Received: by 2002:ac0:a5a7:0:0:0:0:0 with SMTP id m36-v6csp96692imm; Tue, 14 Aug 2018 14:49:26 -0700 (PDT) X-Google-Smtp-Source: AA+uWPx+5GODbxSoKlbPDdJ10IN8Lwe+xmPW+LZJsQM3HfBdr2SrlCcEc5mgBYexOvYCf6NifViS X-Received: by 2002:a63:416:: with SMTP id 22-v6mr22772373pge.229.1534283366320; Tue, 14 Aug 2018 14:49:26 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1534283366; cv=none; d=google.com; s=arc-20160816; b=fX0Y7mbf+IzDnyW/qezAkycZmgz2KeUdxgQtZMnokbYd36kNNYgrDP0bUOiqzKkM71 UR4S046U5hglET8d3FlYxzCoUwuCOpy2hqA0pY0pXI9doTQAyz33dFpeQjMxsgE10RL9 OFdqPgW79XPkTjCwlzHDe3gARM/fVkvmdYazIxGTAn+qNeRrW3Hy+C3o3Mo+qtD8yk9s j2YAlfpcyH5Lqkc6LERhaT2qSrfqWOUTz8u62tkIekQtJYu44pkIq3J0dnJLL+BfaW1V TQe7FVBCO7R191NWK5vAF0Q5Aw1dwHuHUgtSH1DxToOLrivqdnD+hZ0NoS+l2S7AyUmg yH3A== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:sender:message-id:date:subject:cc:to:from :dkim-signature:arc-authentication-results; bh=zjBVlLtDriRz8Bt1Wyl3Fnf0ke6CQZ0pUzYMeu7d3zo=; b=Lfpf1D+SLYzcIlKzxqFkTorzCEGDfK6E2E9OnmlRyVk+1laMTNJjG2NZsJEkYFgn8z aAJHRaVvEvdp4cWMSya3KInWRFXy8poXSNY0Y78XeWD7k2gbdRCCyfGOeJCnc1C4AdPP CGEOqm5rrRlFzXRArkVNUQv8fxxQOcpR8Q9wAhC6Z2s1EJ/YpwC41zL23t62kuoPcBbd rInqe63g4c5jViVsTyY4EH/4jiqoOvhFDaZRDCc5foVf6bd31PJvwlwCZNkTpRQmp3Pm 2XEJ0e1uGX/AU0yfFPfvTHO8y6VLvTZ4nfBGGqgJ2Lu1jVMrepKe38GtzIk82ItMas8w iHhg== ARC-Authentication-Results: i=1; mx.google.com; dkim=temperror (no key for signature) header.i=@makelinux.com header.s=dkim header.b=TSgbFs80; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id e6-v6si24257026pfe.31.2018.08.14.14.49.10; Tue, 14 Aug 2018 14:49:26 -0700 (PDT) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; dkim=temperror (no key for signature) header.i=@makelinux.com header.s=dkim header.b=TSgbFs80; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729829AbeHOAh3 (ORCPT + 99 others); Tue, 14 Aug 2018 20:37:29 -0400 Received: from bosmailout01.eigbox.net ([66.96.190.1]:41853 "EHLO bosmailout01.eigbox.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1728080AbeHOAh3 (ORCPT ); Tue, 14 Aug 2018 20:37:29 -0400 X-Greylist: delayed 1817 seconds by postgrey-1.27 at vger.kernel.org; Tue, 14 Aug 2018 20:37:28 EDT Received: from bosmailscan12.eigbox.net ([10.20.15.12]) by bosmailout01.eigbox.net with esmtp (Exim) id 1fpghb-0005fg-NL; Tue, 14 Aug 2018 17:18:07 -0400 DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=makelinux.com; s=dkim; h=Sender:Message-Id:Date:Subject:Cc:To:From:Reply-To :MIME-Version:Content-Type:Content-Transfer-Encoding:Content-ID: Content-Description:Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc :Resent-Message-ID:In-Reply-To:References:List-Id:List-Help:List-Unsubscribe: List-Subscribe:List-Post:List-Owner:List-Archive; bh=zjBVlLtDriRz8Bt1Wyl3Fnf0ke6CQZ0pUzYMeu7d3zo=; b=TSgbFs80QhSzVcKZ00URAyyroC 6ODPE59lefYSoCYcwvNvWcdSXRTbAxe9AX1nJCyc8g4Wj4HP3qotGSMTGUd9dkh+7a4hxTiMj/2oI 34wQEjjuAgSMnNpwiu4XJ5nOEpzhmadiRS2h+nGwVPu/C6E83HIn+tM6v1nMiuauC/XK3o7HemTcI 4QQnve+nFjvRx/iOHc+BJdEMF259nJDiPWljYKF0df7UHuvuUrlmv4IBhi/HnJsOngo0a+4P/d0Cw