##// END OF EJS Templates
perf: add command to benchmark bundle reading...
perf: add command to benchmark bundle reading Upcoming commits will be refactoring bundle2 I/O code. This commit establishes a `hg perfbundleread` command that measures how long it takes to read a bundle using various mechanisms. As a baseline, here's output from an uncompressed bundle1 bundle of my Firefox repo (7,098,622,890 bytes): ! read(8k) ! wall 0.763481 comb 0.760000 user 0.160000 sys 0.600000 (best of 6) ! read(16k) ! wall 0.644512 comb 0.640000 user 0.110000 sys 0.530000 (best of 16) ! read(32k) ! wall 0.581172 comb 0.590000 user 0.060000 sys 0.530000 (best of 18) ! read(128k) ! wall 0.535183 comb 0.530000 user 0.010000 sys 0.520000 (best of 19) ! cg1 deltaiter() ! wall 0.873500 comb 0.880000 user 0.840000 sys 0.040000 (best of 12) ! cg1 getchunks() ! wall 6.283797 comb 6.270000 user 5.570000 sys 0.700000 (best of 3) ! cg1 read(8k) ! wall 1.097173 comb 1.100000 user 0.400000 sys 0.700000 (best of 10) ! cg1 read(16k) ! wall 0.810750 comb 0.800000 user 0.200000 sys 0.600000 (best of 13) ! cg1 read(32k) ! wall 0.671215 comb 0.670000 user 0.110000 sys 0.560000 (best of 15) ! cg1 read(128k) ! wall 0.597857 comb 0.600000 user 0.020000 sys 0.580000 (best of 15) And from an uncompressed bundle2 bundle (6,070,036,163 bytes): ! read(8k) ! wall 0.676997 comb 0.680000 user 0.160000 sys 0.520000 (best of 15) ! read(16k) ! wall 0.592706 comb 0.590000 user 0.080000 sys 0.510000 (best of 17) ! read(32k) ! wall 0.529395 comb 0.530000 user 0.050000 sys 0.480000 (best of 16) ! read(128k) ! wall 0.491270 comb 0.490000 user 0.010000 sys 0.480000 (best of 19) ! bundle2 forwardchunks() ! wall 2.997131 comb 2.990000 user 2.270000 sys 0.720000 (best of 4) ! bundle2 iterparts() ! wall 12.247197 comb 10.670000 user 8.170000 sys 2.500000 (best of 3) ! bundle2 part seek() ! wall 11.761675 comb 10.500000 user 8.240000 sys 2.260000 (best of 3) ! bundle2 part read(8k) ! wall 9.116163 comb 9.110000 user 8.240000 sys 0.870000 (best of 3) ! bundle2 part read(16k) ! wall 8.984362 comb 8.970000 user 8.110000 sys 0.860000 (best of 3) ! bundle2 part read(32k) ! wall 8.758364 comb 8.740000 user 7.860000 sys 0.880000 (best of 3) ! bundle2 part read(128k) ! wall 8.749040 comb 8.730000 user 7.830000 sys 0.900000 (best of 3) We already see some interesting data. Notably that bundle2 has significant overhead compared to bundle1. This matters for e.g. stream clone bundles, which can be applied at >1Gbps. Differential Revision: https://phab.mercurial-scm.org/D1385

File last commit:

r30895:c32454d6 default
r35108:e9661304 default
Show More
threading.h
104 lines | 2.8 KiB | text/x-c | CLexer
/**
* Copyright (c) 2016 Tino Reichardt
* All rights reserved.
*
* This source code is licensed under the BSD-style license found in the
* LICENSE file in the root directory of this source tree. An additional grant
* of patent rights can be found in the PATENTS file in the same directory.
*
* You can contact the author at:
* - zstdmt source repository: https://github.com/mcmilk/zstdmt
*/
#ifndef THREADING_H_938743
#define THREADING_H_938743
#if defined (__cplusplus)
extern "C" {
#endif
#if defined(ZSTD_MULTITHREAD) && defined(_WIN32)
/**
* Windows minimalist Pthread Wrapper, based on :
* http://www.cse.wustl.edu/~schmidt/win32-cv-1.html
*/
#ifdef WINVER
# undef WINVER
#endif
#define WINVER 0x0600
#ifdef _WIN32_WINNT
# undef _WIN32_WINNT
#endif
#define _WIN32_WINNT 0x0600
#ifndef WIN32_LEAN_AND_MEAN
# define WIN32_LEAN_AND_MEAN
#endif
#include <windows.h>
/* mutex */
#define pthread_mutex_t CRITICAL_SECTION
#define pthread_mutex_init(a,b) InitializeCriticalSection((a))
#define pthread_mutex_destroy(a) DeleteCriticalSection((a))
#define pthread_mutex_lock(a) EnterCriticalSection((a))
#define pthread_mutex_unlock(a) LeaveCriticalSection((a))
/* condition variable */
#define pthread_cond_t CONDITION_VARIABLE
#define pthread_cond_init(a, b) InitializeConditionVariable((a))
#define pthread_cond_destroy(a) /* No delete */
#define pthread_cond_wait(a, b) SleepConditionVariableCS((a), (b), INFINITE)
#define pthread_cond_signal(a) WakeConditionVariable((a))
#define pthread_cond_broadcast(a) WakeAllConditionVariable((a))
/* pthread_create() and pthread_join() */
typedef struct {
HANDLE handle;
void* (*start_routine)(void*);
void* arg;
} pthread_t;
int pthread_create(pthread_t* thread, const void* unused,
void* (*start_routine) (void*), void* arg);
#define pthread_join(a, b) _pthread_join(&(a), (b))
int _pthread_join(pthread_t* thread, void** value_ptr);
/**
* add here more wrappers as required
*/
#elif defined(ZSTD_MULTITHREAD) /* posix assumed ; need a better detection mathod */
/* === POSIX Systems === */
# include <pthread.h>
#else /* ZSTD_MULTITHREAD not defined */
/* No multithreading support */
#define pthread_mutex_t int /* #define rather than typedef, as sometimes pthread support is implicit, resulting in duplicated symbols */
#define pthread_mutex_init(a,b)
#define pthread_mutex_destroy(a)
#define pthread_mutex_lock(a)
#define pthread_mutex_unlock(a)
#define pthread_cond_t int
#define pthread_cond_init(a,b)
#define pthread_cond_destroy(a)
#define pthread_cond_wait(a,b)
#define pthread_cond_signal(a)
#define pthread_cond_broadcast(a)
/* do not use pthread_t */
#endif /* ZSTD_MULTITHREAD */
#if defined (__cplusplus)
}
#endif
#endif /* THREADING_H_938743 */