Il 11/03/2013 05:33, michael.r.hines.mrhi...@linux.vnet.ibm.com ha scritto:
> From: "Michael R. Hines" <mrhi...@us.ibm.com>
>
> For performance reasons, dup_page() and xbzrle() is skipped because
> they are too expensive for zero-copy RDMA.
>
> Signed-off-by: Michael R. Hines <mrhi...@us.ibm.com>
> ---
> arch_init.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
> 1 file changed, 56 insertions(+), 1 deletion(-)
>
> diff --git a/arch_init.c b/arch_init.c
> index 8daeafa..437cb47 100644
> --- a/arch_init.c
> +++ b/arch_init.c
> @@ -45,6 +45,7 @@
> #include "exec/address-spaces.h"
> #include "hw/pcspk.h"
> #include "migration/page_cache.h"
> +#include "migration/rdma.h"
> #include "qemu/config-file.h"
> #include "qmp-commands.h"
> #include "trace.h"
> @@ -245,6 +246,18 @@ uint64_t norm_mig_pages_transferred(void)
> return acct_info.norm_pages;
> }
>
> +/*
> + * RDMA does not use the buffered_file,
> + * but we still need a way to do accounting...
> + */
> +uint64_t delta_norm_mig_bytes_transferred(void)
> +{
> + static uint64_t last_norm_pages = 0;
> + uint64_t delta_bytes = (acct_info.norm_pages - last_norm_pages) *
> TARGET_PAGE_SIZE;
> + last_norm_pages = acct_info.norm_pages;
> + return delta_bytes;
> +}
> +
> uint64_t xbzrle_mig_bytes_transferred(void)
> {
> return acct_info.xbzrle_bytes;
> @@ -282,6 +295,45 @@ static size_t save_block_hdr(QEMUFile *f, RAMBlock
> *block, ram_addr_t offset,
> return size;
> }
>
> +static size_t save_rdma_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
> + int cont)
> +{
> + int ret;
> + size_t bytes_sent = 0;
> + ram_addr_t current_addr;
> + RDMAData * rdma = &migrate_get_current()->rdma;
> +
> + acct_info.norm_pages++;
> +
> + /*
> + * use RDMA to send page
> + */
Not quite true, the page is added to the current chunk. Please make the
comments a quick-and-dirty reference of the protocol, or leave them out
altogether.
> + current_addr = block->offset + offset;
> + if ((ret = qemu_rdma_write(rdma, current_addr, TARGET_PAGE_SIZE)) < 0) {
> + fprintf(stderr, "rdma migration: write error! %d\n", ret);
> + qemu_file_set_error(f, ret);
> + return ret;
> + }
> +
> + /*
> + * do some polling
> + */
Again, that's quite self-evident. Poll for what though? :)
> + while (1) {
> + int ret = qemu_rdma_poll(rdma);
> + if (ret == RDMA_WRID_NONE) {
> + break;
> + }
> + if (ret < 0) {
> + fprintf(stderr, "rdma migration: polling error! %d\n", ret);
> + qemu_file_set_error(f, ret);
> + return ret;
> + }
> + }
> +
> + bytes_sent += TARGET_PAGE_SIZE;
> + return bytes_sent;
> +}
As written in the other message, I think this should be an additional
QEMUFile operation, hopefully the same that Orit is introducing in her
patches.
> #define ENCODING_FLAG_XBZRLE 0x1
>
> static int save_xbzrle_page(QEMUFile *f, uint8_t *current_data,
> @@ -462,7 +514,10 @@ static int ram_save_block(QEMUFile *f, bool last_stage)
>
> /* In doubt sent page as normal */
> bytes_sent = -1;
> - if (is_dup_page(p)) {
> + if (migrate_use_rdma()) {
> + /* searching for zeros is still too expensive for RDMA */
> + bytes_sent = save_rdma_page(f, block, offset, cont);
Again as written in the other message, this is not really an RDMA thing,
it's mostly the effect of a fast link. Of course to some extent it
depends on the CPU and RAM speed, but we can fake that it isn't.
> + } else if (is_dup_page(p)) {
> acct_info.dup_pages++;
> bytes_sent = save_block_hdr(f, block, offset, cont,
> RAM_SAVE_FLAG_COMPRESS);
>
Thanks,
Paolo
