead-locks on freebsd 6.2
    ... invariant_support and witness. ... diagnositc, debug_locks and debug_vfs_locks as per the handbook ... the serial console setup as the default console so I can remotely access ... the box and break into the debugger etc. ...
    (freebsd-performance)
  • Re: Freeze.Panes revisited
    ... etc. would suffice for him. ... and court summons to follow that if enough solid proof is found. ... > Locks get changed as quickly as I can get a locksmith out. ... > who witness this the better. ...
    (sci.med.dentistry)
  • Re: PLEASE TEST: IPI deadlock avoidance patch
    ... >> news server (heavy disk and network traffic) still locks up within one ... >> and no WITNESS or INVARIANTS. ...
    (freebsd-current)
Loading