From nobody Sun Nov 24 09:05:20 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org ARC-Seal: i=1; a=rsa-sha256; t=1725891970; cv=none; d=zohomail.com; s=zohoarc; b=i+vHmWKFhOH3KFJF+jZ1Br2UgRg6KQ4Jrhc/JTUOIDRIZ/H4afxNa1YD18597kbs2DA7sJRT9EtXCY9Oe6rA+UsbOm49b2lJd/mXqMDP27sZz08eqM1DOOxnrcUakaayofFmqwf5juuMK4bn42Xl+wFtsUzafTIOHdeOd71ZWRo= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1725891970; h=Content-Transfer-Encoding:Cc:Cc:Date:Date:From:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:Subject:To:To:Message-Id:Reply-To; bh=pVk80rEdIzOmBvs0atZRrFtqRDrxfejNxURYXwd1kcM=; b=bnXgREATVhqjTfYg1LmJRuBNCrQIqcq68B9aLDCIQz9uDSFAkM7A3h3YETHECj9QuZaZ4JNsqXlP5vM6TBUB2T6rytyCVW1ZjN8t4Xlo6+hJ+uXpal/43wlB+kIrwr0TpKiYRAoZX/8X95DOcLhYqQ7tHw6/bctaZ+KYa9c6Ql8= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=pass; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1725891970374325.24096425836376; Mon, 9 Sep 2024 07:26:10 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1snfL9-0000os-V5; Mon, 09 Sep 2024 10:26:03 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1snfL8-0000fc-3P for qemu-devel@nongnu.org; Mon, 09 Sep 2024 10:26:02 -0400 Received: from mail-pg1-x534.google.com ([2607:f8b0:4864:20::534]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128) (Exim 4.90_1) (envelope-from ) id 1snfL6-0004TR-0T for qemu-devel@nongnu.org; Mon, 09 Sep 2024 10:26:01 -0400 Received: by mail-pg1-x534.google.com with SMTP id 41be03b00d2f7-7b8884631c4so2063179a12.2 for ; Mon, 09 Sep 2024 07:25:59 -0700 (PDT) Received: from localhost.localdomain ([118.114.94.226]) by smtp.gmail.com with ESMTPSA id d2e1a72fcca58-718e58b2a88sm3561164b3a.46.2024.09.09.07.25.54 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 09 Sep 2024 07:25:57 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=smartx-com.20230601.gappssmtp.com; s=20230601; t=1725891958; x=1726496758; darn=nongnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=pVk80rEdIzOmBvs0atZRrFtqRDrxfejNxURYXwd1kcM=; b=XkCWhf1c1QSG2/F6I7U7UhCOlEhmETHg00CdzlFZxFuTaJYgUVP8e0ewiRtpOYC+PX MduPwTe8J8iZPoXsWvJGM+45oW0U/k/Q6dZA1qkG4FssFudxqKIPRtjr2iiMJZ7jCxby 6bcFI4xZGpFhpeUQ0jzL2/pqorJZTTVyFYWGEDzrNxxL4oUUj8WC5b5zl+LopGVAimag /bQV6FDddC/QhnbvFXInogf1udUNmhNYOcdo6dhI7UKtQAw2AP1UcSujGjacUraFrWOO OV1PGjUB4NgMk4sBlOmSb4SuKbGFWD9Ix9rFAdE514evAcChfVILn1R9JpsBxf9AdS0X 9D8g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1725891958; x=1726496758; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=pVk80rEdIzOmBvs0atZRrFtqRDrxfejNxURYXwd1kcM=; b=AV89oCU3Mtf5hKepcyu+I1ld3nPQ8ShT/aacesHH9Lb+23qW9hOqQMy5i4S+QRwaXT 1F9YfeR39hw0HswitH0lYQLP+eGz6Yhu0jBWiGcNnUtLlXyGd5FrR9XOaxAMH5ys5gQ/ YvMqvL9BHaMT3nv8PDxp8KuLRSACagQvng5uKk6hJZiUXL792cxOkx2LkfnjKKbhGkgo fppu7IOIQ4Y91phCJ1glEm5boE0S+dsZ4BEAKfo5dt32j5dB9vYFQuWp5sI2AqFD8/5I 09/D/JNf3JOxP9Uk/uCAqvxlKqWgB6Qnye8M4Oeva2KlAuyBQ8JcFE7QOpa2oVioNjNa MeJQ== X-Gm-Message-State: AOJu0YwR11HnrRalKEjeS7hv5zwTjMqsaXDlC4hmn/c1PeboKmIkoerU S5CuCSfaYNXmlIA9g5HtX6Z5xUPUgpjm/zwuqhJIPjI4E3z9Zw/leF+jZxKv9XrdzvAnLWYsOJa jAtqsUw== X-Google-Smtp-Source: AGHT+IH0b9iAa+5uGsRzRkUT07ozgShtleqSF/hJslwjR5dy0x/GT7PDQ5UV25wQpjRaEYmjN1qZMQ== X-Received: by 2002:a05:6a21:2d84:b0:1cf:337e:9920 with SMTP id adf61e73a8af0-1cf337ecfd3mr10061661637.47.1725891957579; Mon, 09 Sep 2024 07:25:57 -0700 (PDT) From: Hyman Huang To: qemu-devel@nongnu.org Cc: Peter Xu , Fabiano Rosas , Eric Blake , Markus Armbruster , David Hildenbrand , =?UTF-8?q?Philippe=20Mathieu-Daud=C3=A9?