From 7c5d187581f57657de79e795602d9f1a0254c88c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Sep 2014 08:23:29 -0700 Subject: pnfs: force a layout commit when encountering busy segments during recall Expedite layout recall processing by forcing a layout commit when we see busy segments. Without it the layout recall might have to wait until the VM decided to start writeback for the file, which can introduce long delays. Signed-off-by: Christoph Hellwig Signed-off-by: Trond Myklebust --- fs/nfs/callback_proc.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'fs/nfs/callback_proc.c') diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 41db5258e7a..0d269515c64 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -171,6 +171,13 @@ static u32 initiate_file_draining(struct nfs_client *clp, goto out; ino = lo->plh_inode; + + spin_lock(&ino->i_lock); + pnfs_set_layout_stateid(lo, &args->cbl_stateid, true); + spin_unlock(&ino->i_lock); + + pnfs_layoutcommit_inode(ino, false); + spin_lock(&ino->i_lock); if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) || pnfs_mark_matching_lsegs_invalid(lo, &free_me_list, @@ -178,7 +185,6 @@ static u32 initiate_file_draining(struct nfs_client *clp, rv = NFS4ERR_DELAY; else rv = NFS4ERR_NOMATCHING_LAYOUT; - pnfs_set_layout_stateid(lo, &args->cbl_stateid, true); spin_unlock(&ino->i_lock); pnfs_free_lseg_list(&free_me_list); pnfs_put_layout_hdr(lo); -- cgit v1.2.3-70-g09d2 From c88953d87f5c8cd95bebcbd6d15f2f0cdd348136 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Sep 2014 08:23:31 -0700 Subject: pnfs: add return_range method If a layout driver keeps per-inode state outside of the layout segments it needs to be notified of any layout returns or recalls on an inode, and not just about the freeing of layout segments. Add a method to acomplish this, which will allow the block layout driver to handle the case of truncated and re-expanded files properly. Signed-off-by: Christoph Hellwig Signed-off-by: Trond Myklebust --- fs/nfs/callback_proc.c | 12 +++++++++--- fs/nfs/pnfs.c | 10 ++++++++++ fs/nfs/pnfs.h | 3 +++ 3 files changed, 22 insertions(+), 3 deletions(-) (limited to 'fs/nfs/callback_proc.c') diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 0d269515c64..56bd0eaf645 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -181,10 +181,16 @@ static u32 initiate_file_draining(struct nfs_client *clp, spin_lock(&ino->i_lock); if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) || pnfs_mark_matching_lsegs_invalid(lo, &free_me_list, - &args->cbl_range)) + &args->cbl_range)) { rv = NFS4ERR_DELAY; - else - rv = NFS4ERR_NOMATCHING_LAYOUT; + goto unlock; + } + + if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) { + NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo, + &args->cbl_range); + } +unlock: spin_unlock(&ino->i_lock); pnfs_free_lseg_list(&free_me_list); pnfs_put_layout_hdr(lo); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index ce5d1ea695d..76de7f56811 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -857,6 +857,16 @@ _pnfs_return_layout(struct inode *ino) empty = list_empty(&lo->plh_segs); pnfs_clear_layoutcommit(ino, &tmp_list); pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL); + + if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) { + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .offset = 0, + .length = NFS4_MAX_UINT64, + }; + NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo, &range); + } + /* Don't send a LAYOUTRETURN if list was initially empty */ if (empty) { spin_unlock(&ino->i_lock); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index a4c530e5214..2c249422593 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -94,6 +94,9 @@ struct pnfs_layoutdriver_type { struct pnfs_layout_segment * (*alloc_lseg) (struct pnfs_layout_hdr *layoutid, struct nfs4_layoutget_res *lgr, gfp_t gfp_flags); void (*free_lseg) (struct pnfs_layout_segment *lseg); + void (*return_range) (struct pnfs_layout_hdr *lo, + struct pnfs_layout_range *range); + /* test for nfs page cache coalescing */ const struct nfs_pageio_ops *pg_read_ops; const struct nfs_pageio_ops *pg_write_ops; -- cgit v1.2.3-70-g09d2 From 84c9dee3adc2bc49a52af74f18378a4887448288 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 10 Sep 2014 17:37:28 -0700 Subject: pnfs: enable CB_NOTIFY_DEVICEID support This code has been around for a while, but never was enabled, although it is in a working shape. Note that we implement NOTIFY_DEVICEID4_CHANGE identical to NOTIFY_DEVICEID4_DELETE. Given that in either case we can't do anything but preventing further lookups of a given device ID there isn't much difference in semantics for the two. For the delete case the server MUST ensure that there are no outstanding layouts, while for the change case it doesn't, but that has little relevance to the client. Signed-off-by: Christoph Hellwig Signed-off-by: Trond Myklebust --- fs/nfs/callback_proc.c | 3 --- fs/nfs/nfs4xdr.c | 31 +++++++++++++++++++++++-------- 2 files changed, 23 insertions(+), 11 deletions(-) (limited to 'fs/nfs/callback_proc.c') diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 56bd0eaf645..73466b93409 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -289,9 +289,6 @@ __be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args, } found: - if (dev->cbd_notify_type == NOTIFY_DEVICEID4_CHANGE) - dprintk("%s: NOTIFY_DEVICEID4_CHANGE not supported, " - "deleting instead\n", __func__); nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id); } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index b8165eab0a3..005d03c5d27 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -362,14 +362,19 @@ static int nfs4_stat_to_errno(int); XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5) #define encode_reclaim_complete_maxsz (op_encode_hdr_maxsz + 4) #define decode_reclaim_complete_maxsz (op_decode_hdr_maxsz + 4) -#define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + 4 + \ - XDR_QUADLEN(NFS4_DEVICEID4_SIZE)) +#define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + \ + XDR_QUADLEN(NFS4_DEVICEID4_SIZE) + \ + 1 /* layout type */ + \ + 1 /* maxcount */ + \ + 1 /* bitmap size */ + \ + 1 /* notification bitmap length */ + \ + 1 /* notification bitmap, word 0 */) #define decode_getdeviceinfo_maxsz (op_decode_hdr_maxsz + \ 1 /* layout type */ + \ 1 /* opaque devaddr4 length */ + \ /* devaddr4 payload is read into page */ \ 1 /* notification bitmap length */ + \ - 1 /* notification bitmap */) + 1 /* notification bitmap, word 0 */) #define encode_layoutget_maxsz (op_encode_hdr_maxsz + 10 + \ encode_stateid_maxsz) #define decode_layoutget_maxsz (op_decode_hdr_maxsz + 8 + \ @@ -1918,12 +1923,15 @@ encode_getdeviceinfo(struct xdr_stream *xdr, __be32 *p; encode_op_hdr(xdr, OP_GETDEVICEINFO, decode_getdeviceinfo_maxsz, hdr); - p = reserve_space(xdr, 12 + NFS4_DEVICEID4_SIZE); + p = reserve_space(xdr, NFS4_DEVICEID4_SIZE + 4 + 4); p = xdr_encode_opaque_fixed(p, args->pdev->dev_id.data, NFS4_DEVICEID4_SIZE); *p++ = cpu_to_be32(args->pdev->layout_type); *p++ = cpu_to_be32(args->pdev->maxcount); /* gdia_maxcount */ - *p++ = cpu_to_be32(0); /* bitmap length 0 */ + + p = reserve_space(xdr, 4 + 4); + *p++ = cpu_to_be32(1); /* bitmap length */ + *p++ = cpu_to_be32(NOTIFY_DEVICEID4_CHANGE | NOTIFY_DEVICEID4_DELETE); } static void @@ -5767,9 +5775,16 @@ static int decode_getdeviceinfo(struct xdr_stream *xdr, p = xdr_inline_decode(xdr, 4 * len); if (unlikely(!p)) goto out_overflow; - for (i = 0; i < len; i++, p++) { - if (be32_to_cpup(p)) { - dprintk("%s: notifications not supported\n", + + if (be32_to_cpup(p++) & + ~(NOTIFY_DEVICEID4_CHANGE | NOTIFY_DEVICEID4_DELETE)) { + dprintk("%s: unsupported notification\n", + __func__); + } + + for (i = 1; i < len; i++) { + if (be32_to_cpup(p++)) { + dprintk("%s: unsupported notification\n", __func__); return -EIO; } -- cgit v1.2.3-70-g09d2