From patchwork Mon Oct 29 04:30:45 2012 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Zhiyong Wu X-Patchwork-Id: 1661021 Return-Path: X-Original-To: patchwork-linux-btrfs@patchwork.kernel.org Delivered-To: patchwork-process-083081@patchwork1.kernel.org Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by patchwork1.kernel.org (Postfix) with ESMTP id 8A2B33FCF7 for ; Mon, 29 Oct 2012 04:38:13 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932156Ab2J2Ebu (ORCPT ); Mon, 29 Oct 2012 00:31:50 -0400 Received: from e5.ny.us.ibm.com ([32.97.182.145]:58824 "EHLO e5.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753625Ab2J2Ebq (ORCPT ); Mon, 29 Oct 2012 00:31:46 -0400 Received: from /spool/local by e5.ny.us.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Mon, 29 Oct 2012 00:31:45 -0400 Received: from d01dlp02.pok.ibm.com (9.56.250.167) by e5.ny.us.ibm.com (192.168.1.105) with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted; Mon, 29 Oct 2012 00:31:42 -0400 Received: from d01relay03.pok.ibm.com (d01relay03.pok.ibm.com [9.56.227.235]) by d01dlp02.pok.ibm.com (Postfix) with ESMTP id CDF096E8036; Mon, 29 Oct 2012 00:31:41 -0400 (EDT) Received: from d01av04.pok.ibm.com (d01av04.pok.ibm.com [9.56.224.64]) by d01relay03.pok.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id q9T4VfMM288990; Mon, 29 Oct 2012 00:31:41 -0400 Received: from d01av04.pok.ibm.com (loopback [127.0.0.1]) by d01av04.pok.ibm.com (8.14.4/8.13.1/NCO v10.0 AVout) with ESMTP id q9T4Ve6h012015; Mon, 29 Oct 2012 00:31:41 -0400 Received: from us.ibm.com ([9.115.122.193]) by d01av04.pok.ibm.com (8.14.4/8.13.1/NCO v10.0 AVin) with SMTP id q9T4VZEC011728; Mon, 29 Oct 2012 00:31:36 -0400 Received: by us.ibm.com (sSMTP sendmail emulation); Mon, 29 Oct 2012 12:31:31 +0800 From: zwu.kernel@gmail.com To: linux-fsdevel@vger.kernel.org Cc: linux-ext4@vger.kernel.org, linux-btrfs@vger.kernel.org, linux-kernel@vger.kernel.org, linuxram@linux.vnet.ibm.com, viro@zeniv.linux.org.uk, david@fromorbit.com, tytso@mit.edu, cmm@us.ibm.com, wuzhy@linux.vnet.ibm.com, wenqing.lz@taobao.com Subject: [RFC v4+ hot_track 03/19] vfs: add I/O frequency update function Date: Mon, 29 Oct 2012 12:30:45 +0800 Message-Id: <1351485061-12297-4-git-send-email-zwu.kernel@gmail.com> X-Mailer: git-send-email 1.7.6.5 In-Reply-To: <1351485061-12297-1-git-send-email-zwu.kernel@gmail.com> References: <1351485061-12297-1-git-send-email-zwu.kernel@gmail.com> X-Content-Scanned: Fidelis XPS MAILER x-cbid: 12102904-5930-0000-0000-00000D8CB7B0 Sender: linux-btrfs-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-btrfs@vger.kernel.org From: Zhi Yong Wu Add some util helpers to update access frequencies for one file or its range. Signed-off-by: Zhi Yong Wu --- fs/hot_tracking.c | 179 ++++++++++++++++++++++++++++++++++++++++++ fs/hot_tracking.h | 7 ++ include/linux/hot_tracking.h | 2 + 3 files changed, 188 insertions(+), 0 deletions(-) diff --git a/fs/hot_tracking.c b/fs/hot_tracking.c index 68591f0..0a7d9a3 100644 --- a/fs/hot_tracking.c +++ b/fs/hot_tracking.c @@ -172,6 +172,137 @@ static void hot_inode_tree_exit(struct hot_info *root) } } +struct hot_inode_item +*hot_inode_item_find(struct hot_info *root, u64 ino) +{ + struct hot_inode_item *he; + int ret; + +again: + spin_lock(&root->lock); + he = radix_tree_lookup(&root->hot_inode_tree, ino); + if (he) { + kref_get(&he->hot_inode.refs); + spin_unlock(&root->lock); + return he; + } + spin_unlock(&root->lock); + + he = kmem_cache_zalloc(hot_inode_item_cachep, + GFP_KERNEL | GFP_NOFS); + if (!he) + return ERR_PTR(-ENOMEM); + + hot_inode_item_init(he, ino, &root->hot_inode_tree); + + ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM); + if (ret) { + kmem_cache_free(hot_inode_item_cachep, he); + return ERR_PTR(ret); + } + + spin_lock(&root->lock); + ret = radix_tree_insert(&root->hot_inode_tree, ino, he); + if (ret == -EEXIST) { + kmem_cache_free(hot_inode_item_cachep, he); + spin_unlock(&root->lock); + radix_tree_preload_end(); + goto again; + } + spin_unlock(&root->lock); + radix_tree_preload_end(); + + kref_get(&he->hot_inode.refs); + return he; +} +EXPORT_SYMBOL_GPL(hot_inode_item_find); + +static struct hot_range_item +*hot_range_item_find(struct hot_inode_item *he, + u32 