Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

partition speed improvement #16

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

partition speed improvement #16

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Empty file modified mecat2canu/src/canu_version_update.pl
100644 → 100755
View file
Open in desktop
Empty file.
8 changes: 4 additions & 4 deletions src/mecat2cns/overlaps_partition.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,10 +176,10 @@ partition_candidates(const char* input, const idx_t batch_size, const int min_re

ExtensionCandidate ec, nec;
PartitionResultsWriter<ExtensionCandidate> prw;
for (index_t i = 0; i < num_batches; i += PartitionResultsWriter<ExtensionCandidate>::kNumFiles)
for (index_t i = 0; i < num_batches; i += prw.kNumFiles)
{
const index_t sfid = i;
const index_t efid = std::min(sfid + PartitionResultsWriter<ExtensionCandidate>::kNumFiles, num_batches);
const index_t efid = std::min(sfid + prw.kNumFiles, num_batches);
const int nf = efid - sfid;
const index_t L = batch_size * sfid;
const index_t R = batch_size * efid;
Expand Down Expand Up @@ -231,10 +231,10 @@ partition_m4records(const char* m4_file_name, const double min_cov_ratio, const
M4Record m4, nm4;
ExtensionCandidate ec;
PartitionResultsWriter<ExtensionCandidate> prw;
for (index_t i = 0; i < num_batches; i += PartitionResultsWriter<ExtensionCandidate>::kNumFiles)
for (index_t i = 0; i < num_batches; i += prw.kNumFiles)
{
const index_t sfid = i;
const index_t efid = std::min(sfid + PartitionResultsWriter<ExtensionCandidate>::kNumFiles, num_batches);
const index_t efid = std::min(sfid + prw.kNumFiles, num_batches);
const int nf = efid - sfid;
const index_t L = batch_size * sfid;
const index_t R = batch_size * efid;
Expand Down
72 changes: 46 additions & 26 deletions src/mecat2cns/overlaps_store.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,9 @@
#include <fstream>
#include <limits>
#include <string>
#include <vector>
#include <unistd.h>
#include <iostream>

#include "../common/defs.h"
#include "../common/pod_darr.h"
Expand All @@ -19,28 +22,37 @@ class PartitionResultsWriter
{
file_is_open = false;
num_open_files = false;
for (int i = 0; i < num_open_files; ++i) results[i].reserve(kStoreSize);

kStoreSize = 0;
// leave room for stdin, stdout, stderr, a few others
kNumFiles = sysconf(_SC_OPEN_MAX) - 10;
files = NULL;
results = NULL;
}
~PartitionResultsWriter()
{

CloseFiles();
}
void OpenFiles(const idx_t sfid, const idx_t efid, const std::string& prefix, file_name_generator fng)
{
if (file_is_open) CloseFiles();

CloseFiles();
const int nf = efid - sfid;
if (nf == 0) return;
for (int i = 0; i < nf; ++i)
{
fng(prefix.data(), i + sfid, file_names[i]);
open_fstream(files[i], file_names[i].c_str(), std::ios::binary);
min_seq_ids[i] = std::numeric_limits<index_t>::max();
max_seq_ids[i] = std::numeric_limits<index_t>::min();
results[i].clear();
}
num_open_files = nf;
file_is_open = true;
if (nf == 0) return;
// allocate about a gb of memory as buffer
kStoreSize = 1073741824 / sizeof(ExtensionCandidate) / nf;
file_names.assign(nf, "");
min_seq_ids.assign(nf, std::numeric_limits<idx_t>::max());
max_seq_ids.assign(nf, std::numeric_limits<idx_t>::min());
files = new std::ofstream[nf];
results = new PODArray<T>[nf];
for (int i = 0; i < nf; ++i)
{
fng(prefix.data(), i + sfid, file_names[i]);
open_fstream(files[i], file_names[i].c_str(), std::ios::binary);
results[i].reserve(kStoreSize);
}
num_open_files = nf;
file_is_open = true;
}
void CloseFiles()
{
Expand All @@ -54,9 +66,17 @@ class PartitionResultsWriter
files[i].write(buf, s);
}
}
for (int i = 0; i < num_open_files; ++i) close_fstream(files[i]);
file_is_open = false;
num_open_files = 0;
for (int i = 0; i < num_open_files; ++i) close_fstream(files[i]);
file_names.clear();
min_seq_ids.clear();
max_seq_ids.clear();
delete[] files;
delete[] results;
files = NULL;
results = NULL;
kStoreSize = 0;
file_is_open = false;
num_open_files = 0;
}
void WriteOneResult(const int fid, const idx_t seq_id, const T& r)
{
Expand All @@ -74,16 +94,16 @@ class PartitionResultsWriter
}

public:
static const int kNumFiles = 10;
static const int kStoreSize = 500000;
int kNumFiles;
int kStoreSize;

PODArray<T> results[kNumFiles];
PODArray<T> *results; // can't use vector<>, causes memory corruption
bool file_is_open;
int num_open_files;
std::ofstream files[kNumFiles];
std::string file_names[kNumFiles];
idx_t min_seq_ids[kNumFiles];
idx_t max_seq_ids[kNumFiles];
int num_open_files;
std::ofstream *files; // can't use vector<>, non-copyable
std::vector<std::string> file_names;
std::vector<idx_t> min_seq_ids;
std::vector<idx_t> max_seq_ids;
};

template <class T>
Expand Down