search for: blkif_req

All the resources allocated based on xen_blkif_reqs are global in blkback. While (without having measured anything) I think that this is bad from a QoS perspective (not the least implied from a warning issued by Citrix''es multi-page-ring patches: if (blkif_reqs < BLK_RING_SIZE(order)) printk(KERN_WARNING "WARNING: "...

.../drivers/xen/blktap/blktap.c 2007-10-19 17:17:15.000000000 +0200 +++ head-2007-10-15/drivers/xen/blktap/blktap.c 2007-06-22 09:21:11.000000000 +0200 @@ -116,13 +116,7 @@ typedef struct tap_blkif { static struct tap_blkif *tapfds[MAX_TAP_DEV]; static int blktap_next_minor; -static int __init set_blkif_reqs(char *str) -{ - get_option(&str, &blkif_reqs); - return 1; -} -__setup("blkif_reqs=", set_blkif_reqs); - +module_param(blkif_reqs, int, 0); /* Run-time switchable: /sys/module/blktap/parameters/ */ static unsigned int log_stats = 0; static unsigned int debug_lvl = 0; _____...

Hi, Here is the refreshed version of the multi-page ring patch for blkfront and blkback. I currently don''t have time to refresh the blktap part of the patch. The patch should apply cleanly to the following changeset in the linux 2.6.18 tree: changeset: 752:0b859c9516ba tag: qparent parent: 751:6591b4869889 parent: 748:5012c470f875 user: Keir Fraser

...uct page **pages; }; #define BLKBACK_INVALID_HANDLE (~0) @@ -123,28 +133,9 @@ static inline unsigned long vaddr(struct pending_req *req, int seg) static int do_block_io_op(struct xen_blkif *blkif); static int dispatch_rw_block_io(struct xen_blkif *blkif, - struct blkif_request *req, struct pending_req *pending_req); static void make_response(struct xen_blkif *blkif, u64 id, - unsigned short op, int st); - -/* - * Retrieve from the ''pending_reqs'' a free pending_req structure to be used. - */ -static struct pending_...