Updated tg3 driver available

Gabriel Rosenkoetter grosen at cc3.com
Wed Jan 22 18:15:01 CST 2003


Be wary of this kernel.

I tried it on a production system today when we had an NFS read hang and
had to reboot to clear the zombied process anyway, and just a cat of a
small file on the low-processor-usage system hung the NFS mount in the
same way. This is across a Tigon3, using the tg3 driver (provided the
aragorn kernel respected my /etc/modules.conf, but I think it's a safe
presumption that it did).

Jeff, any thoughts?

I *might* be able to do some testing, and can gladly provide more
information than what follows, if necessary:

PowerEdge 2650
RedHat 7.3 install
2 GBs RAM
2 Xeons, hyperthreading disabled
(back to) running RedHat's 2.4.18-19.7.xsmp now
across an NFS mount from a Solaris 8 (can get more info on revs there if
you like, but I'd like to have left the office nearly two hours ago, so
tell me what you want :^>) with these options:
  rw,nosuid,nodev,noatime,hard,intr,bg,rsize=32768,wsize=32768

> -----Original Message-----
> From: linux-poweredge-admin at dell.com 
> [mailto:linux-poweredge-admin at dell.com] On Behalf Of Jeff Garzik
> Sent: Tuesday, January 21, 2003 3:01 PM
> To: linux-poweredge at dell.com
> Subject: Updated tg3 driver available
> 
> 
> Since Red Hat's internal Q/A process takes a long time [that's a good
> thing...], and since our next errata and release kernels are a ways
> away, I will continue to post tg3 driver updates as bugs are 
> fixed, and
> new BroadCom hardware errata is learned, and worked-around.
> 
> To this end, I have rolled the tg3 bug fixes into a new set of rpms.
> These rpms are (as always) based on the latest Red Hat errata kernel,
> and add:
> * tg3 crash fixes, and other fixes
> * better support for BCM5704 chips
> * e1000 fixes
> 
> The rpms are in sub-directories of:  
> http://people.redhat.com/jgarzik/pub/
> A more detailed 
> description of the kernels in the directory is in
> 	http://people.redhat.com/jgarzik/pub/PLEASE_READ_ME.txt
> 
> For bcm5700 users, if it's working for you, fine and dandy.  I am a
> Southerner, who believes strongly in the "if it ain't broke, don't fix
> it" mantra.  However, just to reiterate, there continue to be 
> known bugs
> in the bcm5700 driver, over and above the slower performance 
> it offers.
> The internal driver locking functions are incorrect and could lead to
> stack corruption at high loads.  The hardware errata workarounds are
> incredibly heavy handed, and serve to severely limit performance in
> exchange for working around hardware errata.
> 
> Have fun,
> 
> 	Jeff
> 
> 
> 
> _______________________________________________
> Linux-PowerEdge mailing list
> Linux-PowerEdge at dell.com
> http://lists.us.dell.com/mailman/listinfo/linux-poweredge
> Please read the FAQ at http://lists.us.dell.com/faq or search 
> the list archives at http://lists.us.dell.com/htdig/
> 




More information about the Linux-PowerEdge mailing list