We are running some database runs which overcommit memory. One of the
things I've noticed is that, with mulitple swap volumes, it does NOT spread
the load, but fills up the first swap volume, then the second and so forth.

The result during heavy paging is then a bottleneck against the fullest
device and the other devices are idle.

Shouldn't the paging algorithm spread the I/O across all of the swap
devices available to balance the load?

Regards, Jim
Linux S/390-zSeries Support, SEEL, IBM Silicon Valley Labs
t/l 543-4021, 408-463-4021, [EMAIL PROTECTED]
*** Grace Happens ***

Reply via email to