From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:59428) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1df7Kx-0001RF-Id for qemu-devel@nongnu.org; Tue, 08 Aug 2017 12:26:35 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1df7Kw-0007ST-4I for qemu-devel@nongnu.org; Tue, 08 Aug 2017 12:26:31 -0400 Received: from mx1.redhat.com ([209.132.183.28]:38264) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1df7Kv-0007S9-RU for qemu-devel@nongnu.org; Tue, 08 Aug 2017 12:26:30 -0400 Received: from smtp.corp.redhat.com (int-mx04.intmail.prod.int.phx2.redhat.com [10.5.11.14]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id DE11A267C2 for ; Tue, 8 Aug 2017 16:26:28 +0000 (UTC) From: Juan Quintela Date: Tue, 8 Aug 2017 18:22:24 +0200 Message-Id: <20170808162224.32419-20-quintela@redhat.com> In-Reply-To: <20170808162224.32419-1-quintela@redhat.com> References: <20170808162224.32419-1-quintela@redhat.com> Subject: [Qemu-devel] [PATCH v6 19/19] migration: Flush receive queue List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: dgilbert@redhat.com, lvivier@redhat.com, peterx@redhat.com Each time that we sync the bitmap, it is a possiblity that we receive a page that is being processed by a different thread. We fix this problem just making sure that we wait for all receiving threads to finish its work before we procedeed with the next stage. We are low on page flags, so we use a combination that is not valid to emit that message: MULTIFD_PAGE and COMPRESSED. I tried to make a migration command for it, but it don't work because we sync the bitmap sometimes when we have already sent the beggining of the section, so I just added a new page flag. Signed-off-by: Juan Quintela -- Create RAM_SAVE_FLAG_MULTIFD_SYNC (dave suggestion) Move the set of need_flush to inside the bitmap_sync code (peter suggestion) --- migration/ram.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/migration/ram.c b/migration/ram.c index f337360..ee08fd2 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -71,6 +71,13 @@ #define RAM_SAVE_FLAG_COMPRESS_PAGE 0x100 #define RAM_SAVE_FLAG_MULTIFD_PAGE 0x200 +/* We are getting low on pages flags, so we start using combinations + When we need to flush a page, we sent it as + RAM_SAVE_FLAG_MULTIFD_PAGE | RAM_SAVE_FLAG_COMPRESS_PAGE + We don't allow that combination +*/ +#define RAM_SAVE_FLAG_MULTIFD_SYNC (RAM_SAVE_FLAG_MULTIFD_PAGE | RAM_SAVE_FLAG_ZERO) + static inline bool is_zero_range(uint8_t *p, uint64_t size) { return buffer_is_zero(p, size); @@ -193,6 +200,9 @@ struct RAMState { uint64_t iterations_prev; /* Iterations since start */ uint64_t iterations; + /* Indicates if we have synced the bitmap and we need to assure that + target has processeed all previous pages */ + bool multifd_needs_flush; /* number of dirty bits in the bitmap */ uint64_t migration_dirty_pages; /* protects modification of the bitmap */ @@ -592,9 +602,11 @@ struct MultiFDRecvParams { QIOChannel *c; QemuSemaphore ready; QemuSemaphore sem; + QemuCond cond_sync; QemuMutex mutex; /* proteced by param mutex */ bool quit; + bool sync; multifd_pages_t pages; bool done; }; @@ -640,6 +652,7 @@ void multifd_load_cleanup(void) qemu_thread_join(&p->thread); qemu_mutex_destroy(&p->mutex); qemu_sem_destroy(&p->sem); + qemu_cond_destroy(&p->cond_sync); socket_recv_channel_destroy(p->c); g_free(p); multifd_recv_state->params[i] = NULL; @@ -679,6 +692,10 @@ static void *multifd_recv_thread(void *opaque) return NULL; } p->done = true; + if (p->sync) { + qemu_cond_signal(&p->cond_sync); + p->sync = false; + } qemu_mutex_unlock(&p->mutex); qemu_sem_post(&p->ready); continue; @@ -727,9 +744,11 @@ void multifd_new_channel(QIOChannel *ioc) qemu_mutex_init(&p->mutex); qemu_sem_init(&p->sem, 0); qemu_sem_init(&p->ready, 0); + qemu_cond_init(&p->cond_sync); p->quit = false; p->id = id; p->done = false; + p->sync = false; multifd_init_group(&p->pages); p->c = ioc; atomic_set(&multifd_recv_state->params[id], p); @@ -789,6 +808,27 @@ static void multifd_recv_page(uint8_t *address, uint16_t fd_num) qemu_sem_post(&p->sem); } +static int multifd_flush(void) +{ + int i, thread_count; + + if (!migrate_use_multifd()) { + return 0; + } + thread_count = migrate_multifd_threads(); + for (i = 0; i < thread_count; i++) { + MultiFDRecvParams *p = multifd_recv_state->params[i]; + + qemu_mutex_lock(&p->mutex); + while (!p->done) { + p->sync = true; + qemu_cond_wait(&p->cond_sync, &p->mutex); + } + qemu_mutex_unlock(&p->mutex); + } + return 0; +} + /** * save_page_header: write page header to wire * @@ -806,6 +846,12 @@ static size_t save_page_header(RAMState *rs, QEMUFile *f, RAMBlock *block, { size_t size, len; + if (rs->multifd_needs_flush && + (offset & RAM_SAVE_FLAG_MULTIFD_PAGE)) { + offset |= RAM_SAVE_FLAG_ZERO; + rs->multifd_needs_flush = false; + } + if (block == rs->last_sent_block) { offset |= RAM_SAVE_FLAG_CONTINUE; } @@ -1091,6 +1137,9 @@ static void migration_bitmap_sync(RAMState *rs) if (migrate_use_events()) { qapi_event_send_migration_pass(ram_counters.dirty_sync_count, NULL); } + if (!rs->ram_bulk_stage && migrate_use_multifd()) { + rs->multifd_needs_flush = true; + } } /** @@ -3009,6 +3058,11 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id) break; } + if ((flags & RAM_SAVE_FLAG_MULTIFD_SYNC) + == RAM_SAVE_FLAG_MULTIFD_SYNC) { + multifd_flush(); + flags = flags & ~RAM_SAVE_FLAG_ZERO; + } if (flags & (RAM_SAVE_FLAG_ZERO | RAM_SAVE_FLAG_PAGE | RAM_SAVE_FLAG_COMPRESS_PAGE | RAM_SAVE_FLAG_XBZRLE | RAM_SAVE_FLAG_MULTIFD_PAGE)) { -- 2.9.4