2012/2/28 Steve French <[email protected]>: > I got a chance to look through this patch set in more detail on the way > to the SMB2.2 test event. I liked many of the patches, but this one > seems to complicate, rather than simplify by adding a spinlock > to what used to be an atomic_inc. There is also a possibility that this > spinlock will become hot. I don't mind moving the atomic_inc inside the > new dec_in_flight macro though to make it easier in the future. >
I tested the performance with and without this patch with dbench 3. The variant with the patch is slightly worse (~1%). So, seems no problem with this approach because we need to spinlock echo/oplock specific variables anyway further. -- Best regards, Pavel Shilovsky. -- To unsubscribe from this list: send the line "unsubscribe linux-cifs" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
