afs: Avoid GetDCache delays on screwy cache

Currently, if our afs_AllocDCache call fails in afs_GetDCache, we
retry once per second for 5 minutes. The reasoning is that we're out
of dcache slots, and so if we wait a little while, maybe something
will become freeable and we can continue.

However, afs_AllocDCache can also fail if we have plenty of free
dslots, but we are unable to successfully call afs_GetUnusedDSlot() on
any of them. This can happen if our disk cache is screwed up, and so
waiting and retrying will not make things better (but we'll spew a ton
of "disk cache read error in CacheItems slot" errors in the log each
time, and do so 300 times).

So instead, only do our sleep/retry loop if we actually appear to be
out of free or discarded dslots. Otherwise, just return an error
immediately, since sleeping and retrying will not make anything
better.

Change-Id: I331913ab882216e3f71cc44da91f7f7d33c34004
Reviewed-on: https://gerrit.openafs.org/13033
Reviewed-by: Mark Vitale <mvitale@sinenomine.net>
Reviewed-by: Michael Meffie <mmeffie@sinenomine.net>
Reviewed-by: Marcio Brito Barbosa <mbarbosa@sinenomine.net>
Reviewed-by: Benjamin Kaduk <kaduk@mit.edu>
Tested-by: BuildBot <buildbot@rampaginggeek.com>

diff --git a/src/afs/afs_dcache.c b/src/afs/afs_dcache.c
index 659e5ef..6dd79a5 100644 (file)
--- a/src/afs/afs_dcache.c
+++ b/src/afs/afs_dcache.c
@@ -1972,25 +1972,34 @@ afs_GetDCache(struct vcache *avc, afs_size_t abyte,
            tdc = afs_AllocDCache(avc, chunk, aflags, NULL);
            if (!tdc) {
                ReleaseWriteLock(&afs_xdcache);
-
-               /* If we can't get space for 5 mins we give up and bail out */
-               if (++downDCount > 300) {
-                    afs_warn("afs: Unable to get free cache space for file "
-                             "%u:%u.%u.%u for 5 minutes; failing with an i/o error\n",
-                             avc->f.fid.Cell,
-                             avc->f.fid.Fid.Volume,
-                             avc->f.fid.Fid.Vnode,
-                             avc->f.fid.Fid.Unique);
-                   goto done;
+                if (afs_discardDCList == NULLIDX && afs_freeDCList == NULLIDX) {
+                    /* It looks like afs_AllocDCache failed because we don't
+                     * have any free dslots to use. Maybe if we wait a little
+                     * while, we'll be able to free up some slots, so try for 5
+                     * minutes, then bail out. */
+                    if (++downDCount > 300) {
+                        afs_warn("afs: Unable to get free cache space for file "
+                                 "%u:%u.%u.%u for 5 minutes; failing with an i/o error\n",
+                                 avc->f.fid.Cell,
+                                 avc->f.fid.Fid.Volume,
+                                 avc->f.fid.Fid.Vnode,
+                                 avc->f.fid.Fid.Unique);
+                        goto done;
+                    }
+                    afs_osi_Wait(1000, 0, 0);
+                    goto RetryLookup;
                 }
 
-               /*
-                * Locks held:
-                * avc->lock(R) if setLocks
-                * avc->lock(W) if !setLocks
-                */
-               afs_osi_Wait(1000, 0, 0);
-               goto RetryLookup;
+                /* afs_AllocDCache failed, but not because we're out of free
+                 * dslots. Something must be screwy with the cache, so bail out
+                 * immediately without waiting. */
+                afs_warn("afs: Error while alloc'ing cache slot for file "
+                         "%u:%u.%u.%u; failing with an i/o error\n",
+                         avc->f.fid.Cell,
+                         avc->f.fid.Fid.Volume,
+                         avc->f.fid.Fid.Vnode,
+                         avc->f.fid.Fid.Unique);
+                goto done;
            }
 
            /*