Z5i40frQGvDOMF61F33mtF1o+gKdGcU/Nk14YrOGN+bhJxGivrXfC/GIbDE1QCAreft5yZksBk9RY TSD7VDjw==; Received: from [10.115.3.32] (helo=bosimpout12) by bosmailscan12.eigbox.net with esmtp (Exim) id 1fpghb-0004j2-Jd; Tue, 14 Aug 2018 17:18:07 -0400 Received: from bosauthsmtp13.yourhostingaccount.com ([10.20.18.13]) by bosimpout12 with id P9J01y00D0GvDVm019J3hb; Tue, 14 Aug 2018 17:18:07 -0400 X-Authority-Analysis: v=2.2 cv=UN2tJGXy c=1 sm=1 tr=0 a=UH8/iCWBfdUmbm4Ft4Vi3Q==:117 a=WFC+M0LbvcyalcFcVaxzsg==:17 a=dapMudl6Dx4A:10 a=I7kt_hwf06sA:10 a=3nbZYyFuAAAA:8 a=D19gQVrFAAAA:8 a=dSbym95GAAAA:8 a=Yg5zNgTIajdXgUii3roA:9 a=dpHoGtPToazjF0Ic:21 a=o-Xh6Cstk23zPY3r:21 a=PHK7miK30xPilJovnRLP:22 a=W4TVW4IDbPiebHqcZpNg:22 a=eg0O5KPjxGrMl0Mu5AXQ:22 Received: from [77.139.214.119] (port=50384 helo=localhost.localdomain) by bosauthsmtp13.eigbox.net with esmtpa (Exim) id 1fpghU-0000xX-BY; Tue, 14 Aug 2018 17:18:00 -0400 From: Constantine Shulyupin To: miklos@szeredi.hu, viro@zeniv.linux.org.uk, corbet@lwn.net, liushuoran@jd.com, mitsuo.hayasaka.hu@hitachi.com, linux-fsdevel@vger.kernel.org (open list:FUSE: FILESYSTEM IN USERSPACE), linux-kernel@vger.kernel.org (open list) Cc: amir73il@gmail.com, Constantine Shulyupin Subject: [PATCH v3 1/3] fuse: add max_pages option Date: Wed, 15 Aug 2018 00:17:14 +0300 Message-Id: <20180814211717.22170-1-const@MakeLinux.com> X-Mailer: git-send-email 2.17.1 X-EN-UserInfo: 49eb4aefa70c42fb849786903cdd8376:931c98230c6409dcc37fa7e93b490c27 X-EN-AuthUser: smtp@makelinux.net X-EN-OrigIP: 77.139.214.119 X-EN-OrigHost: unknown Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Replace FUSE_MAX_PAGES_PER_REQ with the configurable mount parameter max_pages to improve performance. Old RFC with detailed description of the problem and many fixes by Mitsuo Hayasaka (mitsuo.hayasaka.hu@hitachi.com): - https://lkml.org/lkml/2012/7/5/136 Changes in v3: - used clamp_val - split documentation change - split EXPORT_SYMBOL(pipe_max_size) Changes in v2: - add limitation by pipe_max_size, which was requested in https://lkml.org/lkml/2012/7/12/32 Changes in v1: https://lkml.org/lkml/2017/8/6/194 - replace FUSE_MAX_PAGES_PER_REQ with FUSE_DEFAULT_MAX_PAGES_PER_REQ and fc->max_pages - add mount option max_pages Signed-off-by: Constantine Shulyupin --- fs/fuse/dev.c | 4 ++-- fs/fuse/file.c | 54 ++++++++++++++++++++++++------------------------ fs/fuse/fuse_i.h | 5 ++++- fs/fuse/inode.c | 14 +++++++++++++ 4 files changed, 47 insertions(+), 30 deletions(-) diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 11ea2c4a38ab..b324ffc2d82a 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1663,7 +1663,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, unsigned int num; unsigned int offset; size_t total_len = 0; - int num_pages; + unsigned num_pages; offset = outarg->offset & ~PAGE_MASK; file_size = i_size_read(inode); @@ -1675,7 +1675,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, num = file_size - outarg->offset; num_pages = (num + offset + PAGE_SIZE - 1) >> PAGE_SHIFT; - num_pages = min(num_pages, FUSE_MAX_PAGES_PER_REQ); + num_pages = min(num_pages, fc->max_pages); req = fuse_get_req(fc, num_pages); if (IS_ERR(req)) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index fe8d84eb714a..e0924e46ef24 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -847,11 +847,11 @@ static int fuse_readpages_fill(void *_data, struct page *page) fuse_wait_on_page_writeback(inode, page->index); if (req->num_pages && - (req->num_pages == FUSE_MAX_PAGES_PER_REQ || + (req->num_pages == fc->max_pages || (req->num_pages + 1) * PAGE_SIZE > fc->max_read || req->pages[req->num_pages - 1]->index + 1 != page->index)) { int nr_alloc = min_t(unsigned, data->nr_pages, - FUSE_MAX_PAGES_PER_REQ); + fc->max_pages); fuse_send_readpages(req, data->file); if (fc->async_read) req = fuse_get_req_for_background(fc, nr_alloc); @@ -886,7 +886,7 @@ static int fuse_readpages(struct file *file, struct address_space *mapping, struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_fill_data data; int err; - int nr_alloc = min_t(unsigned, nr_pages, FUSE_MAX_PAGES_PER_REQ); + int nr_alloc = min_t(unsigned, nr_pages, fc->max_pages); err = -EIO; if (is_bad_inode(inode)) @@ -1101,12 +1101,12 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, return count > 0 ? count : err; } -static inline unsigned fuse_wr_pages(loff_t pos, size_t len) +static inline unsigned fuse_wr_pages(loff_t pos, size_t len, unsigned max_pages) { return min_t(unsigned, ((pos + len - 1) >> PAGE_SHIFT) - (pos >> PAGE_SHIFT) + 1, - FUSE_MAX_PAGES_PER_REQ); + max_pages); } static ssize_t fuse_perform_write(struct kiocb *iocb, @@ -1128,7 +1128,8 @@ static ssize_t fuse_perform_write(struct kiocb *iocb, do { struct fuse_req *req; ssize_t count; - unsigned nr_pages = fuse_wr_pages(pos, iov_iter_count(ii)); + unsigned nr_pages = fuse_wr_pages(pos, iov_iter_count(ii), + fc->max_pages); req = fuse_get_req(fc, nr_pages); if (IS_ERR(req)) { @@ -1318,11 +1319,6 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii, return ret < 0 ? ret : 0; } -static inline int fuse_iter_npages(const struct iov_iter *ii_p) -{ - return iov_iter_npages(ii_p, FUSE_MAX_PAGES_PER_REQ); -} - ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, loff_t *ppos, int flags) { @@ -1342,9 +1338,10 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, int err = 0; if (io->async) - req = fuse_get_req_for_background(fc, fuse_iter_npages(iter)); + req = fuse_get_req_for_background(fc, iov_iter_npages(iter, + fc->max_pages)); else - req = fuse_get_req(fc, fuse_iter_npages(iter)); + req = fuse_get_req(fc, iov_iter_npages(iter, fc->max_pages)); if (IS_ERR(req)) return PTR_ERR(req); @@ -1389,9 +1386,10 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, fuse_put_request(fc, req); if (io->async) req = fuse_get_req_for_background(fc, - fuse_iter_npages(iter)); + iov_iter_npages(iter, fc->max_pages)); else - req = fuse_get_req(fc, fuse_iter_npages(iter)); + req = fuse_get_req(fc, iov_iter_npages(iter, + fc->max_pages)); if (IS_ERR(req)) break; } @@ -1818,7 +1816,7 @@ static int fuse_writepages_fill(struct page *page, is_writeback = fuse_page_is_writeback(inode, page->index); if (req && req->num_pages && - (is_writeback || req->num_pages == FUSE_MAX_PAGES_PER_REQ || + (is_writeback || req->num_pages == fc->max_pages || (req->num_pages + 1) * PAGE_SIZE > fc->max_write || data->orig_pages[req->num_pages - 1]->index + 1 != page->index)) { fuse_writepages_send(data); @@ -1846,7 +1844,7 @@ static int fuse_writepages_fill(struct page *page, struct fuse_inode *fi = get_fuse_inode(inode); err = -ENOMEM; - req = fuse_request_alloc_nofs(FUSE_MAX_PAGES_PER_REQ); + req = fuse_request_alloc_nofs(fc->max_pages); if (!req) { __free_page(tmp_page); goto out_unlock; @@ -1903,6 +1901,7 @@ static int fuse_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; + struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_fill_wb_data data; int err; @@ -1915,7 +1914,7 @@ static int fuse_writepages(struct address_space *mapping, data.ff = NULL; err = -ENOMEM; - data.orig_pages = kcalloc(FUSE_MAX_PAGES_PER_REQ, + data.orig_pages = kcalloc(fc->max_pages, sizeof(struct page *), GFP_NOFS); if (!data.orig_pages) @@ -2386,10 +2385,11 @@ static int fuse_copy_ioctl_iovec_old(struct iovec *dst, void *src, } /* Make sure iov_length() won't overflow */ -static int fuse_verify_ioctl_iov(struct iovec *iov, size_t count) +static int fuse_verify_ioctl_iov(struct fuse_conn *fc, struct iovec *iov, + size_t count) { size_t n; - u32 max = FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT; + u32 max = fc->max_pages << PAGE_SHIFT; for (n = 0; n < count; n++, iov++) { if (iov->iov_len > (size_t) max) @@ -2513,7 +2513,7 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg, BUILD_BUG_ON(sizeof(struct fuse_ioctl_iovec) * FUSE_IOCTL_MAX_IOV > PAGE_SIZE); err = -ENOMEM; - pages = kcalloc(FUSE_MAX_PAGES_PER_REQ, sizeof(pages[0]), GFP_KERNEL); + pages = kcalloc(fc->max_pages, sizeof(pages[0]), GFP_KERNEL); iov_page = (struct iovec *) __get_free_page(GFP_KERNEL); if (!pages || !iov_page) goto out; @@ -2552,7 +2552,7 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg, /* make sure there are enough buffer pages and init request with them */ err = -ENOMEM; - if (max_pages > FUSE_MAX_PAGES_PER_REQ) + if (max_pages > fc->max_pages) goto out; while (num_pages < max_pages) { pages[num_pages] = alloc_page(GFP_KERNEL | __GFP_HIGHMEM); @@ -2639,11 +2639,11 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg, in_iov = iov_page; out_iov = in_iov + in_iovs; - err = fuse_verify_ioctl_iov(in_iov, in_iovs); + err = fuse_verify_ioctl_iov(fc, in_iov, in_iovs); if (err) goto out; - err = fuse_verify_ioctl_iov(out_iov, out_iovs); + err = fuse_verify_ioctl_iov(fc, out_iov, out_iovs); if (err) goto out; @@ -2834,9 +2834,9 @@ static void fuse_do_truncate(struct file *file) fuse_do_setattr(file_dentry(file), &attr, file); } -static inline loff_t fuse_round_up(loff_t off) +static