From: Michael Haggerty <mhagger@alum.mit.edu>
To: Jeff King <peff@peff.net>
Cc: git@vger.kernel.org, Johan Herland <johan@herland.net>,
Junio C Hamano <gitster@pobox.com>,
Michael Haggerty <mhagger@alum.mit.edu>
Subject: [RFC 1/2] Extract a struct stat_data from cache_entry
Date: Mon, 13 May 2013 05:00:06 +0200 [thread overview]
Message-ID: <1368414007-3819-2-git-send-email-mhagger@alum.mit.edu> (raw)
In-Reply-To: <1368414007-3819-1-git-send-email-mhagger@alum.mit.edu>
This structure will later be used to check the validity of other types
of file.
Signed-off-by: Michael Haggerty <mhagger@alum.mit.edu>
---
Feel free to suggest better names. I tried to follow the convention
of names used nearby.
builtin/ls-files.c | 12 ++--
cache.h | 33 ++++++++---
read-cache.c | 161 +++++++++++++++++++++++++++++++----------------------
3 files changed, 126 insertions(+), 80 deletions(-)
diff --git a/builtin/ls-files.c b/builtin/ls-files.c
index 2202072..6a0730f 100644
--- a/builtin/ls-files.c
+++ b/builtin/ls-files.c
@@ -165,11 +165,13 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce)
}
write_name(ce->name, ce_namelen(ce));
if (debug_mode) {
- printf(" ctime: %d:%d\n", ce->ce_ctime.sec, ce->ce_ctime.nsec);
- printf(" mtime: %d:%d\n", ce->ce_mtime.sec, ce->ce_mtime.nsec);
- printf(" dev: %d\tino: %d\n", ce->ce_dev, ce->ce_ino);
- printf(" uid: %d\tgid: %d\n", ce->ce_uid, ce->ce_gid);
- printf(" size: %d\tflags: %x\n", ce->ce_size, ce->ce_flags);
+ struct stat_data *sd = &ce->ce_stat_data;
+
+ printf(" ctime: %d:%d\n", sd->sd_ctime.sec, sd->sd_ctime.nsec);
+ printf(" mtime: %d:%d\n", sd->sd_mtime.sec, sd->sd_mtime.nsec);
+ printf(" dev: %d\tino: %d\n", sd->sd_dev, sd->sd_ino);
+ printf(" uid: %d\tgid: %d\n", sd->sd_uid, sd->sd_gid);
+ printf(" size: %d\tflags: %x\n", sd->sd_size, ce->ce_flags);
}
}
diff --git a/cache.h b/cache.h
index 94ca1ac..55b4b14 100644
--- a/cache.h
+++ b/cache.h
@@ -119,15 +119,19 @@ struct cache_time {
unsigned int nsec;
};
+struct stat_data {
+ struct cache_time sd_ctime;
+ struct cache_time sd_mtime;
+ unsigned int sd_dev;
+ unsigned int sd_ino;
+ unsigned int sd_uid;
+ unsigned int sd_gid;
+ unsigned int sd_size;
+};
+
struct cache_entry {
- struct cache_time ce_ctime;
- struct cache_time ce_mtime;
- unsigned int ce_dev;
- unsigned int ce_ino;
+ struct stat_data ce_stat_data;
unsigned int ce_mode;
- unsigned int ce_uid;
- unsigned int ce_gid;
- unsigned int ce_size;
unsigned int ce_flags;
unsigned int ce_namelen;
unsigned char sha1[20];
@@ -509,6 +513,21 @@ extern int limit_pathspec_to_literal(void);
#define HASH_FORMAT_CHECK 2
extern int index_fd(unsigned char *sha1, int fd, struct stat *st, enum object_type type, const char *path, unsigned flags);
extern int index_path(unsigned char *sha1, const char *path, struct stat *st, unsigned flags);
+
+/*
+ * Record to sd the data from st that we use to check whether a file
+ * might have changed.
