From patchwork Mon May 15 01:20:43 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xiubo Li X-Patchwork-Id: 683950 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 7E607C77B7F for ; Mon, 15 May 2023 01:22:09 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S238069AbjEOBWI (ORCPT ); Sun, 14 May 2023 21:22:08 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:39640 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S237940AbjEOBWG (ORCPT ); Sun, 14 May 2023 21:22:06 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 96F6A10F4 for ; Sun, 14 May 2023 18:21:26 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1684113685; 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=Q2vil5fNHPh3ahW/PrS375FoKsDzccFBDF2qhT3I+4M=; b=EYLOh2jrQNQZ+0cZqwyTEgDIS+9M479yQ34hYBFg5/9qLhsETY/WXn9mXibpNwKEFNxwR9 VmBUL7gPY8PXn1htxbUeJv/3PtWrB8FbwdwfZ/zJecWcoeWROItAXi0eodzMlInyOaBj5l atC51lEJvuJXqNp7uvq/6pDDiwy23oY= Received: from mimecast-mx02.redhat.com (mx3-rdu2.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-258-Rq6qWJZSO1qqML0XoYcgNg-1; Sun, 14 May 2023 21:21:22 -0400 X-MC-Unique: Rq6qWJZSO1qqML0XoYcgNg-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 2FF973813F23; Mon, 15 May 2023 01:21:22 +0000 (UTC) Received: from li-a71a4dcc-35d1-11b2-a85c-951838863c8d.ibm.com.com (ovpn-12-56.pek2.redhat.com [10.72.12.56]) by smtp.corp.redhat.com (Postfix) with ESMTP id E754D63F8B; Mon, 15 May 2023 01:21:17 +0000 (UTC) From: xiubli@redhat.com To: idryomov@gmail.com, ceph-devel@vger.kernel.org Cc: jlayton@kernel.org, vshankar@redhat.com, sehuww@mail.scut.edu.cn, Xiubo Li , stable@vger.kernel.org Subject: [PATCH v6 1/2] ceph: add a dedicated private data for netfs rreq Date: Mon, 15 May 2023 09:20:43 +0800 Message-Id: <20230515012044.98096-2-xiubli@redhat.com> In-Reply-To: <20230515012044.98096-1-xiubli@redhat.com> References: <20230515012044.98096-1-xiubli@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org From: Xiubo Li We need to save the 'f_ra.ra_pages' to expand the readahead window later. Cc: stable@vger.kernel.org Fixes: 49870056005c ("ceph: convert ceph_readpages to ceph_readahead") URL: https://lore.kernel.org/ceph-devel/20230504082510.247-1-sehuww@mail.scut.edu.cn URL: https://www.spinics.net/lists/ceph-users/msg76183.html Cc: Hu Weiwen Signed-off-by: Xiubo Li --- fs/ceph/addr.c | 45 ++++++++++++++++++++++++++++++++++----------- fs/ceph/super.h | 13 +++++++++++++ 2 files changed, 47 insertions(+), 11 deletions(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 3b20873733af..93fff1a7373f 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -404,18 +404,28 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) { struct inode *inode = rreq->inode; int got = 0, want = CEPH_CAP_FILE_CACHE; + struct ceph_netfs_request_data *priv; int ret = 0; if (rreq->origin != NETFS_READAHEAD) return 0; + priv = kzalloc(sizeof(*priv), GFP_NOFS); + if (!priv) + return -ENOMEM; + if (file) { struct ceph_rw_context *rw_ctx; struct ceph_file_info *fi = file->private_data; + priv->file_ra_pages = file->f_ra.ra_pages; + priv->file_ra_disabled = file->f_mode & FMODE_RANDOM; + rw_ctx = ceph_find_rw_context(fi); - if (rw_ctx) + if (rw_ctx) { + rreq->netfs_priv = priv; return 0; + } } /* @@ -425,27 +435,40 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) ret = ceph_try_get_caps(inode, CEPH_CAP_FILE_RD, want, true, &got); if (ret < 0) { dout("start_read %p, error getting cap\n", inode); - return ret; + goto out; } if (!(got & want)) { dout("start_read %p, no cache cap\n", inode); - return -EACCES; + ret = -EACCES; + goto out; + } + if (ret == 0) { + ret = -EACCES; + goto out; } - if (ret == 0) - return -EACCES; - rreq->netfs_priv = (void *)(uintptr_t)got; - return 0; + priv->caps = got; + rreq->netfs_priv = priv; + +out: + if (ret < 0) + kfree(priv); + + return ret; } static void ceph_netfs_free_request(struct netfs_io_request *rreq) { - struct ceph_inode_info *ci = ceph_inode(rreq->inode); - int got = (uintptr_t)rreq->netfs_priv; + struct ceph_netfs_request_data *priv = rreq->netfs_priv; + + if (!priv) + return; - if (got) - ceph_put_cap_refs(ci, got); + if (priv->caps) + ceph_put_cap_refs(ceph_inode(rreq->inode), priv->caps); + kfree(priv); + rreq->netfs_priv = NULL; } const struct netfs_request_ops ceph_netfs_ops = { diff --git a/fs/ceph/super.h b/fs/ceph/super.h index a226d36b3ecb..3a24b7974d46 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -470,6 +470,19 @@ struct ceph_inode_info { #endif }; +struct ceph_netfs_request_data { + int caps; + + /* + * Maximum size of a file readahead request. + * The fadvise could update the bdi's default ra_pages. + */ + unsigned int file_ra_pages; + + /* Set it if fadvise disables file readahead