= , Paolo Bonzini , yong.huang@smartx.com Subject: [PATCH RESEND RFC 02/10] migration: Refine util functions to support periodic CPU throttle Date: Mon, 9 Sep 2024 22:25:35 +0800 Message-Id: <83f9756eb21e21300ced2bf77fdb3585a918f05e.1725891841.git.yong.huang@smartx.com> X-Mailer: git-send-email 2.39.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2607:f8b0:4864:20::534; envelope-from=yong.huang@smartx.com; helo=mail-pg1-x534.google.com X-Spam_score_int: -18 X-Spam_score: -1.9 X-Spam_bar: - X-Spam_report: (-1.9 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZohoMail-DKIM: pass (identity @smartx-com.20230601.gappssmtp.com) X-ZM-MESSAGEID: 1725891971950116600 Content-Type: text/plain; charset="utf-8" Supply the migration_bitmap_sync function along with a periodic argument. Introduce the sync_mode global variable to track the sync mode and support periodic throttling while keeping backward compatibility. Signed-off-by: Hyman Huang --- include/exec/ram_addr.h | 107 +++++++++++++++++++++++++++++++++++++--- migration/ram.c | 49 ++++++++++++++---- 2 files changed, 140 insertions(+), 16 deletions(-) diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h index 891c44cf2d..7df926ed96 100644 --- a/include/exec/ram_addr.h +++ b/include/exec/ram_addr.h @@ -472,17 +472,68 @@ static inline void cpu_physical_memory_clear_dirty_ra= nge(ram_addr_t start, cpu_physical_memory_test_and_clear_dirty(start, length, DIRTY_MEMORY_C= ODE); } =20 +static void ramblock_clear_iter_bmap(RAMBlock *rb, + ram_addr_t start, + ram_addr_t length) +{ + ram_addr_t addr; + unsigned long *bmap =3D rb->bmap; + unsigned long *shadow_bmap =3D rb->shadow_bmap; + unsigned long *iter_bmap =3D rb->iter_bmap; + + for (addr =3D 0; addr < length; addr +=3D TARGET_PAGE_SIZE) { + long k =3D (start + addr) >> TARGET_PAGE_BITS; + if (test_bit(k, shadow_bmap) && !test_bit(k, bmap)) { + /* Page has been sent, clear the iter bmap */ + clear_bit(k, iter_bmap); + } + } +} + +static void ramblock_update_iter_bmap(RAMBlock *rb, + ram_addr_t start, + ram_addr_t length) +{ + ram_addr_t addr; + unsigned long *bmap =3D rb->bmap; + unsigned long *iter_bmap =3D rb->iter_bmap; + + for (addr =3D 0; addr < length; addr +=3D TARGET_PAGE_SIZE) { + long k =3D (start + addr) >> TARGET_PAGE_BITS; + if (test_bit(k, iter_bmap)) { + if (!test_bit(k, bmap)) { + set_bit(k, bmap); + rb->iter_dirty_pages++; + } + } + } +} =20 /* Called with RCU critical section */ static inline uint64_t cpu_physical_memory_sync_dirty_bitmap(RAMBlock *rb, ram_addr_t start, - ram_addr_t length) + ram_addr_t length, + unsigned int flag) { ram_addr_t addr; unsigned long word =3D BIT_WORD((start + rb->offset) >> TARGET_PAGE_BI= TS); uint64_t num_dirty =3D 0; unsigned long *dest =3D rb->bmap; + unsigned long *shadow_bmap =3D rb->shadow_bmap; + unsigned long *iter_bmap =3D rb->iter_bmap; + + assert(flag && !