From: Liang Li <liang.z.li@intel.com> To: qemu-devel@nongnu.org Cc: mst@redhat.com, pbonzini@redhat.com, quintela@redhat.com, amit.shah@redhat.com, kvm@vger.kernel.org, dgilbert@redhat.com, thuth@redhat.com, virtio-dev@lists.oasis-open.org, dave.hansen@intel.com, Liang Li <liang.z.li@intel.com> Subject: [PATCH qemu v3 6/6] migration: skip free pages during live migration Date: Fri, 21 Oct 2016 14:48:24 +0800 [thread overview] Message-ID: <1477032504-12745-7-git-send-email-liang.z.li@intel.com> (raw) In-Reply-To: <1477032504-12745-1-git-send-email-liang.z.li@intel.com> After sending out the request for free pages, live migration process will start without waiting for the free page bitmap is ready. If the free page bitmap is not ready when doing the 1st migration_bitmap_sync() after ram_save_setup(), the free page bitmap will be ignored, this means the free pages will not be filtered out in this case. The current implementation can not work with post copy, if post copy is enabled, we simply ignore the free pages. Will make it work later. Signed-off-by: Liang Li <liang.z.li@intel.com> --- migration/ram.c | 86 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) diff --git a/migration/ram.c b/migration/ram.c index bc6154f..00ce97e 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -43,6 +43,8 @@ #include "trace.h" #include "exec/ram_addr.h" #include "qemu/rcu_queue.h" +#include "sysemu/balloon.h" +#include "sysemu/kvm.h" #ifdef DEBUG_MIGRATION_RAM #define DPRINTF(fmt, ...) \ @@ -228,6 +230,8 @@ static QemuMutex migration_bitmap_mutex; static uint64_t migration_dirty_pages; static uint32_t last_version; static bool ram_bulk_stage; +static bool ignore_freepage_rsp; +static uint64_t free_page_req_id; /* used by the search for pages to send */ struct PageSearchStatus { @@ -244,6 +248,7 @@ static struct BitmapRcu { struct rcu_head rcu; /* Main migration bitmap */ unsigned long *bmap; + unsigned long *free_page_bmap; /* bitmap of pages that haven't been sent even once * only maintained and used in postcopy at the moment * where it's used to send the dirtymap at the start @@ -636,6 +641,7 @@ static void migration_bitmap_sync(void) rcu_read_unlock(); qemu_mutex_unlock(&migration_bitmap_mutex); + ignore_freepage_rsp = true; trace_migration_bitmap_sync_end(migration_dirty_pages - num_dirty_pages_init); num_dirty_pages_period += migration_dirty_pages - num_dirty_pages_init; @@ -1411,6 +1417,7 @@ static void migration_bitmap_free(struct BitmapRcu *bmap) { g_free(bmap->bmap); g_free(bmap->unsentmap); + g_free(bmap->free_page_bmap); g_free(bmap); } @@ -1481,6 +1488,77 @@ void migration_bitmap_extend(ram_addr_t old, ram_addr_t new) } } +static void filter_out_guest_free_page(unsigned long *free_page_bmap, + long nbits) +{ + long i, page_count = 0, len; + unsigned long *bitmap; + + tighten_guest_free_page_bmap(free_page_bmap); + qemu_mutex_lock(&migration_bitmap_mutex); + bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap; + slow_bitmap_complement(bitmap, free_page_bmap, nbits); + + len = (last_ram_offset() >> TARGET_PAGE_BITS) / BITS_PER_LONG; + for (i = 0; i < len; i++) { + page_count += hweight_long(bitmap[i]); + } + + migration_dirty_pages = page_count; + qemu_mutex_unlock(&migration_bitmap_mutex); +} + +static void ram_request_free_page(unsigned long *bmap, unsigned long max_pfn) +{ + BalloonReqStatus status; + + free_page_req_id++; + status = balloon_get_free_pages(bmap, max_pfn / BITS_PER_BYTE, + free_page_req_id); + if (status == REQ_START) { + ignore_freepage_rsp = false; + } +} + +static void ram_handle_free_page(void) +{ + unsigned long nbits, req_id = 0; + RAMBlock *pc_ram_block; + BalloonReqStatus status; + + status = balloon_free_page_ready(&req_id); + switch (status) { + case REQ_DONE: + if (req_id != free_page_req_id) { + return; + } + rcu_read_lock(); + pc_ram_block = QLIST_FIRST_RCU(&ram_list.blocks); + nbits = pc_ram_block->used_length >> TARGET_PAGE_BITS; + filter_out_guest_free_page(migration_bitmap_rcu->free_page_bmap, nbits); + rcu_read_unlock(); + + qemu_mutex_lock_iothread(); + migration_bitmap_sync(); + qemu_mutex_unlock_iothread(); + /* + * bulk stage assumes in (migration_bitmap_find_and_reset_dirty) that + * every page is dirty, that's no longer ture