From 4e40eff0b5737c0de39e1ae5812509efbc0b986e Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:18 -0400 Subject: fs: add infrastructure for multigrain timestamps The VFS has always used coarse-grained timestamps when updating the ctime and mtime after a change. This has the benefit of allowing filesystems to optimize away a lot metadata updates, down to around 1 per jiffy, even when a file is under heavy writes. Unfortunately, this has always been an issue when we're exporting via NFSv3, which relies on timestamps to validate caches. A lot of changes can happen in a jiffy, so timestamps aren't sufficient to help the client decide when to invalidate the cache. Even with NFSv4, a lot of exported filesystems don't properly support a change attribute and are subject to the same problems with timestamp granularity. Other applications have similar issues with timestamps (e.g backup applications). If fine-grained timestamps were always used, that would improve the situation, but that becomes rather expensive, as the underlying filesystem would have to log a lot more metadata updates. What is needed is a way to only use fine-grained timestamps when they are being actively queried. Use the (unused) top bit in inode->i_ctime_nsec as a flag that indicates whether the current timestamps have been queried via stat() or the like. When it's set, allow the update to use a fine-grained timestamp iff it's necessary to make the ctime show a different value. If it has been queried, then first see whether the current coarse time is later than the existing ctime. If it is, accept that value. If it isn't, then get a fine-grained timestamp and attempt to stamp the inode ctime with that value. If that races with another concurrent stamp, then abandon the update and take the new value without retrying. Filesystems can opt into this by setting the FS_MGTIME fstype flag. Others should be unaffected (other than being subject to the same floor value as multigrain filesystems). Tested-by: Randy Dunlap # documentation bits Reviewed-by: Jan Kara Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/20241002-mgtime-v10-3-d1c4717f5284@kernel.org Signed-off-by: Christian Brauner --- fs/stat.c | 43 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 41 insertions(+), 2 deletions(-) (limited to 'fs/stat.c') diff --git a/fs/stat.c b/fs/stat.c index 89ce1be56310..dd480bf51a2a 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -26,6 +26,39 @@ #include "internal.h" #include "mount.h" +/** + * fill_mg_cmtime - Fill in the mtime and ctime and flag ctime as QUERIED + * @stat: where to store the resulting values + * @request_mask: STATX_* values requested + * @inode: inode from which to grab the c/mtime + * + * Given @inode, grab the ctime and mtime out if it and store the result + * in @stat. When fetching the value, flag it as QUERIED (if not already) + * so the next write will record a distinct timestamp. + * + * NB: The QUERIED flag is tracked in the ctime, but we set it there even + * if only the mtime was requested, as that ensures that the next mtime + * change will be distinct. + */ +void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode) +{ + atomic_t *pcn = (atomic_t *)&inode->i_ctime_nsec; + + /* If neither time was requested, then don't report them */ + if (!(request_mask & (STATX_CTIME|STATX_MTIME))) { + stat->result_mask &= ~(STATX_CTIME|STATX_MTIME); + return; + } + + stat->mtime = inode_get_mtime(inode); + stat->ctime.tv_sec = inode->i_ctime_sec; + stat->ctime.tv_nsec = (u32)atomic_read(pcn); + if (!(stat->ctime.tv_nsec & I_CTIME_QUERIED)) + stat->ctime.tv_nsec = ((u32)atomic_fetch_or(I_CTIME_QUERIED, pcn)); + stat->ctime.tv_nsec &= ~I_CTIME_QUERIED; +} +EXPORT_SYMBOL(fill_mg_cmtime); + /** * generic_fillattr - Fill in the basic attributes from the inode struct * @idmap: idmap of the mount the inode was found from @@ -58,8 +91,14 @@ void generic_fillattr(struct mnt_idmap *idmap, u32 request_mask, stat->rdev = inode->i_rdev; stat->size = i_size_read(inode); stat->atime = inode_get_atime(inode); - stat->mtime = inode_get_mtime(inode); - stat->ctime = inode_get_ctime(inode); + + if (is_mgtime(inode)) { + fill_mg_cmtime(stat, request_mask, inode); + } else { + stat->ctime = inode_get_ctime(inode); + stat->mtime = inode_get_mtime(inode); + } + stat->blksize = i_blocksize(inode); stat->blocks = inode->i_blocks; -- cgit v1.2.3 From c86e3c47187ad7fa17f8533a4142453991684b46 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:21 -0400 Subject: fs: tracepoints around multigrain timestamp events Add some tracepoints around various multigrain timestamp events. Reviewed-by: Josef Bacik Reviewed-by: Darrick J. Wong Reviewed-by: Jan Kara Reviewed-by: Steven Rostedt (Google) Tested-by: Randy Dunlap # documentation bits Signed-off-by: Jeff Layton Link: https://lore.kernel.org/r/20241002-mgtime-v10-6-d1c4717f5284@kernel.org