(flag & (~RAMBLOCK_SYN_MASK))); + + /* + * We must remove the sent dirty page from the iter_bmap in order to + * minimize redundant page transfers if periodic sync has appeared + * during this iteration. + */ + if (rb->periodic_sync_shown_up && + (flag & (RAMBLOCK_SYN_MODERN_ITER | RAMBLOCK_SYN_MODERN_PERIOD))) { + ramblock_clear_iter_bmap(rb, start, length); + } =20 /* start address and length is aligned at the start of a word? */ if (((word * BITS_PER_LONG) << TARGET_PAGE_BITS) =3D=3D @@ -503,8 +554,20 @@ uint64_t cpu_physical_memory_sync_dirty_bitmap(RAMBloc= k *rb, if (src[idx][offset]) { unsigned long bits =3D qatomic_xchg(&src[idx][offset], 0); unsigned long new_dirty; + if (flag & (RAMBLOCK_SYN_MODERN_ITER | + RAMBLOCK_SYN_MODERN_PERIOD)) { + /* Back-up bmap for the next iteration */ + iter_bmap[k] |=3D bits; + if (flag =3D=3D RAMBLOCK_SYN_MODERN_PERIOD) { + /* Back-up bmap to detect pages has been sent */ + shadow_bmap[k] =3D dest[k]; + } + } new_dirty =3D ~dest[k]; - dest[k] |=3D bits; + if (flag =3D=3D RAMBLOCK_SYN_LEGACY_ITER) { + dest[k] |=3D bits; + } + new_dirty &=3D bits; num_dirty +=3D ctpopl(new_dirty); } @@ -534,18 +597,50 @@ uint64_t cpu_physical_memory_sync_dirty_bitmap(RAMBlo= ck *rb, ram_addr_t offset =3D rb->offset; =20 for (addr =3D 0; addr < length; addr +=3D TARGET_PAGE_SIZE) { - if (cpu_physical_memory_test_and_clear_dirty( + bool dirty =3D false; + long k =3D (start + addr) >> TARGET_PAGE_BITS; + if (flag =3D=3D RAMBLOCK_SYN_MODERN_PERIOD) { + if (test_bit(k, dest)) { + /* Back-up bmap to detect pages has been sent */ + set_bit(k, shadow_bmap); + } + } + + dirty =3D cpu_physical_memory_test_and_clear_dirty( start + addr + offset, TARGET_PAGE_SIZE, - DIRTY_MEMORY_MIGRATION)) { - long k =3D (start + addr) >> TARGET_PAGE_BITS; - if (!test_and_set_bit(k, dest)) { + DIRTY_MEMORY_MIGRATION); + + if (flag =3D=3D RAMBLOCK_SYN_LEGACY_ITER) { + if (dirty && !test_and_set_bit(k, dest)) { num_dirty++; } + } else { + if (dirty) { + if (!test_bit(k, dest)) { + num_dirty++; + } + /* Back-up bmap for the next iteration */ + set_bit(k, iter_bmap); + } } } } =20 + /* + * We have to re-fetch dirty pages from the iter_bmap one by one. + * It's possible that not all of the dirty pages that meant to + * send in the current iteration are included in the bitmap + * that the current sync retrieved from the KVM. + */ + if (flag =3D=3D RAMBLOCK_SYN_MODERN_ITER) { + ramblock_update_iter_bmap(rb, start, length); + } + + if (flag =3D=3D RAMBLOCK_SYN_MODERN_PERIOD) { + rb->periodic_sync_shown_up =3D true; + } + return num_dirty; } #endif diff --git a/migration/ram.c b/migration/ram.c index f29faa82d6..a56634eb46 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -112,6 +112,8 @@ =20 XBZRLECacheStats xbzrle_counters; =20 +static RAMBlockSynMode sync_mode =3D RAMBLOCK_SYN_LEGACY; + /* used by the search for pages to send */ struct PageSearchStatus { /* The migration channel used for a specific host page */ @@ -912,13 +914,38 @@ bool ramblock_page_is_discarded(RAMBlock *rb, ram_add= r_t start) return false; } =20 +static void ramblock_reset_iter_stats(RAMBlock *rb) +{ + bitmap_clear(rb->shadow_bmap, 