[v3,03/10] bloom: fix logic in get_bloom_filter()
diff mbox series

Message ID 2f809499abadd83b81b3d38d0cad9a2fd08b5440.1593174637.git.gitgitgadget@gmail.com
State New
Headers show
Series
  • More commit-graph/Bloom filter improvements
Related show

Commit Message

Philippe Blain via GitGitGadget June 26, 2020, 12:30 p.m. UTC
From: Derrick Stolee <dstolee@microsoft.com>

The get_bloom_filter() method is a bit complicated in some parts where
it does not need to be. In particular, it needs to return a NULL filter
only when compute_if_not_present is zero AND the filter data cannot be
loaded from a commit-graph file. This currently happens by accident
because the commit-graph does not load changed-path Bloom filters from
an existing commit-graph when writing a new one. This will change in a
later patch.

Also clean up some style issues while we are here.

Helped-by: René Scharfe <l.s.r@web.de>
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 bloom.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

Comments

SZEDER Gábor June 27, 2020, 4:33 p.m. UTC | #1
On Fri, Jun 26, 2020 at 12:30:29PM +0000, Derrick Stolee via GitGitGadget wrote:
> From: Derrick Stolee <dstolee@microsoft.com>
> 
> The get_bloom_filter() method is a bit complicated in some parts where
> it does not need to be. In particular, it needs to return a NULL filter
> only when compute_if_not_present is zero AND the filter data cannot be
> loaded from a commit-graph file. This currently happens by accident
> because the commit-graph does not load changed-path Bloom filters from
> an existing commit-graph when writing a new one. This will change in a
> later patch.
> 
> Also clean up some style issues while we are here.
> 
> Helped-by: René Scharfe <l.s.r@web.de>
> Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
> ---
>  bloom.c | 14 ++++++--------
>  1 file changed, 6 insertions(+), 8 deletions(-)
> 
> diff --git a/bloom.c b/bloom.c
> index c38d1cff0c..2af5389795 100644
> --- a/bloom.c
> +++ b/bloom.c
> @@ -186,7 +186,7 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
>  	struct diff_options diffopt;
>  	int max_changes = 512;
>  
> -	if (bloom_filters.slab_size == 0)
> +	if (!bloom_filters.slab_size)
>  		return NULL;
>
>  	filter = bloom_filter_slab_at(&bloom_filters, c);
> @@ -194,16 +194,14 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
>  	if (!filter->data) {
>  		load_commit_graph_info(r, c);
>  		if (c->graph_pos != COMMIT_NOT_FROM_GRAPH &&
> -			r->objects->commit_graph->chunk_bloom_indexes) {
> -			if (load_bloom_filter_from_graph(r->objects->commit_graph, filter, c))
> -				return filter;
> -			else
> -				return NULL;
> -		}
> +		    r->objects->commit_graph->chunk_bloom_indexes)
> +			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c);
>  	}
>  
> -	if (filter->data || !compute_if_not_present)
> +	if (filter->data)
>  		return filter;
> +	if (!compute_if_not_present)
> +		return NULL;

Some callers of get_bloom_filter() invoke it with
compute_if_not_present=0, but are not prepared to handle a NULL return
value and dereference it right away:

  write_graph_chunk_bloom_indexes():

                struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
                cur_pos += filter->len;

  write_graph_chunk_bloom_data():

                struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
                display_progress(progress, ++i);
                hashwrite(f, filter->data, filter->len * sizeof(unsigned char));

I don't know whether this was an issue before, but I didn't really
tried.  Unfortunately, starting with this patch this causes
segmentation faults basically in all real repositories I use for
testing.

