summaryrefslogtreecommitdiff
path: root/pack-objects.h
diff options
context:
space:
mode:
authorNguyễn Thái Ngọc Duy <pclouds@gmail.com>2018-07-22 08:04:21 (GMT)
committerJunio C Hamano <gitster@pobox.com>2018-07-23 17:21:29 (GMT)
commit9ac3f0e5b3e4cebe5bc9a24e3adef8b8e64fe692 (patch)
treebceffc511eb1c1a00fc073fea477da624bb4b723 /pack-objects.h
parentf6a5576d521693963092dd69355d8e96ecd73635 (diff)
downloadgit-9ac3f0e5b3e4cebe5bc9a24e3adef8b8e64fe692.zip
git-9ac3f0e5b3e4cebe5bc9a24e3adef8b8e64fe692.tar.gz
git-9ac3f0e5b3e4cebe5bc9a24e3adef8b8e64fe692.tar.bz2
pack-objects: fix performance issues on packing large deltas
Let's start with some background about oe_delta_size() and oe_set_delta_size(). If you already know, skip the next paragraph. These two are added in 0aca34e826 (pack-objects: shrink delta_size field in struct object_entry - 2018-04-14) to help reduce 'struct object_entry' size. The delta size field in this struct is reduced to only contain max 1MB. So if any new delta is produced and larger than 1MB, it's dropped because we can't really save such a large size anywhere. Fallback is provided in case existing packfiles already have large deltas, then we can retrieve it from the pack. While this should help small machines repacking large repos without large deltas (i.e. less memory pressure), dropping large deltas during the delta selection process could end up with worse pack files. And if existing packfiles already have >1MB delta and pack-objects is instructed to not reuse deltas, all of them will be dropped on the floor, and the resulting pack would be definitely bigger. There is also a regression in terms of CPU/IO if we have large on-disk deltas because fallback code needs to parse the pack every time the delta size is needed and just access to the mmap'd pack data is enough for extra page faults when memory is under pressure. Both of these issues were reported on the mailing list. Here's some numbers for comparison. Version Pack (MB) MaxRSS(kB) Time (s) ------- --------- ---------- -------- 2.17.0 5498 43513628 2494.85 2.18.0 10531 40449596 4168.94 This patch provides a better fallback that is - cheaper in terms of cpu and io because we won't have to read existing pack files as much - better in terms of pack size because the pack heuristics is back to 2.17.0 time, we do not drop large deltas at all If we encounter any delta (on-disk or created during try_delta phase) that is larger than the 1MB limit, we stop using delta_size_ field for this because it can't contain such size anyway. A new array of delta size is dynamically allocated and can hold all the deltas that 2.17.0 can. This array only contains delta sizes that delta_size_ can't contain. With this, we do not have to drop deltas in try_delta() anymore. Of course the downside is we use slightly more memory, even compared to 2.17.0. But since this is considered an uncommon case, a bit more memory consumption should not be a problem. Delta size limit is also raised from 1MB to 16MB to better cover common case and avoid that extra memory consumption (99.999% deltas in this reported repo are under 12MB; Jeff noted binary artifacts topped out at about 3MB in some other private repos). Other fields are shuffled around to keep this struct packed tight. We don't use more memory in common case even with this limit update. A note about thread synchronization. Since this code can be run in parallel during delta searching phase, we need a mutex. The realloc part in packlist_alloc() is not protected because it only happens during the object counting phase, which is always single-threaded. Access to e->delta_size_ (and by extension pack->delta_size[e - pack->objects]) is unprotected as before, the thread scheduler in pack-objects must make sure "e" is never updated by two different threads. The area under the new lock is as small as possible, avoiding locking at all in common case, since lock contention with high thread count could be expensive (most blobs are small enough that delta compute time is short and we end up taking the lock very often). The previous attempt to always hold a lock in oe_delta_size() and oe_set_delta_size() increases execution time by 33% when repacking linux.git with with 40 threads. Reported-by: Elijah Newren <newren@gmail.com> Helped-by: Elijah Newren <newren@gmail.com> Helped-by: Jeff King <peff@peff.net> Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'pack-objects.h')
-rw-r--r--pack-objects.h59
1 files changed, 48 insertions, 11 deletions
diff --git a/pack-objects.h b/pack-objects.h
index e5456c6..6ffbdcf 100644
--- a/pack-objects.h
+++ b/pack-objects.h
@@ -2,6 +2,7 @@
#define PACK_OBJECTS_H
#include "object-store.h"
+#include "thread-utils.h"
#define OE_DFS_STATE_BITS 2
#define OE_DEPTH_BITS 12
@@ -12,7 +13,7 @@
* above this limit. Don't lower it too much.