+ */
+extern void fill_stat_data(struct stat_data *sd, struct stat *st);
+
+/*
+ * Return 0 if st is consistent with a file not having been changed
+ * since sd was filled. If there are differences, return a
+ * combination of MTIME_CHANGED, CTIME_CHANGED, OWNER_CHANGED,
+ * INODE_CHANGED, and DATA_CHANGED.
+ */
+extern int match_stat_data(struct stat_data *sd, struct stat *st);
+
extern void fill_stat_cache_info(struct cache_entry *ce, struct stat *st);
#define REFRESH_REALLY 0x0001 /* ignore_valid */
diff --git a/read-cache.c b/read-cache.c
index 04ed561..9c1e089 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -68,21 +68,78 @@ void rename_index_entry_at(struct index_state *istate, int nr, const char *new_n
}
/*
+ * Record to sd the data from st that we use to check whether a file
+ * might have changed.
+ */
+void fill_stat_data(struct stat_data *sd, struct stat *st)
+{
+ sd->sd_ctime.sec = (unsigned int)st->st_ctime;
+ sd->sd_mtime.sec = (unsigned int)st->st_mtime;
+ sd->sd_ctime.nsec = ST_CTIME_NSEC(*st);
+ sd->sd_mtime.nsec = ST_MTIME_NSEC(*st);
+ sd->sd_dev = st->st_dev;
+ sd->sd_ino = st->st_ino;
+ sd->sd_uid = st->st_uid;
+ sd->sd_gid = st->st_gid;
+ sd->sd_size = st->st_size;
+}
+
+/*
+ * Return 0 if st is consistent with a file not having been changed
+ * since sd was filled. If there are differences, return a
+ * combination of MTIME_CHANGED, CTIME_CHANGED, OWNER_CHANGED,
+ * INODE_CHANGED, and DATA_CHANGED.
+ */
+int match_stat_data(struct stat_data *sd, struct stat *st)
+{
+ int changed = 0;
+
+ if (sd->sd_mtime.sec != (unsigned int)st->st_mtime)
+ changed |= MTIME_CHANGED;
+ if (trust_ctime && check_stat &&
+ sd->sd_ctime.sec != (unsigned int)st->st_ctime)
+ changed |= CTIME_CHANGED;
+
+#ifdef USE_NSEC
+ if (check_stat && sd->sd_mtime.nsec != ST_MTIME_NSEC(*st))
+ changed |= MTIME_CHANGED;
+ if (trust_ctime && check_stat &&
+ sd->sd_ctime.nsec != ST_CTIME_NSEC(*st))
+ changed |= CTIME_CHANGED;
+#endif
+
+ if (check_stat) {
+ if (sd->sd_uid != (unsigned int) st->st_uid ||
+ sd->sd_gid != (unsigned int) st->st_gid)
+ changed |= OWNER_CHANGED;
+ if (sd->sd_ino != (unsigned int) st->st_ino)
+ changed |= INODE_CHANGED;
+ }
+
+#ifdef USE_STDEV
+ /*
+ * st_dev breaks on network filesystems where different
+ * clients will have different views of what "device"
+ * the filesystem is on
+ */
+ if (check_stat && sd->sd_dev != (unsigned int) st->st_dev)
+ changed |= INODE_CHANGED;
+#endif
+
+ if (sd->sd_size != (unsigned int) st->st_size)
+ changed |= DATA_CHANGED;
+
+ return changed;
+}
+
+/*
* This only updates the "non-critical" parts of the directory
* cache, ie the parts that aren't tracked by GIT, and only used
* to validate the cache.
