[XFS] Use power-of-2 sized buffers to reduce overhead
Now that the ktrace_enter() code is using atomics, the non-power-of-2
buffer sizes - which require modulus operations to get the index - are
showing up as using substantial CPU in the profiles.
Force the buffer sizes to be rounded up to the nearest power of two and
use masking rather than modulus operations to convert the index counter to
the buffer index. This reduces ktrace_enter overhead to 8% of a CPU time,
and again almost halves the trace intensive test runtime.
SGI-PV: 977546
SGI-Modid: xfs-linux-melb:xfs-kern:30538a
Signed-off-by: David Chinner <dgc@sgi.com>
Signed-off-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
diff --git a/fs/xfs/support/ktrace.c b/fs/xfs/support/ktrace.c
index 4e0444c..0b75d30 100644
--- a/fs/xfs/support/ktrace.c
+++ b/fs/xfs/support/ktrace.c
@@ -24,7 +24,7 @@
void __init
ktrace_init(int zentries)
{
- ktrace_zentries = zentries;
+ ktrace_zentries = roundup_pow_of_two(zentries);
ktrace_hdr_zone = kmem_zone_init(sizeof(ktrace_t),
"ktrace_hdr");
@@ -47,13 +47,16 @@
* ktrace_alloc()
*
* Allocate a ktrace header and enough buffering for the given
- * number of entries.
+ * number of entries. Round the number of entries up to a
+ * power of 2 so we can do fast masking to get the index from
+ * the atomic index counter.
*/
ktrace_t *
ktrace_alloc(int nentries, unsigned int __nocast sleep)
{
ktrace_t *ktp;
ktrace_entry_t *ktep;
+ int entries;
ktp = (ktrace_t*)kmem_zone_alloc(ktrace_hdr_zone, sleep);
@@ -70,11 +73,12 @@
/*
* Special treatment for buffers with the ktrace_zentries entries
*/
- if (nentries == ktrace_zentries) {
+ entries = roundup_pow_of_two(nentries);
+ if (entries == ktrace_zentries) {
ktep = (ktrace_entry_t*)kmem_zone_zalloc(ktrace_ent_zone,
sleep);
} else {
- ktep = (ktrace_entry_t*)kmem_zalloc((nentries * sizeof(*ktep)),
+ ktep = (ktrace_entry_t*)kmem_zalloc((entries * sizeof(*ktep)),
sleep | KM_LARGE);
}
@@ -91,7 +95,9 @@
}
ktp->kt_entries = ktep;
- ktp->kt_nentries = nentries;
+ ktp->kt_nentries = entries;
+ ASSERT(is_power_of_2(entries));
+ ktp->kt_index_mask = entries - 1;
atomic_set(&ktp->kt_index, 0);
ktp->kt_rollover = 0;
return ktp;
@@ -160,7 +166,7 @@
* Grab an entry by pushing the index up to the next one.
*/
index = atomic_add_return(1, &ktp->kt_index);
- index = (index - 1) % ktp->kt_nentries;
+ index = (index - 1) & ktp->kt_index_mask;
if (!ktp->kt_rollover && index == ktp->kt_nentries - 1)
ktp->kt_rollover = 1;
@@ -197,7 +203,7 @@
if (ktp == NULL)
return 0;
- index = atomic_read(&ktp->kt_index) % ktp->kt_nentries;
+ index = atomic_read(&ktp->kt_index) & ktp->kt_index_mask;
return (ktp->kt_rollover ? ktp->kt_nentries : index);
}
@@ -223,7 +229,7 @@
int nentries;
if (ktp->kt_rollover)
- index = atomic_read(&ktp->kt_index) % ktp->kt_nentries;
+ index = atomic_read(&ktp->kt_index) & ktp->kt_index_mask;
else
index = 0;
diff --git a/fs/xfs/support/ktrace.h b/fs/xfs/support/ktrace.h
index 782dbbb..741d694 100644
--- a/fs/xfs/support/ktrace.h
+++ b/fs/xfs/support/ktrace.h
@@ -31,6 +31,7 @@
typedef struct ktrace {
int kt_nentries; /* number of entries in trace buf */
atomic_t kt_index; /* current index in entries */
+ unsigned int kt_index_mask;
int kt_rollover;
ktrace_entry_t *kt_entries; /* buffer of entries */
} ktrace_t;