IB/iser: Rewrite bounce buffer code path

Browse source

In some rare cases, IO operations may be not aligned to page
boundaries. This prevents iser from performing fast memory
registration. In order to overcome that iser uses a bounce
buffer to carry the transaction. We basically allocate a buffer
in the size of the transaction and perform a copy.

The buffer allocation using kmalloc is too restrictive since it
requires higher order (atomic) allocations for large transactions
(which may result in memory exhaustion fairly fast for some workloads).
We rewrite the bounce buffer code path to allocate scattered pages
and perform a copy between the transaction sg and the bounce sg.

Reported-by: Alex Lyakas <alex@zadarastorage.com>
Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

...

This commit is contained in:

Sagi Grimberg 2015-04-14 18:08:28 +03:00 • committed by Doug Ledford

parent 4fcd1470a0

commit ba943fb237

3 changed files with 137 additions and 88 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

8

drivers/infiniband/ulp/iser/iscsi_iser.h

View file

8

drivers/infiniband/ulp/iser/iser_initiator.c

View file

207

drivers/infiniband/ulp/iser/iser_memory.c

View file