*/
void fill_stat_cache_info(struct cache_entry *ce, struct stat *st)
{
- ce->ce_ctime.sec = (unsigned int)st->st_ctime;
- ce->ce_mtime.sec = (unsigned int)st->st_mtime;
- ce->ce_ctime.nsec = ST_CTIME_NSEC(*st);
- ce->ce_mtime.nsec = ST_MTIME_NSEC(*st);
- ce->ce_dev = st->st_dev;
- ce->ce_ino = st->st_ino;
- ce->ce_uid = st->st_uid;
- ce->ce_gid = st->st_gid;
- ce->ce_size = st->st_size;
+ fill_stat_data(&ce->ce_stat_data, st);
if (assume_unchanged)
ce->ce_flags |= CE_VALID;
@@ -195,43 +252,11 @@ static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st)
default:
die("internal error: ce_mode is %o", ce->ce_mode);
}
- if (ce->ce_mtime.sec != (unsigned int)st->st_mtime)
- changed |= MTIME_CHANGED;
- if (trust_ctime && check_stat &&
- ce->ce_ctime.sec != (unsigned int)st->st_ctime)
- changed |= CTIME_CHANGED;
-
-#ifdef USE_NSEC
- if (check_stat && ce->ce_mtime.nsec != ST_MTIME_NSEC(*st))
- changed |= MTIME_CHANGED;
- if (trust_ctime && check_stat &&
- ce->ce_ctime.nsec != ST_CTIME_NSEC(*st))
- changed |= CTIME_CHANGED;
-#endif
- if (check_stat) {
- if (ce->ce_uid != (unsigned int) st->st_uid ||
- ce->ce_gid != (unsigned int) st->st_gid)
- changed |= OWNER_CHANGED;
- if (ce->ce_ino != (unsigned int) st->st_ino)
- changed |= INODE_CHANGED;
- }
-
-#ifdef USE_STDEV
- /*
- * st_dev breaks on network filesystems where different
- * clients will have different views of what "device"
- * the filesystem is on
- */
- if (check_stat && ce->ce_dev != (unsigned int) st->st_dev)
- changed |= INODE_CHANGED;
-#endif
-
- if (ce->ce_size != (unsigned int) st->st_size)
- changed |= DATA_CHANGED;
+ changed |= match_stat_data(&ce->ce_stat_data, st);
/* Racily smudged entry? */
- if (!ce->ce_size) {
+ if (!ce->ce_stat_data.sd_size) {
if (!is_empty_blob_sha1(ce->sha1))
changed |= DATA_CHANGED;
}
@@ -245,11 +270,11 @@ static int is_racy_timestamp(const struct index_state *istate, struct cache_entr
istate->timestamp.sec &&
#ifdef USE_NSEC
/* nanosecond timestamped files can also be racy! */
- (istate->timestamp.sec < ce->ce_mtime.sec ||
- (istate->timestamp.sec == ce->ce_mtime.sec &&
- istate->timestamp.nsec <= ce->ce_mtime.nsec))
+ (istate->timestamp.sec < ce->ce_stat_data.sd_mtime.sec ||
+ (istate->timestamp.sec == ce->ce_stat_data.sd_mtime.sec &&
+ istate->timestamp.nsec <= ce->ce_stat_data.sd_mtime.nsec))
#else
- istate->timestamp.sec <= ce->ce_mtime.sec
+ istate->timestamp.sec <= ce->ce_stat_data.sd_mtime.sec
#endif
);
}
@@ -340,7 +365,7 @@ int ie_modified(const struct index_state *istate,
* then we know it is.
*/
if ((changed & DATA_CHANGED) &&
- (S_ISGITLINK(ce->ce_mode) || ce->ce_size != 0))
+ (S_ISGITLINK(ce->ce_mode) || ce->ce_stat_data.sd_size != 0))
return changed;
changed_fs = ce_modified_check_fs(ce, st);
@@ -1322,16 +1347,16 @@ static struct cache_entry *cache_entry_from_ondisk(struct ondisk_cache_entry *on
{
struct cache_entry *ce = xmalloc(cache_entry_size(len));
- ce->ce_ctime.sec = ntoh_l(ondisk->ctime.sec);
- ce->ce_mtime.sec = ntoh_l(ondisk->mtime.sec);
- ce->ce_ctime.nsec = ntoh_l(ondisk->ctime.nsec);
- ce->ce_mtime.nsec = ntoh_l(ondisk->mtime.nsec);
- ce->ce_dev = ntoh_l(ondisk->dev);
- ce->ce_ino = ntoh_l(ondisk->ino);
+ ce->ce_stat_data.sd_ctime.sec = ntoh_l(ondisk->ctime.sec);
+ ce->ce_stat_data.sd_mtime.sec = ntoh_l(ondisk->mtime.sec);
+ ce->ce_stat_data.sd_ctime.nsec = ntoh_l(ondisk->ctime.nsec);
+ ce->ce_stat_data.sd_mtime.nsec = ntoh_l(ondisk->mtime.nsec);
+ ce->ce_stat_data.sd_dev = ntoh_l(ondisk->dev);
+ ce->ce_stat_data.sd_ino = ntoh_l(ondisk->ino);
ce->ce_mode = ntoh_l(ondisk->mode);
- ce->ce_uid = ntoh_l(ondisk->uid);
- ce->ce_gid = ntoh_l(ondisk->gid);
- ce->ce_size = ntoh_l(ondisk->size);
+ ce->ce_stat_data.sd_uid = ntoh_l(ondisk->uid);
+ ce->ce_stat_data.sd_gid = ntoh_l(ondisk->gid);
+ ce->ce_stat_data.sd_size = ntoh_l(ondisk->size);
ce->ce_flags = flags & ~CE_NAMEMASK;
ce->ce_namelen = len;
hashcpy(ce->sha1, ondisk->sha1);
@@ -1608,7 +1633,7 @@ static void ce_smudge_racily_clean_entry(struct cache_entry *ce)
* The only thing we care about in this function is to smudge the
* falsely clean entry due to touch-update-touch race, so we leave
* everything else as they are. We are called for entries whose
- * ce_mtime match the index file mtime.
+ * ce_stat_data.sd_mtime match the index file mtime.
*
* Note that this actually does not do much for gitlinks, for
* which ce_match_stat_basic() always goes to the actual
@@ -1647,7 +1672,7 @@ static void ce_smudge_racily_clean_entry(struct cache_entry *ce)
* file, and never calls us, so the cached size information
* for "frotz" stays 6 which does not match the filesystem.
*/
- ce->ce_size = 0;
+ ce->ce_stat_data.sd_size = 0;
}
}
@@ -1657,16 +1682,16 @@ static char *copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk,
{
short flags;
- ondisk->ctime.sec = htonl(ce->ce_ctime.sec);
- ondisk->mtime.sec = htonl(ce->ce_mtime.sec);
- ondisk->ctime.nsec = htonl(ce->ce_ctime.nsec);
- ondisk->mtime.nsec = htonl(ce->ce_mtime.nsec);
- ondisk->dev = htonl(ce->ce_dev);
- ondisk->ino = htonl(ce->ce_ino);
+ ondisk->ctime.sec = htonl(ce->ce_stat_data.sd_ctime.sec);
+ ondisk->mtime.sec = htonl(ce->ce_stat_data.sd_mtime.sec);
+ ondisk->ctime.nsec = htonl(ce->ce_stat_data.sd_ctime.nsec);
+ ondisk->mtime.nsec = htonl(ce->ce_stat_data.sd_mtime.nsec);
+ ondisk->dev = htonl(ce->ce_stat_data.sd_dev);
+ ondisk->ino = htonl(ce->ce_stat_data.sd_ino);
ondisk->mode = htonl(ce->ce_mode);
- ondisk->uid = htonl(ce->ce_uid);
- ondisk->gid = htonl(ce->ce_gid);
- ondisk->size = htonl(ce->ce_size);
+ ondisk->uid = htonl(ce->ce_stat_data.sd_uid);
+ ondisk->gid = htonl(ce->ce_stat_data.sd_gid);
+ ondisk->size = htonl(ce->ce_stat_data.sd_size);
hashcpy(ondisk->sha1, ce->sha1);
