From nobody Tue Nov 26 14:36:13 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; dmarc=pass(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1707361839; cv=none; d=zohomail.com; s=zohoarc; b=fyNIWVo3D55sHQ36kR/E4FQOG5efrX1qlIf4M9nPYTd5kVBEMyOmmqzspPqlNwpzbrBKwlAwAyxA+3yCUxKJRQ2lce014EnZestOhj6YSpapb7cPiVToA8AwqMEbnpI5q0U4+AuTaV943z1doUQWH9hVeNw0C8r9protTSfzRK8= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1707361839; 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=LOpRDl/zE/OAEgC9rgz4jRiLK5ook8APjNrgtvwvbQI=; b=g11NGl1eeBqslkILeodSZ4zBoA+s0Y+CLJQC5Flm6novjc2wUsqDD4c24QEqbHsfQeZ9MFKFVWAjiSwxJw1vNkrEuaLPN4+0vB1l+KZTh0ysYn9cmKO9kwH4Q/uCoIHsV51nlKRkNhtppfzeF6wqwamWhPtwLALLzDz7feXKG+E= 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; dmarc=pass header.from= (p=none dis=none) Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 17073618393901003.1426209673165; Wed, 7 Feb 2024 19:10:39 -0800 (PST) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1rXulL-0000Yl-PB; Wed, 07 Feb 2024 22:07:43 -0500 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 1rXukX-0006q0-3F for qemu-devel@nongnu.org; Wed, 07 Feb 2024 22:06:56 -0500 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1rXukU-0004Qc-W2 for qemu-devel@nongnu.org; Wed, 07 Feb 2024 22:06:52 -0500 Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-620-D-xbqwfSP_iFbxs4FwchGQ-1; Wed, 07 Feb 2024 22:06:48 -0500 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.rdu2.redhat.com [10.11.54.9]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id EFF07811E81; Thu, 8 Feb 2024 03:06:47 +0000 (UTC) Received: from x1n.redhat.com (unknown [10.72.116.45]) by smtp.corp.redhat.com (Postfix) with ESMTP id 7C708492BC7; Thu, 8 Feb 2024 03:06:45 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1707361610; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=LOpRDl/zE/OAEgC9rgz4jRiLK5ook8APjNrgtvwvbQI=; b=jO14D5LtceNwzgmDm+EhOp4sMWzNbrv4wnOaIL9nC3bgALIMu24BBVqhMjepIPCtFoXRfw OpiNTPEAknqhnwlTtQ8yal1YRuRG1Hs0iSi9z/VY3VWHRXbzObXMslAjjgpPptK+Ircpu9 QOv/2ARNprgEt8R1RcIEETVi/e81IWw= X-MC-Unique: D-xbqwfSP_iFbxs4FwchGQ-1 From: peterx@redhat.com To: Peter Maydell , qemu-devel@nongnu.org Cc: peterx@redhat.com, Fabiano Rosas Subject: [PULL 24/34] migration/multifd: Optimize sender side to be lockless Date: Thu, 8 Feb 2024 11:05:18 +0800 Message-ID: <20240208030528.368214-25-peterx@redhat.com> In-Reply-To: <20240208030528.368214-1-peterx@redhat.com> References: <20240208030528.368214-1-peterx@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.9 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=170.10.133.124; envelope-from=peterx@redhat.com; helo=us-smtp-delivery-124.mimecast.com X-Spam_score_int: -21 X-Spam_score: -2.2 X-Spam_bar: -- X-Spam_report: (-2.2 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.106, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H5=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 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 @redhat.com) X-ZM-MESSAGEID: 1707361840461100001 Content-Type: text/plain; charset="utf-8" From: Peter Xu When reviewing my attempt to refactor send_prepare(), Fabiano suggested we try out with dropping the mutex in multifd code [1]. I thought about that before but I never tried to change the code. Now maybe it's time to give it a stab. This only optimizes the sender side. The trick here is multifd has a clear provider/consumer model, that the migration main thread publishes requests (either pending_job/pending_sync), while the multifd sender threads are consumers. Here we don't have a lot of complicated data sharing, and the jobs can logically be submitted lockless. Arm the code with atomic weapons. Two things worth mentioning: - For multifd_send_pages(): we can use qatomic_load_acquire() when trying to find a free channel, but that's expensive if we attach one ACQUIRE per channel. Instead, keep the qatomic_read() on reading the pending_job flag as we do already, meanwhile use one smp_mb_acquire() after the loop to guarantee the memory ordering. - For pending_sync: it doesn't have any extra data required since now p->flags are never touched, it should be safe to not use memory barrier. That's different from pending_job. Provide rich comments for all the lockless operations to state how they are paired. With that, we can remove the mutex. [1] https://lore.kernel.org/r/87o7d1jlu5.fsf@suse.de Suggested-by: Fabiano Rosas Reviewed-by: Fabiano Rosas Link: https://lore.kernel.org/r/20240202102857.110210-24-peterx@redhat.com Signed-off-by: Peter Xu --- migration/multifd.h | 2 -- migration/multifd.c | 51 +++++++++++++++++++++++---------------------- 2 