On Wed, Dec 01, 2021 at 01:03:39PM -0500, Bruce Fields wrote:
> On Wed, Dec 01, 2021 at 12:42:05PM -0500, Bruce Fields wrote:
> > On Wed, Dec 01, 2021 at 09:36:30AM -0500, Bruce Fields wrote:
> > > OK, good to know. It'd be interesting to dig into where nfsdcltrack is
> > > spending its time, which we could do by replacing it with a wrapper that
> > > runs the real nfsdcltrack under strace.
> > >
> > > Though maybe it'd be better to do this on a system using nfsdcld, since
> > > that's what we're transitioning to.
> >
> > Trying that on a test VM here, I see each upcall doing 3 fdatasyncs() of
> > an sqlite-journal file. On my setup, each of those is taking a few
> > milliseconds. I wonder if it an do better.
>
> If I understand the sqlite documentation correctly, I *think* that if we
> use journal_mode WAL with synchronous FULL, we should get the assurances
> nfsd needs with one sync per transaction.
So I *think* that would mean just doing something like (untested, don't have
much idea what I'm doing):
diff --git a/utils/nfsdcld/sqlite.c b/utils/nfsdcld/sqlite.c
index 03016fb95823..b30f2614497b 100644
--- a/utils/nfsdcld/sqlite.c
+++ b/utils/nfsdcld/sqlite.c
@@ -826,6 +826,13 @@ sqlite_prepare_dbh(const char *topdir)
goto out_close;
}
+ ret = sqlite3_exec(dbh, "PRAGMA journal_mode = WAL;", NULL, NULL, NULL);
+ if (ret)
+ goto out_close;
+ ret = sqlite3_exec(dbh, "PRAGMA synchronous = FULL;", NULL, NULL, NULL);
+ if (ret)
+ goto out_close;
+
ret = sqlite_query_schema_version();
switch (ret) {
case CLD_SQLITE_LATEST_SCHEMA_VERSION:
I also wonder how expensive may be the extra overhead of starting up
nfsdcltrack each time.
--b.
