GGLinnk/bees
1
0
Fork 0
mirror of https://github.com/Zygo/bees.git synced 2025-07-02 00:32:27 +02:00
Code Packages Activity

seeker: add a runtime debug stream

Browse Source 
This allows detailed but selective debugging when using the library,
particularly when something goes wrong.

Signed-off-by: Zygo Blaxell <bees@furryterror.org>
This commit is contained in:
Zygo Blaxell
2025-02-10 23:25:03 -05:00
parent 9a9644659c
commit 50e012ad6d
4 changed files with 122 additions and 116 deletions
Download Patch File Download Diff File Expand all files Collapse all files

222
include/crucible/seeker.h
View File

@ -6,23 +6,23 @@
#include <algorithm> #include <algorithm>
#include <limits> #include <limits>
#include <cstdint> // Debug stream
#include <memory>
#if 0
#include <iostream> #include <iostream>
#include <sstream> #include <sstream>
#define DINIT(__x) __x
#define DLOG(__x) do { logs << __x << std::endl; } while (false) #include <cstdint>
#define DOUT(__err) do { __err << logs.str(); } while (false)
#else
#define DINIT(__x) do {} while (false)
#define DLOG(__x) do {} while (false)
#define DOUT(__x) do {} while (false)
#endif
namespace crucible { namespace crucible {
using namespace std; using namespace std;
extern thread_local shared_ptr<ostream> tl_seeker_debug_str;
#define SEEKER_DEBUG_LOG(__x) do { \
if (tl_seeker_debug_str) { \
(*tl_seeker_debug_str) << __x << "\n"; \
} \
} while (false)
// Requirements for Container<Pos> Fetch(Pos lower, Pos upper): // Requirements for Container<Pos> Fetch(Pos lower, Pos upper):
// - fetches objects in Pos order, starting from lower (must be >= lower) // - fetches objects in Pos order, starting from lower (must be >= lower)
// - must return upper if present, may or may not return objects after that // - must return upper if present, may or may not return objects after that
@ -49,113 +49,107 @@ namespace crucible {
Pos Pos
seek_backward(Pos const target_pos, Fetch fetch, Pos min_step = 1, size_t max_loops = numeric_limits<size_t>::max()) seek_backward(Pos const target_pos, Fetch fetch, Pos min_step = 1, size_t max_loops = numeric_limits<size_t>::max())
{ {
DINIT(ostringstream logs); static const Pos end_pos = numeric_limits<Pos>::max();
try { // TBH this probably won't work if begin_pos != 0, i.e. any signed type
static const Pos end_pos = numeric_limits<Pos>::max(); static const Pos begin_pos = numeric_limits<Pos>::min();
// TBH this probably won't work if begin_pos != 0, i.e. any signed type // Run a binary search looking for the highest key below target_pos.
static const Pos begin_pos = numeric_limits<Pos>::min(); // Initial upper bound of the search is target_pos.
// Run a binary search looking for the highest key below target_pos. // Find initial lower bound by doubling the size of the range until a key below target_pos
// Initial upper bound of the search is target_pos. // is found, or the lower bound reaches the beginning of the search space.
// Find initial lower bound by doubling the size of the range until a key below target_pos // If the lower bound search reaches the beginning of the search space without finding a key,
// is found, or the lower bound reaches the beginning of the search space. // return the beginning of the search space; otherwise, perform a binary search between
// If the lower bound search reaches the beginning of the search space without finding a key, // the bounds now established.
// return the beginning of the search space; otherwise, perform a binary search between Pos lower_bound = 0;
// the bounds now established. Pos upper_bound = target_pos;
Pos lower_bound = 0; bool found_low = false;
Pos upper_bound = target_pos; Pos probe_pos = target_pos;
bool found_low = false; // We need one loop for each bit of the search space to find the lower bound,
Pos probe_pos = target_pos; // one loop for each bit of the search space to find the upper bound,
// We need one loop for each bit of the search space to find the lower bound, // and one extra loop to confirm the boundary is correct.
// one loop for each bit of the search space to find the upper bound, for (size_t loop_count = min(numeric_limits<Pos>::digits * size_t(2) + 1, max_loops); loop_count; --loop_count) {
// and one extra loop to confirm the boundary is correct. SEEKER_DEBUG_LOG("fetch(probe_pos = " << probe_pos << ", target_pos = " << target_pos << ")");
for (size_t loop_count = min(numeric_limits<Pos>::digits * size_t(2) + 1, max_loops); loop_count; --loop_count) { auto result = fetch(probe_pos, target_pos);
DLOG("fetch(probe_pos = " << probe_pos << ", target_pos = " << target_pos << ")"); const Pos low_pos = result.empty() ? end_pos : *result.begin();
auto result = fetch(probe_pos, target_pos); const Pos high_pos = result.empty() ? end_pos : *result.rbegin();
const Pos low_pos = result.empty() ? end_pos : *result.begin(); SEEKER_DEBUG_LOG(" = " << low_pos << ".." << high_pos);
const Pos high_pos = result.empty() ? end_pos : *result.rbegin(); // check for correct behavior of the fetch function
DLOG(" = " << low_pos << ".." << high_pos); THROW_CHECK2(out_of_range, high_pos, probe_pos, probe_pos <= high_pos);
// check for correct behavior of the fetch function THROW_CHECK2(out_of_range, low_pos, probe_pos, probe_pos <= low_pos);
THROW_CHECK2(out_of_range, high_pos, probe_pos, probe_pos <= high_pos); THROW_CHECK2(out_of_range, low_pos, high_pos, low_pos <= high_pos);
THROW_CHECK2(out_of_range, low_pos, probe_pos, probe_pos <= low_pos); if (!found_low) {
THROW_CHECK2(out_of_range, low_pos, high_pos, low_pos <= high_pos); // if target_pos == end_pos then we will find it in every empty result set,
if (!found_low) { // so in that case we force the lower bound to be lower than end_pos
// if target_pos == end_pos then we will find it in every empty result set, if ((target_pos == end_pos) ? (low_pos < target_pos) : (low_pos <= target_pos)) {
// so in that case we force the lower bound to be lower than end_pos // found a lower bound, set the low bound there and switch to binary search
if ((target_pos == end_pos) ? (low_pos < target_pos) : (low_pos <= target_pos)) { found_low = true;