files changed, 26 insertions(+), 27 deletions(-) diff --git a/migration/multifd.h b/migration/multifd.h index 98876ff94a..78a2317263 100644 --- a/migration/multifd.h +++ b/migration/multifd.h @@ -91,8 +91,6 @@ typedef struct { /* syncs main thread and channels */ QemuSemaphore sem_sync; =20 - /* this mutex protects the following parameters */ - QemuMutex mutex; /* is this channel thread running */ bool running; /* multifd flags for each packet */ diff --git a/migration/multifd.c b/migration/multifd.c index b317d57d61..fbdb129088 100644 --- a/migration/multifd.c +++ b/migration/multifd.c @@ -501,19 +501,19 @@ static bool multifd_send_pages(void) } } =20 - qemu_mutex_lock(&p->mutex); - assert(!p->pages->num); - assert(!p->pages->block); /* - * Double check on pending_job=3D=3Dfalse with the lock. In the futur= e if - * we can have >1 requester thread, we can replace this with a "goto - * retry", but that is for later. + * Make sure we read p->pending_job before all the rest. Pairs with + * qatomic_store_release() in multifd_send_thread(). */ - assert(qatomic_read(&p->pending_job) =3D=3D false); - qatomic_set(&p->pending_job, true); + smp_mb_acquire(); + assert(!p->pages->num); multifd_send_state->pages =3D p->pages; p->pages =3D pages; - qemu_mutex_unlock(&p->mutex); + /* + * Making sure p->pages is setup before marking pending_job=3Dtrue. Pa= irs + * with the qatomic_load_acquire() in multifd_send_thread(). + */ + qatomic_store_release(&p->pending_job, true); qemu_sem_post(&p->sem); =20 return true; @@ -648,7 +648,6 @@ static bool multifd_send_cleanup_channel(MultiFDSendPar= ams *p, Error **errp) } multifd_send_channel_destroy(p->c); p->c =3D NULL; - qemu_mutex_destroy(&p->mutex); qemu_sem_destroy(&p->sem); qemu_sem_destroy(&p->sem_sync); g_free(p->name); @@ -742,14 +741,12 @@ int multifd_send_sync_main(void) =20 trace_multifd_send_sync_main_signal(p->id); =20 - qemu_mutex_lock(&p->mutex); /* * We should be the only user so far, so not possible to be set by * others concurrently. */ assert(qatomic_read(&p->pending_sync) =3D=3D false); qatomic_set(&p->pending_sync, true); - qemu_mutex_unlock(&p->mutex); qemu_sem_post(&p->sem); } for (i =3D 0; i < migrate_multifd_channels(); i++) { @@ -796,9 +793,12 @@ static void *multifd_send_thread(void *opaque) if (multifd_send_should_exit()) { break; } - qemu_mutex_lock(&p->mutex); =20 - if (qatomic_read(&p->pending_job)) { + /* + * Read pending_job flag before p->pages. Pairs with the + * qatomic_store_release() in multifd_send_pages(). + */ + if (qatomic_load_acquire(&p->pending_job)) { MultiFDPages_t *pages =3D p->pages; =20 p->iovs_num =3D 0; @@ -806,14 +806,12 @@ static void *multifd_send_thread(void *opaque) =20 ret =3D multifd_send_state->ops->send_prepare(p, &local_err); if (ret !=3D 0) { - qemu_mutex_unlock(&p->mutex); break; } =20 ret =3D qio_channel_writev_full_all(p->c, p->iov, p->iovs_num,= NULL, 0, p->write_flags, &local_er= r); if (ret !=3D 0) { - qemu_mutex_unlock(&p->mutex); break; } =20 @@ -822,24 +820,31 @@ static void *multifd_send_thread(void *opaque) =20 multifd_pages_reset(p->pages); p->next_packet_size =3D 0; - qatomic_set(&p->pending_job, false); - qemu_mutex_unlock(&p->mutex); + + /* + * Making sure p->pages is published before saying "we're + * free". Pairs with the smp_mb_acquire() in + * multifd_send_pages(). + */ + qatomic_store_release(&p->pending_job, false); } else { - /* If not a normal job, must be a sync request */ + /* + * If not a normal job, must be a sync request. Note that + * pending_sync is a standalone flag (unlike pending_job), so + * it doesn't require explicit memory barriers. + */ assert(qatomic_read(&p->pending_sync)); p->flags =3D MULTIFD_FLAG_SYNC; multifd_send_fill_packet(p); ret =3D qio_channel_write_all(p->c, (void *)p->packet, p->packet_len, &local_err); if (ret !=3D 0) { - qemu_mutex_unlock(&p->mutex); break; } /* p->next_packet_size will always be zero for a SYNC packet */ stat64_add(&mig_stats.multifd_bytes, p->packet_len); p->flags =3D 0; qatomic_set(&p->pending_sync, false); - qemu_mutex_unlock(&p->mutex); qemu_sem_post(&p->sem_sync); } } @@ -853,10 +858,7 @@ out: error_free(local_err); } =20 - qemu_mutex_lock(&p->mutex); p->running =3D false; - qemu_mutex_unlock(&p->mutex); - rcu_unregister_thread(); migration_threads_remove(thread); trace_multifd_send_thread_end(p->id, p->packets_sent, p->total_normal_= pages); @@ -998,7 +1000,6 @@ int multifd_send_setup(Error **errp) for (i =3D 0; i < thread_count; i++) { MultiFDSendParams *p =3D &multifd_send_state->params[i]; =20 - qemu_mutex_init(&p->mutex); qemu_sem_init(&p->sem, 0); qemu_sem_init(&p->sem_sync, 0); p->id =3D i; --=20 2.43.0