| Message ID | 1615525383-59071-9-git-send-email-lei.rao@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Fixed some bugs and optimized some codes for COLO. | expand |
On 3/12/21 1:03 PM, leirao wrote: > From: "Rao, Lei" <lei.rao@intel.com> > > When flushing memory from ram cache to ram during every checkpoint > on secondary VM, we can copy continuous chunks of memory instead of > 4096 bytes per time to reduce the time of VM stop during checkpoint. > > Signed-off-by: Lei Rao <lei.rao@intel.com> > --- > migration/ram.c | 44 +++++++++++++++++++++++++++++++++++++++++--- > 1 file changed, 41 insertions(+), 3 deletions(-) > > diff --git a/migration/ram.c b/migration/ram.c > index e795a8d..b269637 100644 > --- a/migration/ram.c > +++ b/migration/ram.c > @@ -823,6 +823,39 @@ unsigned long migration_bitmap_find_dirty(RAMState *rs, RAMBlock *rb, > return next; > } > > +/* > + * colo_bitmap_find_diry:find contiguous dirty pages from start > + * > + * Returns the page offset within memory region of the start of the contiguout > + * dirty page > + * > + * @rs: current RAM state > + * @rb: RAMBlock where to search for dirty pages > + * @start: page where we start the search > + * @num: the number of contiguous dirty pages > + */ > +static inline > +unsigned long colo_bitmap_find_dirty(RAMState *rs, RAMBlock *rb, > + unsigned long start, unsigned long *num) > +{ > + unsigned long size = rb->used_length >> TARGET_PAGE_BITS; > + unsigned long *bitmap = rb->bmap; > + unsigned long first, next; > + > + if (ramblock_is_ignored(rb)) { > + return size; > + } > + > + first = find_next_bit(bitmap, size, start); > + if (first >= size) { > + return first; > + } > + next = find_next_zero_bit(bitmap, size, first + 1); > + assert(next >= first); > + *num = next - first; > + return first; The idea is outstanding i wonder it should return (next - 1) ? Thanks Zhijian > +} > + > static inline bool migration_bitmap_clear_dirty(RAMState *rs, > RAMBlock *rb, > unsigned long page) > @@ -3669,6 +3702,8 @@ void colo_flush_ram_cache(void) > void *dst_host; > void *src_host; > unsigned long offset = 0; > + unsigned long num = 0; > + unsigned long i = 0; > > memory_global_dirty_log_sync(); > WITH_RCU_READ_LOCK_GUARD() { > @@ -3682,19 +3717,22 @@ void colo_flush_ram_cache(void) > block = QLIST_FIRST_RCU(&ram_list.blocks); > > while (block) { > - offset = migration_bitmap_find_dirty(ram_state, block, offset); > + offset = colo_bitmap_find_dirty(ram_state, block, offset, &num); > > if (((ram_addr_t)offset) << TARGET_PAGE_BITS > >= block->used_length) { > offset = 0; > + num = 0; > block = QLIST_NEXT_RCU(block, next); > } else { > - migration_bitmap_clear_dirty(ram_state, block, offset); > + for (i = 0; i < num; i++) { > + migration_bitmap_clear_dirty(ram_state, block, offset + i); > + } > dst_host = block->host > + (((ram_addr_t)offset) << TARGET_PAGE_BITS); > src_host = block->colo_cache > + (((ram_addr_t)offset) << TARGET_PAGE_BITS); > - memcpy(dst_host, src_host, TARGET_PAGE_SIZE); > + memcpy(dst_host, src_host, TARGET_PAGE_SIZE * num); > } > } > }
I think it's enough to know the start and the number of dirty pages in the bitmap. Because the size of consecutive dirty pages can be calculated. By the way, no problems were found in our automated testing. Thanks, Lei. -----Original Message----- From: lizhijian@fujitsu.com <lizhijian@fujitsu.com> Sent: Friday, March 12, 2021 3:54 PM To: Rao, Lei <lei.rao@intel.com>; Zhang, Chen <chen.zhang@intel.com>; jasowang@redhat.com; quintela@redhat.com; dgilbert@redhat.com; pbonzini@redhat.com; lukasstraub2@web.de Cc: qemu-devel@nongnu.org Subject: Re: [PATCH v2 08/10] Reduce the PVM stop time during Checkpoint On 3/12/21 1:03 PM, leirao wrote: > From: "Rao, Lei" <lei.rao@intel.com> > > When flushing memory from ram cache to ram during every checkpoint on > secondary VM, we can copy continuous chunks of memory instead of > 4096 bytes per time to reduce the time of VM stop during checkpoint. > > Signed-off-by: Lei Rao <lei.rao@intel.com> > --- > migration/ram.c | 44 +++++++++++++++++++++++++++++++++++++++++--- > 1 file changed, 41 insertions(+), 3 deletions(-) > > diff --git a/migration/ram.c b/migration/ram.c index e795a8d..b269637 > 100644 > --- a/migration/ram.c > +++ b/migration/ram.c > @@ -823,6 +823,39 @@ unsigned long migration_bitmap_find_dirty(RAMState *rs, RAMBlock *rb, > return