// found a lower bound, set the low bound there and switch to binary search lower_bound = low_pos;
found_low = true; SEEKER_DEBUG_LOG("found_low = true, lower_bound = " << lower_bound);
lower_bound = low_pos; } else {
DLOG("found_low = true, lower_bound = " << lower_bound); // still looking for lower bound
} else { // if probe_pos was begin_pos then we can stop with no result
// still looking for lower bound if (probe_pos == begin_pos) {
// if probe_pos was begin_pos then we can stop with no result SEEKER_DEBUG_LOG("return: probe_pos == begin_pos " << begin_pos);
if (probe_pos == begin_pos) { return begin_pos;
DLOG("return: probe_pos == begin_pos " << begin_pos);
return begin_pos;
}
// double the range size, or use the distance between objects found so far
THROW_CHECK2(out_of_range, upper_bound, probe_pos, probe_pos <= upper_bound);
// already checked low_pos <= high_pos above
const Pos want_delta = max(upper_bound - probe_pos, min_step);
// avoid underflowing the beginning of the search space
const Pos have_delta = min(want_delta, probe_pos - begin_pos);
THROW_CHECK2(out_of_range, want_delta, have_delta, have_delta <= want_delta);
// move probe and try again
probe_pos = probe_pos - have_delta;
DLOG("probe_pos " << probe_pos << " = probe_pos - have_delta " << have_delta << " (want_delta " << want_delta << ")");
continue;
} }
// double the range size, or use the distance between objects found so far
THROW_CHECK2(out_of_range, upper_bound, probe_pos, probe_pos <= upper_bound);
// already checked low_pos <= high_pos above
const Pos want_delta = max(upper_bound - probe_pos, min_step);
// avoid underflowing the beginning of the search space
const Pos have_delta = min(want_delta, probe_pos - begin_pos);
THROW_CHECK2(out_of_range, want_delta, have_delta, have_delta <= want_delta);
// move probe and try again
probe_pos = probe_pos - have_delta;
SEEKER_DEBUG_LOG("probe_pos " << probe_pos << " = probe_pos - have_delta " << have_delta << " (want_delta " << want_delta << ")");
continue;
} }
if (low_pos <= target_pos && target_pos <= high_pos) {
// have keys on either side of target_pos in result
// search from the high end until we find the highest key below target
for (auto i = result.rbegin(); i != result.rend(); ++i) {
// more correctness checking for fetch
THROW_CHECK2(out_of_range, *i, probe_pos, probe_pos <= *i);
if (*i <= target_pos) {
DLOG("return: *i " << *i << " <= target_pos " << target_pos);
return *i;
}
}
// if the list is empty then low_pos = high_pos = end_pos
// if target_pos = end_pos also, then we will execute the loop
// above but not find any matching entries.
THROW_CHECK0(runtime_error, result.empty());
}
if (target_pos <= low_pos) {
// results are all too high, so probe_pos..low_pos is too high
// lower the high bound to the probe pos
upper_bound = probe_pos;
DLOG("upper_bound = probe_pos " << probe_pos);
}
if (high_pos < target_pos) {
// results are all too low, so probe_pos..high_pos is too low
// raise the low bound to the high_pos
DLOG("lower_bound = high_pos " << high_pos);
lower_bound = high_pos;
}
// compute a new probe pos at the middle of the range and try again
// we can't have a zero-size range here because we would not have set found_low yet
THROW_CHECK2(out_of_range, lower_bound, upper_bound, lower_bound <= upper_bound);
const Pos delta = (upper_bound - lower_bound) / 2;
probe_pos = lower_bound + delta;
if (delta < 1) {
// nothing can exist in the range (lower_bound, upper_bound)
// and an object is known to exist at lower_bound
DLOG("return: probe_pos == lower_bound " << lower_bound);
return lower_bound;
}
THROW_CHECK2(out_of_range, lower_bound, probe_pos, lower_bound <= probe_pos);
THROW_CHECK2(out_of_range, upper_bound, probe_pos, probe_pos <= upper_bound);
DLOG("loop: lower_bound " << lower_bound << ", probe_pos " << probe_pos << ", upper_bound " << upper_bound);
} }
THROW_ERROR(runtime_error, "FIXME: should not reach this line: " if (low_pos <= target_pos && target_pos <= high_pos) {
"lower_bound..upper_bound " << lower_bound << ".." << upper_bound << ", " // have keys on either side of target_pos in result
"found_low " << found_low); // search from the high end until we find the highest key below target
} catch (...) { for (auto i = result.rbegin(); i != result.rend(); ++i) {
DOUT(cerr); // more correctness checking for fetch
throw; THROW_CHECK2(out_of_range, *i, probe_pos, probe_pos <= *i);
if (*i <= target_pos) {
SEEKER_DEBUG_LOG("return: *i " << *i << " <= target_pos " << target_pos);
return *i;
}
}
// if the list is empty then low_pos = high_pos = end_pos
// if target_pos = end_pos also, then we will execute the loop
// above but not find any matching entries.
THROW_CHECK0(runtime_error, result.empty());
}
if (target_pos <= low_pos) {
// results are all too high, so probe_pos..low_pos is too high
// lower the high bound to the probe pos, low_pos cannot be lower
SEEKER_DEBUG_LOG("upper_bound = probe_pos " << probe_pos);
upper_bound = probe_pos;
}
if (high_pos < target_pos) {
// results are all too low, so probe_pos..high_pos is too low
// raise the low bound to high_pos since it's above probe_pos
SEEKER_DEBUG_LOG("lower_bound = high_pos " << high_pos);
lower_bound = high_pos;
}
// compute a new probe pos at the middle of the range and try again
// we can't have a zero-size range here because we would not have set found_low yet
THROW_CHECK2(out_of_range, lower_bound, upper_bound, lower_bound <= upper_bound);
const Pos delta = (upper_bound - lower_bound) / 2;
probe_pos = lower_bound + delta;
if (delta < 1) {
// nothing can exist in the range (lower_bound, upper_bound)
// and an object is known to exist at lower_bound
SEEKER_DEBUG_LOG("return: probe_pos == lower_bound " << lower_bound);
return lower_bound;
}
THROW_CHECK2(out_of_range, lower_bound, probe_pos, lower_bound <= probe_pos);
THROW_CHECK2(out_of_range, upper_bound, probe_pos, probe_pos <= upper_bound);
SEEKER_DEBUG_LOG("loop bottom: lower_bound " << lower_bound << ", probe_pos " << probe_pos << ", upper_bound " << upper_bound);
} }
THROW_ERROR(runtime_error, "FIXME: should not reach this line: "
"lower_bound..upper_bound " << lower_bound << ".." << upper_bound << ", "
"found_low " << found_low);
} }
} }

