Re: Packet loss every 30.999 seconds

* David G Lawrence <dg@xxxxxxxxxxxxxx> [071219 09:12] wrote:
Try it with "find / -type f >/dev/null" to duplicate the problem
almost
instantly.

I was able to verify last night that (cd /; tar -cpf -) > all.tar would
trigger the problem. I'm working getting a test running with
David's ffs_sync() workaround now, adding a few counters there should
get this narrowed down a little more.

Unfortunately, the version of the patch that I sent out isn't going to
help your problem. It needs to yield at the top of the loop, but vp isn't
necessarily valid after the wakeup from the msleep. That's a problem that
I'm having trouble figuring out a solution to - the solutions that come
to mind will all significantly increase the overhead of the loop.
As a very inadequate work-around, you might consider lowering
kern.maxvnodes to something like 20000 - that might be low enough to
not trigger the problem, but also be high enough to not significantly
affect system I/O performance.

I apologize for not reading the code as I am swamped, but a technique
that Matt Dillon used for bufs might work here.

Can you use a placeholder vnode as a place to restart the scan?
you might have to mark it special so that other threads/things
(getnewvnode()?) don't molest it, but it can provide for a convenient
restart point.

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

Relevant Pages

  • Re: Packet loss every 30.999 seconds
    ... adding a few counters there should ... to mind will all significantly increase the overhead of the loop. ... not trigger the problem, but also be high enough to not significantly ... Can you use a placeholder vnode as a place to restart the scan? ...
    (freebsd-net)
  • Re: Packet loss every 30.999 seconds
    ... David's ffs_syncworkaround now, adding a few counters there should ... to mind will all significantly increase the overhead of the loop. ... not trigger the problem, but also be high enough to not significantly ...
    (freebsd-net)
  • Re: Packet loss every 30.999 seconds
    ... David's ffs_syncworkaround now, adding a few counters there should ... to mind will all significantly increase the overhead of the loop. ... not trigger the problem, but also be high enough to not significantly ...
    (freebsd-stable)
  • Re: Modifying application folder structure results in application rest
    ... After 15th, application will restart. ... Actually from my experience it does recycle on create/rename sub folder ... aren't supposed to trigger filesystemwatcher behavior...but you're right, ... modifying or deleting global.asax or web.config. ...
    (microsoft.public.dotnet.framework.aspnet)
  • Re: "Green Light Trigger"
    ... to is for when you get stuck at a red light that won't change because you can't trigger the loop in the pavement. ... th' actual timing allowing them to get greens faster. ... '95 FLHTCUI Fuel Injected 30th Anniversary Electraglide "Fueley" '66 H-D Bobcat "Baby Blue"--Harley Hummer Club Member #1066 http://spoiled-brat.com/rwr (m/c related site) http://userpages.chorus.net/witw "There's only *one* RE.". ...
    (rec.motorcycles.harley)