From fdcc0bc02a93636bde2ed2f0b6c1f11b6fe9e11e Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Tue, 20 Apr 2021 14:40:56 -0400 Subject: [PATCH 01/30] simple-ipc: preparations for supporting binary messages. Add `command_len` argument to the Simple IPC API. In my original Simple IPC API, I assumed that the request would always be a null-terminated string of text characters. The command arg was just a `const char *`. I found a caller that would like to pass a binary command to the daemon, so I want to ammend the Simple IPC API to take `const char *command, size_t command_len` and pass that to the daemon. (Really, the first arg should just be a `void *` or `const unsigned byte *` to make that clearer.) Note, the response side has always been a `struct strbuf` which includes the buffer and length, so we already support returning a binary answer. (Yes, it feels a little weird returning a binary buffer in a `strbuf`, but it works.) Signed-off-by: Jeff Hostetler --- compat/simple-ipc/ipc-unix-socket.c | 14 +++++++----- compat/simple-ipc/ipc-win32.c | 14 +++++++----- simple-ipc.h | 7 ++++-- t/helper/test-simple-ipc.c | 34 +++++++++++++++++++---------- 4 files changed, 46 insertions(+), 23 deletions(-) diff --git a/compat/simple-ipc/ipc-unix-socket.c b/compat/simple-ipc/ipc-unix-socket.c index 1927e6ef4b..4e28857a0a 100644 --- a/compat/simple-ipc/ipc-unix-socket.c +++ b/compat/simple-ipc/ipc-unix-socket.c @@ -168,7 +168,8 @@ void ipc_client_close_connection(struct ipc_client_connection *connection) int ipc_client_send_command_to_connection( struct ipc_client_connection *connection, - const char *message, struct strbuf *answer) + const char *message, size_t message_len, + struct strbuf *answer) { int ret = 0; @@ -176,7 +177,7 @@ int ipc_client_send_command_to_connection( trace2_region_enter("ipc-client", "send-command", NULL); - if (write_packetized_from_buf_no_flush(message, strlen(message), + if (write_packetized_from_buf_no_flush(message, message_len, connection->fd) < 0 || packet_flush_gently(connection->fd) < 0) { ret = error(_("could not send IPC command")); @@ -197,7 +198,8 @@ done: int ipc_client_send_command(const char *path, const struct ipc_client_connect_options *options, - const char *message, struct strbuf *answer) + const char *message, size_t message_len, + struct strbuf *answer) { int ret = -1; enum ipc_active_state state; @@ -208,7 +210,9 @@ int ipc_client_send_command(const char *path, if (state != IPC_STATE__LISTENING) return ret; - ret = ipc_client_send_command_to_connection(connection, message, answer); + ret = ipc_client_send_command_to_connection(connection, + message, message_len, + answer); ipc_client_close_connection(connection); @@ -503,7 +507,7 @@ static int worker_thread__do_io( if (ret >= 0) { ret = worker_thread_data->server_data->application_cb( worker_thread_data->server_data->application_data, - buf.buf, do_io_reply_callback, &reply_data); + buf.buf, buf.len, do_io_reply_callback, &reply_data); packet_flush_gently(reply_data.fd); } diff --git a/compat/simple-ipc/ipc-win32.c b/compat/simple-ipc/ipc-win32.c index 8dc7bda087..8e889d6a50 100644 --- a/compat/simple-ipc/ipc-win32.c +++ b/compat/simple-ipc/ipc-win32.c @@ -208,7 +208,8 @@ void ipc_client_close_connection(struct ipc_client_connection *connection) int ipc_client_send_command_to_connection( struct ipc_client_connection *connection, - const char *message, struct strbuf *answer) + const char *message, size_t message_len, + struct strbuf *answer) { int ret = 0; @@ -216,7 +217,7 @@ int ipc_client_send_command_to_connection( trace2_region_enter("ipc-client", "send-command", NULL); - if (write_packetized_from_buf_no_flush(message, strlen(message), + if (write_packetized_from_buf_no_flush(message, message_len, connection->fd) < 0 || packet_flush_gently(connection->fd) < 0) { ret = error(_("could not send IPC command")); @@ -239,7 +240,8 @@ done: int ipc_client_send_command(const char *path, const struct ipc_client_connect_options *options, - const char *message, struct strbuf *response) + const char *message, size_t message_len, + struct strbuf *response) { int ret = -1; enum ipc_active_state state; @@ -250,7 +252,9 @@ int ipc_client_send_command(const char *path, if (state != IPC_STATE__LISTENING) return ret; - ret = ipc_client_send_command_to_connection(connection, message, response); + ret = ipc_client_send_command_to_connection(connection, + message, message_len, + response); ipc_client_close_connection(connection); @@ -458,7 +462,7 @@ static int do_io(struct ipc_server_thread_data *server_thread_data) if (ret >= 0) { ret = server_thread_data->server_data->application_cb( server_thread_data->server_data->application_data, - buf.buf, do_io_reply_callback, &reply_data); + buf.buf, buf.len, do_io_reply_callback, &reply_data); packet_flush_gently(reply_data.fd); diff --git a/simple-ipc.h b/simple-ipc.h index 2c48a5ee00..9c7330fcda 100644 --- a/simple-ipc.h +++ b/simple-ipc.h @@ -107,7 +107,8 @@ void ipc_client_close_connection(struct ipc_client_connection *connection); */ int ipc_client_send_command_to_connection( struct ipc_client_connection *connection, - const char *message, struct strbuf *answer); + const char *message, size_t message_len, + struct strbuf *answer); /* * Used by the client to synchronously connect and send and receive a @@ -119,7 +120,8 @@ int ipc_client_send_command_to_connection( */ int ipc_client_send_command(const char *path, const struct ipc_client_connect_options *options, - const char *message, struct strbuf *answer); + const char *message, size_t message_len, + struct strbuf *answer); /* * Simple IPC Server Side API. @@ -144,6 +146,7 @@ typedef int (ipc_server_reply_cb)(struct ipc_server_reply_data *, */ typedef int (ipc_server_application_cb)(void *application_data, const char *request, + size_t request_len, ipc_server_reply_cb *reply_cb, struct ipc_server_reply_data *reply_data); diff --git a/t/helper/test-simple-ipc.c b/t/helper/test-simple-ipc.c index 42040ef81b..9134518075 100644 --- a/t/helper/test-simple-ipc.c +++ b/t/helper/test-simple-ipc.c @@ -112,7 +112,7 @@ static int app__slow_command(ipc_server_reply_cb *reply_cb, /* * The client sent a command followed by a (possibly very) large buffer. */ -static int app__sendbytes_command(const char *received, +static int app__sendbytes_command(const char *received, size_t received_len, ipc_server_reply_cb *reply_cb, struct ipc_server_reply_data *reply_data) { @@ -123,6 +123,13 @@ static int app__sendbytes_command(const char *received, int errs = 0; int ret; + /* + * The test is setup to send: + * "sendbytes" SP + */ + if (received_len < strlen("sendbytes ")) + BUG("received_len is short in app__sendbytes_command"); + if (skip_prefix(received, "sendbytes ", &p)) len_ballast = strlen(p); @@ -160,7 +167,7 @@ static ipc_server_application_cb test_app_cb; * by this application. */ static int test_app_cb(void *application_data, - const char *command, + const char *command, size_t command_len, ipc_server_reply_cb *reply_cb, struct ipc_server_reply_data *reply_data) { @@ -173,7 +180,7 @@ static int test_app_cb(void *application_data, if (application_data != (void*)&my_app_data) BUG("application_cb: application_data pointer wrong"); - if (!strcmp(command, "quit")) { + if (command_len == 4 && !strncmp(command, "quit", 4)) { /* * The client sent a "quit" command. This is an async * request for the server to shutdown. @@ -193,22 +200,23 @@ static int test_app_cb(void *application_data, return SIMPLE_IPC_QUIT; } - if (!strcmp(command, "ping")) { + if (command_len == 4 && !strncmp(command, "ping", 4)) { const char *answer = "pong"; return reply_cb(reply_data, answer, strlen(answer)); } - if (!strcmp(command, "big")) + if (command_len == 3 && !strncmp(command, "big", 3)) return app__big_command(reply_cb, reply_data); - if (!strcmp(command, "chunk")) + if (command_len == 5 && !strncmp(command, "chunk", 5)) return app__chunk_command(reply_cb, reply_data); - if (!strcmp(command, "slow")) + if (command_len == 4 && !strncmp(command, "slow", 4)) return app__slow_command(reply_cb, reply_data); - if (starts_with(command, "sendbytes ")) - return app__sendbytes_command(command, reply_cb, reply_data); + if (command_len >= 10 && starts_with(command, "sendbytes ")) + return app__sendbytes_command(command, command_len, + reply_cb, reply_data); return app__unhandled_command(command, reply_cb, reply_data); } @@ -488,7 +496,9 @@ static int client__send_ipc(void) options.wait_if_busy = 1; options.wait_if_not_found = 0; - if (!ipc_client_send_command(cl_args.path, &options, command, &buf)) { + if (!ipc_client_send_command(cl_args.path, &options, + command, strlen(command), + &buf)) { if (buf.len) { printf("%s\n", buf.buf); fflush(stdout); @@ -556,7 +566,9 @@ static int do_sendbytes(int bytecount, char byte, const char *path, strbuf_addstr(&buf_send, "sendbytes "); strbuf_addchars(&buf_send, byte, bytecount); - if (!ipc_client_send_command(path, options, buf_send.buf, &buf_resp)) { + if (!ipc_client_send_command(path, options, + buf_send.buf, buf_send.len, + &buf_resp)) { strbuf_rtrim(&buf_resp); printf("sent:%c%08d %s\n", byte, bytecount, buf_resp.buf); fflush(stdout); From ab8d99ba23ddea509f0819f3aeb44f18f5654c95 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Tue, 11 May 2021 17:20:18 -0400 Subject: [PATCH 02/30] fsmonitor--daemon: man page Create a manual page describing the `git fsmonitor--daemon` feature. Signed-off-by: Jeff Hostetler --- Documentation/git-fsmonitor--daemon.txt | 75 +++++++++++++++++++++++++ 1 file changed, 75 insertions(+) create mode 100644 Documentation/git-fsmonitor--daemon.txt diff --git a/Documentation/git-fsmonitor--daemon.txt b/Documentation/git-fsmonitor--daemon.txt new file mode 100644 index 0000000000..154e7684da --- /dev/null +++ b/Documentation/git-fsmonitor--daemon.txt @@ -0,0 +1,75 @@ +git-fsmonitor--daemon(1) +======================== + +NAME +---- +git-fsmonitor--daemon - A Built-in File System Monitor + +SYNOPSIS +-------- +[verse] +'git fsmonitor--daemon' start +'git fsmonitor--daemon' run +'git fsmonitor--daemon' stop +'git fsmonitor--daemon' status + +DESCRIPTION +----------- + +A daemon to watch the working directory for file and directory +changes using platform-specific file system notification facilities. + +This daemon communicates directly with commands like `git status` +using the link:technical/api-simple-ipc.html[simple IPC] interface +instead of the slower linkgit:githooks[5] interface. + +This daemon is built into Git so that no third-party tools are +required. + +OPTIONS +------- + +start:: + Starts a daemon in the background. + +run:: + Runs a daemon in the foreground. + +stop:: + Stops the daemon running in the current working + directory, if present. + +status:: + Exits with zero status if a daemon is watching the + current working directory. + +REMARKS +------- + +This daemon is a long running process used to watch a single working +directory and maintain a list of the recently changed files and +directories. Performance of commands such as `git status` can be +increased if they just ask for a summary of changes to the working +directory and can avoid scanning the disk. + +When `core.useBuiltinFSMonitor` is set to `true` (see +linkgit:git-config[1]) commands, such as `git status`, will ask the +daemon for changes and automatically start it (if necessary). + +For more information see the "File System Monitor" section in +linkgit:git-update-index[1]. + +CAVEATS +------- + +The fsmonitor daemon does not currently know about submodules and does +not know to filter out file system events that happen within a +submodule. If fsmonitor daemon is watching a super repo and a file is +modified within the working directory of a submodule, it will report +the change (as happening against the super repo). However, the client +will properly ignore these extra events, so performance may be affected +but it will not cause an incorrect result. + +GIT +--- +Part of the linkgit:git[1] suite From a044e62b4a1ceb9b49dd38c1e02894112ee08ae3 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Tue, 11 May 2021 17:21:21 -0400 Subject: [PATCH 03/30] fsmonitor--daemon: update fsmonitor documentation Update references to `core.fsmonitor` and `core.fsmonitorHookVersion` and pointers to `Watchman` to mention the new built-in `fsmonitor--daemon`. Signed-off-by: Jeff Hostetler --- Documentation/config/core.txt | 56 ++++++++++++++++++++++-------- Documentation/git-update-index.txt | 25 +++++++------ Documentation/githooks.txt | 3 +- 3 files changed, 58 insertions(+), 26 deletions(-) diff --git a/Documentation/config/core.txt b/Documentation/config/core.txt index c04f62a54a..4f6e519bc0 100644 --- a/Documentation/config/core.txt +++ b/Documentation/config/core.txt @@ -62,22 +62,50 @@ core.protectNTFS:: Defaults to `true` on Windows, and `false` elsewhere. core.fsmonitor:: - If set, the value of this variable is used as a command which - will identify all files that may have changed since the - requested date/time. This information is used to speed up git by - avoiding unnecessary processing of files that have not changed. - See the "fsmonitor-watchman" section of linkgit:githooks[5]. + If set, this variable contains the pathname of the "fsmonitor" + hook command. ++ +This hook command is used to identify all files that may have changed +since the requested date/time. This information is used to speed up +git by avoiding unnecessary scanning of files that have not changed. ++ +See the "fsmonitor-watchman" section of linkgit:githooks[5]. ++ +Note: The value of this config setting is ignored if the +built-in file system monitor is enabled (see `core.useBuiltinFSMonitor`). core.fsmonitorHookVersion:: - Sets the version of hook that is to be used when calling fsmonitor. - There are currently versions 1 and 2. When this is not set, - version 2 will be tried first and if it fails then version 1 - will be tried. Version 1 uses a timestamp as input to determine - which files have changes since that time but some monitors - like watchman have race conditions when used with a timestamp. - Version 2 uses an opaque string so that the monitor can return - something that can be used to determine what files have changed - without race conditions. + Sets the protocol version to be used when invoking the + "fsmonitor" hook. ++ +There are currently versions 1 and 2. When this is not set, +version 2 will be tried first and if it fails then version 1 +will be tried. Version 1 uses a timestamp as input to determine +which files have changes since that time but some monitors +like Watchman have race conditions when used with a timestamp. +Version 2 uses an opaque string so that the monitor can return +something that can be used to determine what files have changed +without race conditions. ++ +Note: The value of this config setting is ignored if the +built-in file system monitor is enabled (see `core.useBuiltinFSMonitor`). + +core.useBuiltinFSMonitor:: + If set to true, enable the built-in file system monitor + daemon for this working directory (linkgit:git-fsmonitor--daemon[1]). ++ +Like hook-based file system monitors, the built-in file system monitor +can speed up Git commands that need to refresh the Git index +(e.g. `git status`) in a working directory with many files. The +built-in monitor eliminates the need to install and maintain an +external third-party tool. ++ +The built-in file system monitor is currently available only on a +limited set of supported platforms. Currently, this includes Windows +and MacOS. ++ +Note: if this config setting is set to `true`, the values of +`core.fsmonitor` and `core.fsmonitorHookVersion` are ignored. core.trustctime:: If false, the ctime differences between the index and the diff --git a/Documentation/git-update-index.txt b/Documentation/git-update-index.txt index 2853f168d9..c7c31b3fcf 100644 --- a/Documentation/git-update-index.txt +++ b/Documentation/git-update-index.txt @@ -498,7 +498,9 @@ FILE SYSTEM MONITOR This feature is intended to speed up git operations for repos that have large working directories. -It enables git to work together with a file system monitor (see the +It enables git to work together with a file system monitor (see +linkgit:git-fsmonitor--daemon[1] +and the "fsmonitor-watchman" section of linkgit:githooks[5]) that can inform it as to what files have been modified. This enables git to avoid having to lstat() every file to find modified files. @@ -508,17 +510,18 @@ performance by avoiding the cost of scanning the entire working directory looking for new files. If you want to enable (or disable) this feature, it is easier to use -the `core.fsmonitor` configuration variable (see -linkgit:git-config[1]) than using the `--fsmonitor` option to -`git update-index` in each repository, especially if you want to do so -across all repositories you use, because you can set the configuration -variable in your `$HOME/.gitconfig` just once and have it affect all -repositories you touch. +the `core.fsmonitor` or `core.useBuiltinFSMonitor` configuration +variable (see linkgit:git-config[1]) than using the `--fsmonitor` +option to `git update-index` in each repository, especially if you +want to do so across all repositories you use, because you can set the +configuration variable in your `$HOME/.gitconfig` just once and have +it affect all repositories you touch. -When the `core.fsmonitor` configuration variable is changed, the -file system monitor is added to or removed from the index the next time -a command reads the index. When `--[no-]fsmonitor` are used, the file -system monitor is immediately added to or removed from the index. +When the `core.fsmonitor` or `core.useBuiltinFSMonitor` configuration +variable is changed, the file system monitor is added to or removed +from the index the next time a command reads the index. When +`--[no-]fsmonitor` are used, the file system monitor is immediately +added to or removed from the index. CONFIGURATION ------------- diff --git a/Documentation/githooks.txt b/Documentation/githooks.txt index b51959ff94..b7d5e926f7 100644 --- a/Documentation/githooks.txt +++ b/Documentation/githooks.txt @@ -593,7 +593,8 @@ fsmonitor-watchman This hook is invoked when the configuration option `core.fsmonitor` is set to `.git/hooks/fsmonitor-watchman` or `.git/hooks/fsmonitor-watchmanv2` -depending on the version of the hook to use. +depending on the version of the hook to use, unless overridden via +`core.useBuiltinFSMonitor` (see linkgit:git-config[1]). Version 1 takes two arguments, a version (1) and the time in elapsed nanoseconds since midnight, January 1, 1970. From 99e09ffffafcd7839e28952a4bd9c14e27907720 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Wed, 12 May 2021 08:47:57 -0400 Subject: [PATCH 04/30] fsmonitor-ipc: create client routines for git-fsmonitor--daemon Create fsmonitor_ipc__*() client routines to spawn the built-in file system monitor daemon and send it an IPC request using the `Simple IPC` API. Stub in empty fsmonitor_ipc__*() functions for unsupported platforms. Signed-off-by: Jeff Hostetler --- Makefile | 1 + fsmonitor-ipc.c | 179 ++++++++++++++++++++++++++++++++++++++++++++++++ fsmonitor-ipc.h | 48 +++++++++++++ 3 files changed, 228 insertions(+) create mode 100644 fsmonitor-ipc.c create mode 100644 fsmonitor-ipc.h diff --git a/Makefile b/Makefile index c3565fc0f8..209c97aa22 100644 --- a/Makefile +++ b/Makefile @@ -893,6 +893,7 @@ LIB_OBJS += fetch-pack.o LIB_OBJS += fmt-merge-msg.o LIB_OBJS += fsck.o LIB_OBJS += fsmonitor.o +LIB_OBJS += fsmonitor-ipc.o LIB_OBJS += gettext.o LIB_OBJS += gpg-interface.o LIB_OBJS += graph.o diff --git a/fsmonitor-ipc.c b/fsmonitor-ipc.c new file mode 100644 index 0000000000..47afb4709f --- /dev/null +++ b/fsmonitor-ipc.c @@ -0,0 +1,179 @@ +#include "cache.h" +#include "fsmonitor.h" +#include "simple-ipc.h" +#include "fsmonitor-ipc.h" +#include "run-command.h" +#include "strbuf.h" +#include "trace2.h" + +#ifdef HAVE_FSMONITOR_DAEMON_BACKEND + +int fsmonitor_ipc__is_supported(void) +{ + return 1; +} + +GIT_PATH_FUNC(fsmonitor_ipc__get_path, "fsmonitor--daemon.ipc") + +enum ipc_active_state fsmonitor_ipc__get_state(void) +{ + return ipc_get_active_state(fsmonitor_ipc__get_path()); +} + +static int spawn_daemon(void) +{ + const char *args[] = { "fsmonitor--daemon", "start", NULL }; + + return run_command_v_opt_tr2(args, RUN_COMMAND_NO_STDIN | RUN_GIT_CMD, + "fsmonitor"); +} + +int fsmonitor_ipc__send_query(const char *since_token, + struct strbuf *answer) +{ + int ret = -1; + int tried_to_spawn = 0; + enum ipc_active_state state = IPC_STATE__OTHER_ERROR; + struct ipc_client_connection *connection = NULL; + struct ipc_client_connect_options options + = IPC_CLIENT_CONNECT_OPTIONS_INIT; + + options.wait_if_busy = 1; + options.wait_if_not_found = 0; + + trace2_region_enter("fsm_client", "query", NULL); + + trace2_data_string("fsm_client", NULL, "query/command", + since_token ? since_token : "(null-token)"); + +try_again: + state = ipc_client_try_connect(fsmonitor_ipc__get_path(), &options, + &connection); + + switch (state) { + case IPC_STATE__LISTENING: + ret = ipc_client_send_command_to_connection( + connection, since_token, since_token ? strlen(since_token) : 0, answer); + ipc_client_close_connection(connection); + + trace2_data_intmax("fsm_client", NULL, + "query/response-length", answer->len); + + if (fsmonitor_is_trivial_response(answer)) + trace2_data_intmax("fsm_client", NULL, + "query/trivial-response", 1); + + goto done; + + case IPC_STATE__NOT_LISTENING: + ret = error(_("fsmonitor_ipc__send_query: daemon not available")); + goto done; + + case IPC_STATE__PATH_NOT_FOUND: + if (tried_to_spawn) + goto done; + + tried_to_spawn++; + if (spawn_daemon()) + goto done; + + /* + * Try again, but this time give the daemon a chance to + * actually create the pipe/socket. + * + * Granted, the daemon just started so it can't possibly have + * any FS cached yet, so we'll always get a trivial answer. + * BUT the answer should include a new token that can serve + * as the basis for subsequent requests. + */ + options.wait_if_not_found = 1; + goto try_again; + + case IPC_STATE__INVALID_PATH: + ret = error(_("fsmonitor_ipc__send_query: invalid path '%s'"), + fsmonitor_ipc__get_path()); + goto done; + + case IPC_STATE__OTHER_ERROR: + default: + ret = error(_("fsmonitor_ipc__send_query: unspecified error on '%s'"), + fsmonitor_ipc__get_path()); + goto done; + } + +done: + trace2_region_leave("fsm_client", "query", NULL); + + return ret; +} + +int fsmonitor_ipc__send_command(const char *command, + struct strbuf *answer) +{ + struct ipc_client_connection *connection = NULL; + struct ipc_client_connect_options options + = IPC_CLIENT_CONNECT_OPTIONS_INIT; + int ret; + enum ipc_active_state state; + + strbuf_reset(answer); + + options.wait_if_busy = 1; + options.wait_if_not_found = 0; + + state = ipc_client_try_connect(fsmonitor_ipc__get_path(), &options, + &connection); + if (state != IPC_STATE__LISTENING) { + die("fsmonitor--daemon is not running"); + return -1; + } + + ret = ipc_client_send_command_to_connection(connection, + command, strlen(command), + answer); + ipc_client_close_connection(connection); + + if (ret == -1) { + die("could not send '%s' command to fsmonitor--daemon", + command); + return -1; + } + + return 0; +} + +#else + +/* + * A trivial implementation of the fsmonitor_ipc__ API for unsupported + * platforms. + */ + +int fsmonitor_ipc__is_supported(void) +{ + return 0; +} + +const char *fsmonitor_ipc__get_path(void) +{ + return NULL; +} + +enum ipc_active_state fsmonitor_ipc__get_state(void) +{ + return IPC_STATE__OTHER_ERROR; +} + +int fsmonitor_ipc__send_query(const char *since_token, + struct strbuf *answer) +{ + return -1; +} + +int fsmonitor_ipc__send_command(const char *command, + struct strbuf *answer) +{ + return -1; +} + +#endif diff --git a/fsmonitor-ipc.h b/fsmonitor-ipc.h new file mode 100644 index 0000000000..837c5e5b64 --- /dev/null +++ b/fsmonitor-ipc.h @@ -0,0 +1,48 @@ +#ifndef FSMONITOR_IPC_H +#define FSMONITOR_IPC_H + +/* + * Returns true if built-in file system monitor daemon is defined + * for this platform. + */ +int fsmonitor_ipc__is_supported(void); + +/* + * Returns the pathname to the IPC named pipe or Unix domain socket + * where a `git-fsmonitor--daemon` process will listen. This is a + * per-worktree value. + * + * Returns NULL if the daemon is not supported on this platform. + */ +const char *fsmonitor_ipc__get_path(void); + +/* + * Try to determine whether there is a `git-fsmonitor--daemon` process + * listening on the IPC pipe/socket. + */ +enum ipc_active_state fsmonitor_ipc__get_state(void); + +/* + * Connect to a `git-fsmonitor--daemon` process via simple-ipc + * and ask for the set of changed files since the given token. + * + * This DOES NOT use the hook interface. + * + * Spawn a daemon process in the background if necessary. + * + * Returns -1 on error; 0 on success. + */ +int fsmonitor_ipc__send_query(const char *since_token, + struct strbuf *answer); + +/* + * Connect to a `git-fsmonitor--daemon` process via simple-ipc and + * send a command verb. If no daemon is available, we DO NOT try to + * start one. + * + * Returns -1 on error; 0 on success. + */ +int fsmonitor_ipc__send_command(const char *command, + struct strbuf *answer); + +#endif /* FSMONITOR_IPC_H */ From 2e5c2bc446d5b893553b95a9a9eef2f51ef69da3 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Wed, 12 May 2021 08:40:50 -0400 Subject: [PATCH 05/30] help: include fsmonitor--daemon feature flag in version info Add the "feature: fsmonitor--daemon" message to the output of `git version --build-options`. This allows users to know if the built-in fsmonitor feature is supported on their platform. Signed-off-by: Jeff Hostetler --- help.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/help.c b/help.c index 3c3bdec213..e22ba1d246 100644 --- a/help.c +++ b/help.c @@ -11,6 +11,7 @@ #include "version.h" #include "refs.h" #include "parse-options.h" +#include "fsmonitor-ipc.h" struct category_description { uint32_t category; @@ -664,6 +665,9 @@ void get_version_info(struct strbuf *buf, int show_build_options) strbuf_addf(buf, "sizeof-size_t: %d\n", (int)sizeof(size_t)); strbuf_addf(buf, "shell-path: %s\n", SHELL_PATH); /* NEEDSWORK: also save and output GIT-BUILD_OPTIONS? */ + + if (fsmonitor_ipc__is_supported()) + strbuf_addstr(buf, "feature: fsmonitor--daemon\n"); } } From 0ed2e673dffee975b52a5b64ef6e4d16f2f40362 Mon Sep 17 00:00:00 2001 From: Johannes Schindelin Date: Fri, 5 Mar 2021 21:20:26 +0100 Subject: [PATCH 06/30] config: FSMonitor is repository-specific This commit refactors `git_config_get_fsmonitor()` into the `repo_*()` form that takes a parameter `struct repository *r`. That change prepares for the upcoming `core.useBuiltinFSMonitor` flag which will be stored in the `repo_settings` struct. Signed-off-by: Johannes Schindelin --- builtin/update-index.c | 4 ++-- config.c | 4 ++-- config.h | 2 +- fsmonitor.c | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) diff --git a/builtin/update-index.c b/builtin/update-index.c index f1f16f2de5..87a1d439a1 100644 --- a/builtin/update-index.c +++ b/builtin/update-index.c @@ -1216,14 +1216,14 @@ int cmd_update_index(int argc, const char **argv, const char *prefix) } if (fsmonitor > 0) { - if (git_config_get_fsmonitor() == 0) + if (repo_config_get_fsmonitor(r) == 0) warning(_("core.fsmonitor is unset; " "set it if you really want to " "enable fsmonitor")); add_fsmonitor(&the_index); report(_("fsmonitor enabled")); } else if (!fsmonitor) { - if (git_config_get_fsmonitor() == 1) + if (repo_config_get_fsmonitor(r) == 1) warning(_("core.fsmonitor is set; " "remove it if you really want to " "disable fsmonitor")); diff --git a/config.c b/config.c index f9c400ad30..7bf51a1ff2 100644 --- a/config.c +++ b/config.c @@ -2516,9 +2516,9 @@ int git_config_get_max_percent_split_change(void) return -1; /* default value */ } -int git_config_get_fsmonitor(void) +int repo_config_get_fsmonitor(struct repository *r) { - if (git_config_get_pathname("core.fsmonitor", &core_fsmonitor)) + if (repo_config_get_pathname(r, "core.fsmonitor", &core_fsmonitor)) core_fsmonitor = getenv("GIT_TEST_FSMONITOR"); if (core_fsmonitor && !*core_fsmonitor) diff --git a/config.h b/config.h index 9038538ffd..e14a9d1fe1 100644 --- a/config.h +++ b/config.h @@ -609,7 +609,7 @@ int git_config_get_index_threads(int *dest); int git_config_get_untracked_cache(void); int git_config_get_split_index(void); int git_config_get_max_percent_split_change(void); -int git_config_get_fsmonitor(void); +int repo_config_get_fsmonitor(struct repository *r); /* This dies if the configured or default date is in the future */ int git_config_get_expiry(const char *key, const char **output); diff --git a/fsmonitor.c b/fsmonitor.c index ab9bfc60b3..9c9b2abc94 100644 --- a/fsmonitor.c +++ b/fsmonitor.c @@ -411,7 +411,7 @@ void remove_fsmonitor(struct index_state *istate) void tweak_fsmonitor(struct index_state *istate) { unsigned int i; - int fsmonitor_enabled = git_config_get_fsmonitor(); + int fsmonitor_enabled = repo_config_get_fsmonitor(istate->repo ? istate->repo : the_repository); if (istate->fsmonitor_dirty) { if (fsmonitor_enabled) { From 98487f09aaa223461755baea0adfbfcb744f661f Mon Sep 17 00:00:00 2001 From: Johannes Schindelin Date: Fri, 2 Aug 2019 19:17:25 +0200 Subject: [PATCH 07/30] fsmonitor: introduce `core.useBuiltinFSMonitor` to call the daemon via IPC Use simple IPC to directly communicate with the new builtin file system monitor daemon. Define a new config setting `core.useBuiltinFSMonitor` to enable the builtin file system monitor. The `core.fsmonitor` setting has already been defined as a HOOK pathname. Historically, this has been set to a HOOK script that will talk with Watchman. For compatibility reasons, we do not want to overload that definition (and cause problems if users have multiple versions of Git installed). Signed-off-by: Johannes Schindelin Signed-off-by: Jeff Hostetler --- config.c | 5 +++++ fsmonitor.c | 43 +++++++++++++++++++++++++++++++++++++++++++ repo-settings.c | 3 +++ repository.h | 2 ++ 4 files changed, 53 insertions(+) diff --git a/config.c b/config.c index 7bf51a1ff2..d8649cda05 100644 --- a/config.c +++ b/config.c @@ -2518,6 +2518,11 @@ int git_config_get_max_percent_split_change(void) int repo_config_get_fsmonitor(struct repository *r) { + if (r->settings.use_builtin_fsmonitor > 0) { + core_fsmonitor = "(built-in daemon)"; + return 1; + } + if (repo_config_get_pathname(r, "core.fsmonitor", &core_fsmonitor)) core_fsmonitor = getenv("GIT_TEST_FSMONITOR"); diff --git a/fsmonitor.c b/fsmonitor.c index 9c9b2abc94..c6d3c34ad7 100644 --- a/fsmonitor.c +++ b/fsmonitor.c @@ -3,6 +3,7 @@ #include "dir.h" #include "ewah/ewok.h" #include "fsmonitor.h" +#include "fsmonitor-ipc.h" #include "run-command.h" #include "strbuf.h" @@ -231,6 +232,7 @@ static void fsmonitor_refresh_callback(struct index_state *istate, char *name) void refresh_fsmonitor(struct index_state *istate) { + struct repository *r = istate->repo ? istate->repo : the_repository; struct strbuf query_result = STRBUF_INIT; int query_success = 0, hook_version = -1; size_t bol = 0; /* beginning of line */ @@ -247,6 +249,46 @@ void refresh_fsmonitor(struct index_state *istate) istate->fsmonitor_has_run_once = 1; trace_printf_key(&trace_fsmonitor, "refresh fsmonitor"); + + if (r->settings.use_builtin_fsmonitor > 0) { + query_success = !fsmonitor_ipc__send_query( + istate->fsmonitor_last_update, &query_result); + if (query_success) { + /* + * The response contains a series of nul terminated + * strings. The first is the new token. + * + * Use `char *buf` as an interlude to trick the CI + * static analysis to let us use `strbuf_addstr()` + * here (and only copy the token) rather than + * `strbuf_addbuf()`. + */ + buf = query_result.buf; + strbuf_addstr(&last_update_token, buf); + bol = last_update_token.len + 1; + } else { + /* + * The builtin daemon is not available on this + * platform -OR- we failed to get a response. + * + * Generate a fake token (rather than a V1 + * timestamp) for the index extension. (If + * they switch back to the hook API, we don't + * want ambiguous state.) + */ + strbuf_addstr(&last_update_token, "builtin:fake"); + } + + /* + * Regardless of whether we successfully talked to a + * fsmonitor daemon or not, we skip over and do not + * try to use the hook. The "core.useBuiltinFSMonitor" + * config setting ALWAYS overrides the "core.fsmonitor" + * hook setting. + */ + goto apply_results; + } + /* * This could be racy so save the date/time now and query_fsmonitor * should be inclusive to ensure we don't miss potential changes. @@ -301,6 +343,7 @@ void refresh_fsmonitor(struct index_state *istate) core_fsmonitor, query_success ? "success" : "failure"); } +apply_results: /* a fsmonitor process can return '/' to indicate all entries are invalid */ if (query_success && query_result.buf[bol] != '/') { /* Mark all entries returned by the monitor as dirty */ diff --git a/repo-settings.c b/repo-settings.c index 0cfe8b787d..bbcf71461b 100644 --- a/repo-settings.c +++ b/repo-settings.c @@ -58,6 +58,9 @@ void prepare_repo_settings(struct repository *r) r->settings.core_multi_pack_index = value; UPDATE_DEFAULT_BOOL(r->settings.core_multi_pack_index, 1); + if (!repo_config_get_bool(r, "core.usebuiltinfsmonitor", &value) && value) + r->settings.use_builtin_fsmonitor = 1; + if (!repo_config_get_bool(r, "feature.manyfiles", &value) && value) { UPDATE_DEFAULT_BOOL(r->settings.index_version, 4); UPDATE_DEFAULT_BOOL(r->settings.core_untracked_cache, UNTRACKED_CACHE_WRITE); diff --git a/repository.h b/repository.h index a45f7520fd..1e7a09a1fa 100644 --- a/repository.h +++ b/repository.h @@ -29,6 +29,8 @@ enum fetch_negotiation_setting { struct repo_settings { int initialized; + int use_builtin_fsmonitor; + int core_commit_graph; int commit_graph_read_changed_paths; int gc_write_commit_graph; From cd59abb902390ff0d0b106b455229f0f5830be9b Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Wed, 16 Dec 2020 10:24:30 -0500 Subject: [PATCH 08/30] fsmonitor--daemon: add a built-in fsmonitor daemon Create a built-in file system monitoring daemon that can be used by the existing `fsmonitor` feature (protocol API and index extension) to improve the performance of various Git commands, such as `status`. The `fsmonitor--daemon` feature builds upon the `Simple IPC` API and provides an alternative to hook access to existing fsmonitors such as `watchman`. This commit merely adds the new command without any functionality. Co-authored-by: Johannes Schindelin Signed-off-by: Jeff Hostetler --- .gitignore | 1 + Makefile | 1 + builtin.h | 1 + builtin/fsmonitor--daemon.c | 53 +++++++++++++++++++++++++++++++++++++ git.c | 1 + 5 files changed, 57 insertions(+) create mode 100644 builtin/fsmonitor--daemon.c diff --git a/.gitignore b/.gitignore index 311841f9be..4baba472aa 100644 --- a/.gitignore +++ b/.gitignore @@ -72,6 +72,7 @@ /git-format-patch /git-fsck /git-fsck-objects +/git-fsmonitor--daemon /git-gc /git-get-tar-commit-id /git-grep diff --git a/Makefile b/Makefile index 209c97aa22..8fe1e42a43 100644 --- a/Makefile +++ b/Makefile @@ -1097,6 +1097,7 @@ BUILTIN_OBJS += builtin/fmt-merge-msg.o BUILTIN_OBJS += builtin/for-each-ref.o BUILTIN_OBJS += builtin/for-each-repo.o BUILTIN_OBJS += builtin/fsck.o +BUILTIN_OBJS += builtin/fsmonitor--daemon.o BUILTIN_OBJS += builtin/gc.o BUILTIN_OBJS += builtin/get-tar-commit-id.o BUILTIN_OBJS += builtin/grep.o diff --git a/builtin.h b/builtin.h index 16ecd5586f..2470d1cd3a 100644 --- a/builtin.h +++ b/builtin.h @@ -159,6 +159,7 @@ int cmd_for_each_ref(int argc, const char **argv, const char *prefix); int cmd_for_each_repo(int argc, const char **argv, const char *prefix); int cmd_format_patch(int argc, const char **argv, const char *prefix); int cmd_fsck(int argc, const char **argv, const char *prefix); +int cmd_fsmonitor__daemon(int argc, const char **argv, const char *prefix); int cmd_gc(int argc, const char **argv, const char *prefix); int cmd_get_tar_commit_id(int argc, const char **argv, const char *prefix); int cmd_grep(int argc, const char **argv, const char *prefix); diff --git a/builtin/fsmonitor--daemon.c b/builtin/fsmonitor--daemon.c new file mode 100644 index 0000000000..df2bad5311 --- /dev/null +++ b/builtin/fsmonitor--daemon.c @@ -0,0 +1,53 @@ +#include "builtin.h" +#include "config.h" +#include "parse-options.h" +#include "fsmonitor.h" +#include "fsmonitor-ipc.h" +#include "simple-ipc.h" +#include "khash.h" + +static const char * const builtin_fsmonitor__daemon_usage[] = { + NULL +}; + +#ifdef HAVE_FSMONITOR_DAEMON_BACKEND + +int cmd_fsmonitor__daemon(int argc, const char **argv, const char *prefix) +{ + const char *subcmd; + + struct option options[] = { + OPT_END() + }; + + if (argc < 2) + usage_with_options(builtin_fsmonitor__daemon_usage, options); + + if (argc == 2 && !strcmp(argv[1], "-h")) + usage_with_options(builtin_fsmonitor__daemon_usage, options); + + git_config(git_default_config, NULL); + + subcmd = argv[1]; + argv--; + argc++; + + argc = parse_options(argc, argv, prefix, options, + builtin_fsmonitor__daemon_usage, 0); + + die(_("Unhandled subcommand '%s'"), subcmd); +} + +#else +int cmd_fsmonitor__daemon(int argc, const char **argv, const char *prefix) +{ + struct option options[] = { + OPT_END() + }; + + if (argc == 2 && !strcmp(argv[1], "-h")) + usage_with_options(builtin_fsmonitor__daemon_usage, options); + + die(_("fsmonitor--daemon not supported on this platform")); +} +#endif diff --git a/git.c b/git.c index 18bed9a996..c6160f4a88 100644 --- a/git.c +++ b/git.c @@ -533,6 +533,7 @@ static struct cmd_struct commands[] = { { "format-patch", cmd_format_patch, RUN_SETUP }, { "fsck", cmd_fsck, RUN_SETUP }, { "fsck-objects", cmd_fsck, RUN_SETUP }, + { "fsmonitor--daemon", cmd_fsmonitor__daemon, RUN_SETUP }, { "gc", cmd_gc, RUN_SETUP }, { "get-tar-commit-id", cmd_get_tar_commit_id, NO_PARSEOPT }, { "grep", cmd_grep, RUN_SETUP_GENTLY }, From 3c1410b298e8bc9be1fb0add610804a8e5ccb558 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Wed, 16 Dec 2020 11:02:46 -0500 Subject: [PATCH 09/30] fsmonitor--daemon: implement client command options Implement `stop` and `status` client commands to control and query the status of a `fsmonitor--daemon` server process (and implicitly start a server process if necessary). Later commits will implement the actual server and monitor the file system. Signed-off-by: Jeff Hostetler --- builtin/fsmonitor--daemon.c | 49 +++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) diff --git a/builtin/fsmonitor--daemon.c b/builtin/fsmonitor--daemon.c index df2bad5311..16ff68b654 100644 --- a/builtin/fsmonitor--daemon.c +++ b/builtin/fsmonitor--daemon.c @@ -7,10 +7,53 @@ #include "khash.h" static const char * const builtin_fsmonitor__daemon_usage[] = { + N_("git fsmonitor--daemon stop"), + N_("git fsmonitor--daemon status"), NULL }; #ifdef HAVE_FSMONITOR_DAEMON_BACKEND +/* + * Acting as a CLIENT. + * + * Send a "quit" command to the `git-fsmonitor--daemon` (if running) + * and wait for it to shutdown. + */ +static int do_as_client__send_stop(void) +{ + struct strbuf answer = STRBUF_INIT; + int ret; + + ret = fsmonitor_ipc__send_command("quit", &answer); + + /* The quit command does not return any response data. */ + strbuf_release(&answer); + + if (ret) + return ret; + + trace2_region_enter("fsm_client", "polling-for-daemon-exit", NULL); + while (fsmonitor_ipc__get_state() == IPC_STATE__LISTENING) + sleep_millisec(50); + trace2_region_leave("fsm_client", "polling-for-daemon-exit", NULL); + + return 0; +} + +static int do_as_client__status(void) +{ + enum ipc_active_state state = fsmonitor_ipc__get_state(); + + switch (state) { + case IPC_STATE__LISTENING: + printf(_("The built-in file system monitor is active\n")); + return 0; + + default: + printf(_("The built-in file system monitor is not active\n")); + return 1; + } +} int cmd_fsmonitor__daemon(int argc, const char **argv, const char *prefix) { @@ -35,6 +78,12 @@ int cmd_fsmonitor__daemon(int argc, const char **argv, const char *prefix) argc = parse_options(argc, argv, prefix, options, builtin_fsmonitor__daemon_usage, 0); + if (!strcmp(subcmd, "stop")) + return !!do_as_client__send_stop(); + + if (!strcmp(subcmd, "status")) + return !!do_as_client__status(); + die(_("Unhandled subcommand '%s'"), subcmd); } From d87be8f05b6709e464cba09310681d3b973c0eca Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Tue, 11 May 2021 18:32:07 -0400 Subject: [PATCH 10/30] t/helper/fsmonitor-client: create IPC client to talk to FSMonitor Daemon Create an IPC client to send query and flush commands to the daemon. Signed-off-by: Jeff Hostetler --- Makefile | 1 + t/helper/test-fsmonitor-client.c | 125 +++++++++++++++++++++++++++++++ t/helper/test-tool.c | 1 + t/helper/test-tool.h | 1 + 4 files changed, 128 insertions(+) create mode 100644 t/helper/test-fsmonitor-client.c diff --git a/Makefile b/Makefile index 8fe1e42a43..c45caacf2c 100644 --- a/Makefile +++ b/Makefile @@ -709,6 +709,7 @@ TEST_BUILTINS_OBJS += test-dump-split-index.o TEST_BUILTINS_OBJS += test-dump-untracked-cache.o TEST_BUILTINS_OBJS += test-example-decorate.o TEST_BUILTINS_OBJS += test-fast-rebase.o +TEST_BUILTINS_OBJS += test-fsmonitor-client.o TEST_BUILTINS_OBJS += test-genrandom.o TEST_BUILTINS_OBJS += test-genzeros.o TEST_BUILTINS_OBJS += test-hash-speed.o diff --git a/t/helper/test-fsmonitor-client.c b/t/helper/test-fsmonitor-client.c new file mode 100644 index 0000000000..4961f28e3e --- /dev/null +++ b/t/helper/test-fsmonitor-client.c @@ -0,0 +1,125 @@ +/* + * test-fsmonitor-client.c: client code to send commands/requests to + * a `git fsmonitor--daemon` daemon. + */ + +#include "test-tool.h" +#include "cache.h" +#include "parse-options.h" +//#include "fsmonitor.h" +#include "fsmonitor-ipc.h" +//#include "compat/fsmonitor/fsmonitor-fs-listen.h" +//#include "fsmonitor--daemon.h" +//#include "simple-ipc.h" + +#ifndef HAVE_FSMONITOR_DAEMON_BACKEND +int cmd__fsmonitor_client(int argc, const char **argv) +{ + die("fsmonitor--daemon not available on this platform"); +} +#else + +/* + * Read the `.git/index` to get the last token written to the + * FSMonitor Index Extension. + */ +static const char *get_token_from_index(void) +{ + struct index_state *istate = the_repository->index; + + if (do_read_index(istate, the_repository->index_file, 0) < 0) + die("unable to read index file"); + if (!istate->fsmonitor_last_update) + die("index file does not have fsmonitor extension"); + + return istate->fsmonitor_last_update; +} + +/* + * Send an IPC query to a `git-fsmonitor--daemon` daemon and + * ask for the changes since the given token or from the last + * token in the index extension. + * + * This will implicitly start a daemon process if necessary. The + * daemon process will persist after we exit. + */ +static int do_send_query(const char *token) +{ + struct strbuf answer = STRBUF_INIT; + int ret; + + if (!token || !*token) + token = get_token_from_index(); + + ret = fsmonitor_ipc__send_query(token, &answer); + if (ret < 0) + die(_("could not query fsmonitor--daemon")); + + write_in_full(1, answer.buf, answer.len); + strbuf_release(&answer); + + return 0; +} + +/* + * Send a "flush" command to the `git-fsmonitor--daemon` (if running) + * and tell it to flush its cache. + * + * This feature is primarily used by the test suite to simulate a loss of + * sync with the filesystem where we miss kernel events. + */ +static int do_send_flush(void) +{ + struct strbuf answer = STRBUF_INIT; + int ret; + + ret = fsmonitor_ipc__send_command("flush", &answer); + if (ret) + return ret; + + write_in_full(1, answer.buf, answer.len); + strbuf_release(&answer); + + return 0; +} + +int cmd__fsmonitor_client(int argc, const char **argv) +{ + const char *subcmd; + const char *token = NULL; + + const char * const fsmonitor_client_usage[] = { + N_("test-helper fsmonitor-client query []"), + N_("test-helper fsmonitor-client flush"), + NULL, + }; + + struct option options[] = { + OPT_STRING(0, "token", &token, N_("token"), + N_("command token to send to the server")), + OPT_END() + }; + + if (argc < 2) + usage_with_options(fsmonitor_client_usage, options); + + if (argc == 2 && !strcmp(argv[1], "-h")) + usage_with_options(fsmonitor_client_usage, options); + + subcmd = argv[1]; + argv--; + argc++; + + argc = parse_options(argc, argv, NULL, options, fsmonitor_client_usage, 0); + + setup_git_directory(); + + if (!strcmp(subcmd, "query")) + return !!do_send_query(token); + + if (!strcmp(subcmd, "flush")) + return !!do_send_flush(); + + die("Unhandled subcommand: '%s'", subcmd); +} +#endif diff --git a/t/helper/test-tool.c b/t/helper/test-tool.c index c5bd0c6d4c..af879e4a5d 100644 --- a/t/helper/test-tool.c +++ b/t/helper/test-tool.c @@ -31,6 +31,7 @@ static struct test_cmd cmds[] = { { "dump-untracked-cache", cmd__dump_untracked_cache }, { "example-decorate", cmd__example_decorate }, { "fast-rebase", cmd__fast_rebase }, + { "fsmonitor-client", cmd__fsmonitor_client }, { "genrandom", cmd__genrandom }, { "genzeros", cmd__genzeros }, { "hashmap", cmd__hashmap }, diff --git a/t/helper/test-tool.h b/t/helper/test-tool.h index e8069a3b22..6c5134b46d 100644 --- a/t/helper/test-tool.h +++ b/t/helper/test-tool.h @@ -21,6 +21,7 @@ int cmd__dump_split_index(int argc, const char **argv); int cmd__dump_untracked_cache(int argc, const char **argv); int cmd__example_decorate(int argc, const char **argv); int cmd__fast_rebase(int argc, const char **argv); +int cmd__fsmonitor_client(int argc, const char **argv); int cmd__genrandom(int argc, const char **argv); int cmd__genzeros(int argc, const char **argv); int cmd__hashmap(int argc, const char **argv); From fe124291e2e919c1c3cf75ba8faf7be5dfcbe1f4 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Thu, 17 Dec 2020 10:29:17 -0500 Subject: [PATCH 11/30] fsmonitor-fs-listen-win32: stub in backend for Windows Stub in empty backend for fsmonitor--daemon on Windows. Signed-off-by: Jeff Hostetler --- Makefile | 13 ++++++ compat/fsmonitor/fsmonitor-fs-listen-win32.c | 21 +++++++++ compat/fsmonitor/fsmonitor-fs-listen.h | 49 ++++++++++++++++++++ config.mak.uname | 2 + contrib/buildsystems/CMakeLists.txt | 5 ++ 5 files changed, 90 insertions(+) create mode 100644 compat/fsmonitor/fsmonitor-fs-listen-win32.c create mode 100644 compat/fsmonitor/fsmonitor-fs-listen.h diff --git a/Makefile b/Makefile index c45caacf2c..a2a6e1f20f 100644 --- a/Makefile +++ b/Makefile @@ -467,6 +467,11 @@ all:: # directory, and the JSON compilation database 'compile_commands.json' will be # created at the root of the repository. # +# If your platform supports a built-in fsmonitor backend, set +# FSMONITOR_DAEMON_BACKEND to the "" of the corresponding +# `compat/fsmonitor/fsmonitor-fs-listen-.c` that implements the +# `fsmonitor_fs_listen__*()` routines. +# # Define DEVELOPER to enable more compiler warnings. Compiler version # and family are auto detected, but could be overridden by defining # COMPILER_FEATURES (see config.mak.dev). You can still set @@ -1929,6 +1934,11 @@ ifdef NEED_ACCESS_ROOT_HANDLER COMPAT_OBJS += compat/access.o endif +ifdef FSMONITOR_DAEMON_BACKEND + COMPAT_CFLAGS += -DHAVE_FSMONITOR_DAEMON_BACKEND + COMPAT_OBJS += compat/fsmonitor/fsmonitor-fs-listen-$(FSMONITOR_DAEMON_BACKEND).o +endif + ifeq ($(TCLTK_PATH),) NO_TCLTK = NoThanks endif @@ -2793,6 +2803,9 @@ GIT-BUILD-OPTIONS: FORCE @echo PAGER_ENV=\''$(subst ','\'',$(subst ','\'',$(PAGER_ENV)))'\' >>$@+ @echo DC_SHA1=\''$(subst ','\'',$(subst ','\'',$(DC_SHA1)))'\' >>$@+ @echo X=\'$(X)\' >>$@+ +ifdef FSMONITOR_DAEMON_BACKEND + @echo FSMONITOR_DAEMON_BACKEND=\''$(subst ','\'',$(subst ','\'',$(FSMONITOR_DAEMON_BACKEND)))'\' >>$@+ +endif ifdef TEST_OUTPUT_DIRECTORY @echo TEST_OUTPUT_DIRECTORY=\''$(subst ','\'',$(subst ','\'',$(TEST_OUTPUT_DIRECTORY)))'\' >>$@+ endif diff --git a/compat/fsmonitor/fsmonitor-fs-listen-win32.c b/compat/fsmonitor/fsmonitor-fs-listen-win32.c new file mode 100644 index 0000000000..880446b49e --- /dev/null +++ b/compat/fsmonitor/fsmonitor-fs-listen-win32.c @@ -0,0 +1,21 @@ +#include "cache.h" +#include "config.h" +#include "fsmonitor.h" +#include "fsmonitor-fs-listen.h" + +void fsmonitor_fs_listen__stop_async(struct fsmonitor_daemon_state *state) +{ +} + +void fsmonitor_fs_listen__loop(struct fsmonitor_daemon_state *state) +{ +} + +int fsmonitor_fs_listen__ctor(struct fsmonitor_daemon_state *state) +{ + return -1; +} + +void fsmonitor_fs_listen__dtor(struct fsmonitor_daemon_state *state) +{ +} diff --git a/compat/fsmonitor/fsmonitor-fs-listen.h b/compat/fsmonitor/fsmonitor-fs-listen.h new file mode 100644 index 0000000000..c7b5776b3b --- /dev/null +++ b/compat/fsmonitor/fsmonitor-fs-listen.h @@ -0,0 +1,49 @@ +#ifndef FSMONITOR_FS_LISTEN_H +#define FSMONITOR_FS_LISTEN_H + +/* This needs to be implemented by each backend */ + +#ifdef HAVE_FSMONITOR_DAEMON_BACKEND + +struct fsmonitor_daemon_state; + +/* + * Initialize platform-specific data for the fsmonitor listener thread. + * This will be called from the main thread PRIOR to staring the + * fsmonitor_fs_listener thread. + * + * Returns 0 if successful. + * Returns -1 otherwise. + */ +int fsmonitor_fs_listen__ctor(struct fsmonitor_daemon_state *state); + +/* + * Cleanup platform-specific data for the fsmonitor listener thread. + * This