0, rb->used_length >> TARGET_PAGE_BITS); + bitmap_clear(rb->iter_bmap, 0, rb->used_length >> TARGET_PAGE_BITS); + rb->iter_dirty_pages =3D 0; + rb->periodic_sync_shown_up =3D false; +} + /* Called with RCU critical section */ -static void ramblock_sync_dirty_bitmap(RAMState *rs, RAMBlock *rb) +static void ramblock_sync_dirty_bitmap(RAMState *rs, + RAMBlock *rb, + bool periodic) { - uint64_t new_dirty_pages =3D - cpu_physical_memory_sync_dirty_bitmap(rb, 0, rb->used_length); + uint64_t new_dirty_pages; + unsigned int flag =3D RAMBLOCK_SYN_LEGACY_ITER; + + if (sync_mode =3D=3D RAMBLOCK_SYN_MODERN) { + flag =3D periodic ? RAMBLOCK_SYN_MODERN_PERIOD : RAMBLOCK_SYN_MODE= RN_ITER; + } + + new_dirty_pages =3D + cpu_physical_memory_sync_dirty_bitmap(rb, 0, rb->used_length, flag= ); + + if (flag & (RAMBLOCK_SYN_LEGACY_ITER | RAMBLOCK_SYN_MODERN_ITER)) { + if (flag =3D=3D RAMBLOCK_SYN_LEGACY_ITER) { + rs->migration_dirty_pages +=3D new_dirty_pages; + } else { + rs->migration_dirty_pages +=3D rb->iter_dirty_pages; + ramblock_reset_iter_stats(rb); + } + } =20 - rs->migration_dirty_pages +=3D new_dirty_pages; rs->num_dirty_pages_period +=3D new_dirty_pages; } =20 @@ -1041,7 +1068,9 @@ static void migration_trigger_throttle(RAMState *rs) } } =20 -static void migration_bitmap_sync(RAMState *rs, bool last_stage) +static void migration_bitmap_sync(RAMState *rs, + bool last_stage, + bool periodic) { RAMBlock *block; int64_t end_time; @@ -1058,7 +1087,7 @@ static void migration_bitmap_sync(RAMState *rs, bool = last_stage) WITH_QEMU_LOCK_GUARD(&rs->bitmap_mutex) { WITH_RCU_READ_LOCK_GUARD() { RAMBLOCK_FOREACH_NOT_IGNORED(block) { - ramblock_sync_dirty_bitmap(rs, block); + ramblock_sync_dirty_bitmap(rs, block, periodic); } stat64_set(&mig_stats.dirty_bytes_last_sync, ram_bytes_remaini= ng()); } @@ -1101,7 +1130,7 @@ static void migration_bitmap_sync_precopy(RAMState *r= s, bool last_stage) local_err =3D NULL; } =20 - migration_bitmap_sync(rs, last_stage); + migration_bitmap_sync(rs, last_stage, false); =20 if (precopy_notify(PRECOPY_NOTIFY_AFTER_BITMAP_SYNC, &local_err)) { error_report_err(local_err); @@ -2594,7 +2623,7 @@ void ram_postcopy_send_discard_bitmap(MigrationState = *ms) RCU_READ_LOCK_GUARD(); =20 /* This should be our last sync, the src is now paused */ - migration_bitmap_sync(rs, false); + migration_bitmap_sync(rs, false, false); =20 /* Easiest way to make sure we don't resume in the middle of a host-pa= ge */ rs->pss[RAM_CHANNEL_PRECOPY].last_sent_block =3D NULL; @@ -3581,7 +3610,7 @@ void colo_incoming_start_dirty_log(void) memory_global_dirty_log_sync(false); WITH_RCU_READ_LOCK_GUARD() { RAMBLOCK_FOREACH_NOT_IGNORED(block) { - ramblock_sync_dirty_bitmap(ram_state, block); + ramblock_sync_dirty_bitmap(ram_state, block, false); /* Discard this dirty bitmap record */ bitmap_zero(block->bmap, block->max_length >> TARGET_PAGE_BITS= ); } @@ -3862,7 +3891,7 @@ void colo_flush_ram_cache(void) qemu_mutex_lock(&ram_state->bitmap_mutex); WITH_RCU_READ_LOCK_GUARD() { RAMBLOCK_FOREACH_NOT_IGNORED(block) { - ramblock_sync_dirty_bitmap(ram_state, block); + ramblock_sync_dirty_bitmap(ram_state, block, false); } } =20 --=20 2.39.1