start) +{ + struct hot_range_item *hr; + int ret; + +again: + spin_lock(&he->lock); + hr = radix_tree_lookup(&he->hot_range_tree, start); + if (hr) { + kref_get(&hr->hot_range.refs); + spin_unlock(&he->lock); + return hr; + } + spin_unlock(&he->lock); + + hr = kmem_cache_zalloc(hot_range_item_cachep, + GFP_KERNEL | GFP_NOFS); + if (!hr) + return ERR_PTR(-ENOMEM); + + hot_range_item_init(hr, start, he); + + ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM); + if (ret) { + kmem_cache_free(hot_range_item_cachep, hr); + return ERR_PTR(ret); + } + + spin_lock(&he->lock); + ret = radix_tree_insert(&he->hot_range_tree, start, hr); + if (ret == -EEXIST) { + kmem_cache_free(hot_range_item_cachep, hr); + spin_unlock(&he->lock); + radix_tree_preload_end(); + goto again; + } + spin_unlock(&he->lock); + radix_tree_preload_end(); + + kref_get(&hr->hot_range.refs); + return hr; +} + +/* + * This function does the actual work of updating + * the frequency numbers, whatever they turn out to be. + */ +static u64 hot_average_update(struct timespec old_atime, + struct timespec cur_time, u64 old_avg) +{ + struct timespec delta_ts; + u64 new_avg; + u64 new_delta; + + delta_ts = timespec_sub(cur_time, old_atime); + new_delta = timespec_to_ns(&delta_ts) >> FREQ_POWER; + + new_avg = (old_avg << FREQ_POWER) - old_avg + new_delta; + new_avg = new_avg >> FREQ_POWER; + + return new_avg; +} + +static void hot_freq_data_update(struct hot_freq_data *freq_data, bool write) +{ + struct timespec cur_time = current_kernel_time(); + + if (write) { + freq_data->nr_writes += 1; + freq_data->avg_delta_writes = hot_average_update( + freq_data->last_write_time, + cur_time, + freq_data->avg_delta_writes); + freq_data->last_write_time = cur_time; + } else { + freq_data->nr_reads += 1; + freq_data->avg_delta_reads = hot_average_update( + freq_data->last_read_time, + cur_time, + freq_data->avg_delta_reads); + freq_data->last_read_time = cur_time; + } +} + /* * Initialize kmem cache for hot_inode_item and hot_range_item. */ @@ -199,6 +330,54 @@ err: EXPORT_SYMBOL_GPL(hot_cache_init); /* + * Main function to update access frequency from read/writepage(s) hooks + */ +void hot_update_freqs(struct inode *inode, u64 start, + u64 len, int rw) +{ + struct hot_info *root = inode->i_sb->s_hot_root; + struct hot_inode_item *he; + struct hot_range_item *hr; + u32 cur, end; + + if (!root || (len == 0)) + return; + + he = hot_inode_item_find(root, inode->i_ino); + if (IS_ERR(he)) { + WARN_ON(1); + return; + } + + spin_lock(&he->hot_inode.lock); + hot_freq_data_update(&he->hot_inode.hot_freq_data, rw); + spin_unlock(&he->hot_inode.lock); + + /* + * Align ranges on RANGE_SIZE boundary + * to prevent proliferation of range structs + */ + end = (start + len + RANGE_SIZE - 1) >> RANGE_BITS; + for (cur = (start >> RANGE_BITS); cur < end; cur++) { + hr = hot_range_item_find(he, cur); + if (IS_ERR(hr)) { + WARN_ON(1); + hot_inode_item_put(he); + return; + } + + spin_lock(&hr->hot_range.lock); + hot_freq_data_update(&hr->hot_range.hot_freq_data, rw); + spin_unlock(&hr->hot_range.lock); + + hot_range_item_put(hr); + } + + hot_inode_item_put(he); +} +EXPORT_SYMBOL_GPL(hot_update_freqs); + +/* * Initialize the data structures for hot data tracking. */ int hot_track_init(struct super_block *sb) diff --git a/fs/hot_tracking.h b/fs/hot_tracking.h index e7ba121..cc4666e 100644 --- a/fs/hot_tracking.h +++ b/fs/hot_tracking.h @@ -20,6 +20,13 @@ #define FREQ_DATA_TYPE_INODE (1 << 0) #define FREQ_DATA_TYPE_RANGE (1 << 1) +/* size of sub-file ranges */ +#define RANGE_BITS 20 +#define RANGE_SIZE (1 << RANGE_BITS) + +#define FREQ_POWER 4 + void hot_inode_item_put(struct hot_inode_item *he); +struct hot_inode_item *hot_inode_item_find(struct hot_info *root, u64 ino); #endif /* __HOT_TRACKING__ */ diff --git a/include/linux/hot_tracking.h b/include/linux/hot_tracking.h index 4233207..e2d6028 100644 --- a/include/linux/hot_tracking.h +++ b/include/linux/hot_tracking.h @@ -71,5 +71,7 @@ struct hot_info { extern void __init hot_cache_init(void); extern int hot_track_init(struct super_block *sb); extern void hot_track_exit(struct super_block *sb); +extern void hot_update_freqs(struct inode *inode, u64 start, + u64 len, int rw); #endif /* _LINUX_HOTTRACK_H */