From 60d9222c8f50c3e5dd3df9ee84ddd1d1c4b35389 Mon Sep 17 00:00:00 2001 From: "Michael R. Hines" Date: Tue, 25 Jun 2013 21:35:36 -0400 Subject: rdma: introduce capability x-rdma-pin-all This capability allows you to disable dynamic chunk registration for better throughput on high-performance links. For example, using an 8GB RAM virtual machine with all 8GB of memory in active use and the VM itself is completely idle using a 40 gbps infiniband link: 1. x-rdma-pin-all disabled total time: approximately 7.5 seconds @ 9.5 Gbps 2. x-rdma-pin-all enabled total time: approximately 4 seconds @ 26 Gbps These numbers would of course scale up to whatever size virtual machine you have to migrate using RDMA. Enabling this feature does *not* have any measurable affect on migration *downtime*. This is because, without this feature, all of the memory will have already been registered already in advance during the bulk round and does not need to be re-registered during the successive iteration rounds. Reviewed-by: Juan Quintela Reviewed-by: Paolo Bonzini Reviewed-by: Chegu Vinod Reviewed-by: Eric Blake Tested-by: Chegu Vinod Tested-by: Michael R. Hines Signed-off-by: Michael R. Hines Signed-off-by: Juan Quintela --- include/migration/migration.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/migration/migration.h') diff --git a/include/migration/migration.h b/include/migration/migration.h index 3ddd64ffcb..f0640e0eec 100644 --- a/include/migration/migration.h +++ b/include/migration/migration.h @@ -123,6 +123,8 @@ void migrate_add_blocker(Error *reason); */ void migrate_del_blocker(Error *reason); +bool migrate_rdma_pin_all(void); + int xbzrle_encode_buffer(uint8_t *old_buf, uint8_t *new_buf, int slen, uint8_t *dst, int dlen); int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen); -- cgit v1.2.3