[Beowulf] 1.2 us IB latency?
patrick at myri.com
Thu Apr 19 15:47:01 PDT 2007
greg.lindahl at qlogic.com wrote:
>> Back then we were struggling with PIO transfers and how they were
>> treated in the CPU/North bridge (write combining and all that). I
>> believe this might still be an issue, correct ?
WC is well implemented on Opteron, it will aggregate consecutive PIO
writes at 16, 32 and 64 Bytes smoothly. On Intel processors, this is
more painful: WC is only 64 Bytes. If you flush the WC buffer with less
than 64 bytes in it, you will see multiple 8-byte PIO writes, and not
always in order.
> cases we can manipulate the mtrrs after boot to fix this. Getting
> formal support for PAT in the Linux kernel is the long-term fix for
It's interesting to note that most current OSes have native PAT support,
except Linux. Even Windows does it well :-)
More information about the Beowulf