at this point. + */ + ram_bulk_stage = false; + last_seen_block = NULL; + last_sent_block = NULL; + last_offset = 0; + break; + case REQ_ERROR: + ignore_freepage_rsp = true; + error_report("failed to get free page"); + break; + default: + break; + } +} + /* * 'expected' is the value you expect the bitmap mostly to be full * of; it won't bother printing lines that are all this value. @@ -1946,6 +2024,11 @@ static int ram_save_setup(QEMUFile *f, void *opaque) qemu_mutex_unlock_ramlist(); qemu_mutex_unlock_iothread(); + if (balloon_free_pages_support() && !migrate_postcopy_ram()) { + unsigned long max_pfn = get_guest_max_pfn(); + migration_bitmap_rcu->free_page_bmap = bitmap_new(max_pfn); + ram_request_free_page(migration_bitmap_rcu->free_page_bmap, max_pfn); + } qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE); QLIST_FOREACH_RCU(block, &ram_list.blocks, next) { @@ -1986,6 +2069,9 @@ static int ram_save_iterate(QEMUFile *f, void *opaque) while ((ret = qemu_file_rate_limit(f)) == 0) { int pages; + if (!ignore_freepage_rsp) { + ram_handle_free_page(); + } pages = ram_find_and_save_block(f, false, &bytes_transferred); /* no more pages to sent */ if (pages == 0) { -- 1.8.3.1
WARNING: multiple messages have this Message-ID (diff)
From: Liang Li <liang.z.li@intel.com> To: qemu-devel@nongnu.org Cc: mst@redhat.com, pbonzini@redhat.com, quintela@redhat.com, amit.shah@redhat.com, kvm@vger.kernel.org, dgilbert@redhat.com, thuth@redhat.com, virtio-dev@lists.oasis-open.org, dave.hansen@intel.com, Liang Li <liang.z.li@intel.com> Subject: [Qemu-devel] [PATCH qemu v3 6/6] migration: skip free pages during live migration Date: Fri, 21 Oct 2016 14:48:24 +0800 [thread overview] Message-ID: <1477032504-12745-7-git-send-email-liang.z.li@intel.com> (raw) In-Reply-To: <1477032504-12745-1-git-send-email-liang.z.li@intel.com> After sending out the request for free pages, live migration process will start without waiting for the free page bitmap is ready. If the free page bitmap is not ready when doing the 1st migration_bitmap_sync() after ram_save_setup(), the free page bitmap will be ignored, this means the free pages will not be filtered out in this case. The current implementation can not work with post copy, if post copy is enabled, we simply ignore the free pages. Will make it work later. Signed-off-by: Liang Li <liang.z.li@intel.com> --- migration/ram.c | 86 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) diff --git a/migration/ram.c b/migration/ram.c index bc6154f..00ce97e 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -43,6 +43,8 @@ #include "trace.h" #include "exec/ram_addr.h" #include "qemu/rcu_queue.h" +#include "sysemu/balloon.h" +#include "sysemu/kvm.h" #ifdef DEBUG_MIGRATION_RAM #define DPRINTF(fmt, ...) \ @@ -228,6 +230,8 @@ static QemuMutex migration_bitmap_mutex; static uint64_t migration_dirty_pages; static uint32_t last_version; static bool ram_bulk_stage; +static bool ignore_freepage_rsp; +static uint64_t free_page_req_id; /* used by the search for pages to send */ struct PageSearchStatus { @@ -244,6 +248,7 @@ static struct BitmapRcu { struct rcu_head rcu; /* Main migration bitmap */ unsigned long *bmap; + unsigned long *free_page_bmap; /* bitmap of pages that haven't been sent even once * only maintained and used in postcopy at the moment * where it's used to send the dirtymap at the start @@ -636,6 +641,7 @@ static void migration_bitmap_sync(void) rcu_read_unlock(); qemu_mutex_unlock(&migration_bitmap_mutex); + ignore_freepage_rsp = true; trace_migration_bitmap_sync_end(migration_dirty_pages - num_dirty_pages_init); num_dirty_pages_period += migration_dirty_pages - num_dirty_pages_init; @@ -1411,6 +1417,7 @@ static void migration_bitmap_free(struct BitmapRcu *bmap) { g_free(bmap->bmap); g_free(bmap->unsentmap); + g_free(bmap->free_page_bmap); g_free(bmap); } @@ -1481,6 +1488,77 @@ void migration_bitmap_extend(ram_addr_t old, ram_addr_t new) } } +static void filter_out_guest_free_page(unsigned long *free_page_bmap, + long nbits) +{ + long i, page_count = 0, len; + unsigned long *bitmap; + + tighten_guest_free_page_bmap(free_page_bmap); + qemu_mutex_lock(&migration_bitmap_mutex); + bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap; + slow_bitmap_complement(bitmap, free_page_bmap, nbits); + + len = (last_ram_offset() >> TARGET_PAGE_BITS) / BITS_PER_LONG; + for (i = 0; i < len; i++) { + page_count += hweight_long(bitmap[i]); + } + + migration_dirty_pages = page_count; + qemu_mutex_unlock(&migration_bitmap_mutex); +} + +static void ram_request_free_page(unsigned long *bmap, unsigned long max_pfn) +{ + BalloonReqStatus status; + + free_page_req_id++; + status = balloon_get_free_pages(bmap, max_pfn / BITS_PER_BYTE, + free_page_req_id); + if (status == REQ_START) { + ignore_freepage_rsp = false; + } +} + +static void ram_handle_free_page(void) +{ + unsigned long nbits, req_id = 0; + RAMBlock *pc_ram_block; + BalloonReqStatus status; + + status = balloon_free_page_ready(&req_id); + switch (status) { + case REQ_DONE: + if (req_id != free_page_req_id) { + return; + } + rcu_read_lock(); + pc_ram_block = QLIST_FIRST_RCU(&ram_list.blocks); + nbits = pc_ram_block->used_length >> TARGET_PAGE_BITS; + filter_out_guest_free_page(migration_bitmap_rcu->free_page_bmap, nbits); + rcu_read_unlock(); + + qemu_mutex_lock_iothread(); + migration_bitmap_sync(); + qemu_mutex_unlock_iothread(); + /* + * bulk stage assumes in (migration_bitmap_find_and_reset_dirty) that + * every page is dirty, that's no longer ture at this point. + */ + ram_bulk_stage = false; + last_seen_block = NULL; + last_sent_block = NULL; + last_offset = 0; + break; + case REQ_ERROR: + ignore_freepage_rsp = true; + error_report("failed to get free page"); + break; + default: + break; + } +} + /* * 'expected' is the value you expect the bitmap mostly to be full * of; it won't bother printing lines that are all this value. @@ -1946,6 +2024,11 @@ static int ram_save_setup(QEMUFile *f, void *opaque) qemu_mutex_unlock_ramlist(); qemu_mutex_unlock_iothread(); + if (balloon_free_pages_support() && !migrate_postcopy_ram()) { + unsigned long max_pfn = get_guest_max_pfn(); + migration_bitmap_rcu->free_page_bmap = bitmap_new(max_pfn); + ram_request_free_page(migration_bitmap_rcu->free_page_bmap, max_pfn); + } qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE); QLIST_FOREACH_RCU(block, &ram_list.blocks, next) { @@ -1986,6 +2069,9 @@ static int ram_save_iterate(QEMUFile *f, void *opaque) while ((ret = qemu_file_rate_limit(f)) == 0) { int pages; + if (!ignore_freepage_rsp) { + ram_handle_free_page(); + } pages = ram_find_and_save_block(f, false, &bytes_transferred); /* no more pages to sent */ if (pages == 0) { -- 1.8.3.1
next prev parent reply other threads:[~2016-10-21 6:48 UTC|newest] Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top 2016-10-21 6:48 [PATCH qemu v3 0/6] Fast (de)inflating & fast live migration Liang Li 2016-10-21 6:48 ` [Qemu-devel] " Liang Li 2016-10-21 6:48 ` [PATCH qemu v3 1/6] virtio-balloon: update linux head file Liang Li 2016-10-21 6:48 ` [Qemu-devel] " Liang Li 2016-10-21 6:48 ` [PATCH qemu v3 2/6] virtio-balloon: speed up inflating & deflating process Liang Li 2016-10-21 6:48 ` [Qemu-devel] " Liang Li 2016-10-21 6:48 ` [PATCH qemu v3 3/6] balloon: get free page info from guest Liang Li 2016-10-21 6:48 ` [Qemu-devel] " Liang Li 2016-10-21 6:48 ` [PATCH qemu v3 4/6] bitmap: Add a new bitmap_move function Liang Li 2016-10-21 6:48 ` [Qemu-devel] " Liang Li 2016-10-21 6:48 ` [PATCH qemu v3 5/6] kvm: Add two new arch specific functions Liang Li 2016-10-21 6:48 ` [Qemu-devel] " Liang Li 2016-10-21 6:48 ` Liang Li [this message] 2016-10-21 6:48 ` [Qemu-devel] [PATCH qemu v3 6/6] migration: skip free pages during live migration Liang Li 2016-10-21 7:19 ` [Qemu-devel] [PATCH qemu v3 0/6] Fast (de)inflating & fast " no-reply 2016-10-21 7:19 ` no-reply 2016-10-21 7:22 ` no-reply 2016-10-21 7:22 ` no-reply 2016-10-30 22:05 ` Michael S. Tsirkin 2016-10-30 22:05 ` [Qemu-devel] " Michael S. Tsirkin
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=1477032504-12745-7-git-send-email-liang.z.li@intel.com \ --to=liang.z.li@intel.com \ --cc=amit.shah@redhat.com \ --cc=dave.hansen@intel.com \ --cc=dgilbert@redhat.com \ --cc=kvm@vger.kernel.org \ --cc=mst@redhat.com \ --cc=pbonzini@redhat.com \ --cc=qemu-devel@nongnu.org \ --cc=quintela@redhat.com \ --cc=thuth@redhat.com \ --cc=virtio-dev@lists.oasis-open.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.