  expecting success of 9999.1 'test': 
          for i in $(test_seq 1 513)
          do
                  >file-$i || return 1
          done &&
          git add file-* &&
          git commit -q -m one &&
  
          git commit-graph write --reachable --changed-paths
  
  Segmentation fault
  not ok 1 - test


  Program received signal SIGSEGV, Segmentation fault.
  0x0000000000515848 in write_graph_chunk_bloom_indexes (f=0x9fe650, 
      ctx=0x9d2000) at commit-graph.c:1101
  1101                    cur_pos += filter->len;
  (gdb) print filter
  $1 = (struct bloom_filter *) 0x0



>  	repo_diff_setup(r, &diffopt);
>  	diffopt.flags.recursive = 1;
> -- 
> gitgitgadget
>
Derrick Stolee June 29, 2020, 1:02 p.m. UTC | #2
On 6/27/2020 12:33 PM, SZEDER Gábor wrote:
> On Fri, Jun 26, 2020 at 12:30:29PM +0000, Derrick Stolee via GitGitGadget wrote:
>> From: Derrick Stolee <dstolee@microsoft.com>
>>
>> The get_bloom_filter() method is a bit complicated in some parts where
>> it does not need to be. In particular, it needs to return a NULL filter
>> only when compute_if_not_present is zero AND the filter data cannot be
>> loaded from a commit-graph file. This currently happens by accident
>> because the commit-graph does not load changed-path Bloom filters from
>> an existing commit-graph when writing a new one. This will change in a
>> later patch.
>>
>> Also clean up some style issues while we are here.
>>
>> Helped-by: René Scharfe <l.s.r@web.de>
>> Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
>> ---
>>  bloom.c | 14 ++++++--------
>>  1 file changed, 6 insertions(+), 8 deletions(-)
>>
>> diff --git a/bloom.c b/bloom.c
>> index c38d1cff0c..2af5389795 100644
>> --- a/bloom.c
>> +++ b/bloom.c
>> @@ -186,7 +186,7 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
>>  	struct diff_options diffopt;
>>  	int max_changes = 512;
>>  
>> -	if (bloom_filters.slab_size == 0)
>> +	if (!bloom_filters.slab_size)
>>  		return NULL;
>>
>>  	filter = bloom_filter_slab_at(&bloom_filters, c);
>> @@ -194,16 +194,14 @@ struct bloom_filter *get_bloom_filter(struct repository *r,
>>  	if (!filter->data) {
>>  		load_commit_graph_info(r, c);
>>  		if (c->graph_pos != COMMIT_NOT_FROM_GRAPH &&
>> -			r->objects->commit_graph->chunk_bloom_indexes) {
>> -			if (load_bloom_filter_from_graph(r->objects->commit_graph, filter, c))
>> -				return filter;
>> -			else
>> -				return NULL;
>> -		}
>> +		    r->objects->commit_graph->chunk_bloom_indexes)
>> +			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c);
>>  	}
>>  
>> -	if (filter->data || !compute_if_not_present)
>> +	if (filter->data)
>>  		return filter;
>> +	if (!compute_if_not_present)
>> +		return NULL;
> 
> Some callers of get_bloom_filter() invoke it with
> compute_if_not_present=0, but are not prepared to handle a NULL return
> value and dereference it right away:
> 
>   write_graph_chunk_bloom_indexes():
> 
>                 struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
>                 cur_pos += filter->len;
> 
>   write_graph_chunk_bloom_data():
> 
>                 struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
>                 display_progress(progress, ++i);
>                 hashwrite(f, filter->data, filter->len * sizeof(unsigned char));

In theory, these _should_ be safe, because we already computed
the filters in an earlier step, right? We should have generated
the filter and populated it in the slab.

> I don't know whether this was an issue before, but I didn't really
> tried.  Unfortunately, starting with this patch this causes
> segmentation faults basically in all real repositories I use for
> testing.
> 
>   expecting success of 9999.1 'test': 
>           for i in $(test_seq 1 513)
>           do
>                   >file-$i || return 1
>           done &&
>           git add file-* &&
>           git commit -q -m one &&
>   
>           git commit-graph write --reachable --changed-paths
>   
>   Segmentation fault
>   not ok 1 - test

However, you are demonstrating a failure that doesn't appear
in our test suite. I was able to reproduce it.