entirely */ + bool file_ra_disabled; +}; + static inline struct ceph_inode_info * ceph_inode(const struct inode *inode) { From patchwork Mon May 15 01:20:44 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xiubo Li X-Patchwork-Id: 681993 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id DAC3CC7EE22 for ; Mon, 15 May 2023 01:22:22 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S237940AbjEOBWV (ORCPT ); Sun, 14 May 2023 21:22:21 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:39652 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S238046AbjEOBWU (ORCPT ); Sun, 14 May 2023 21:22:20 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id B72E31707 for ; Sun, 14 May 2023 18:21:31 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1684113690; 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=OmB3wXr05ZF4mv5+5tdgNLyO+5Jy1xAtgK7GM+TTU58=; b=G19TJWQ+g4CanY+Ht/C/6uHmwKVWzW94HUzp23cdoYJyApP8FjwwVTspAsaafMxxubEwRH vsqlgnvzUcb2RbqrqYJahRC0aFoEDWTDGZ/8caIygnDUeGYT3qIUQXUhaDnD9828TxcSYQ 7FeluE6vufq5V/zYRTFrkgVNEuQRf/c= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-209-JM9T5lI2P46YW92KpEk3OQ-1; Sun, 14 May 2023 21:21:27 -0400 X-MC-Unique: JM9T5lI2P46YW92KpEk3OQ-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 2DF71101A551; Mon, 15 May 2023 01:21:27 +0000 (UTC) Received: from li-a71a4dcc-35d1-11b2-a85c-951838863c8d.ibm.com.com (ovpn-12-56.pek2.redhat.com [10.72.12.56]) by smtp.corp.redhat.com (Postfix) with ESMTP id 0C73A63F5F; Mon, 15 May 2023 01:21:22 +0000 (UTC) From: xiubli@redhat.com To: idryomov@gmail.com, ceph-devel@vger.kernel.org Cc: jlayton@kernel.org, vshankar@redhat.com, sehuww@mail.scut.edu.cn, Xiubo Li , stable@vger.kernel.org Subject: [PATCH v6 2/2] ceph: fix blindly expanding the readahead windows Date: Mon, 15 May 2023 09:20:44 +0800 Message-Id: <20230515012044.98096-3-xiubli@redhat.com> In-Reply-To: <20230515012044.98096-1-xiubli@redhat.com> References: <20230515012044.98096-1-xiubli@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.5 Precedence: bulk List-ID: X-Mailing-List: ceph-devel@vger.kernel.org From: Xiubo Li Blindly expanding the readahead windows will cause unneccessary pagecache thrashing and also will introdue the network workload. We should disable expanding the windows if the readahead is disabled and also shouldn't expand the windows too much. Expanding forward firstly instead of expanding backward for possible sequential reads. Bound `rreq->len` to the actual file size to restore the previous page cache usage. The posix_fadvise may change the maximum size of a file readahead. Cc: stable@vger.kernel.org Fixes: 49870056005c ("ceph: convert ceph_readpages to ceph_readahead") URL: https://lore.kernel.org/ceph-devel/20230504082510.247-1-sehuww@mail.scut.edu.cn URL: https://www.spinics.net/lists/ceph-users/msg76183.html Cc: Hu Weiwen Signed-off-by: Xiubo Li Reviewed-by: Hu Weiwen Tested-by: Hu Weiwen --- fs/ceph/addr.c | 40 +++++++++++++++++++++++++++++++++------- 1 file changed, 33 insertions(+), 7 deletions(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 93fff1a7373f..4b29777c01d7 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -188,16 +188,42 @@ static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq) struct inode *inode = rreq->inode; struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_file_layout *lo = &ci->i_layout; + unsigned long max_pages = inode->i_sb->s_bdi->ra_pages; + loff_t end = rreq->start + rreq->len, new_end; + struct ceph_netfs_request_data *priv = rreq->netfs_priv; + unsigned long max_len; u32 blockoff; - u64 blockno; - /* Expand the start downward */ - blockno = div_u64_rem(rreq->start, lo->stripe_unit, &blockoff); - rreq->start = blockno * lo->stripe_unit; - rreq->len += blockoff; + if (priv) { + /* Readahead is disabled by posix_fadvise POSIX_FADV_RANDOM */ + if (priv->file_ra_disabled) + max_pages = 0; + else + max_pages = priv->file_ra_pages; + + } + + /* Readahead is disabled */ + if (!max_pages) + return; - /* Now, round up the length to the next block */ - rreq->len = roundup(rreq->len, lo->stripe_unit); + max_len = max_pages << PAGE_SHIFT; + + /* + * Try to expand the length forward by rounding up it to the next + * block, but do not exceed the file size, unless the original + * request already exceeds it. + */ + new_end = min(round_up(end, lo->stripe_unit), rreq->i_size); + if (new_end > end && new_end <= rreq->start + max_len) + rreq->len = new_end - rreq->start; + + /* Try to expand the start downward */ + div_u64_rem(rreq->start, lo->stripe_unit, &blockoff); + if (rreq->len + blockoff <= max_len) { + rreq->start -= blockoff; + rreq->len += blockoff; + } } static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq)