| Message ID | 20190627135122.12817-1-lhenriques@suse.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [RFC] ceph: initialize superblock s_time_gran to 1 | expand |
On Thu, 2019-06-27 at 14:51 +0100, Luis Henriques wrote: > Having granularity set to 1us results in having inode timestamps with a > accurancy different from the fuse client (i.e. atime, ctime and mtime will > always end with '000'). This patch normalizes this behaviour and sets the > granularity to 1. > > Signed-off-by: Luis Henriques <lhenriques@suse.com> > --- > fs/ceph/super.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > Hi! > > As far as I could see there are no other side-effects of changing > s_time_gran but I'm really not sure why it was initially set to 1000 in > the first place so I may be missing something. > > diff --git a/fs/ceph/super.c b/fs/ceph/super.c > index d57fa60dcd43..35dd75bc9cd0 100644 > --- a/fs/ceph/super.c > +++ b/fs/ceph/super.c > @@ -980,7 +980,7 @@ static int ceph_set_super(struct super_block *s, void *data) > s->s_d_op = &ceph_dentry_ops; > s->s_export_op = &ceph_export_ops; > > - s->s_time_gran = 1000; /* 1000 ns == 1 us */ > + s->s_time_gran = 1; > > ret = set_anon_super(s, NULL); /* what is that second arg for? */ > if (ret != 0) Looks like it was set that way since the client code was originally merged. Was this an earlier limitation of ceph that is no longer applicable? In any case, I see no need at all to keep this at 1000, so: Reviewed-by: Jeff Layton <jlayton@kernel.org>
On Thu, 27 Jun 2019, Jeff Layton wrote: > On Thu, 2019-06-27 at 14:51 +0100, Luis Henriques wrote: > > Having granularity set to 1us results in having inode timestamps with a > > accurancy different from the fuse client (i.e. atime, ctime and mtime will > > always end with '000'). This patch normalizes this behaviour and sets the > > granularity to 1. > > > > Signed-off-by: Luis Henriques <lhenriques@suse.com> > > --- > > fs/ceph/super.c | 2 +- > > 1 file changed, 1 insertion(+), 1 deletion(-) > > > > Hi! > > > > As far as I could see there are no other side-effects of changing > > s_time_gran but I'm really not sure why it was initially set to 1000 in > > the first place so I may be missing something. > > > > diff --git a/fs/ceph/super.c b/fs/ceph/super.c > > index d57fa60dcd43..35dd75bc9cd0 100644 > > --- a/fs/ceph/super.c > > +++ b/fs/ceph/super.c > > @@ -980,7 +980,7 @@ static int ceph_set_super(struct super_block *s, void *data) > > s->s_d_op = &ceph_dentry_ops; > > s->s_export_op = &ceph_export_ops; > > > > - s->s_time_gran = 1000; /* 1000 ns == 1 us */ > > + s->s_time_gran = 1; > > > > ret = set_anon_super(s, NULL); /* what is that second arg for? */ > > if (ret != 0) > > > Looks like it was set that way since the client code was originally > merged. Was this an earlier limitation of ceph that is no longer > applicable? > > In any case, I see no need at all to keep this at 1000, so: As long as the encoded on-write time value is at ns resolution, I agree! No recollection of why I did this :( Reviewed-by: Sage Weil <sage@redhat.com>
On Thu, 2019-06-27 at 15:44 +0000, Sage Weil wrote: > On Thu, 27 Jun 2019, Jeff Layton wrote: > > On Thu, 2019-06-27 at 14:51 +0100, Luis Henriques wrote: > > > Having granularity set to 1us results in having inode timestamps with a > > > accurancy different from the fuse client (i.e. atime, ctime and mtime will > > > always end with '000'). This patch normalizes this behaviour and sets the > > > granularity to 1. > > > > > > Signed-off-by: Luis Henriques <lhenriques@suse.com> > > > --- > > > fs/ceph/super.c | 2 +- > > > 1 file changed, 1 insertion(+), 1 deletion(-) > > > > > > Hi! > > > > > > As far as I could see there are no other side-effects of changing > > > s_time_gran but I'm really not sure why it was initially set to 1000 in > > > the first place so I may be missing something. > > > > > > diff --git a/fs/ceph/super.c b/fs/ceph/super.c > > > index d57fa60dcd43..35dd75bc9cd0 100644 > > > --- a/fs/ceph/super.c > > > +++ b/fs/ceph/super.c > > > @@ -980,7 +980,7 @@ static int ceph_set_super(struct super_block *s, void *data) > > > s->s_d_op = &ceph_dentry_ops; > > > s->s_export_op = &ceph_export_ops; > > > > > > - s->s_time_gran = 1000; /* 1000 ns == 1 us */ > > > + s->s_time_gran = 1; > > > > > > ret = set_anon_super(s, NULL); /* what is that second arg for? */ > > > if (ret != 0) > > > > > > Looks like it was set that way since the client code was originally > > merged. Was this an earlier limitation of ceph that is no longer > > applicable? > > > > In any case, I see no need at all to keep this at 1000, so: > > As long as the encoded on-write time value is at ns resolution, I > agree! No recollection of why I did this :( > > Reviewed-by: Sage Weil <sage@redhat.com> Good enough for me. I went ahead and merged this into the testing branch. Assuming nothing breaks, this should make v5.3. Thanks,
Jeff Layton <jlayton@kernel.org> writes: > On Thu, 2019-06-27 at 15:44 +0000, Sage Weil wrote: >> On Thu, 27 Jun 2019, Jeff Layton wrote: >> > On Thu, 2019-06-27 at 14:51 +0100, Luis Henriques wrote: >> > > Having granularity set to 1us results in having inode timestamps with a >> > > accurancy different from the fuse client (i.e. atime, ctime and mtime will >> > > always end with '000'). This patch normalizes this behaviour and sets the >> > > granularity to 1. >> > > >> > > Signed-off-by: Luis Henriques <lhenriques@suse.com> >> > > --- >> > > fs/ceph/super.c | 2 +- >> > > 1 file changed, 1 insertion(+), 1 deletion(-) >> > > >> > > Hi! >> > > >> > > As far as I could see there are no other side-effects of changing >> > > s_time_gran but I'm really not sure why it was initially set to 1000 in >> > > the first place so I may be missing something. >> > > >> > > diff --git a/fs/ceph/super.c b/fs/ceph/super.c >> > > index d57fa60dcd43..35dd75bc9cd0 100644 >> > > --- a/fs/ceph/super.c >> > > +++ b/fs/ceph/super.c >> > > @@ -980,7 +980,7 @@ static int ceph_set_super(struct super_block *s, void *data) >> > > s->s_d_op = &ceph_dentry_ops; >> > > s->s_export_op = &ceph_export_ops; >> > > >> > > - s->s_time_gran = 1000; /* 1000 ns == 1 us */ >> > > + s->s_time_gran = 1; >> > > >> > > ret = set_anon_super(s, NULL); /* what is that second arg for? */ >> > > if (ret != 0) >> > >> > >> > Looks like it was set that way since the client code was originally >> > merged. Was this an earlier limitation of ceph that is no longer >> > applicable? >> > >> > In any case, I see no need at all to keep this at 1000, so: >> >> As long as the encoded on-write time value is at ns resolution, I >> agree! No recollection of why I did this :( >> >> Reviewed-by: Sage Weil <sage@redhat.com> > > Good enough for me. I went ahead and merged this into the testing > branch. Assuming nothing breaks, this should make v5.3. Awesome, thanks. AFAICS it shouldn't break anything, specially because the fuse client seems to be using ns resolution too. But yeah unexpected side-effects show up in unexpected ways :-) Cheers,
diff --git a/fs/ceph/super.c b/fs/ceph/super.c index d57fa60dcd43..35dd75bc9cd0 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -980,7 +980,7 @@ static int ceph_set_super(struct super_block *s, void *data) s->s_d_op = &ceph_dentry_ops; s->s_export_op = &ceph_export_ops; - s->s_time_gran = 1000; /* 1000 ns == 1 us */ + s->s_time_gran = 1; ret = set_anon_super(s, NULL); /* what is that second arg for? */ if (ret != 0)
Having granularity set to 1us results in having inode timestamps with a accurancy different from the fuse client (i.e. atime, ctime and mtime will always end with '000'). This patch normalizes this behaviour and sets the granularity to 1. Signed-off-by: Luis Henriques <lhenriques@suse.com> --- fs/ceph/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) Hi! As far as I could see there are no other side-effects of changing s_time_gran but I'm really not sure why it was initially set to 1000 in the first place so I may be missing something.