FS-Cache doesn't correctly handle the netfs requesting a read from the cache
on an object that failed or was withdrawn by the cache. A trace similar to
the following might be seen:
CacheFiles: Lookup failed error -105
[exe ] unexpected submission OP165afe [OBJ6cac OBJECT_LC_DYING]
[exe ] objstate=OBJECT_LC_DYING [OBJECT_LC_DYING]
[exe ] objflags=0
[exe ] objevent=9 [
fffffffffffffffb]
[exe ] ops=0 inp=0 exc=0
Pid: 6970, comm: exe Not tainted 2.6.32-rc6-cachefs #50
Call Trace:
[<
ffffffffa0076477>] fscache_submit_op+0x3ff/0x45a [fscache]
[<
ffffffffa0077997>] __fscache_read_or_alloc_pages+0x187/0x3c4 [fscache]
[<
ffffffffa00b6480>] ? nfs_readpage_from_fscache_complete+0x0/0x66 [nfs]
[<
ffffffffa00b6388>] __nfs_readpages_from_fscache+0x7e/0x176 [nfs]
[<
ffffffff8108e483>] ? __alloc_pages_nodemask+0x11c/0x5cf
[<
ffffffffa009d796>] nfs_readpages+0x114/0x1d7 [nfs]
[<
ffffffff81090314>] __do_page_cache_readahead+0x15f/0x1ec
[<
ffffffff81090228>] ? __do_page_cache_readahead+0x73/0x1ec
[<
ffffffff810903bd>] ra_submit+0x1c/0x20
[<
ffffffff810906bb>] ondemand_readahead+0x227/0x23a
[<
ffffffff81090762>] page_cache_sync_readahead+0x17/0x19
[<
ffffffff8108a99e>] generic_file_aio_read+0x236/0x5a0
[<
ffffffffa00937bd>] nfs_file_read+0xe4/0xf3 [nfs]
[<
ffffffff810b2fa2>] do_sync_read+0xe3/0x120
[<
ffffffff81354cc3>] ? _spin_unlock_irq+0x2b/0x31
[<
ffffffff8104c0f1>] ? autoremove_wake_function+0x0/0x34
[<
ffffffff811848e5>] ? selinux_file_permission+0x5d/0x10f
[<
ffffffff81352bdb>] ? thread_return+0x3e/0x101
[<
ffffffff8117d7b0>] ? security_file_permission+0x11/0x13
[<
ffffffff810b3b06>] vfs_read+0xaa/0x16f
[<
ffffffff81058df0>] ? trace_hardirqs_on_caller+0x10c/0x130
[<
ffffffff810b3c84>] sys_read+0x45/0x6c
[<
ffffffff8100ae2b>] system_call_fastpath+0x16/0x1b
The object state might also be OBJECT_DYING or OBJECT_WITHDRAWING.
This should be handled by simply rejecting the new operation with ENOBUFS.
There's no need to log an error for it. Events of this type now appear in the
stats file under Ops:rej.
Signed-off-by: David Howells <dhowells@redhat.com>
run=N Number of times async ops given CPU time
enq=N Number of times async ops queued for processing
can=N Number of async ops cancelled
+ rej=N Number of async ops rejected due to object lookup/create failure
dfr=N Number of async ops queued for deferred release
rel=N Number of async ops released
gc=N Number of deferred-release async ops garbage collected
extern atomic_t fscache_n_op_release;
extern atomic_t fscache_n_op_gc;
extern atomic_t fscache_n_op_cancelled;
+extern atomic_t fscache_n_op_rejected;
extern atomic_t fscache_n_attr_changed;
extern atomic_t fscache_n_attr_changed_ok;
list_add_tail(&op->pend_link, &object->pending_ops);
fscache_stat(&fscache_n_op_pend);
ret = 0;
+ } else if (object->state == FSCACHE_OBJECT_DYING ||
+ object->state == FSCACHE_OBJECT_LC_DYING ||
+ object->state == FSCACHE_OBJECT_WITHDRAWING) {
+ fscache_stat(&fscache_n_op_rejected);
+ ret = -ENOBUFS;
} else if (!test_bit(FSCACHE_IOERROR, &object->cache->flags)) {
fscache_report_unexpected_submission(object, op, ostate);
ASSERT(!fscache_object_is_active(object));
atomic_t fscache_n_op_release;
atomic_t fscache_n_op_gc;
atomic_t fscache_n_op_cancelled;
+atomic_t fscache_n_op_rejected;
atomic_t fscache_n_attr_changed;
atomic_t fscache_n_attr_changed_ok;
atomic_read(&fscache_n_store_radix_deletes),
atomic_read(&fscache_n_store_pages_over_limit));
- seq_printf(m, "Ops : pend=%u run=%u enq=%u can=%u\n",
+ seq_printf(m, "Ops : pend=%u run=%u enq=%u can=%u rej=%u\n",
atomic_read(&fscache_n_op_pend),
atomic_read(&fscache_n_op_run),
atomic_read(&fscache_n_op_enqueue),
- atomic_read(&fscache_n_op_cancelled));
+ atomic_read(&fscache_n_op_cancelled),
+ atomic_read(&fscache_n_op_rejected));
seq_printf(m, "Ops : dfr=%u rel=%u gc=%u\n",
atomic_read(&fscache_n_op_deferred_release),
atomic_read(&fscache_n_op_release),