*/
#define OE_SIZE_BITS 31
-#define OE_DELTA_SIZE_BITS 20
+#define OE_DELTA_SIZE_BITS 23
/*
* State flags for depth-first search used for analyzing delta cycles.
@@ -92,11 +93,12 @@ struct object_entry {
*/
unsigned delta_size_:OE_DELTA_SIZE_BITS; /* delta data size (uncompressed) */
unsigned delta_size_valid:1;
+ unsigned char in_pack_header_size;
unsigned in_pack_idx:OE_IN_PACK_BITS; /* already in pack */
unsigned z_delta_size:OE_Z_DELTA_BITS;
unsigned type_valid:1;
- unsigned type_:TYPE_BITS;
unsigned no_try_delta:1;
+ unsigned type_:TYPE_BITS;
unsigned in_pack_type:TYPE_BITS; /* could be delta */
unsigned preferred_base:1; /*
* we do not pack this, but is available
@@ -106,17 +108,16 @@ struct object_entry {
unsigned tagged:1; /* near the very tip of refs */
unsigned filled:1; /* assigned write-order */
unsigned dfs_state:OE_DFS_STATE_BITS;
- unsigned char in_pack_header_size;
unsigned depth:OE_DEPTH_BITS;
/*
* pahole results on 64-bit linux (gcc and clang)
*
- * size: 80, bit_padding: 20 bits, holes: 8 bits
+ * size: 80, bit_padding: 9 bits
*
* and on 32-bit (gcc)
*
- * size: 76, bit_padding: 20 bits, holes: 8 bits
+ * size: 76, bit_padding: 9 bits
*/
};
@@ -128,6 +129,7 @@ struct packing_data {
uint32_t index_size;
unsigned int *in_pack_pos;
+ unsigned long *delta_size;
/*
* Only one of these can be non-NULL and they have different
@@ -138,10 +140,29 @@ struct packing_data {
struct packed_git **in_pack_by_idx;
struct packed_git **in_pack;
+#ifndef NO_PTHREADS
+ pthread_mutex_t lock;
+#endif
+
uintmax_t oe_size_limit;
+ uintmax_t oe_delta_size_limit;
};
void prepare_packing_data(struct packing_data *pdata);
+
+static inline void packing_data_lock(struct packing_data *pdata)
+{
+#ifndef NO_PTHREADS
+ pthread_mutex_lock(&pdata->lock);
+#endif
+}
+static inline void packing_data_unlock(struct packing_data *pdata)
+{
+#ifndef NO_PTHREADS
+ pthread_mutex_unlock(&pdata->lock);
+#endif
+}
+
struct object_entry *packlist_alloc(struct packing_data *pdata,
const unsigned char *sha1,
uint32_t index_pos);
@@ -330,18 +351,34 @@ static inline unsigned long oe_delta_size(struct packing_data *pack,
{
if (e->delta_size_valid)
return e->delta_size_;
- return oe_size(pack, e);
+
+ /*
+ * pack->detla_size[] can't be NULL because oe_set_delta_size()
+ * must have been called when a new delta is saved with
+ * oe_set_delta().
+ * If oe_delta() returns NULL (i.e. default state, which means
+ * delta_size_valid is also false), then the caller must never
+ * call oe_delta_size().
+ */
+ return pack->delta_size[e - pack->objects];
}
static inline void oe_set_delta_size(struct packing_data *pack,
struct object_entry *e,
unsigned long size)
{
- e->delta_size_ = size;
- e->delta_size_valid = e->delta_size_ == size;
- if (!e->delta_size_valid && size != oe_size(pack, e))
- BUG("this can only happen in check_object() "
- "where delta size is the same as entry size");
+ if (size < pack->oe_delta_size_limit) {
+ e->delta_size_ = size;
+ e->delta_size_valid = 1;
+ } else {
+ packing_data_lock(pack);
+ if (!pack->delta_size)
+ ALLOC_ARRAY(pack->delta_size, pack->nr_alloc);
+ packing_data_unlock(pack);
+
+ pack->delta_size[e - pack->objects] = size;
+ e->delta_size_valid = 0;
+ }
}
#endif