From 5ef7e26bdb7eda10d6d5e1b77121be9945e5e550 Mon Sep 17 00:00:00 2001 From: Yuan Liu Date: Mon, 1 Apr 2024 23:41:10 +0800 Subject: [PATCH] migration/multifd: solve zero page causing multiple page faults Implemented recvbitmap tracking of received pages in multifd. If the zero page appears for the first time in the recvbitmap, this page is not checked and set. If the zero page has already appeared in the recvbitmap, there is no need to check the data but directly set the data to 0, because it is unlikely that the zero page will be migrated multiple times. Signed-off-by: Yuan Liu Reviewed-by: Fabiano Rosas Link: https://lore.kernel.org/r/20240401154110.2028453-2-yuan1.liu@intel.com [peterx: touch up the comment, as the bitmap is used outside postcopy now] Signed-off-by: Peter Xu --- include/exec/ramblock.h | 2 +- migration/multifd-zero-page.c | 4 +++- migration/multifd-zlib.c | 1 + migration/multifd-zstd.c | 1 + migration/multifd.c | 1 + migration/ram.c | 4 ++++ migration/ram.h | 1 + 7 files changed, 12 insertions(+), 2 deletions(-) diff --git a/include/exec/ramblock.h b/include/exec/ramblock.h index 848915ea5bf..7062da380b7 100644 --- a/include/exec/ramblock.h +++ b/include/exec/ramblock.h @@ -57,7 +57,7 @@ struct RAMBlock { off_t bitmap_offset; uint64_t pages_offset; - /* bitmap of already received pages in postcopy */ + /* Bitmap of already received pages. Only used on destination side. */ unsigned long *receivedmap; /* diff --git a/migration/multifd-zero-page.c b/migration/multifd-zero-page.c index 1ba38be6361..e1b8370f88e 100644 --- a/migration/multifd-zero-page.c +++ b/migration/multifd-zero-page.c @@ -80,8 +80,10 @@ void multifd_recv_zero_page_process(MultiFDRecvParams *p) { for (int i = 0; i < p->zero_num; i++) { void *page = p->host + p->zero[i]; - if (!buffer_is_zero(page, p->page_size)) { + if (ramblock_recv_bitmap_test_byte_offset(p->block, p->zero[i])) { memset(page, 0, p->page_size); + } else { + ramblock_recv_bitmap_set_offset(p->block, p->zero[i]); } } } diff --git a/migration/multifd-zlib.c b/migration/multifd-zlib.c index 99821cd4d5e..737a9645d2f 100644 --- a/migration/multifd-zlib.c +++ b/migration/multifd-zlib.c @@ -284,6 +284,7 @@ static int zlib_recv(MultiFDRecvParams *p, Error **errp) int flush = Z_NO_FLUSH; unsigned long start = zs->total_out; + ramblock_recv_bitmap_set_offset(p->block, p->normal[i]); if (i == p->normal_num - 1) { flush = Z_SYNC_FLUSH; } diff --git a/migration/multifd-zstd.c b/migration/multifd-zstd.c index 02112255adc..256858df0a0 100644 --- a/migration/multifd-zstd.c +++ b/migration/multifd-zstd.c @@ -278,6 +278,7 @@ static int zstd_recv(MultiFDRecvParams *p, Error **errp) z->in.pos = 0; for (i = 0; i < p->normal_num; i++) { + ramblock_recv_bitmap_set_offset(p->block, p->normal[i]); z->out.dst = p->host + p->normal[i]; z->out.size = p->page_size; z->out.pos = 0; diff --git a/migration/multifd.c b/migration/multifd.c index 2802afe79d0..f317bff0774 100644 --- a/migration/multifd.c +++ b/migration/multifd.c @@ -277,6 +277,7 @@ static int nocomp_recv(MultiFDRecvParams *p, Error **errp) for (int i = 0; i < p->normal_num; i++) { p->iov[i].iov_base = p->host + p->normal[i]; p->iov[i].iov_len = p->page_size; + ramblock_recv_bitmap_set_offset(p->block, p->normal[i]); } return qio_channel_readv_all(p->c, p->iov, p->normal_num, errp); } diff --git a/migration/ram.c b/migration/ram.c index daffcd82d4f..a975c5af16f 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -275,6 +275,10 @@ void ramblock_recv_bitmap_set_range(RAMBlock *rb, void *host_addr, nr); } +void ramblock_recv_bitmap_set_offset(RAMBlock *rb, uint64_t byte_offset) +{ + set_bit_atomic(byte_offset >> TARGET_PAGE_BITS, rb->receivedmap); +} #define RAMBLOCK_RECV_BITMAP_ENDING (0x0123456789abcdefULL) /* diff --git a/migration/ram.h b/migration/ram.h index 08feecaf516..bc0318b8346 100644 --- a/migration/ram.h +++ b/migration/ram.h @@ -69,6 +69,7 @@ int ramblock_recv_bitmap_test(RAMBlock *rb, void *host_addr); bool ramblock_recv_bitmap_test_byte_offset(RAMBlock *rb, uint64_t byte_offset); void ramblock_recv_bitmap_set(RAMBlock *rb, void *host_addr); void ramblock_recv_bitmap_set_range(RAMBlock *rb, void *host_addr, size_t nr); +void ramblock_recv_bitmap_set_offset(RAMBlock *rb, uint64_t byte_offset); int64_t ramblock_recv_bitmap_send(QEMUFile *file, const char *block_name); bool ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *rb, Error **errp); -- 2.39.5