flags = ce->ce_flags;
--
1.8.2.2
next prev parent reply other threads:[~2013-05-13 3:00 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-05-03 8:38 another packed-refs race Jeff King
2013-05-03 9:26 ` Johan Herland
2013-05-03 17:28 ` Jeff King
2013-05-03 18:26 ` Jeff King
2013-05-03 21:02 ` Johan Herland
2013-05-06 12:12 ` Michael Haggerty
2013-05-06 18:44 ` Jeff King
2013-05-03 21:21 ` Jeff King
2013-05-06 12:03 ` Michael Haggerty
2013-05-06 18:41 ` Jeff King
2013-05-06 22:18 ` Jeff King
2013-05-07 4:32 ` Michael Haggerty
2013-05-07 4:44 ` Jeff King
2013-05-07 8:03 ` Michael Haggerty
2013-05-07 2:36 ` [PATCH 0/4] fix packed-refs races Jeff King
2013-05-07 2:38 ` [PATCH 1/4] resolve_ref: close race condition for packed refs Jeff King
2013-05-12 22:56 ` Michael Haggerty
2013-05-16 3:47 ` Jeff King
2013-05-16 5:50 ` Michael Haggerty
2013-05-12 23:26 ` Michael Haggerty
2013-06-11 14:26 ` [PATCH 0/4] Fix a race condition when reading loose refs Michael Haggerty
2013-06-11 14:26 ` [PATCH 1/4] resolve_ref_unsafe(): extract function handle_missing_loose_ref() Michael Haggerty
2013-06-11 14:26 ` [PATCH 2/4] resolve_ref_unsafe(): handle the case of an SHA-1 within loop Michael Haggerty
2013-06-11 14:26 ` [PATCH 3/4] resolve_ref_unsafe(): nest reference-reading code in an infinite loop Michael Haggerty
2013-06-11 14:26 ` [PATCH 4/4] resolve_ref_unsafe(): close race condition reading loose refs Michael Haggerty
2013-06-12 8:04 ` Jeff King
2013-06-13 8:22 ` Thomas Rast
2013-06-14 7:17 ` Michael Haggerty
2013-06-11 20:57 ` [PATCH 0/4] Fix a race condition when " Junio C Hamano
2013-05-07 2:39 ` [PATCH 2/4] add a stat_validity struct Jeff King
2013-05-13 2:29 ` Michael Haggerty
2013-05-13 3:00 ` [RFC 0/2] Separate stat_data from cache_entry Michael Haggerty
2013-05-13 3:00 ` Michael Haggerty [this message]
2013-05-13 3:00 ` [RFC 2/2] add a stat_validity struct Michael Haggerty
2013-05-13 5:10 ` [RFC 0/2] Separate stat_data from cache_entry Junio C Hamano
2013-05-16 3:51 ` [PATCH 2/4] add a stat_validity struct Jeff King
2013-05-07 2:43 ` [PATCH 3/4] get_packed_refs: reload packed-refs file when it changes Jeff King
2013-05-07 2:54 ` [PATCH 0/2] peel_ref cleanups changes Jeff King
2013-05-07 2:56 ` [PATCH 1/2] peel_ref: rename "sha1" argument to "peeled" Jeff King
2013-05-07 3:06 ` [PATCH 2/2] peel_ref: refactor for safety with simultaneous update Jeff King
2013-05-09 19:18 ` [PATCH 3/4] get_packed_refs: reload packed-refs file when it changes Eric Sunshine
2013-05-13 2:43 ` Michael Haggerty
2013-05-07 2:51 ` [PATCH 4/4] for_each_ref: load all loose refs before packed refs Jeff King
2013-05-07 6:40 ` [PATCH 0/4] fix packed-refs races Junio C Hamano
2013-05-07 14:19 ` Jeff King
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: http://vger.kernel.org/majordomo-info.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1368414007-3819-2-git-send-email-mhagger@alum.mit.edu \
--to=mhagger@alum.mit.edu \
--cc=git@vger.kernel.org \
--cc=gitster@pobox.com \
--cc=johan@herland.net \
--cc=peff@peff.net \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://80x24.org/mirrors/git.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).