1
lib/Makefile
View File

@ -17,6 +17,7 @@ CRUCIBLE_OBJS = \
openat2.o \ openat2.o \
path.o \ path.o \
process.o \ process.o \
seeker.o \
string.o \ string.o \
table.o \ table.o \
task.o \ task.o \

7
lib/seeker.cc Normal file
View File

@ -0,0 +1,7 @@
#include "crucible/seeker.h"
namespace crucible {
thread_local shared_ptr<ostream> tl_seeker_debug_str;
};

8
test/seeker.cc
View File

@ -36,6 +36,8 @@ seeker_test(const vector<uint64_t> &vec, uint64_t const target)
} }
cerr << " } = "; cerr << " } = ";
size_t loops = 0; size_t loops = 0;
tl_seeker_debug_str = make_shared<ostringstream>();
bool local_test_fails = false;
bool excepted = catch_all([&]() { bool excepted = catch_all([&]() {
auto found = seek_backward(target, [&](uint64_t lower, uint64_t upper) { auto found = seek_backward(target, [&](uint64_t lower, uint64_t upper) {
++loops; ++loops;
@ -52,13 +54,15 @@ seeker_test(const vector<uint64_t> &vec, uint64_t const target)
cerr << " (correct)"; cerr << " (correct)";
} else { } else {
cerr << " (INCORRECT - right answer is " << my_found << ")"; cerr << " (INCORRECT - right answer is " << my_found << ")";
test_fails = true; local_test_fails = true;
} }
}); });
cerr << " (" << loops << " loops)" << endl; cerr << " (" << loops << " loops)" << endl;
if (excepted) { if (excepted || local_test_fails) {
cerr << dynamic_pointer_cast<ostringstream>(tl_seeker_debug_str)->str();
test_fails = true; test_fails = true;
} }
tl_seeker_debug_str.reset();
} }
static static