inline loff_t fuse_round_up(struct fuse_conn *fc, loff_t off) { - return round_up(off, FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT); + return round_up(off, fc->max_pages << PAGE_SHIFT); } static ssize_t @@ -2865,7 +2865,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) if (async_dio && iov_iter_rw(iter) != WRITE && offset + count > i_size) { if (offset >= i_size) return 0; - iov_iter_truncate(iter, fuse_round_up(i_size - offset)); + iov_iter_truncate(iter, fuse_round_up(ff->fc, i_size - offset)); count = iov_iter_count(iter); } diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index f78e9614bb5f..7556301cb493 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -29,7 +29,7 @@ #include /** Max number of pages that can be used in a single read request */ -#define FUSE_MAX_PAGES_PER_REQ 32 +#define FUSE_DEFAULT_MAX_PAGES_PER_REQ 32 /** Bias for fi->writectr, meaning new writepages must not be sent */ #define FUSE_NOWRITE INT_MIN @@ -476,6 +476,9 @@ struct fuse_conn { /** Maximum write size */ unsigned max_write; + /** Maxmum number of pages that can be used in a single request */ + unsigned max_pages; + /** Input queue */ struct fuse_iqueue iq; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index db9e60b7eb69..aed77c77cccc 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -22,6 +22,7 @@ #include #include #include +#include MODULE_AUTHOR("Miklos Szeredi "); MODULE_DESCRIPTION("Filesystem in Userspace"); @@ -71,6 +72,7 @@ struct fuse_mount_data { unsigned default_permissions:1; unsigned allow_other:1; unsigned max_read; + unsigned max_pages; unsigned blksize; }; @@ -453,6 +455,7 @@ enum { OPT_DEFAULT_PERMISSIONS, OPT_ALLOW_OTHER, OPT_MAX_READ, + OPT_MAX_PAGES, OPT_BLKSIZE, OPT_ERR }; @@ -465,6 +468,7 @@ static const match_table_t tokens = { {OPT_DEFAULT_PERMISSIONS, "default_permissions"}, {OPT_ALLOW_OTHER, "allow_other"}, {OPT_MAX_READ, "max_read=%u"}, + {OPT_MAX_PAGES, "max_pages=%u"}, {OPT_BLKSIZE, "blksize=%u"}, {OPT_ERR, NULL} }; @@ -546,6 +550,12 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev, d->max_read = value; break; + case OPT_MAX_PAGES: + if (match_int(&args[0], &value)) + return 0; + d->max_pages = value; + break; + case OPT_BLKSIZE: if (!is_bdev || match_int(&args[0], &value)) return 0; @@ -577,6 +587,8 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",allow_other"); if (fc->max_read != ~0) seq_printf(m, ",max_read=%u", fc->max_read); + if (fc->max_pages != FUSE_DEFAULT_MAX_PAGES_PER_REQ) + seq_printf(m, ",max_pages=%u", fc->max_pages); if (sb->s_bdev && sb->s_blocksize != FUSE_DEFAULT_BLKSIZE) seq_printf(m, ",blksize=%lu", sb->s_blocksize); return 0; @@ -1141,6 +1153,8 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) fc->user_id = d.user_id; fc->group_id = d.group_id; fc->max_read = max_t(unsigned, 4096, d.max_read); + fc->max_pages = clamp_val(d.max_pages, FUSE_DEFAULT_MAX_PAGES_PER_REQ, + pipe_max_size >> PAGE_SHIFT); /* Used by get_root_inode() */ sb->s_fs_info = fc; -- 2.17.1