Return-Path: linux-nfs-owner@vger.kernel.org Received: from mail-vw0-f46.google.com ([209.85.212.46]:59122 "EHLO mail-vw0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755950Ab1K2QKM (ORCPT ); Tue, 29 Nov 2011 11:10:12 -0500 Received: by vbbfc26 with SMTP id fc26so4879229vbb.19 for ; Tue, 29 Nov 2011 08:10:11 -0800 (PST) From: Peng Tao To: Trond.Myklebust@netapp.com Cc: linux-nfs@vger.kernel.org, bhalevy@tonian.com, Peng Tao Subject: [PATCH 4/4] pnfsblock: do ask for layout in pg_init Date: Fri, 2 Dec 2011 20:52:45 -0800 Message-Id: <1322887965-2938-5-git-send-email-bergwolf@gmail.com> In-Reply-To: <1322887965-2938-1-git-send-email-bergwolf@gmail.com> References: <1322887965-2938-1-git-send-email-bergwolf@gmail.com> Sender: linux-nfs-owner@vger.kernel.org List-ID: Asking for layout in pg_init will always make client ask for only 4KB layout in every layoutget. This way, client drops the IO size information that is meaningful for MDS in handing out layout. In stead, if layout is not find in cache, do not send layoutget at once. Wait until before issuing IO in pnfs_do_multiple_reads/writes because that is where we know the real size of current IO. By telling the real IO size to MDS, MDS will have a better chance to give proper layout. Signed-off-by: Peng Tao --- fs/nfs/blocklayout/blocklayout.c | 54 ++++++++++++++++++++++++++++++++++++- 1 files changed, 52 insertions(+), 2 deletions(-) diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 48cfac3..fd585fe 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -39,6 +39,7 @@ #include #include "blocklayout.h" +#include "../internal.h" #define NFSDBG_FACILITY NFSDBG_PNFS_LD @@ -990,14 +991,63 @@ bl_clear_layoutdriver(struct nfs_server *server) return 0; } +/* While RFC doesn't limit maximum size of layout, we better limit it ourself. */ +#define PNFSBLK_MAXRSIZE (0x1<<22) +#define PNFSBLK_MAXWSIZE (0x1<<21) +static void +bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + struct inode *ino = pgio->pg_inode; + struct pnfs_layout_hdr *lo; + + BUG_ON(pgio->pg_lseg != NULL); + spin_lock(&ino->i_lock); + lo = pnfs_find_alloc_layout(ino, req->wb_context, GFP_KERNEL); + if (!lo || test_bit(lo_fail_bit(IOMODE_READ), &lo->plh_flags)) { + spin_unlock(&ino->i_lock); + nfs_pageio_reset_read_mds(pgio); + return; + } + + pgio->pg_bsize = PNFSBLK_MAXRSIZE; + pgio->pg_lseg = pnfs_find_get_layout_locked(ino, + req_offset(req), + req->wb_bytes, + IOMODE_READ); + spin_unlock(&ino->i_lock); +} + +static void +bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + struct inode *ino = pgio->pg_inode; + struct pnfs_layout_hdr *lo; + + BUG_ON(pgio->pg_lseg != NULL); + spin_lock(&ino->i_lock); + lo = pnfs_find_alloc_layout(ino, req->wb_context, GFP_NOFS); + if (!lo || test_bit(lo_fail_bit(IOMODE_RW), &lo->plh_flags)) { + spin_unlock(&ino->i_lock); + nfs_pageio_reset_write_mds(pgio); + return; + } + + pgio->pg_bsize = PNFSBLK_MAXWSIZE; + pgio->pg_lseg = pnfs_find_get_layout_locked(ino, + req_offset(req), + req->wb_bytes, + IOMODE_RW); + spin_unlock(&ino->i_lock); +} + static const struct nfs_pageio_ops bl_pg_read_ops = { - .pg_init = pnfs_generic_pg_init_read, + .pg_init = bl_pg_init_read, .pg_test = pnfs_generic_pg_test, .pg_doio = pnfs_generic_pg_readpages, }; static const struct nfs_pageio_ops bl_pg_write_ops = { - .pg_init = pnfs_generic_pg_init_write, + .pg_init = bl_pg_init_write, .pg_test = pnfs_generic_pg_test, .pg_doio = pnfs_generic_pg_writepages, }; -- 1.7.1.262.g5ef3d