Signed-off-by: Christian Brauner --- fs/inode.c | 9 ++- fs/stat.c | 3 + include/trace/events/timestamp.h | 124 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 135 insertions(+), 1 deletion(-) create mode 100644 include/trace/events/timestamp.h (limited to 'fs/stat.c') diff --git a/fs/inode.c b/fs/inode.c index 7d1ede60e549..f7a25c511d6b 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -22,6 +22,9 @@ #include #include #include +#define CREATE_TRACE_POINTS +#include + #include "internal.h" /* @@ -2603,6 +2606,7 @@ EXPORT_SYMBOL(inode_nohighmem); struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts) { + trace_inode_set_ctime_to_ts(inode, &ts); set_normalized_timespec64(&ts, ts.tv_sec, ts.tv_nsec); inode->i_ctime_sec = ts.tv_sec; inode->i_ctime_nsec = ts.tv_nsec; @@ -2689,14 +2693,17 @@ struct timespec64 inode_set_ctime_current(struct inode *inode) } /* No need to cmpxchg if it's exactly the same */ - if (cns == now.tv_nsec && inode->i_ctime_sec == now.tv_sec) + if (cns == now.tv_nsec && inode->i_ctime_sec == now.tv_sec) { + trace_ctime_xchg_skip(inode, &now); goto out; + } cur = cns; retry: /* Try to swap the nsec value into place. */ if (try_cmpxchg(&inode->i_ctime_nsec, &cur, now.tv_nsec)) { /* If swap occurred, then we're (mostly) done */ inode->i_ctime_sec = now.tv_sec; + trace_ctime_ns_xchg(inode, cns, now.tv_nsec, cur); } else { /* * Was the change due to someone marking the old ctime QUERIED? diff --git a/fs/stat.c b/fs/stat.c index dd480bf51a2a..6eb6c39d0037 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -23,6 +23,8 @@ #include #include +#include + #include "internal.h" #include "mount.h" @@ -56,6 +58,7 @@ void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode) if (!(stat->ctime.tv_nsec & I_CTIME_QUERIED)) stat->ctime.tv_nsec = ((u32)atomic_fetch_or(I_CTIME_QUERIED, pcn)); stat->ctime.tv_nsec &= ~I_CTIME_QUERIED; + trace_fill_mg_cmtime(inode, &stat->ctime, &stat->mtime); } EXPORT_SYMBOL(fill_mg_cmtime); diff --git a/include/trace/events/timestamp.h b/include/trace/events/timestamp.h new file mode 100644 index 000000000000..c9e5ec930054 --- /dev/null +++ b/include/trace/events/timestamp.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM timestamp + +#if !defined(_TRACE_TIMESTAMP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_TIMESTAMP_H + +#include +#include + +#define CTIME_QUERIED_FLAGS \ + { I_CTIME_QUERIED, "Q" } + +DECLARE_EVENT_CLASS(ctime, + TP_PROTO(struct inode *inode, + struct timespec64 *ctime), + + TP_ARGS(inode, ctime), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(time64_t, ctime_s) + __field(u32, ctime_ns) + __field(u32, gen) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->gen = inode->i_generation; + __entry->ctime_s = ctime->tv_sec; + __entry->ctime_ns = ctime->tv_nsec; + ), + + TP_printk("ino=%d:%d:%ld:%u ctime=%lld.%u", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, + __entry->ctime_s, __entry->ctime_ns + ) +); + +DEFINE_EVENT(ctime, inode_set_ctime_to_ts, + TP_PROTO(struct inode *inode, + struct timespec64 *ctime), + TP_ARGS(inode, ctime)); + +DEFINE_EVENT(ctime, ctime_xchg_skip, + TP_PROTO(struct inode *inode, + struct timespec64 *ctime), + TP_ARGS(inode, ctime)); + +TRACE_EVENT(ctime_ns_xchg, + TP_PROTO(struct inode *inode, + u32 old, + u32 new, + u32 cur), + + TP_ARGS(inode, old, new, cur), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(u32, gen) + __field(u32, old) + __field(u32, new) + __field(u32, cur) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->gen = inode->i_generation; + __entry->old = old; + __entry->new = new; + __entry->cur = cur; + ), + + TP_printk("ino=%d:%d:%ld:%u old=%u:%s new=%u cur=%u:%s", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, + __entry->old & ~I_CTIME_QUERIED, + __print_flags(__entry->old & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS), + __entry->new, + __entry->cur & ~I_CTIME_QUERIED, + __print_flags(__entry->cur & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS) + ) +); + +TRACE_EVENT(fill_mg_cmtime, + TP_PROTO(struct inode *inode, + struct timespec64 *ctime, + struct timespec64 *mtime), + + TP_ARGS(inode, ctime, mtime), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(ino_t, ino) + __field(time64_t, ctime_s) + __field(time64_t, mtime_s) + __field(u32, ctime_ns) + __field(u32, mtime_ns) + __field(u32, gen) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->gen = inode->i_generation; + __entry->ctime_s = ctime->tv_sec; + __entry->mtime_s = mtime->tv_sec; + __entry->ctime_ns = ctime->tv_nsec; + __entry->mtime_ns = mtime->tv_nsec; + ), + + TP_printk("ino=%d:%d:%ld:%u ctime=%lld.%u mtime=%lld.%u", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, + __entry->ctime_s, __entry->ctime_ns, + __entry->mtime_s, __entry->mtime_ns + ) +); +#endif /* _TRACE_TIMESTAMP_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3