I can confirm that this patch causes a SIGSEGV when writing
the commit-graph in the Git repository, too.

So, what is wrong with my earlier assumption? There are
two problems.

The thing I notice is that an empty filter (no changes
with respect to the first parent) will have NULL
filter->data, so we are returning NULL instead of a
correctly-empty filter (with len zero).

But what you are hitting here is the max number of changes
limit. That also returns a NULL filter, because we mark
the filter as "TOO LARGE" to store. We store that as a
zero-length filter.

The following fixup corrects the bug and adds a test
similar to yours, but with extra care around ensuring the
revision walk still works appropriately for that large
commit.

In the next version, I will include more in the commit
message about these side-effect changes, especially around
the stats for zero-length filters. The trace2 message will
no longer differentiate between zero-length filters and
NULL filters.

Thanks,
-Stolee

-- >8 --

From f9867adc5de8a072f41b91fd6cd87edfcc92e05e Mon Sep 17 00:00:00 2001
From: Derrick Stolee <dstolee@microsoft.com>
Date: Mon, 29 Jun 2020 08:52:33 -0400
Subject: [PATCH] fixup! bloom: fix logic in get_bloom_filter()

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 commit-graph.c       |  8 ++++++--
 revision.c           |  7 -------
 t/t4216-log-bloom.sh | 24 ++++++++++++++++++++++--
 3 files changed, 28 insertions(+), 11 deletions(-)

diff --git a/commit-graph.c b/commit-graph.c
index a0766a86f5..6752916c1a 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -1108,7 +1108,8 @@ static int write_graph_chunk_bloom_indexes(struct hashfile *f,
 
 	while (list < last) {
 		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
-		cur_pos += filter->len;
+		size_t len = filter ? filter->len : 0;
+		cur_pos += len;
 		display_progress(progress, ++i);
 		hashwrite_be32(f, cur_pos);
 		list++;
@@ -1154,8 +1155,11 @@ static int write_graph_chunk_bloom_data(struct hashfile *f,
 
 	while (list < last) {
 		struct bloom_filter *filter = get_bloom_filter(ctx->r, *list, 0);
+		size_t len = filter ? filter->len : 0;
 		display_progress(progress, ++i);
-		hashwrite(f, filter->data, filter->len * sizeof(unsigned char));
+
+		if (len)
+			hashwrite(f, filter->data, len * sizeof(unsigned char));
 		list++;
 	}
 
diff --git a/revision.c b/revision.c
index b40bc5b51b..b9118001f9 100644
--- a/revision.c
+++ b/revision.c
@@ -633,7 +633,6 @@ static unsigned int count_bloom_filter_maybe;
 static unsigned int count_bloom_filter_definitely_not;
 static unsigned int count_bloom_filter_false_positive;
 static unsigned int count_bloom_filter_not_present;
-static unsigned int count_bloom_filter_length_zero;
 
 static void trace2_bloom_filter_statistics_atexit(void)
 {
@@ -641,7 +640,6 @@ static void trace2_bloom_filter_statistics_atexit(void)
 
 	jw_object_begin(&jw, 0);
 	jw_object_intmax(&jw, "filter_not_present", count_bloom_filter_not_present);
-	jw_object_intmax(&jw, "zero_length_filter", count_bloom_filter_length_zero);
 	jw_object_intmax(&jw, "maybe", count_bloom_filter_maybe);
 	jw_object_intmax(&jw, "definitely_not", count_bloom_filter_definitely_not);
 	jw_object_intmax(&jw, "false_positive", count_bloom_filter_false_positive);
@@ -765,11 +763,6 @@ static int check_maybe_different_in_bloom_filter(struct rev_info *revs,
 		return -1;
 	}
 
