From mboxrd@z Thu Jan 1 00:00:00 1970 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 D3870C433F5 for ; Mon, 29 Nov 2021 16:31:19 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1345450AbhK2Qee (ORCPT ); Mon, 29 Nov 2021 11:34:34 -0500 Received: from ams.source.kernel.org ([145.40.68.75]:60578 "EHLO ams.source.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231803AbhK2Qcb (ORCPT ); Mon, 29 Nov 2021 11:32:31 -0500 Received: from smtp.kernel.org (relay.kernel.org [52.25.139.140]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ams.source.kernel.org (Postfix) with ESMTPS id 93B9EB80E61; Mon, 29 Nov 2021 16:29:12 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id A8CFFC53FCF; Mon, 29 Nov 2021 16:29:10 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1638203351; bh=rwlbl++E+/pNBj67zK0jPmFfSxmZNwn+m2oop6yd0IE=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=l97tsHhscZqhYF3v+bx0+ol5uEWZdnkjCtJqcZl2OiBtJ0b50AOXQ/T3hBQw7ztu+ ajLEiQQGAY6nVs0uKW0zVtL08ifsPoH7gtvQYrKd/YXPxim5BwyWsv74IpD9xBbG/9 pLbyefc1fYbHqvoUeYS/Nns/OYsKOoRBsJ1UThuPTvH/AkfFy1E6C+06/vyMjbXRrs p78jinZ7Yk1El5lIhaSZiw9gYBskjLj/JycJtKmiaaoVaKzxJmDRZygoBhQudT+zhg EPmTEWkmTZy2LvcX+L8cIVY5CligX/WLH+NIifhTA9SIXJATx0WBBsY3HPcALd0dre O7rVDuWoj0Lvg== From: Jeff Layton To: ceph-devel@vger.kernel.org Cc: idryomov@gmail.com, dhowells@redhat.com, linux-fsdevel@vger.kernel.org, linux-cachefs@redhat.com, linux-kernel@vger.kernel.org Subject: [PATCH 2/2] ceph: add fscache writeback support Date: Mon, 29 Nov 2021 11:29:07 -0500 Message-Id: <20211129162907.149445-3-jlayton@kernel.org> X-Mailer: git-send-email 2.33.1 In-Reply-To: <20211129162907.149445-1-jlayton@kernel.org> References: <20211129162907.149445-1-jlayton@kernel.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org When updating the backing store from the pagecache (a'la writepage or writepages), write to the cache first. This allows us to keep caching files even when they are being written, as long as we have appropriate caps. Signed-off-by: Jeff Layton --- fs/ceph/addr.c | 67 ++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 59 insertions(+), 8 deletions(-) diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index c052c0dc0135..9b8c8d110440 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -5,7 +5,6 @@ #include #include #include -#include /* generic_writepages */ #include #include #include @@ -384,6 +383,38 @@ static void ceph_readahead(struct readahead_control *ractl) netfs_readahead(ractl, &ceph_netfs_read_ops, (void *)(uintptr_t)got); } +#ifdef CONFIG_CEPH_FSCACHE +static void ceph_set_page_fscache(struct page *page) +{ + set_page_fscache(page); +} + +static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async) +{ + struct inode *inode = priv; + + if (IS_ERR_VALUE(error) && error != -ENOBUFS) + ceph_fscache_invalidate(inode, false); +} + +static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + struct fscache_cookie *cookie = ceph_fscache_cookie(ci); + + fscache_write_to_cache(cookie, inode->i_mapping, off, len, i_size_read(inode), + ceph_fscache_write_terminated, inode, caching); +} +#else +static inline void ceph_set_page_fscache(struct page *page) +{ +} + +static inline void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching) +{ +} +#endif /* CONFIG_CEPH_FSCACHE */ + struct ceph_writeback_ctl { loff_t i_size; @@ -499,6 +530,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) struct ceph_writeback_ctl ceph_wbc; struct ceph_osd_client *osdc = &fsc->client->osdc; struct ceph_osd_request *req; + bool caching = ceph_is_cache_enabled(inode); dout("writepage %p idx %lu\n", page, page->index); @@ -537,16 +569,17 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb)) set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC); - set_page_writeback(page); req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode), page_off, &len, 0, 1, CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE, snapc, ceph_wbc.truncate_seq, ceph_wbc.truncate_size, true); - if (IS_ERR(req)) { - redirty_page_for_writepage(wbc, page); - end_page_writeback(page); + if (IS_ERR(req)) return PTR_ERR(req); - } + + set_page_writeback(page); + if (caching) + ceph_set_page_fscache(page); + ceph_fscache_write_to_cache(inode, page_off, len, caching); /* it may be a short write due to an object boundary */ WARN_ON_ONCE(len > thp_size(page)); @@ -605,6 +638,9 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc) struct inode *inode = page->mapping->host; BUG_ON(!inode); ihold(inode); + + wait_on_page_fscache(page); + err = writepage_nounlock(page, wbc); if (err == -ERESTARTSYS) { /* direct memory reclaimer was killed by SIGKILL. return 0 @@ -726,6 +762,7 @@ static int ceph_writepages_start(struct address_space *mapping, struct ceph_writeback_ctl ceph_wbc; bool should_loop, range_whole = false; bool done = false; + bool caching = ceph_is_cache_enabled(inode); dout("writepages_start %p (mode=%s)\n", inode, wbc->sync_mode == WB_SYNC_NONE ? "NONE" : @@ -849,7 +886,7 @@ static int ceph_writepages_start(struct address_space *mapping, unlock_page(page); break; } - if (PageWriteback(page)) { + if (PageWriteback(page) || PageFsCache(page)) { if (wbc->sync_mode == WB_SYNC_NONE) { dout("%p under writeback\n", page); unlock_page(page); @@ -857,6 +894,7 @@ static int ceph_writepages_start(struct address_space *mapping, } dout("waiting on writeback %p\n", page); wait_on_page_writeback(page); + wait_on_page_fscache(page); } if (!clear_page_dirty_for_io(page)) { @@ -989,9 +1027,19 @@ static int ceph_writepages_start(struct address_space *mapping, op_idx = 0; for (i = 0; i < locked_pages; i++) { u64 cur_offset = page_offset(pages[i]); + /* + * Discontinuity in page range? Ceph can handle that by just passing + * multiple extents in the write op. + */ if (offset + len != cur_offset) { + /* If it's full, stop here */ if (op_idx + 1 == req->r_num_ops) break; + + /* Kick off an fscache write with what we have so far. */ + ceph_fscache_write_to_cache(inode, offset, len, caching); + + /* Start a new extent */ osd_req_op_extent_dup_last(req, op_idx, cur_offset - offset); dout("writepages got pages at %llu~%llu\n", @@ -1002,14 +1050,17 @@ static int ceph_writepages_start(struct address_space *mapping, osd_req_op_extent_update(req, op_idx, len); len = 0; - offset = cur_offset; + offset = cur_offset; data_pages = pages + i; op_idx++; } set_page_writeback(pages[i]); + if (caching) + ceph_set_page_fscache(pages[i]); len += thp_size(page); } + ceph_fscache_write_to_cache(inode, offset, len, caching); if (ceph_wbc.size_stable) { len = min(len, ceph_wbc.i_size - offset); -- 2.33.1