Re: SMP Lockups III -The Search for Stability

• Next message: Andrew Morton: "Re: [patch] repost of netfilter/NIPQUAD patches"
• Previous message: sara@procsys.com: "Re: is (rscsi_disks[i].sector_size != 512) ok ?"
• In reply to: Philippe Troin: "Re: SMP Lockups III -The Search for Stability"
• Next in thread: Philippe Troin: "Re: SMP Lockups III -The Search for Stability"
• Reply: Philippe Troin: "Re: SMP Lockups III -The Search for Stability"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Philippe Troin wrote:
>
> ...
> gcc 2.95 is not supported for kernel compilations.

And it takes 50% longer...

David, the 2.2.x driver for 3c905 has some dubious SMP handling and does
a __global_save_flags()/__global_cli()/__global_restore_flags() for each
Tx packet (slow).

Not sure about the 21140 driver.

I suggest that you drop some different NICs into that box for a while.
If you do, pleeeze tell me the outcome.

Was the unrecoverable network stall on both interfaces?

-- 
-akpm-
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/

• Next message: Andrew Morton: "Re: [patch] repost of netfilter/NIPQUAD patches"
• Previous message: sara@procsys.com: "Re: is (rscsi_disks[i].sector_size != 512) ok ?"
• In reply to: Philippe Troin: "Re: SMP Lockups III -The Search for Stability"
• Next in thread: Philippe Troin: "Re: SMP Lockups III -The Search for Stability"
• Reply: Philippe Troin: "Re: SMP Lockups III -The Search for Stability"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This archive was generated by hypermail 2b29 : Sat Apr 15 2000 - 21:00:24 EST