-	if (!filter->len) {
-		count_bloom_filter_length_zero++;
-		return -1;
-	}
-
 	for (j = 0; result && j < revs->bloom_keys_nr; j++) {
 		result = bloom_filter_contains(filter,
 					       &revs->bloom_keys[j],
diff --git a/t/t4216-log-bloom.sh b/t/t4216-log-bloom.sh
index d7dd717347..4892364e74 100755
--- a/t/t4216-log-bloom.sh
+++ b/t/t4216-log-bloom.sh
@@ -60,7 +60,7 @@ setup () {
 
 test_bloom_filters_used () {
 	log_args=$1
-	bloom_trace_prefix="statistics:{\"filter_not_present\":0,\"zero_length_filter\":0,\"maybe\""
+	bloom_trace_prefix="statistics:{\"filter_not_present\":0,\"maybe\""
 	setup "$log_args" &&
 	grep -q "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.perf" &&
 	test_cmp log_wo_bloom log_w_bloom &&
@@ -146,7 +146,7 @@ test_expect_success 'setup - add commit-graph to the chain with Bloom filters' '
 
 test_bloom_filters_used_when_some_filters_are_missing () {
 	log_args=$1
-	bloom_trace_prefix="statistics:{\"filter_not_present\":3,\"zero_length_filter\":0,\"maybe\":6,\"definitely_not\":8"
+	bloom_trace_prefix="statistics:{\"filter_not_present\":3,\"maybe\":6,\"definitely_not\":8"
 	setup "$log_args" &&
 	grep -q "$bloom_trace_prefix" "$TRASH_DIRECTORY/trace.perf" &&
 	test_cmp log_wo_bloom log_w_bloom
@@ -171,4 +171,24 @@ test_expect_success 'persist filter settings' '
 	grep "{\"hash_version\":1,\"num_hashes\":9,\"bits_per_entry\":15}" trace2-auto.txt
 '
 
+test_expect_success 'correctly report changes over limit' '
+	git init 513changes &&
+	(
+		cd 513changes &&
+		for i in $(test_seq 1 513)
+		do
+			echo $i >file$i.txt || return 1
+		done &&
+		git add . &&
+		git commit -m "files" &&
+		git commit-graph write --reachable --changed-paths &&
+		for i in $(test_seq 1 513)
+		do
+			git -c core.commitGraph=false log -- file$i.txt >expect &&
+			git log -- file$i.txt >actual &&
+			test_cmp expect actual || return 1
+		done
+	)
+'
+
 test_done
\ No newline at end of file

Patch
diff mbox series

diff --git a/bloom.c b/bloom.c
index c38d1cff0c..2af5389795 100644
--- a/bloom.c
+++ b/bloom.c
@@ -186,7 +186,7 @@  struct bloom_filter *get_bloom_filter(struct repository *r,
 	struct diff_options diffopt;
 	int max_changes = 512;
 
-	if (bloom_filters.slab_size == 0)
+	if (!bloom_filters.slab_size)
 		return NULL;
 
 	filter = bloom_filter_slab_at(&bloom_filters, c);
@@ -194,16 +194,14 @@  struct bloom_filter *get_bloom_filter(struct repository *r,
 	if (!filter->data) {
 		load_commit_graph_info(r, c);
 		if (c->graph_pos != COMMIT_NOT_FROM_GRAPH &&
-			r->objects->commit_graph->chunk_bloom_indexes) {
-			if (load_bloom_filter_from_graph(r->objects->commit_graph, filter, c))
-				return filter;
-			else
-				return NULL;
-		}
+		    r->objects->commit_graph->chunk_bloom_indexes)
+			load_bloom_filter_from_graph(r->objects->commit_graph, filter, c);
 	}
 
-	if (filter->data || !compute_if_not_present)
+	if (filter->data)
 		return filter;
+	if (!compute_if_not_present)
+		return NULL;
 
 	repo_diff_setup(r, &diffopt);
 	diffopt.flags.recursive = 1;