next; > } > > +/* > + * colo_bitmap_find_diry:find contiguous dirty pages from start > + * > + * Returns the page offset within memory region of the start of the > +contiguout > + * dirty page > + * > + * @rs: current RAM state > + * @rb: RAMBlock where to search for dirty pages > + * @start: page where we start the search > + * @num: the number of contiguous dirty pages */ static inline > +unsigned long colo_bitmap_find_dirty(RAMState *rs, RAMBlock *rb, > + unsigned long start, unsigned > +long *num) { > + unsigned long size = rb->used_length >> TARGET_PAGE_BITS; > + unsigned long *bitmap = rb->bmap; > + unsigned long first, next; > + > + if (ramblock_is_ignored(rb)) { > + return size; > + } > + > + first = find_next_bit(bitmap, size, start); > + if (first >= size) { > + return first; > + } > + next = find_next_zero_bit(bitmap, size, first + 1); > + assert(next >= first); > + *num = next - first; > + return first; The idea is outstanding i wonder it should return (next - 1) ? Thanks Zhijian > +} > + > static inline bool migration_bitmap_clear_dirty(RAMState *rs, > RAMBlock *rb, > unsigned long page) > @@ -3669,6 +3702,8 @@ void colo_flush_ram_cache(void) > void *dst_host; > void *src_host; > unsigned long offset = 0; > + unsigned long num = 0; > + unsigned long i = 0; > > memory_global_dirty_log_sync(); > WITH_RCU_READ_LOCK_GUARD() { > @@ -3682,19 +3717,22 @@ void colo_flush_ram_cache(void) > block = QLIST_FIRST_RCU(&ram_list.blocks); > > while (block) { > - offset = migration_bitmap_find_dirty(ram_state, block, offset); > + offset = colo_bitmap_find_dirty(ram_state, block, offset, > + &num); > > if (((ram_addr_t)offset) << TARGET_PAGE_BITS > >= block->used_length) { > offset = 0; > + num = 0; > block = QLIST_NEXT_RCU(block, next); > } else { > - migration_bitmap_clear_dirty(ram_state, block, offset); > + for (i = 0; i < num; i++) { > + migration_bitmap_clear_dirty(ram_state, block, offset + i); > + } > dst_host = block->host > + (((ram_addr_t)offset) << TARGET_PAGE_BITS); > src_host = block->colo_cache > + (((ram_addr_t)offset) << TARGET_PAGE_BITS); > - memcpy(dst_host, src_host, TARGET_PAGE_SIZE); > + memcpy(dst_host, src_host, TARGET_PAGE_SIZE * num); > } > } > }
diff --git a/migration/ram.c b/migration/ram.c index e795a8d..b269637 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -823,6 +823,39 @@ unsigned long migration_bitmap_find_dirty(RAMState *rs, RAMBlock *rb, return next; } +/* + * colo_bitmap_find_diry:find contiguous dirty pages from start + * + * Returns the page offset within memory region of the start of the contiguout + * dirty page + * + * @rs: current RAM state + * @rb: RAMBlock where to search for dirty pages + * @start: page where we start the search + * @num: the number of contiguous dirty pages + */ +static inline +unsigned long colo_bitmap_find_dirty(RAMState *rs, RAMBlock *rb, + unsigned long start, unsigned long *num) +{ + unsigned long size = rb->used_length >> TARGET_PAGE_BITS; + unsigned long *bitmap = rb->bmap; + unsigned long first, next; + + if (ramblock_is_ignored(rb)) { + return size; + } + + first = find_next_bit(bitmap, size, start); + if (first >= size) { + return first; + } + next = find_next_zero_bit(bitmap, size, first + 1); + assert(next >= first); + *num = next - first; + return first; +} + static inline bool migration_bitmap_clear_dirty(RAMState *rs, RAMBlock *rb, unsigned long page) @@ -3669,6 +3702,8 @@ void colo_flush_ram_cache(void) void *dst_host; void *src_host; unsigned long offset = 0; + unsigned long num = 0; + unsigned long i = 0; memory_global_dirty_log_sync(); WITH_RCU_READ_LOCK_GUARD() { @@ -3682,19 +3717,22 @@ void colo_flush_ram_cache(void) block = QLIST_FIRST_RCU(&ram_list.blocks); while (block) { - offset = migration_bitmap_find_dirty(ram_state, block, offset); + offset = colo_bitmap_find_dirty(ram_state, block, offset, &num); if (((ram_addr_t)offset) << TARGET_PAGE_BITS >= block->used_length) { offset = 0; + num = 0; block = QLIST_NEXT_RCU(block, next); } else { - migration_bitmap_clear_dirty(ram_state, block, offset); + for (i = 0; i < num; i++) { + migration_bitmap_clear_dirty(ram_state, block, offset + i); + } dst_host = block->host + (((ram_addr_t)offset) << TARGET_PAGE_BITS); src_host = block->colo_cache + (((ram_addr_t)offset) << TARGET_PAGE_BITS); - memcpy(dst_host, src_host, TARGET_PAGE_SIZE); + memcpy(dst_host, src_host, TARGET_PAGE_SIZE * num); } } }