will be called from the main thread AFTER joining the listener. + */ +void fsmonitor_fs_listen__dtor(struct fsmonitor_daemon_state *state); + +/* + * The main body of the platform-specific event loop to watch for + * filesystem events. This will run in the fsmonitor_fs_listen thread. + * + * It should call `ipc_server_stop_async()` if the listener thread + * prematurely terminates (because of a filesystem error or if it + * detects that the .git directory has been deleted). (It should NOT + * do so if the listener thread receives a normal shutdown signal from + * the IPC layer.) + * + * It should set `state->error_code` to -1 if the daemon should exit + * with an error. + */ +void fsmonitor_fs_listen__loop(struct fsmonitor_daemon_state *state); + +/* + * Gently request that the fsmonitor listener thread shutdown. + * It does not wait for it to stop. The caller should do a JOIN + * to wait for it. + */ +void fsmonitor_fs_listen__stop_async(struct fsmonitor_daemon_state *state); + +#endif /* HAVE_FSMONITOR_DAEMON_BACKEND */ +#endif /* FSMONITOR_FS_LISTEN_H */ diff --git a/config.mak.uname b/config.mak.uname index cb443b4e02..fcd88b60b1 100644 --- a/config.mak.uname +++ b/config.mak.uname @@ -420,6 +420,7 @@ ifeq ($(uname_S),Windows) # so we don't need this: # # SNPRINTF_RETURNS_BOGUS = YesPlease + FSMONITOR_DAEMON_BACKEND = win32 NO_SVN_TESTS = YesPlease RUNTIME_PREFIX = YesPlease HAVE_WPGMPTR = YesWeDo @@ -598,6 +599,7 @@ ifneq (,$(findstring MINGW,$(uname_S))) NO_STRTOUMAX = YesPlease NO_MKDTEMP = YesPlease NO_SVN_TESTS = YesPlease + FSMONITOR_DAEMON_BACKEND = win32 RUNTIME_PREFIX = YesPlease HAVE_WPGMPTR = YesWeDo NO_ST_BLOCKS_IN_STRUCT_STAT = YesPlease diff --git a/contrib/buildsystems/CMakeLists.txt b/contrib/buildsystems/CMakeLists.txt index a87841340e..1ab94eb284 100644 --- a/contrib/buildsystems/CMakeLists.txt +++ b/contrib/buildsystems/CMakeLists.txt @@ -263,6 +263,11 @@ else() endif() endif() +if(CMAKE_SYSTEM_NAME STREQUAL "Windows") + add_compile_definitions(HAVE_FSMONITOR_DAEMON_BACKEND) + list(APPEND compat_SOURCES compat/fsmonitor/fsmonitor-fs-listen-win32.c) +endif() + set(EXE_EXTENSION ${CMAKE_EXECUTABLE_SUFFIX}) #header checks From b206a85c82c55d453c9044824629f2f4cb536207 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Thu, 17 Dec 2020 10:41:07 -0500 Subject: [PATCH 12/30] fsmonitor-fs-listen-macos: stub in backend for MacOS Stub in empty implementation of fsmonitor--daemon backend for MacOS. Signed-off-by: Jeff Hostetler --- compat/fsmonitor/fsmonitor-fs-listen-macos.c | 20 ++++++++++++++++++++ config.mak.uname | 2 ++ contrib/buildsystems/CMakeLists.txt | 3 +++ 3 files changed, 25 insertions(+) create mode 100644 compat/fsmonitor/fsmonitor-fs-listen-macos.c diff --git a/compat/fsmonitor/fsmonitor-fs-listen-macos.c b/compat/fsmonitor/fsmonitor-fs-listen-macos.c new file mode 100644 index 0000000000..b91058d1c4 --- /dev/null +++ b/compat/fsmonitor/fsmonitor-fs-listen-macos.c @@ -0,0 +1,20 @@ +#include "cache.h" +#include "fsmonitor.h" +#include "fsmonitor-fs-listen.h" + +int fsmonitor_fs_listen__ctor(struct fsmonitor_daemon_state *state) +{ + return -1; +} + +void fsmonitor_fs_listen__dtor(struct fsmonitor_daemon_state *state) +{ +} + +void fsmonitor_fs_listen__stop_async(struct fsmonitor_daemon_state *state) +{ +} + +void fsmonitor_fs_listen__loop(struct fsmonitor_daemon_state *state) +{ +} diff --git a/config.mak.uname b/config.mak.uname index fcd88b60b1..394355463e 100644 --- a/config.mak.uname +++ b/config.mak.uname @@ -147,6 +147,8 @@ ifeq ($(uname_S),Darwin) MSGFMT = /usr/local/opt/gettext/bin/msgfmt endif endif + FSMONITOR_DAEMON_BACKEND = macos + BASIC_LDFLAGS += -framework CoreServices endif ifeq ($(uname_S),SunOS) NEEDS_SOCKET = YesPlease diff --git a/contrib/buildsystems/CMakeLists.txt b/contrib/buildsystems/CMakeLists.txt index 1ab94eb284..aa80671045 100644 --- a/contrib/buildsystems/CMakeLists.txt +++ b/contrib/buildsystems/CMakeLists.txt @@ -266,6 +266,9 @@ endif() if(CMAKE_SYSTEM_NAME STREQUAL "Windows") add_compile_definitions(HAVE_FSMONITOR_DAEMON_BACKEND) list(APPEND compat_SOURCES compat/fsmonitor/fsmonitor-fs-listen-win32.c) +elseif(CMAKE_SYSTEM_NAME STREQUAL "Darwin") + add_compile_definitions(HAVE_FSMONITOR_DAEMON_BACKEND) + list(APPEND compat_SOURCES compat/fsmonitor/fsmonitor-fs-listen-macos.c) endif() set(EXE_EXTENSION ${CMAKE_EXECUTABLE_SUFFIX}) From 717a7811a19256a78c876a0e8804dc2fa22bf41c Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Thu, 17 Dec 2020 11:34:13 -0500 Subject: [PATCH 13/30] fsmonitor--daemon: implement daemon command options Implement `run` and `start` commands to try to begin listening for file system events. This version defines the thread structure with a single fsmonitor_fs_listen thread to watch for file system events and a simple IPC thread pool to wait for connections from Git clients over a well-known named pipe or Unix domain socket. This version does not actually do anything yet because the backends are still just stubs. Signed-off-by: Jeff Hostetler --- builtin/fsmonitor--daemon.c | 390 +++++++++++++++++++++++++++++++++++- fsmonitor--daemon.h | 34 ++++ 2 files changed, 423 insertions(+), 1 deletion(-) create mode 100644 fsmonitor--daemon.h diff --git a/builtin/fsmonitor--daemon.c b/builtin/fsmonitor--daemon.c index 16ff68b654..85f99dba86 100644 --- a/builtin/fsmonitor--daemon.c +++ b/builtin/fsmonitor--daemon.c @@ -3,16 +3,52 @@ #include "parse-options.h" #include "fsmonitor.h" #include "fsmonitor-ipc.h" +#include "compat/fsmonitor/fsmonitor-fs-listen.h" +#include "fsmonitor--daemon.h" #include "simple-ipc.h" #include "khash.h" static const char * const builtin_fsmonitor__daemon_usage[] = { + N_("git fsmonitor--daemon start []"), + N_("git fsmonitor--daemon run []"), N_("git fsmonitor--daemon stop"), N_("git fsmonitor--daemon status"), NULL }; #ifdef HAVE_FSMONITOR_DAEMON_BACKEND +/* + * Global state loaded from config. + */ +#define FSMONITOR__IPC_THREADS "fsmonitor.ipcthreads" +static int fsmonitor__ipc_threads = 8; + +#define FSMONITOR__START_TIMEOUT "fsmonitor.starttimeout" +static int fsmonitor__start_timeout_sec = 60; + +static int fsmonitor_config(const char *var, const char *value, void *cb) +{ + if (!strcmp(var, FSMONITOR__IPC_THREADS)) { + int i = git_config_int(var, value); + if (i < 1) + return error(_("value of '%s' out of range: %d"), + FSMONITOR__IPC_THREADS, i); + fsmonitor__ipc_threads = i; + return 0; + } + + if (!strcmp(var, FSMONITOR__START_TIMEOUT)) { + int i = git_config_int(var, value); + if (i < 0) + return error(_("value of '%s' out of range: %d"), + FSMONITOR__START_TIMEOUT, i); + fsmonitor__start_timeout_sec = i; + return 0; + } + + return git_default_config(var, value, cb); +} + /* * Acting as a CLIENT. * @@ -55,11 +91,354 @@ static int do_as_client__status(void) } } +static ipc_server_application_cb handle_client; + +static int handle_client(void *data, + const char *command, size_t command_len, + ipc_server_reply_cb *reply, + struct ipc_server_reply_data *reply_data) +{ + /* struct fsmonitor_daemon_state *state = data; */ + int result; + + /* + * The Simple IPC API now supports {char*, len} arguments, but + * FSMonitor always uses proper null-terminated strings, so + * we can ignore the command_len argument. (Trust, but verify.) + */ + if (command_len != strlen(command)) + BUG("FSMonitor assumes text messages"); + + trace2_region_enter("fsmonitor", "handle_client", the_repository); + trace2_data_string("fsmonitor", the_repository, "request", command); + + result = 0; /* TODO Do something here. */ + + trace2_region_leave("fsmonitor", "handle_client", the_repository); + + return result; +} + +static void *fsmonitor_fs_listen__thread_proc(void *_state) +{ + struct fsmonitor_daemon_state *state = _state; + + trace2_thread_start("fsm-listen"); + + trace_printf_key(&trace_fsmonitor, "Watching: worktree '%s'", + state->path_worktree_watch.buf); + if (state->nr_paths_watching > 1) + trace_printf_key(&trace_fsmonitor, "Watching: gitdir '%s'", + state->path_gitdir_watch.buf); + + fsmonitor_fs_listen__loop(state); + + trace2_thread_exit(); + return NULL; +} + +static int fsmonitor_run_daemon_1(struct fsmonitor_daemon_state *state) +{ + struct ipc_server_opts ipc_opts = { + .nr_threads = fsmonitor__ipc_threads, + + /* + * We know that there are no other active threads yet, + * so we can let the IPC layer temporarily chdir() if + * it needs to when creating the server side of the + * Unix domain socket. + */ + .uds_disallow_chdir = 0 + }; + + /* + * Start the IPC thread pool before the we've started the file + * system event listener thread so that we have the IPC handle + * before we need it. + */ + if (ipc_server_run_async(&state->ipc_server_data, + fsmonitor_ipc__get_path(), &ipc_opts, + handle_client, state)) + return error(_("could not start IPC thread pool")); + + /* + * Start the fsmonitor listener thread to collect filesystem + * events. + */ + if (pthread_create(&state->listener_thread, NULL, + fsmonitor_fs_listen__thread_proc, state) < 0) { + ipc_server_stop_async(state->ipc_server_data); + ipc_server_await(state->ipc_server_data); + + return error(_("could not start fsmonitor listener thread")); + } + + /* + * The daemon is now fully functional in background threads. + * Wait for the IPC thread pool to shutdown (whether by client + * request or from filesystem activity). + */ + ipc_server_await(state->ipc_server_data); + + /* + * The fsmonitor listener thread may have received a shutdown + * event from the IPC thread pool, but it doesn't hurt to tell + * it again. And wait for it to shutdown. + */ + fsmonitor_fs_listen__stop_async(state); + pthread_join(state->listener_thread, NULL); + + return state->error_code; +} + +static int fsmonitor_run_daemon(void) +{ + struct fsmonitor_daemon_state state; + int err; + + memset(&state, 0, sizeof(state)); + + pthread_mutex_init(&state.main_lock, NULL); + state.error_code = 0; + state.current_token_data = NULL; + + /* Prepare to (recursively) watch the directory. */ + strbuf_init(&state.path_worktree_watch, 0); + strbuf_addstr(&state.path_worktree_watch, absolute_path(get_git_work_tree())); + state.nr_paths_watching = 1; + + /* + * We create/delete cookie files inside the .git directory to + * help us keep sync with the file system. If ".git" is not a + * directory, then is not inside the cone of + * , so set up a second watch for it. + */ + strbuf_init(&state.path_gitdir_watch, 0); + strbuf_addbuf(&state.path_gitdir_watch, &state.path_worktree_watch); + strbuf_addstr(&state.path_gitdir_watch, "/.git"); + if (!is_directory(state.path_gitdir_watch.buf)) { + strbuf_reset(&state.path_gitdir_watch); + strbuf_addstr(&state.path_gitdir_watch, absolute_path(get_git_dir())); + state.nr_paths_watching = 2; + } + + /* + * Confirm that we can create platform-specific resources for the + * filesystem listener before we bother starting all the threads. + */ + if (fsmonitor_fs_listen__ctor(&state)) { + err = error(_("could not initialize listener thread")); + goto done; + } + + err = fsmonitor_run_daemon_1(&state); + +done: + pthread_mutex_destroy(&state.main_lock); + fsmonitor_fs_listen__dtor(&state); + + ipc_server_free(state.ipc_server_data); + + strbuf_release(&state.path_worktree_watch); + strbuf_release(&state.path_gitdir_watch); + + return err; +} + +static int try_to_run_foreground_daemon(void) +{ + /* + * Technically, we don't need to probe for an existing daemon + * process, since we could just call `fsmonitor_run_daemon()` + * and let it fail if the pipe/socket is busy. + * + * However, this method gives us a nicer error message for a + * common error case. + */ + if (fsmonitor_ipc__get_state() == IPC_STATE__LISTENING) + die("fsmonitor--daemon is already running."); + + return !!fsmonitor_run_daemon(); +} + +#ifndef GIT_WINDOWS_NATIVE +/* + * This is adapted from `daemonize()`. Use `fork()` to directly create + * and run the daemon in a child process. The fork-parent returns the + * child PID so that we can wait for the child to startup before exiting. + */ +static int spawn_background_fsmonitor_daemon(pid_t *pid) +{ + *pid = fork(); + + switch (*pid) { + case 0: + if (setsid() == -1) + error_errno(_("setsid failed")); + close(0); + close(1); + close(2); + sanitize_stdfds(); + + return !!fsmonitor_run_daemon(); + + case -1: + return error_errno(_("could not spawn fsmonitor--daemon in the background")); + + default: + return 0; + } +} +#else +/* + * Conceptually like `daemonize()` but different because Windows does not + * have `fork(2)`. Spawn a normal Windows child process but without the + * limitations of `start_command()` and `finish_command()`. + */ +static int spawn_background_fsmonitor_daemon(pid_t *pid) +{ + char git_exe[MAX_PATH]; + struct strvec args = STRVEC_INIT; + int in, out; + + GetModuleFileNameA(NULL, git_exe, MAX_PATH); + + in = open("/dev/null", O_RDONLY); + out = open("/dev/null", O_WRONLY); + + strvec_push(&args, git_exe); + strvec_push(&args, "fsmonitor--daemon"); + strvec_push(&args, "run"); + + *pid = mingw_spawnvpe(args.v[0], args.v, NULL, NULL, in, out, out); + close(in); + close(out); + + strvec_clear(&args); + + if (*pid < 0) + return error(_("could not spawn fsmonitor--daemon in the background")); + + return 0; +} +#endif + +/* + * This is adapted from `wait_or_whine()`. Watch the child process and + * let it get started and begin listening for requests on the socket + * before reporting our success. + */ +static int wait_for_background_startup(pid_t pid_child) +{ + int status; + pid_t pid_seen; + enum ipc_active_state s; + time_t time_limit, now; + + time(&time_limit); + time_limit += fsmonitor__start_timeout_sec; + + for (;;) { + pid_seen = waitpid(pid_child, &status, WNOHANG); + + if (pid_seen == -1) + return error_errno(_("waitpid failed")); + else if (pid_seen == 0) { + /* + * The child is still running (this should be + * the normal case). Try to connect to it on + * the socket and see if it is ready for + * business. + * + * If there is another daemon already running, + * our child will fail to start (possibly + * after a timeout on the lock), but we don't + * care (who responds) if the socket is live. + */ + s = fsmonitor_ipc__get_state(); + if (s == IPC_STATE__LISTENING) + return 0; + + time(&now); + if (now > time_limit) + return error(_("fsmonitor--daemon not online yet")); + } else if (pid_seen == pid_child) { + /* + * The new child daemon process shutdown while + * it was starting up, so it is not listening + * on the socket. + * + * Try to ping the socket in the odd chance + * that another daemon started (or was already + * running) while our child was starting. + * + * Again, we don't care who services the socket. + */ + s = fsmonitor_ipc__get_state(); + if (s == IPC_STATE__LISTENING) + return 0; + + /* + * We don't care about the WEXITSTATUS() nor + * any of the WIF*(status) values because + * `cmd_fsmonitor__daemon()` does the `!!result` + * trick on all function return values. + * + * So it is sufficient to just report the + * early shutdown as an error. + */ + return error(_("fsmonitor--daemon failed to start")); + } else + return error(_("waitpid is confused")); + } +} + +static int try_to_start_background_daemon(void) +{ + pid_t pid_child; + int ret; + + /* + * Before we try to create a background daemon process, see + * if a daemon process is already listening. This makes it + * easier for us to report an already-listening error to the + * console, since our spawn/daemon can only report the success + * of creating the background process (and not whether it + * immediately exited). + */ + if (fsmonitor_ipc__get_state() == IPC_STATE__LISTENING) + die("fsmonitor--daemon is already running."); + + /* + * Run the actual daemon in a background process. + */ + ret = spawn_background_fsmonitor_daemon(&pid_child); + if (pid_child <= 0) + return ret; + + /* + * Wait (with timeout) for the background child process get + * started and begin listening on the socket/pipe. This makes + * the "start" command more synchronous and more reliable in + * tests. + */ + ret = wait_for_background_startup(pid_child); + + return ret; +} + int cmd_fsmonitor__daemon(int argc, const char **argv, const char *prefix) { const char *subcmd; struct option options[] = { + OPT_INTEGER(0, "ipc-threads", + &fsmonitor__ipc_threads, + N_("use ipc worker threads")), + OPT_INTEGER(0, "start-timeout", + &fsmonitor__start_timeout_sec, + N_("Max seconds to wait for background daemon startup")), + OPT_END() }; @@ -69,7 +448,7 @@ int cmd_fsmonitor__daemon(int argc, const char **argv, const char *prefix) if (argc == 2 && !strcmp(argv[1], "-h")) usage_with_options(builtin_fsmonitor__daemon_usage, options); - git_config(git_default_config, NULL); + git_config(fsmonitor_config, NULL); subcmd = argv[1]; argv--; @@ -77,6 +456,15 @@ int cmd_fsmonitor__daemon(int argc, const char **argv, const char *prefix) argc = parse_options(argc, argv, prefix, options, builtin_fsmonitor__daemon_usage, 0); + if (fsmonitor__ipc_threads < 1) + die(_("invalid 'ipc-threads' value (%d)"), + fsmonitor__ipc_threads); + + if (!strcmp(subcmd, "start")) + return !!try_to_start_background_daemon(); + + if (!strcmp(subcmd, "run")) + return !!try_to_run_foreground_daemon(); if (!strcmp(subcmd, "stop")) return !!do_as_client__send_stop(); diff --git a/fsmonitor--daemon.h b/fsmonitor--daemon.h new file mode 100644 index 0000000000..3009c1a83d --- /dev/null +++ b/fsmonitor--daemon.h @@ -0,0 +1,34 @@ +#ifndef FSMONITOR_DAEMON_H +#define FSMONITOR_DAEMON_H + +#ifdef HAVE_FSMONITOR_DAEMON_BACKEND + +#include "cache.h" +#include "dir.h" +#include "run-command.h" +#include "simple-ipc.h" +#include "thread-utils.h" + +struct fsmonitor_batch; +struct fsmonitor_token_data; + +struct fsmonitor_daemon_backend_data; /* opaque platform-specific data */ + +struct fsmonitor_daemon_state { + pthread_t listener_thread; + pthread_mutex_t main_lock; + + struct strbuf path_worktree_watch; + struct strbuf path_gitdir_watch; + int nr_paths_watching; + + struct fsmonitor_token_data *current_token_data; + + int error_code; + struct fsmonitor_daemon_backend_data *backend_data; + + struct ipc_server_data *ipc_server_data; +}; + +#endif /* HAVE_FSMONITOR_DAEMON_BACKEND */ +#endif /* FSMONITOR_DAEMON_H */ From 31853201561360266b5af52d58d92e03542bf709 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Thu, 17 Dec 2020 12:37:15 -0500 Subject: [PATCH 14/30] fsmonitor--daemon: add pathname classification Teach fsmonitor--daemon to classify relative and absolute pathnames and decide how they should be handled. This will be used by the platform-specific backend to respond to each filesystem event. When we register for filesystem notifications on a directory, we get events for everything (recursively) in the directory. We want to report to clients changes to tracked and untracked paths within the working directory. We do not want to report changes within the .git directory, for example. This classification will be used in a later commit by the different backends to classify paths as events are received. Signed-off-by: Jeff Hostetler --- builtin/fsmonitor--daemon.c | 81 +++++++++++++++++++++++++++++++++++++ fsmonitor--daemon.h | 61 ++++++++++++++++++++++++++++ 2 files changed, 142 insertions(+) diff --git a/builtin/fsmonitor--daemon.c b/builtin/fsmonitor--daemon.c index 85f99dba86..d6e35ded9f 100644 --- a/builtin/fsmonitor--daemon.c +++ b/builtin/fsmonitor--daemon.c @@ -119,6 +119,87 @@ static int handle_client(void *data, return result; } +#define FSMONITOR_COOKIE_PREFIX ".fsmonitor-daemon-" + +enum fsmonitor_path_type fsmonitor_classify_path_workdir_relative( + const char *rel) +{ + if (fspathncmp(rel, ".git", 4)) + return IS_WORKDIR_PATH; + rel += 4; + + if (!*rel) + return IS_DOT_GIT; + if (*rel != '/') + return IS_WORKDIR_PATH; /* e.g. .gitignore */ + rel++; + + if (!fspathncmp(rel, FSMONITOR_COOKIE_PREFIX, + strlen(FSMONITOR_COOKIE_PREFIX))) + return IS_INSIDE_DOT_GIT_WITH_COOKIE_PREFIX; + + return IS_INSIDE_DOT_GIT; +} + +enum fsmonitor_path_type fsmonitor_classify_path_gitdir_relative( + const char *rel) +{ + if (!fspathncmp(rel, FSMONITOR_COOKIE_PREFIX, + strlen(FSMONITOR_COOKIE_PREFIX))) + return IS_INSIDE_GITDIR_WITH_COOKIE_PREFIX; + + return IS_INSIDE_GITDIR; +} + +static enum fsmonitor_path_type try_classify_workdir_abs_path( + struct fsmonitor_daemon_state *state, + const char *path) +{ + const char *rel; + + if (fspathncmp(path, state->path_worktree_watch.buf, + state->path_worktree_watch.len)) + return IS_OUTSIDE_CONE; + + rel = path + state->path_worktree_watch.len; + + if (!*rel) + return IS_WORKDIR_PATH; /* it is the root dir exactly */ + if (*rel != '/') + return IS_OUTSIDE_CONE; + rel++; + + return fsmonitor_classify_path_workdir_relative(rel); +} + +enum fsmonitor_path_type fsmonitor_classify_path_absolute( + struct fsmonitor_daemon_state *state, + const char *path) +{ + const char *rel; + enum fsmonitor_path_type t; + + t = try_classify_workdir_abs_path(state, path); + if (state->nr_paths_watching == 1) + return t; + if (t != IS_OUTSIDE_CONE) + return t; + + if (fspathncmp(path, state->path_gitdir_watch.buf, + state->path_gitdir_watch.len)) + return IS_OUTSIDE_CONE; + + rel = path + state->path_gitdir_watch.len; + + if (!*rel) + return IS_GITDIR; /* it is the exactly */ + if (*rel != '/') + return IS_OUTSIDE_CONE; + rel++; + + return fsmonitor_classify_path_gitdir_relative(rel); +} + static void *fsmonitor_fs_listen__thread_proc(void *_state) { struct fsmonitor_daemon_state *state = _state; diff --git a/fsmonitor--daemon.h b/fsmonitor--daemon.h index 3009c1a83d..7bbb3a27a1 100644 --- a/fsmonitor--daemon.h +++ b/fsmonitor--daemon.h @@ -30,5 +30,66 @@ struct fsmonitor_daemon_state { struct ipc_server_data *ipc_server_data; }; +/* + * Pathname classifications. + * + * The daemon classifies the pathnames that it receives from file + * system notification events into the following categories and uses + * that to decide whether clients are told about them. (And to watch + * for file system synchronization events.) + * + * The client should only care about paths within the working + * directory proper (inside the working directory and not ".git" nor + * inside of ".git/"). That is, the client has read the index and is + * asking for a list of any paths in the working directory that have + * been modified since the last token. The client does not care about + * file system changes within the .git directory (such as new loose + * objects or packfiles). So the client will only receive paths that + * are classified as IS_WORKDIR_PATH. + * + * The daemon uses the IS_DOT_GIT and IS_GITDIR internally to mean the + * exact ".git" directory or GITDIR. If the daemon receives a delete + * event for either of these directories, it will automatically + * shutdown, for example. + * + * Note that the daemon DOES NOT explicitly watch nor special case the + * ".git/index" file. The daemon does not read the index and does not + * have any internal index-relative state. The daemon only collects + * the set of modified paths within the working directory. + */ +enum fsmonitor_path_type { + IS_WORKDIR_PATH = 0, + + IS_DOT_GIT, + IS_INSIDE_DOT_GIT, + IS_INSIDE_DOT_GIT_WITH_COOKIE_PREFIX, + + IS_GITDIR, + IS_INSIDE_GITDIR, + IS_INSIDE_GITDIR_WITH_COOKIE_PREFIX, + + IS_OUTSIDE_CONE, +}; + +/* + * Classify a pathname relative to the root of the working directory. + */ +enum fsmonitor_path_type fsmonitor_classify_path_workdir_relative( + const char *relative_path); + +/* + * Classify a pathname relative to a that is external to the + * worktree directory. + */ +enum fsmonitor_path_type fsmonitor_classify_path_gitdir_relative( + const char *relative_path); + +/* + * Classify an absolute pathname received from a filesystem event. + */ +enum fsmonitor_path_type fsmonitor_classify_path_absolute( + struct fsmonitor_daemon_state *state, + const char *path); + #endif /* HAVE_FSMONITOR_DAEMON_BACKEND */ #endif /* FSMONITOR_DAEMON_H */ From 808a9f3ff1e6a529b897483805e466bd3018f2f7 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Thu, 17 Dec 2020 12:58:14 -0500 Subject: [PATCH 15/30] fsmonitor--daemon: define token-ids Teach fsmonitor--daemon to create token-ids and define the overall token naming scheme. Signed-off-by: Jeff Hostetler --- builtin/fsmonitor--daemon.c | 116 +++++++++++++++++++++++++++++++++++- 1 file changed, 115 insertions(+), 1 deletion(-) diff --git a/builtin/fsmonitor--daemon.c b/builtin/fsmonitor--daemon.c index d6e35ded9f..ecd456dc92 100644 --- a/builtin/fsmonitor--daemon.c +++ b/builtin/fsmonitor--daemon.c @@ -91,6 +91,120 @@ static int do_as_client__status(void) } } +/* + * Requests to and from a FSMonitor Protocol V2 provider use an opaque + * "token" as a virtual timestamp. Clients can request a summary of all + * created/deleted/modified files relative to a token. In the response, + * clients receive a new token for the next (relative) request. + * + * + * Token Format + * ============ + * + * The contents of the token are private and provider-specific. + * + * For the built-in fsmonitor--daemon, we define a token as follows: + * + * "builtin" ":" ":" + * + * The "builtin" prefix is used as a namespace to avoid conflicts + * with other providers (such as Watchman). + * + * The is an arbitrary OPAQUE string, such as a GUID, + * UUID, or {timestamp,pid}. It is used to group all filesystem + * events that happened while the daemon was monitoring (and in-sync + * with the filesystem). + * + * Unlike FSMonitor Protocol V1, it is not defined as a timestamp + * and does not define less-than/greater-than relationships. + * (There are too many race conditions to rely on file system + * event timestamps.) + * + * The is a simple integer incremented whenever the + * daemon needs to make its state public. For example, if 1000 file + * system events come in, but no clients have requested the data, + * the daemon can continue to accumulate file changes in the same + * bin and does not need to advance the sequence number. However, + * as soon as a client does arrive, the daemon needs to start a new + * bin and increment the sequence number. + * + * The sequence number serves as the boundary between 2 sets + * of bins -- the older ones that the client has already seen + * and the newer ones that it hasn't. + * + * When a new is created, the is reset to + * zero. + * + * + * About Token Ids + * =============== + * + * A new token_id is created: + * + * [1] each time the daemon is started. + * + * [2] any time that the daemon must re-sync with the filesystem + * (such as when the kernel drops or we miss events on a very + * active volume). + * + * [3] in response to a client "flush" command (for dropped event + * testing). + * + * When a new token_id is created, the daemon is free to discard all + * cached filesystem events associated with any previous token_ids. + * Events associated with a non-current token_id will never be sent + * to a client. A token_id change implicitly means that the daemon + * has gap in its event history. + * + * Therefore, clients that present a token with a stale (non-current) + * token_id will always be given a trivial response. + */ +struct fsmonitor_token_data { + struct strbuf token_id; + struct fsmonitor_batch *batch_head; + struct fsmonitor_batch *batch_tail; + uint64_t client_ref_count; +}; + +static struct fsmonitor_token_data *fsmonitor_new_token_data(void) +{ + static int test_env_value = -1; + static uint64_t flush_count = 0; + struct fsmonitor_token_data *token; + + CALLOC_ARRAY(token, 1); + + strbuf_init(&token->token_id, 0); + token->batch_head = NULL; + token->batch_tail = NULL; + token->client_ref_count = 0; + + if (test_env_value < 0) + test_env_value = git_env_bool("GIT_TEST_FSMONITOR_TOKEN", 0); + + if (!test_env_value) { + struct timeval tv; + struct tm tm; + time_t secs; + + gettimeofday(&tv, NULL); + secs = tv.tv_sec; + gmtime_r(&secs, &tm); + + strbuf_addf(&token->token_id, + "%"PRIu64".%d.%4d%02d%02dT%02d%02d%02d.%06ldZ", + flush_count++, + getpid(), + tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday, + tm.tm_hour, tm.tm_min, tm.tm_sec, + (long)tv.tv_usec); + } else { + strbuf_addf(&token->token_id, "test_%08x", test_env_value++); + } + + return token; +} + static ipc_server_application_cb handle_client; static int handle_client(void *data, @@ -281,7 +395,7 @@ static int fsmonitor_run_daemon(void) pthread_mutex_init(&state.main_lock, NULL); state.error_code = 0; - state.current_token_data = NULL; + state.current_token_data = fsmonitor_new_token_data(); /* Prepare to (recursively) watch the directory. */ strbuf_init(&state.path_worktree_watch, 0); From e02ccc710a0cfee31bbe38f1cbb7bb82f08a92cd Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Thu, 17 Dec 2020 13:17:33 -0500 Subject: [PATCH 16/30] fsmonitor--daemon: create token-based changed path cache Teach fsmonitor--daemon to build a list of changed paths and associate them with a token-id. This will be used by the platform-specific backends to accumulate changed paths in response to filesystem events. The platform-specific file system listener thread receives file system events containing one or more changed pathnames (with whatever bucketing or grouping that is convenient for the file system). These paths are accumulated (without locking) by the file system layer into a `fsmonitor_batch`. When the file system layer has drained the kernel event queue, it will "publish" them to our token queue and make them visible to concurrent client worker threads. The token layer is free to combine and/or de-dup paths within these batches for efficient presentation to clients. Signed-off-by: Jeff Hostetler --- builtin/fsmonitor--daemon.c | 234 +++++++++++++++++++++++++++++++++++- fsmonitor--daemon.h | 40 ++++++ 2 files changed, 272 insertions(+), 2 deletions(-) diff --git a/builtin/fsmonitor--daemon.c b/builtin/fsmonitor--daemon.c index ecd456dc92..663fead0d6 100644 --- a/builtin/fsmonitor--daemon.c +++ b/builtin/fsmonitor--daemon.c @@ -166,17 +166,27 @@ struct fsmonitor_token_data { uint64_t client_ref_count; }; +struct fsmonitor_batch { + struct fsmonitor_batch *next; + uint64_t batch_seq_nr; + const char **interned_paths; + size_t nr, alloc; + time_t pinned_time; +}; + static struct fsmonitor_token_data *fsmonitor_new_token_data(void) { static int test_env_value = -1; static uint64_t flush_count = 0; struct fsmonitor_token_data *token; + struct fsmonitor_batch *batch; CALLOC_ARRAY(token, 1); + batch = fsmonitor_batch__new(); strbuf_init(&token->token_id, 0); - token->batch_head = NULL; - token->batch_tail = NULL; + token->batch_head = batch; + token->batch_tail = batch; token->client_ref_count = 0; if (test_env_value < 0) @@ -202,9 +212,147 @@ static struct fsmonitor_token_data *fsmonitor_new_token_data(void) strbuf_addf(&token->token_id, "test_%08x", test_env_value++); } + /* + * We created a new and are starting a new series + * of tokens with a zero . + * + * Since clients cannot guess our new (non test) + * they will always receive a trivial response (because of the + * mismatch on the ). The trivial response will + * tell them our new so that subsequent requests + * will be relative to our new series. (And when sending that + * response, we pin the current head of the batch list.) + * + * Even if the client correctly guesses the , their + * request of "builtin::0" asks for all changes MORE + * RECENT than batch/bin 0. + * + * This implies that it is a waste to accumulate paths in the + * initial batch/bin (because they will never be transmitted). + * + * So the daemon could be running for days and watching the + * file system, but doesn't need to actually accumulate any + * paths UNTIL we need to set a reference point for a later + * relative request. + * + * However, it is very useful for testing to always have a + * reference point set. Pin batch 0 to force early file system + * events to accumulate. + */ + if (test_env_value) + batch->pinned_time = time(NULL); + return token; } +struct fsmonitor_batch *fsmonitor_batch__new(void) +{ + struct fsmonitor_batch *batch; + + CALLOC_ARRAY(batch, 1); + + return batch; +} + +struct fsmonitor_batch *fsmonitor_batch__pop(struct fsmonitor_batch *batch) +{ + struct fsmonitor_batch *next; + + if (!batch) + return NULL; + + next = batch->next; + + /* + * The actual strings within the array are interned, so we don't + * own them. + */ + free(batch->interned_paths); + + return next; +} + +void fsmonitor_batch__add_path(struct fsmonitor_batch *batch, + const char *path) +{ + const char *interned_path = strintern(path); + + trace_printf_key(&trace_fsmonitor, "event: %s", interned_path); + + ALLOC_GROW(batch->interned_paths, batch->nr + 1, batch->alloc); + batch->interned_paths[batch->nr++] = interned_path; +} + +static void fsmonitor_batch__combine(struct fsmonitor_batch *batch_dest, + const struct fsmonitor_batch *batch_src) +{ + size_t k; + + ALLOC_GROW(batch_dest->interned_paths, + batch_dest->nr + batch_src->nr + 1, + batch_dest->alloc); + + for (k = 0; k < batch_src->nr; k++) + batch_dest->interned_paths[batch_dest->nr++] = + batch_src->interned_paths[k]; +} + +static void fsmonitor_free_token_data(struct fsmonitor_token_data *token) +{ + struct fsmonitor_batch *p; + + if (!token) + return; + + assert(token->client_ref_count == 0); + + strbuf_release(&token->token_id); + + for (p = token->batch_head; p; p = fsmonitor_batch__pop(p)) + ; + + free(token); +} + +/* + * Flush all of our cached data about the filesystem. Call this if we + * lose sync with the filesystem and miss some notification events. + * + * [1] If we are missing events, then we no longer have a complete + * history of the directory (relative to our current start token). + * We should create a new token and start fresh (as if we just + * booted up). + * + * If there are no concurrent threads readering the current token data + * series, we can free it now. Otherwise, let the last reader free + * it. + * + * Either way, the old token data series is no longer associated with + * our state data. + */ +static void with_lock__do_force_resync(struct fsmonitor_daemon_state *state) +{ + /* assert current thread holding state->main_lock */ + + struct fsmonitor_token_data *free_me = NULL; + struct fsmonitor_token_data *new_one = NULL; + + new_one = fsmonitor_new_token_data(); + + if (state->current_token_data->client_ref_count == 0) + free_me = state->current_token_data; + state->current_token_data = new_one; + + fsmonitor_free_token_data(free_me); +} + +void fsmonitor_force_resync(struct fsmonitor_daemon_state *state) +{ + pthread_mutex_lock(&state->main_lock); + with_lock__do_force_resync(state); + pthread_mutex_unlock(&state->main_lock); +} + static ipc_server_application_cb handle_client; static int handle_client(void *data, @@ -314,6 +462,81 @@ enum fsmonitor_path_type fsmonitor_classify_path_absolute( return fsmonitor_classify_path_gitdir_relative(rel); } +/* + * We try to combine small batches at the front of the batch-list to avoid + * having a long list. This hopefully makes it a little easier when we want + * to truncate and maintain the list. However, we don't want the paths array + * to just keep growing and growing with realloc, so we insert an arbitrary + * limit. + */ +#define MY_COMBINE_LIMIT (1024) + +void fsmonitor_publish(struct fsmonitor_daemon_state *state, + struct fsmonitor_batch *batch, + const struct string_list *cookie_names) +{ + if (!batch && !cookie_names->nr) + return; + + pthread_mutex_lock(&state->main_lock); + + if (batch) { + struct fsmonitor_batch *head; + + head = state->current_token_data->batch_head; + if (!head) { + BUG("token does not have batch"); + } else if (head->pinned_time) { + /* + * We cannot alter the current batch list + * because: + * + * [a] it is being transmitted to at least one + * client and the handle_client() thread has a + * ref-count, but not a lock on the batch list + * starting with this item. + * + * [b] it has been transmitted in the past to + * at least one client such that future + * requests are relative to this head batch. + * + * So, we can only prepend a new batch onto + * the front of the list. + */ + batch->batch_seq_nr = head->batch_seq_nr + 1; + batch->next = head; + state->current_token_data->batch_head = batch; + } else if (!head->batch_seq_nr) { + /* + * Batch 0 is unpinned. See the note in + * `fsmonitor_new_token_data()` about why we + * don't need to accumulate these paths. + */ + fsmonitor_batch__pop(batch); + } else if (head->nr + batch->nr > MY_COMBINE_LIMIT) { + /* + * The head batch in the list has never been + * transmitted to a client, but folding the + * contents of the new batch onto it would + * exceed our arbitrary limit, so just prepend + * the new batch onto the list. + */ + batch->batch_seq_nr = head->batch_seq_nr + 1; + batch->next = head; + state->current_token_data->batch_head = batch; + } else { + /* + * We are free to append the paths in the given + * batch onto the end of the current head batch. + */ + fsmonitor_batch__combine(head, batch); + fsmonitor_batch__pop(batch); + } + } + + pthread_mutex_unlock(&state->main_lock); +} + static void *fsmonitor_fs_listen__thread_proc(void *_state) { struct fsmonitor_daemon_state *state = _state; @@ -328,6 +551,13 @@ static void *fsmonitor_fs_listen__thread_proc(void *_state) fsmonitor_fs_listen__loop(state); + pthread_mutex_lock(&state->main_lock); + if (state->current_token_data && + state->current_token_data->client_ref_count == 0) + fsmonitor_free_token_data(state->current_token_data); + state->current_token_data = NULL; + pthread_mutex_unlock(&state->main_lock); + trace2_thread_exit(); return NULL; } diff --git a/fsmonitor--daemon.h b/fsmonitor--daemon.h index 7bbb3a27a1..89a9ef20b2 100644 --- a/fsmonitor--daemon.h +++ b/fsmonitor--daemon.h @@ -12,6 +12,27 @@ struct fsmonitor_batch; struct fsmonitor_token_data; +/* + * Create a new batch of path(s). The returned batch is considered + * private and not linked into the fsmonitor daemon state. The caller + * should fill this batch with one or more paths and then publish it. + */ +struct fsmonitor_batch *fsmonitor_batch__new(void); + +/* + * Free this batch and return the value of the batch->next field. + */ +struct fsmonitor_batch *fsmonitor_batch__pop(struct fsmonitor_batch *batch); + +/* + * Add this path to this batch of modified files. + * + * The batch should be private and NOT (yet) linked into the fsmonitor + * daemon state and therefore not yet visible to worker threads and so + * no locking is required. + */ +void fsmonitor_batch__add_path(struct fsmonitor_batch *batch, const char *path); + struct fsmonitor_daemon_backend_data; /* opaque platform-specific data */ struct fsmonitor_daemon_state { @@ -91,5 +112,24 @@ enum fsmonitor_path_type fsmonitor_classify_path_absolute( struct fsmonitor_daemon_state *state, const char *path); +/* + * Prepend the this batch of path(s) onto the list of batches associated + * with the current token. This makes the batch visible to worker threads. + * + * The caller no longer owns the batch and must not free it. + * + * Wake up the client threads waiting on these cookies. + */ +void fsmonitor_publish(struct fsmonitor_daemon_state *state, + struct fsmonitor_batch *batch, + const struct string_list *cookie_names); + +/* + * If the platform-specific layer loses sync with the filesystem, + * it should call this to invalidate cached data and abort waiting + * threads. + */ +void fsmonitor_force_resync(struct fsmonitor_daemon_state *state); + #endif /* HAVE_FSMONITOR_DAEMON_BACKEND */ #endif /* FSMONITOR_DAEMON_H */ From 2d30edc027ac9e7eda60ad668acd9f06d9e39508 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Thu, 17 Dec 2020 13:34:30 -0500 Subject: [PATCH 17/30] fsmonitor-fs-listen-win32: implement FSMonitor backend on Windows Teach the win32 backend to register a watch on the working tree root directory (recursively). Also watch the if it is not inside the working tree. And to collect path change notifications into batches and publish. Signed-off-by: Jeff Hostetler --- compat/fsmonitor/fsmonitor-fs-listen-win32.c | 532 +++++++++++++++++++ 1 file changed, 532 insertions(+) diff --git a/compat/fsmonitor/fsmonitor-fs-listen-win32.c b/compat/fsmonitor/fsmonitor-fs-listen-win32.c index 880446b49e..ba087b292d 100644 --- a/compat/fsmonitor/fsmonitor-fs-listen-win32.c +++ b/compat/fsmonitor/fsmonitor-fs-listen-win32.c @@ -2,20 +2,552 @@ #include "config.h" #include "fsmonitor.h" #include "fsmonitor-fs-listen.h" +#include "fsmonitor--daemon.h" + +/* + * The documentation of ReadDirectoryChangesW() states that the maximum + * buffer size is 64K when the monitored directory is remote. + * + * Larger buffers may be used when the monitored directory is local and + * will help us receive events faster from the kernel and avoid dropped + * events. + * + * So we try to use a very large buffer and silently fallback to 64K if + * we get an error. + */ +#define MAX_RDCW_BUF_FALLBACK (65536) +#define MAX_RDCW_BUF (65536 * 8) + +struct one_watch +{ + char buffer[MAX_RDCW_BUF]; + DWORD buf_len; + DWORD count; + + struct strbuf path; + HANDLE hDir; + HANDLE hEvent; + OVERLAPPED overlapped; + + /* + * Is there an active ReadDirectoryChangesW() call pending. If so, we + * need to later call GetOverlappedResult() and possibly CancelIoEx(). + */ + BOOL is_active; +}; + +struct fsmonitor_daemon_backend_data +{ + struct one_watch *watch_worktree; + struct one_watch *watch_gitdir; + + HANDLE hEventShutdown; + + HANDLE hListener[3]; /* we don't own these handles */ +#define LISTENER_SHUTDOWN 0 +#define LISTENER_HAVE_DATA_WORKTREE 1 +#define LISTENER_HAVE_DATA_GITDIR 2 + int nr_listener_handles; +}; + +/* + * Convert the WCHAR path from the notification into UTF8 and + * then normalize it. + */ +static int normalize_path_in_utf8(FILE_NOTIFY_INFORMATION *info, + struct strbuf *normalized_path) +{ + int reserve; + int len = 0; + + strbuf_reset(normalized_path); + if (!info->FileNameLength) + goto normalize; + + /* + * Pre-reserve enough space in the UTF8 buffer for + * each Unicode WCHAR character to be mapped into a + * sequence of 2 UTF8 characters. That should let us + * avoid ERROR_INSUFFICIENT_BUFFER 99.9+% of the time. + */ + reserve = info->FileNameLength + 1; + strbuf_grow(normalized_path, reserve); + + for (;;) { + len = WideCharToMultiByte(CP_UTF8, 0, info->FileName, + info->FileNameLength / sizeof(WCHAR), + normalized_path->buf, + strbuf_avail(normalized_path) - 1, + NULL, NULL); + if (len > 0) + goto normalize; + if (GetLastError() != ERROR_INSUFFICIENT_BUFFER) { + error("[GLE %ld] could not convert path to UTF-8: '%.*ls'", + GetLastError(), + (int)(info->FileNameLength / sizeof(WCHAR)), + info->FileName); + return -1; + } + + strbuf_grow(normalized_path, + strbuf_avail(normalized_path) + reserve); + } + +normalize: + strbuf_setlen(normalized_path, len); + return strbuf_normalize_path(normalized_path); +} void fsmonitor_fs_listen__stop_async(struct fsmonitor_daemon_state *state) { + SetEvent(state->backend_data->hListener[LISTENER_SHUTDOWN]); +} + +static struct one_watch *create_watch(struct fsmonitor_daemon_state *state, + const char *path) +{ + struct one_watch *watch = NULL; + DWORD desired_access = FILE_LIST_DIRECTORY; + DWORD share_mode = + FILE_SHARE_WRITE | FILE_SHARE_READ | FILE_SHARE_DELETE; + HANDLE hDir; + + hDir = CreateFileA(path, + desired_access, share_mode, NULL, OPEN_EXISTING, + FILE_FLAG_BACKUP_SEMANTICS | FILE_FLAG_OVERLAPPED, + NULL); + if (hDir == INVALID_HANDLE_VALUE) { + error(_("[GLE %ld] could not watch '%s'"), + GetLastError(), path); + return NULL; + } + + CALLOC_ARRAY(watch, 1); + + watch->buf_len = sizeof(watch->buffer); /* assume full MAX_RDCW_BUF */ + + strbuf_init(&watch->path, 0); + strbuf_addstr(&watch->path, path); + + watch->hDir = hDir; + watch->hEvent = CreateEvent(NULL, TRUE, FALSE, NULL); + + return watch; +} + +static void destroy_watch(struct one_watch *watch) +{ + if (!watch) + return; + + strbuf_release(&watch->path); + if (watch->hDir != INVALID_HANDLE_VALUE) + CloseHandle(watch->hDir); + if (watch->hEvent != INVALID_HANDLE_VALUE) + CloseHandle(watch->hEvent); + + free(watch); +} + +static int start_rdcw_watch(struct fsmonitor_daemon_backend_data *data, + struct one_watch *watch) +{ + DWORD dwNotifyFilter = + FILE_NOTIFY_CHANGE_FILE_NAME | + FILE_NOTIFY_CHANGE_DIR_NAME | + FILE_NOTIFY_CHANGE_ATTRIBUTES | + FILE_NOTIFY_CHANGE_SIZE | + FILE_NOTIFY_CHANGE_LAST_WRITE | + FILE_NOTIFY_CHANGE_CREATION; + + ResetEvent(watch->hEvent); + + memset(&watch->overlapped, 0, sizeof(watch->overlapped)); + watch->overlapped.hEvent = watch->hEvent; + +start_watch: + /* + * Queue an async call using Overlapped IO. This returns immediately. + * Our event handle will be signalled when the real result is available. + * + * The return value here just means that we successfully queued it. + * We won't know if the Read...() actually produces data until later. + */ + watch->is_active = ReadDirectoryChangesW( + watch->hDir, watch->buffer, watch->buf_len, TRUE, + dwNotifyFilter, &watch->count, &watch->overlapped, NULL); + + /* + * The kernel throws an invalid parameter error when our buffer + * is too big and we are pointed at a remote directory (and possibly + * for other reasons). Quietly set it down and try again. + * + * See note about MAX_RDCW_BUF at the top. + */ + if (!watch->is_active && + GetLastError() == ERROR_INVALID_PARAMETER && + watch->buf_len > MAX_RDCW_BUF_FALLBACK) { + watch->buf_len = MAX_RDCW_BUF_FALLBACK; + goto start_watch; + } + + if (watch->is_active) + return 0; + + error("ReadDirectoryChangedW failed on '%s' [GLE %ld]", + watch->path.buf, GetLastError()); + return -1; +} + +static int recv_rdcw_watch(struct one_watch *watch) +{ + watch->is_active = FALSE; + + /* + * The overlapped result is ready. If the Read...() was successful + * we finally receive the actual result into our buffer. + */ + if (GetOverlappedResult(watch->hDir, &watch->overlapped, &watch->count, + TRUE)) + return 0; + + /* + * NEEDSWORK: If an external is deleted, the above + * returns an error. I'm not sure that there's anything that + * we can do here other than failing -- the /.git + * link file would be broken anyway. We might try to check + * for that and return a better error message, but I'm not + * sure it is worth it. + */ + + error("GetOverlappedResult failed on '%s' [GLE %ld]", + watch->path.buf, GetLastError()); + return -1; +} + +static void cancel_rdcw_watch(struct one_watch *watch) +{ + DWORD count; + + if (!watch || !watch->is_active) + return; + + /* + * The calls to ReadDirectoryChangesW() and GetOverlappedResult() + * form a "pair" (my term) where we queue an IO and promise to + * hang around and wait for the kernel to give us the result. + * + * If for some reason after we queue the IO, we have to quit + * or otherwise not stick around for the second half, we must + * tell the kernel to abort the IO. This prevents the kernel + * from writing to our buffer and/or signalling our event + * after we free them. + * + * (Ask me how much fun it was to track that one down). + */ + CancelIoEx(watch->hDir, &watch->overlapped); + GetOverlappedResult(watch->hDir, &watch->overlapped, &count, TRUE); + watch->is_active = FALSE; +} + +/* + * Process filesystem events that happen anywhere (recursively) under the + * root directory. For a normal working directory, this includes + * both version controlled files and the contents of the .git/ directory. + * + * If /.git is a file, then we only see events for the file + * itself. + */ +static int process_worktree_events(struct fsmonitor_daemon_state *state) +{ + struct fsmonitor_daemon_backend_data *data = state->backend_data; + struct one_watch *watch = data->watch_worktree; + struct strbuf path = STRBUF_INIT; + struct string_list cookie_list = STRING_LIST_INIT_DUP; + struct fsmonitor_batch *batch = NULL; + const char *p = watch->buffer; + + /* + * If the kernel gets more events than will fit in the kernel + * buffer associated with our RDCW handle, it drops them and + * returns a count of zero. + * + * Yes, the call returns WITHOUT error and with length zero. + * + * (The "overflow" case is not ambiguous with the "no data" case + * because we did an INFINITE wait.) + * + * This means we have a gap in coverage. Tell the daemon layer + * to resync. + */ + if (!watch->count) { + trace2_data_string("fsmonitor", NULL, "fsm-listen/kernel", + "overflow"); + fsmonitor_force_resync(state); + return LISTENER_HAVE_DATA_WORKTREE; + } + + /* + * On Windows, `info` contains an "array" of paths that are + * relative to the root of whichever directory handle received + * the event. + */ + for (;;) { + FILE_NOTIFY_INFORMATION *info = (void *)p; + const char *slash; + enum fsmonitor_path_type t; + + strbuf_reset(&path); + if (normalize_path_in_utf8(info, &path) == -1) + goto skip_this_path; + + t = fsmonitor_classify_path_workdir_relative(path.buf); + + switch (t) { + case IS_INSIDE_DOT_GIT_WITH_COOKIE_PREFIX: + /* special case cookie files within .git */ + + /* Use just the filename of the cookie file. */ + slash = find_last_dir_sep(path.buf); + string_list_append(&cookie_list, + slash ? slash + 1 : path.buf); + break; + + case IS_INSIDE_DOT_GIT: + /* ignore everything inside of "/.git/" */ + break; + + case IS_DOT_GIT: + /* "/.git" was deleted (or renamed away) */ + if ((info->Action == FILE_ACTION_REMOVED) || + (info->Action == FILE_ACTION_RENAMED_OLD_NAME)) { + trace2_data_string("fsmonitor", NULL, + "fsm-listen/dotgit", + "removed"); + goto force_shutdown; + } + break; + + case IS_WORKDIR_PATH: + /* queue normal pathname */ + if (!batch) + batch = fsmonitor_batch__new(); + fsmonitor_batch__add_path(batch, path.buf); + break; + + case IS_GITDIR: + case IS_INSIDE_GITDIR: + case IS_INSIDE_GITDIR_WITH_COOKIE_PREFIX: + default: + BUG("unexpected path classification '%d' for '%s'", + t, path.buf); + } + +skip_this_path: + if (!info->NextEntryOffset) + break; + p += info->NextEntryOffset; + } + + fsmonitor_publish(state, batch, &cookie_list); + batch = NULL; + string_list_clear(&cookie_list, 0); + strbuf_release(&path); + return LISTENER_HAVE_DATA_WORKTREE; + +force_shutdown: + fsmonitor_batch__pop(batch); + string_list_clear(&cookie_list, 0); + strbuf_release(&path); + return LISTENER_SHUTDOWN; +} + +/* + * Process filesystem events that happened anywhere (recursively) under the + * external (such as non-primary worktrees or submodules). + * We only care about cookie files that our client threads created here. + * + * Note that we DO NOT get filesystem events on the external + * itself (it is not inside something that we are watching). In particular, + * we do not get an event if the external is deleted. + */ +static int process_gitdir_events(struct fsmonitor_daemon_state *state) +{ + struct fsmonitor_daemon_backend_data *data = state->backend_data; + struct one_watch *watch = data->watch_gitdir; + struct strbuf path = STRBUF_INIT; + struct string_list cookie_list = STRING_LIST_INIT_DUP; + const char *p = watch->buffer; + + if (!watch->count) { + trace2_data_string("fsmonitor", NULL, "fsm-listen/kernel", + "overflow"); + fsmonitor_force_resync(state); + return LISTENER_HAVE_DATA_GITDIR; + } + + for (;;) { + FILE_NOTIFY_INFORMATION *info = (void *)p; + const char *slash; + enum fsmonitor_path_type t; + + strbuf_reset(&path); + if (normalize_path_in_utf8(info, &path) == -1) + goto skip_this_path; + + t = fsmonitor_classify_path_gitdir_relative(path.buf); + + trace_printf_key(&trace_fsmonitor, "BBB: %s", path.buf); + + switch (t) { + case IS_INSIDE_GITDIR_WITH_COOKIE_PREFIX: + /* special case cookie files within gitdir */ + + /* Use just the filename of the cookie file. */ + slash = find_last_dir_sep(path.buf); + string_list_append(&cookie_list, + slash ? slash + 1 : path.buf); + break; + + case IS_INSIDE_GITDIR: + goto skip_this_path; + + default: + BUG("unexpected path classification '%d' for '%s'", + t, path.buf); + } + +skip_this_path: + if (!info->NextEntryOffset) + break; + p += info->NextEntryOffset; + } + + fsmonitor_publish(state, NULL, &cookie_list); + string_list_clear(&cookie_list, 0); + strbuf_release(&path); + return LISTENER_HAVE_DATA_GITDIR; } void fsmonitor_fs_listen__loop(struct fsmonitor_daemon_state *state) { + struct fsmonitor_daemon_backend_data *data = state->backend_data; + DWORD dwWait; + + state->error_code = 0; + + if (start_rdcw_watch(data, data->watch_worktree) == -1) + goto force_error_stop; + + if (data->watch_gitdir && + start_rdcw_watch(data, data->watch_gitdir) == -1) + goto force_error_stop; + + for (;;) { + dwWait = WaitForMultipleObjects(data->nr_listener_handles, + data->hListener, + FALSE, INFINITE); + + if (dwWait == WAIT_OBJECT_0 + LISTENER_HAVE_DATA_WORKTREE) { + if (recv_rdcw_watch(data->watch_worktree) == -1) + goto force_error_stop; + if (process_worktree_events(state) == LISTENER_SHUTDOWN) + goto force_shutdown; + if (start_rdcw_watch(data, data->watch_worktree) == -1) + goto force_error_stop; + continue; + } + + if (dwWait == WAIT_OBJECT_0 + LISTENER_HAVE_DATA_GITDIR) { + if (recv_rdcw_watch(data->watch_gitdir) == -1) + goto force_error_stop; + if (process_gitdir_events(state) == LISTENER_SHUTDOWN) + goto force_shutdown; + if (start_rdcw_watch(data, data->watch_gitdir) == -1) + goto force_error_stop; + continue; + } + + if (dwWait == WAIT_OBJECT_0 + LISTENER_SHUTDOWN) + goto clean_shutdown; + + error(_("could not read directory changes [GLE %ld]"), + GetLastError()); + goto force_error_stop; + } + +force_error_stop: + state->error_code = -1; + +force_shutdown: + /* + * Tell the IPC thead pool to stop (which completes the await + * in the main thread (which will also signal this thread (if + * we are still alive))). + */ + ipc_server_stop_async(state->ipc_server_data); + +clean_shutdown: + cancel_rdcw_watch(data->watch_worktree); + cancel_rdcw_watch(data->watch_gitdir); } int fsmonitor_fs_listen__ctor(struct fsmonitor_daemon_state *state) { + struct fsmonitor_daemon_backend_data *data; + + CALLOC_ARRAY(data, 1); + + data->hEventShutdown = CreateEvent(NULL, TRUE, FALSE, NULL); + + data->watch_worktree = create_watch(state, + state->path_worktree_watch.buf); + if (!data->watch_worktree) + goto failed; + + if (state->nr_paths_watching > 1) { + data->watch_gitdir = create_watch(state, + state->path_gitdir_watch.buf); + if (!data->watch_gitdir) + goto failed; + } + + data->hListener[LISTENER_SHUTDOWN] = data->hEventShutdown; + data->nr_listener_handles++; + + data->hListener[LISTENER_HAVE_DATA_WORKTREE] = + data->watch_worktree->hEvent; + data->nr_listener_handles++; + + if (data->watch_gitdir) { + data->hListener[LISTENER_HAVE_DATA_GITDIR] = + data->watch_gitdir->hEvent; + data->nr_listener_handles++; + } + + state->backend_data = data; + return 0; + +failed: + CloseHandle(data->hEventShutdown); + destroy_watch(data->watch_worktree); + destroy_watch(data->watch_gitdir); + return -1; } void fsmonitor_fs_listen__dtor(struct fsmonitor_daemon_state *state) { + struct fsmonitor_daemon_backend_data *data; + + if (!state || !state->backend_data) + return; + + data = state->backend_data; + + CloseHandle(data->hEventShutdown); + destroy_watch(data->watch_worktree); + destroy_watch(data->watch_gitdir); + + FREE_AND_NULL(state->backend_data); } From e5c3c215bd1dfe666be4f7bad2cff780f5f16c06 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Fri, 18 Dec 2020 11:09:58 -0500 Subject: [PATCH 18/30] fsmonitor-fs-listen-macos: add macos header files for FSEvent Include MacOS system declarations to allow us to use FSEvent and CoreFoundation APIs. We need GCC and clang versions because of compiler and header file conflicts. While it is quite possible to #include Apple's CoreServices.h when compiling C source code with clang, trying to build it with GCC currently fails with this error: In file included from /Library/Developer/CommandLineTools/SDKs/MacOSX10.14.sdk/System/Library/Frameworks/Security.framework/Headers/AuthSession.h:32, from /Library/Developer/CommandLineTools/SDKs/MacOSX10.14.sdk/System/Library/Frameworks/Security.framework/Headers/Security.h:42, from /Library/Developer/CommandLineTools/SDKs/MacOSX10.14.sdk/System/Library/Frameworks/CoreServices.framework/Frameworks/OSServices.framework/Headers/CSIdentity.h:43, from /Library/Developer/CommandLineTools/SDKs/MacOSX10.14.sdk/System/Library/Frameworks/CoreServices.framework/Frameworks/OSServices.framework/Headers/OSServices.h:29, from /Library/Developer/CommandLineTools/SDKs/MacOSX10.14.sdk/System/Library/Frameworks/CoreServices.framework/Frameworks/LaunchServices.framework/Headers/IconsCore.h:23, from /Library/Developer/CommandLineTools/SDKs/MacOSX10.14.sdk/System/Library/Frameworks/CoreServices.framework/Frameworks/LaunchServices.framework/Headers/LaunchServices.h:23, from /Library/Developer/CommandLineTools/SDKs/MacOSX10.14.sdk/System/Library/Frameworks/CoreServices.framework/Headers/CoreServices.h:45, /Library/Developer/CommandLineTools/SDKs/MacOSX10.14.sdk/System/Library/Frameworks/Security.framework/Headers/Authorization.h:193:7: error: variably modified 'bytes' at file scope 193 | char bytes[kAuthorizationExternalFormLength]; | ^~~~~ The underlying reason is that GCC (rightfully) objects that an `enum` value such as `kAuthorizationExternalFormLength` is not a constant (because it is not, the preprocessor has no knowledge of it, only the actual C compiler does) and can therefore not be used to define the size of a C array. This is a known problem and tracked in GCC's bug tracker: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=93082 In the meantime, let's not block things and go the slightly ugly route of declaring/defining the FSEvents constants, data structures and functions that we need, so that we can avoid above-mentioned issue. Let's do this _only_ for GCC, though, so that the CI/PR builds (which build both with clang and with GCC) can guarantee that we _are_ using the correct data types. Signed-off-by: Johannes Schindelin Signed-off-by: Jeff Hostetler --- compat/fsmonitor/fsmonitor-fs-listen-macos.c | 96 ++++++++++++++++++++ 1 file changed, 96 insertions(+) diff --git a/compat/fsmonitor/fsmonitor-fs-listen-macos.c b/compat/fsmonitor/fsmonitor-fs-listen-macos.c index b91058d1c4..bec5130d9e 100644 --- a/compat/fsmonitor/fsmonitor-fs-listen-macos.c +++ b/compat/fsmonitor/fsmonitor-fs-listen-macos.c @@ -1,3 +1,99 @@ +#if defined(__GNUC__) +/* + * It is possible to #include CoreFoundation/CoreFoundation.h when compiling + * with clang, but not with GCC as of time of writing. + * + * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=93082 for details. + */ +typedef unsigned int FSEventStreamCreateFlags; +#define kFSEventStreamEventFlagNone 0x00000000 +#define kFSEventStreamEventFlagMustScanSubDirs 0x00000001 +#define kFSEventStreamEventFlagUserDropped 0x00000002 +#define kFSEventStreamEventFlagKernelDropped 0x00000004 +#define kFSEventStreamEventFlagEventIdsWrapped 0x00000008 +#define kFSEventStreamEventFlagHistoryDone 0x00000010 +#define kFSEventStreamEventFlagRootChanged 0x00000020 +#define kFSEventStreamEventFlagMount 0x00000040 +#define kFSEventStreamEventFlagUnmount 0x00000080 +#define kFSEventStreamEventFlagItemCreated 0x00000100 +#define kFSEventStreamEventFlagItemRemoved 0x00000200 +#define kFSEventStreamEventFlagItemInodeMetaMod 0x00000400 +#define kFSEventStreamEventFlagItemRenamed 0x00000800 +#define kFSEventStreamEventFlagItemModified 0x00001000 +#define kFSEventStreamEventFlagItemFinderInfoMod 0x00002000 +#define kFSEventStreamEventFlagItemChangeOwner 0x00004000 +#define kFSEventStreamEventFlagItemXattrMod 0x00008000 +#define kFSEventStreamEventFlagItemIsFile 0x00010000 +#define kFSEventStreamEventFlagItemIsDir 0x00020000 +#define kFSEventStreamEventFlagItemIsSymlink 0x00040000 +#define kFSEventStreamEventFlagOwnEvent 0x00080000 +#define kFSEventStreamEventFlagItemIsHardlink 0x00100000 +#define kFSEventStreamEventFlagItemIsLastHardlink 0x00200000 +#define kFSEventStreamEventFlagItemCloned 0x00400000 + +typedef struct __FSEventStream *FSEventStreamRef; +typedef const FSEventStreamRef ConstFSEventStreamRef; + +typedef unsigned int CFStringEncoding; +#define kCFStringEncodingUTF8 0x08000100 + +typedef const struct __CFString *CFStringRef; +typedef const struct __CFArray *CFArrayRef; +typedef const struct __CFRunLoop *CFRunLoopRef; + +struct FSEventStreamContext { + long long version; + void *cb_data, *retain, *release, *copy_description; +}; + +typedef struct FSEventStreamContext FSEventStreamContext; +typedef unsigned int FSEventStreamEventFlags; +#define kFSEventStreamCreateFlagNoDefer 0x02 +#define kFSEventStreamCreateFlagWatchRoot 0x04 +#define kFSEventStreamCreateFlagFileEvents 0x10 + +typedef unsigned long long FSEventStreamEventId; +#define kFSEventStreamEventIdSinceNow 0xFFFFFFFFFFFFFFFFULL + +typedef void (*FSEventStreamCallback)(ConstFSEventStreamRef streamRef, + void *context, + __SIZE_TYPE__ num_of_events, + void *event_paths, + const FSEventStreamEventFlags event_flags[], + const FSEventStreamEventId event_ids[]); +typedef double CFTimeInterval; +FSEventStreamRef FSEventStreamCreate(void *allocator, + FSEventStreamCallback callback, + FSEventStreamContext *context, + CFArrayRef paths_to_watch, + FSEventStreamEventId since_when, + CFTimeInterval latency, + FSEventStreamCreateFlags flags); +CFStringRef CFStringCreateWithCString(void *allocator, const char *string, + CFStringEncoding encoding); +CFArrayRef CFArrayCreate(void *allocator, const void **items, long long count, + void *callbacks); +void CFRunLoopRun(void); +void CFRunLoopStop(CFRunLoopRef run_loop); +CFRunLoopRef CFRunLoopGetCurrent(void); +extern CFStringRef kCFRunLoopDefaultMode; +void FSEventStreamScheduleWithRunLoop(FSEventStreamRef stream, + CFRunLoopRef run_loop, + CFStringRef run_loop_mode); +unsigned char FSEventStreamStart(FSEventStreamRef stream); +void FSEventStreamStop(FSEventStreamRef stream); +void FSEventStreamInvalidate(FSEventStreamRef stream); +void FSEventStreamRelease(FSEventStreamRef stream); +#else +/* + * Let Apple's headers declare `isalnum()` first, before + * Git's headers override it via a constant + */ +#include +#include +#include +#endif + #include "cache.h" #include "fsmonitor.h" #include "fsmonitor-fs-listen.h" From ea2f68586420fa3aadb6c0a7bde242b7098cb224 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Fri, 18 Dec 2020 11:22:25 -0500 Subject: [PATCH 19/30] fsmonitor-fs-listen-macos: implement FSEvent listener on MacOS Implement file system event listener on MacOS using FSEvent, CoreFoundation, and CoreServices. Co-authored-by: Kevin Willford Co-authored-by: Johannes Schindelin Signed-off-by: Jeff Hostetler --- compat/fsmonitor/fsmonitor-fs-listen-macos.c | 381 +++++++++++++++++++ 1 file changed, 381 insertions(+) diff --git a/compat/fsmonitor/fsmonitor-fs-listen-macos.c b/compat/fsmonitor/fsmonitor-fs-listen-macos.c index bec5130d9e..02f89de216 100644 --- a/compat/fsmonitor/fsmonitor-fs-listen-macos.c +++ b/compat/fsmonitor/fsmonitor-fs-listen-macos.c @@ -97,20 +97,401 @@ void FSEventStreamRelease(FSEventStreamRef stream); #include "cache.h" #include "fsmonitor.h" #include "fsmonitor-fs-listen.h" +#include "fsmonitor--daemon.h" + +struct fsmonitor_daemon_backend_data +{ + CFStringRef cfsr_worktree_path; + CFStringRef cfsr_gitdir_path; + + CFArrayRef cfar_paths_to_watch; + int nr_paths_watching; + + FSEventStreamRef stream; + + CFRunLoopRef rl; + + enum shutdown_style { + SHUTDOWN_EVENT = 0, + FORCE_SHUTDOWN, + FORCE_ERROR_STOP, + } shutdown_style; + + unsigned int stream_scheduled:1; + unsigned int stream_started:1; +}; + +static void log_flags_set(const char *path, const FSEventStreamEventFlags flag) +{ + struct strbuf msg = STRBUF_INIT; + + if (flag & kFSEventStreamEventFlagMustScanSubDirs) + strbuf_addstr(&msg, "MustScanSubDirs|"); + if (flag & kFSEventStreamEventFlagUserDropped) + strbuf_addstr(&msg, "UserDropped|"); + if (flag & kFSEventStreamEventFlagKernelDropped) + strbuf_addstr(&msg, "KernelDropped|"); + if (flag & kFSEventStreamEventFlagEventIdsWrapped) + strbuf_addstr(&msg, "EventIdsWrapped|"); + if (flag & kFSEventStreamEventFlagHistoryDone) + strbuf_addstr(&msg, "HistoryDone|"); + if (flag & kFSEventStreamEventFlagRootChanged) + strbuf_addstr(&msg, "RootChanged|"); + if (flag & kFSEventStreamEventFlagMount) + strbuf_addstr(&msg, "Mount|"); + if (flag & kFSEventStreamEventFlagUnmount) + strbuf_addstr(&msg, "Unmount|"); + if (flag & kFSEventStreamEventFlagItemChangeOwner) + strbuf_addstr(&msg, "ItemChangeOwner|"); + if (flag & kFSEventStreamEventFlagItemCreated) + strbuf_addstr(&msg, "ItemCreated|"); + if (flag & kFSEventStreamEventFlagItemFinderInfoMod) + strbuf_addstr(&msg, "ItemFinderInfoMod|"); + if (flag & kFSEventStreamEventFlagItemInodeMetaMod) + strbuf_addstr(&msg, "ItemInodeMetaMod|"); + if (flag & kFSEventStreamEventFlagItemIsDir) + strbuf_addstr(&msg, "ItemIsDir|"); + if (flag & kFSEventStreamEventFlagItemIsFile) + strbuf_addstr(&msg, "ItemIsFile|"); + if (flag & kFSEventStreamEventFlagItemIsHardlink) + strbuf_addstr(&msg, "ItemIsHardlink|"); + if (flag & kFSEventStreamEventFlagItemIsLastHardlink) + strbuf_addstr(&msg, "ItemIsLastHardlink|"); + if (flag & kFSEventStreamEventFlagItemIsSymlink) + strbuf_addstr(&msg, "ItemIsSymlink|"); + if (flag & kFSEventStreamEventFlagItemModified) + strbuf_addstr(&msg, "ItemModified|"); + if (flag & kFSEventStreamEventFlagItemRemoved) + strbuf_addstr(&msg, "ItemRemoved|"); + if (flag & kFSEventStreamEventFlagItemRenamed) + strbuf_addstr(&msg, "ItemRenamed|"); + if (flag & kFSEventStreamEventFlagItemXattrMod) + strbuf_addstr(&msg, "ItemXattrMod|"); + if (flag & kFSEventStreamEventFlagOwnEvent) + strbuf_addstr(&msg, "OwnEvent|"); + if (flag & kFSEventStreamEventFlagItemCloned) + strbuf_addstr(&msg, "ItemCloned|"); + + trace_printf_key(&trace_fsmonitor, "fsevent: '%s', flags=%u %s", + path, flag, msg.buf); + + strbuf_release(&msg); +} + +static int ef_is_root_delete(const FSEventStreamEventFlags ef) +{ + return (ef & kFSEventStreamEventFlagItemIsDir && + ef & kFSEventStreamEventFlagItemRemoved); +} + +static int ef_is_root_renamed(const FSEventStreamEventFlags ef) +{ + return (ef & kFSEventStreamEventFlagItemIsDir && + ef & kFSEventStreamEventFlagItemRenamed); +} + +static int ef_is_dropped(const FSEventStreamEventFlags ef) +{ + return (ef & kFSEventStreamEventFlagKernelDropped || + ef & kFSEventStreamEventFlagUserDropped); +} + +static void fsevent_callback(ConstFSEventStreamRef streamRef, + void *ctx, + size_t num_of_events, + void *event_paths, + const FSEventStreamEventFlags event_flags[], + const FSEventStreamEventId event_ids[]) +{ + struct fsmonitor_daemon_state *state = ctx; + struct fsmonitor_daemon_backend_data *data = state->backend_data; + char **paths = (char **)event_paths; + struct fsmonitor_batch *batch = NULL; + struct string_list cookie_list = STRING_LIST_INIT_DUP; + const char *path_k; + const char *slash; + int k; + struct strbuf tmp = STRBUF_INIT; + + /* + * Build a list of all filesystem changes into a private/local + * list and without holding any locks. + */ + for (k = 0; k < num_of_events; k++) { + /* + * On Mac, we receive an array of absolute paths. + */ + path_k = paths[k]; + + /* + * If you want to debug FSEvents, log them to GIT_TRACE_FSMONITOR. + * Please don't log them to Trace2. + * + * trace_printf_key(&trace_fsmonitor, "Path: '%s'", path_k); + */ + + /* + * If event[k] is marked as dropped, we assume that we have + * lost sync with the filesystem and should flush our cached + * data. We need to: + * + * [1] Abort/wake any client threads waiting for a cookie and + * flush the cached state data (the current token), and + * create a new token. + * + * [2] Discard the batch that we were locally building (since + * they are conceptually relative to the just flushed + * token). + */ + if (ef_is_dropped(event_flags[k])) { + /* + * see also kFSEventStreamEventFlagMustScanSubDirs + */ + trace_printf_key(&trace_fsmonitor, "event: dropped"); + + fsmonitor_force_resync(state); + fsmonitor_batch__pop(batch); + string_list_clear(&cookie_list, 0); + + /* + * We assume that any events that we received + * in this callback after this dropped event + * may still be valid, so we continue rather + * than break. (And just in case there is a + * delete of ".git" hiding in there.) + */ + continue; + } + + switch (fsmonitor_classify_path_absolute(state, path_k)) { + + case IS_INSIDE_DOT_GIT_WITH_COOKIE_PREFIX: + case IS_INSIDE_GITDIR_WITH_COOKIE_PREFIX: + /* special case cookie files within .git or gitdir */ + + /* Use just the filename of the cookie file. */ + slash = find_last_dir_sep(path_k); + string_list_append(&cookie_list, + slash ? slash + 1 : path_k); + break; + + case IS_INSIDE_DOT_GIT: + case IS_INSIDE_GITDIR: + /* ignore all other paths inside of .git or gitdir */ + break; + + case IS_DOT_GIT: + case IS_GITDIR: + /* + * If .git directory is deleted or renamed away, + * we have to quit. + */ + if (ef_is_root_delete(event_flags[k])) { + trace_printf_key(&trace_fsmonitor, + "event: gitdir removed"); + goto force_shutdown; + } + if (ef_is_root_renamed(event_flags[k])) { + trace_printf_key(&trace_fsmonitor, + "event: gitdir renamed"); + goto force_shutdown; + } + break; + + case IS_WORKDIR_PATH: + /* try to queue normal pathnames */ + + if (trace_pass_fl(&trace_fsmonitor)) + log_flags_set(path_k, event_flags[k]); + + /* + * Because of the implicit "binning" (the + * kernel calls us at a given frequency) and + * de-duping (the kernel is free to combine + * multiple events for a given pathname), an + * individual fsevent could be marked as both + * a file and directory. Add it to the queue + * with both spellings so that the client will + * know how much to invalidate/refresh. + */ + + if (event_flags[k] & kFSEventStreamEventFlagItemIsFile) { + const char *rel = path_k + + state->path_worktree_watch.len + 1; + + if (!batch) + batch = fsmonitor_batch__new(); + fsmonitor_batch__add_path(batch, rel); + } + + if (event_flags[k] & kFSEventStreamEventFlagItemIsDir) { + const char *rel = path_k + + state->path_worktree_watch.len + 1; + + strbuf_reset(&tmp); + strbuf_addstr(&tmp, rel); + strbuf_addch(&tmp, '/'); + + if (!batch) + batch = fsmonitor_batch__new(); + fsmonitor_batch__add_path(batch, tmp.buf); + } + + break; + + case IS_OUTSIDE_CONE: + default: + trace_printf_key(&trace_fsmonitor, + "ignoring '%s'", path_k); + break; + } + } + + fsmonitor_publish(state, batch, &cookie_list); + string_list_clear(&cookie_list, 0); + strbuf_release(&tmp); + return; + +force_shutdown: + fsmonitor_batch__pop(batch); + string_list_clear(&cookie_list, 0); + + data->shutdown_style = FORCE_SHUTDOWN; + CFRunLoopStop(data->rl); + strbuf_release(&tmp); + return; +} + +/* + * NEEDSWORK: Investigate the proper value for the `latency` argument + * in the call to `FSEventStreamCreate()`. I'm not sure that this + * needs to be a config setting or just something that we tune after + * some testing. + * + * With a latency of 0.1, I was seeing lots of dropped events during + * the "touch 100000" files test within t/perf/p7519, but with a + * latency of 0.001 I did not see any dropped events. So the + * "correct" value may be somewhere in between. + * + * https://developer.apple.com/documentation/coreservices/1443980-fseventstreamcreate + */ int fsmonitor_fs_listen__ctor(struct fsmonitor_daemon_state *state) { + FSEventStreamCreateFlags flags = kFSEventStreamCreateFlagNoDefer | + kFSEventStreamCreateFlagWatchRoot | + kFSEventStreamCreateFlagFileEvents; + FSEventStreamContext ctx = { + 0, + state, + NULL, + NULL, + NULL + }; + struct fsmonitor_daemon_backend_data *data; + const void *dir_array[2]; + + CALLOC_ARRAY(data, 1); + state->backend_data = data; + + data->cfsr_worktree_path = CFStringCreateWithCString( + NULL, state->path_worktree_watch.buf, kCFStringEncodingUTF8); + dir_array[data->nr_paths_watching++] = data->cfsr_worktree_path; + + if (state->nr_paths_watching > 1) { + data->cfsr_gitdir_path = CFStringCreateWithCString( + NULL, state->path_gitdir_watch.buf, + kCFStringEncodingUTF8); + dir_array[data->nr_paths_watching++] = data->cfsr_gitdir_path; + } + + data->cfar_paths_to_watch = CFArrayCreate(NULL, dir_array, + data->nr_paths_watching, + NULL); + data->stream = FSEventStreamCreate(NULL, fsevent_callback, &ctx, + data->cfar_paths_to_watch, + kFSEventStreamEventIdSinceNow, + 0.001, flags); + if (data->stream == NULL) + goto failed; + + /* + * `data->rl` needs to be set inside the listener thread. + */ + + return 0; + +failed: + error("Unable to create FSEventStream."); + + FREE_AND_NULL(state->backend_data); return -1; } void fsmonitor_fs_listen__dtor(struct fsmonitor_daemon_state *state) { + struct fsmonitor_daemon_backend_data *data; + + if (!state || !state->backend_data) + return; + + data = state->backend_data; + + if (data->stream) { + if (data->stream_started) + FSEventStreamStop(data->stream); + if (data->stream_scheduled) + FSEventStreamInvalidate(data->stream); + FSEventStreamRelease(data->stream); + } + + FREE_AND_NULL(state->backend_data); } void fsmonitor_fs_listen__stop_async(struct fsmonitor_daemon_state *state) { + struct fsmonitor_daemon_backend_data *data; + + data = state->backend_data; + data->shutdown_style = SHUTDOWN_EVENT; + + CFRunLoopStop(data->rl); } void fsmonitor_fs_listen__loop(struct fsmonitor_daemon_state *state) { + struct fsmonitor_daemon_backend_data *data; + + data = state->backend_data; + + data->rl = CFRunLoopGetCurrent(); + + FSEventStreamScheduleWithRunLoop(data->stream, data->rl, kCFRunLoopDefaultMode); + data->stream_scheduled = 1; + + if (!FSEventStreamStart(data->stream)) { + error("Failed to start the FSEventStream"); + goto force_error_stop_without_loop; + } + data->stream_started = 1; + + CFRunLoopRun(); + + switch (data->shutdown_style) { + case FORCE_ERROR_STOP: + state->error_code = -1; + /* fall thru */ + case FORCE_SHUTDOWN: + ipc_server_stop_async(state->ipc_server_data); + /* fall thru */ + case SHUTDOWN_EVENT: + default: + break; + } + return; + +force_error_stop_without_loop: + state->error_code = -1; + ipc_server_stop_async(state->ipc_server_data); + return; } From ffb2f2b418da8c7feb2b368d3cdfa7de63dda994 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Fri, 18 Dec 2020 11:43:16 -0500 Subject: [PATCH 20/30] fsmonitor--daemon: implement handle_client callback Teach fsmonitor--daemon to respond to IPC requests from client Git processes and respond with a list of modified pathnames relative to the provided token. Signed-off-by: Jeff Hostetler --- builtin/fsmonitor--daemon.c | 312 +++++++++++++++++++++++++++++++++++- 1 file changed, 310 insertions(+), 2 deletions(-) diff --git a/builtin/fsmonitor--daemon.c b/builtin/fsmonitor--daemon.c index 663fead0d6..33b4f09c72 100644 --- a/builtin/fsmonitor--daemon.c +++ b/builtin/fsmonitor--daemon.c @@ -7,6 +7,7 @@ #include "fsmonitor--daemon.h" #include "simple-ipc.h" #include "khash.h" +#include "pkt-line.h" static const char * const builtin_fsmonitor__daemon_usage[] = { N_("git fsmonitor--daemon start []"), @@ -353,6 +354,311 @@ void fsmonitor_force_resync(struct fsmonitor_daemon_state *state) pthread_mutex_unlock(&state->main_lock); } +/* + * Format an opaque token string to send to the client. + */ +static void with_lock__format_response_token( + struct strbuf *response_token, + const struct strbuf *response_token_id, + const struct fsmonitor_batch *batch) +{ + /* assert current thread holding state->main_lock */ + + strbuf_reset(response_token); + strbuf_addf(response_token, "builtin:%s:%"PRIu64, + response_token_id->buf, batch->batch_seq_nr); +} + +/* + * Parse an opaque token from the client. + * Returns -1 on error. + */ +static int fsmonitor_parse_client_token(const char *buf_token, + struct strbuf *requested_token_id, + uint64_t *seq_nr) +{ + const char *p; + char *p_end; + + strbuf_reset(requested_token_id); + *seq_nr = 0; + + if (!skip_prefix(buf_token, "builtin:", &p)) + return -1; + + while (*p && *p != ':') + strbuf_addch(requested_token_id, *p++); + if (!*p++) + return -1; + + *seq_nr = (uint64_t)strtoumax(p, &p_end, 10); + if (*p_end) + return -1; + + return 0; +} + +KHASH_INIT(str, const char *, int, 0, kh_str_hash_func, kh_str_hash_equal); + +static int do_handle_client(struct fsmonitor_daemon_state *state, + const char *command, + ipc_server_reply_cb *reply, + struct ipc_server_reply_data *reply_data) +{ + struct fsmonitor_token_data *token_data = NULL; + struct strbuf response_token = STRBUF_INIT; + struct strbuf requested_token_id = STRBUF_INIT; + struct strbuf payload = STRBUF_INIT; + uint64_t requested_oldest_seq_nr = 0; + uint64_t total_response_len = 0; + const char *p; + const struct fsmonitor_batch *batch_head; + const struct fsmonitor_batch *batch; + intmax_t count = 0, duplicates = 0; + kh_str_t *shown; + int hash_ret; + int do_trivial = 0; + int do_flush = 0; + + /* + * We expect `command` to be of the form: + * + * := quit NUL + * | flush NUL + * | NUL + * | NUL + */ + + if (!strcmp(command, "quit")) { + /* + * A client has requested over the socket/pipe that the + * daemon shutdown. + * + * Tell the IPC thread pool to shutdown (which completes + * the await in the main thread (which can stop the + * fsmonitor listener thread)). + * + * There is no reply to the client. + */ + return SIMPLE_IPC_QUIT; + + } else if (!strcmp(command, "flush")) { + /* + * Flush all of our cached data and generate a new token + * just like if we lost sync with the filesystem. + * + * Then send a trivial response using the new token. + */ + do_flush = 1; + do_trivial = 1; + + } else if (!skip_prefix(command, "builtin:", &p)) { + /* assume V1 timestamp or garbage */ + + char *p_end; + + strtoumax(command, &p_end, 10); + trace_printf_key(&trace_fsmonitor, + ((*p_end) ? + "fsmonitor: invalid command line '%s'" : + "fsmonitor: unsupported V1 protocol '%s'"), + command); + do_trivial = 1; + + } else { + /* We have "builtin:*" */ + if (fsmonitor_parse_client_token(command, &requested_token_id, + &requested_oldest_seq_nr)) { + trace_printf_key(&trace_fsmonitor, + "fsmonitor: invalid V2 protocol token '%s'", + command); + do_trivial = 1; + + } else { + /* + * We have a V2 valid token: + * "builtin::" + */ + } + } + + pthread_mutex_lock(&state->main_lock); + + if (!state->current_token_data) + BUG("fsmonitor state does not have a current token"); + + if (do_flush) + with_lock__do_force_resync(state); + + /* + * We mark the current head of the batch list as "pinned" so + * that the listener thread will treat this item as read-only + * (and prevent any more paths from being added to it) from + * now on. + */ + token_data = state->current_token_data; + batch_head = token_data->batch_head; + ((struct fsmonitor_batch *)batch_head)->pinned_time = time(NULL); + + /* + * FSMonitor Protocol V2 requires that we send a response header + * with a "new current token" and then all of the paths that changed + * since the "requested token". We send the seq_nr of the just-pinned + * head batch so that future requests from a client will be relative + * to it. + */ + with_lock__format_response_token(&response_token, + &token_data->token_id, batch_head); + + reply(reply_data, response_token.buf, response_token.len + 1); + total_response_len += response_token.len + 1; + + trace2_data_string("fsmonitor", the_repository, "response/token", + response_token.buf); + trace_printf_key(&trace_fsmonitor, "response token: %s", + response_token.buf); + + if (!do_trivial) { + if (strcmp(requested_token_id.buf, token_data->token_id.buf)) { + /* + * The client last spoke to a different daemon + * instance -OR- the daemon had to resync with + * the filesystem (and lost events), so reject. + */ + trace2_data_string("fsmonitor", the_repository, + "response/token", "different"); + do_trivial = 1; + + } else if (requested_oldest_seq_nr < + token_data->batch_tail->batch_seq_nr) { + /* + * The client wants older events than we have for + * this token_id. This means that the end of our + * batch list was truncated and we cannot give the + * client a complete snapshot relative to their + * request. + */ + trace_printf_key(&trace_fsmonitor, + "client requested truncated data"); + do_trivial = 1; + } + } + + if (do_trivial) { + pthread_mutex_unlock(&state->main_lock); + + reply(reply_data, "/", 2); + + trace2_data_intmax("fsmonitor", the_repository, + "response/trivial", 1); + + strbuf_release(&response_token); + strbuf_release(&requested_token_id); + return 0; + } + + /* + * We're going to hold onto a pointer to the current + * token-data while we walk the list of batches of files. + * During this time, we will NOT be under the lock. + * So we ref-count it. + * + * This allows the listener thread to continue prepending + * new batches of items to the token-data (which we'll ignore). + * + * AND it allows the listener thread to do a token-reset + * (and install a new `current_token_data`). + */ + token_data->client_ref_count++; + + pthread_mutex_unlock(&state->main_lock); + + /* + * The client request is relative to the token that they sent, + * so walk the batch list backwards from the current head back + * to the batch (sequence number) they named. + * + * We use khash to de-dup the list of pathnames. + * + * NEEDSWORK: each batch contains a list of interned strings, + * so we only need to do pointer comparisons here to build the + * hash table. Currently, we're still comparing the string + * values. + */ + shown = kh_init_str(); + for (batch = batch_head; + batch && batch->batch_seq_nr > requested_oldest_seq_nr; + batch = batch->next) { + size_t k; + + for (k = 0; k < batch->nr; k++) { + const char *s = batch->interned_paths[k]; + size_t s_len; + + if (kh_get_str(shown, s) != kh_end(shown)) + duplicates++; + else { + kh_put_str(shown, s, &hash_ret); + + trace_printf_key(&trace_fsmonitor, + "send[%"PRIuMAX"]: %s", + count, s); + + /* Each path gets written with a trailing NUL */ + s_len = strlen(s) + 1; + + if (payload.len + s_len >= + LARGE_PACKET_DATA_MAX) { + reply(reply_data, payload.buf, + payload.len); + total_response_len += payload.len; + strbuf_reset(&payload); + } + + strbuf_add(&payload, s, s_len); + count++; + } + } + } + + if (payload.len) { + reply(reply_data, payload.buf, payload.len); + total_response_len += payload.len; + } + + kh_release_str(shown); + + pthread_mutex_lock(&state->main_lock); + + if (token_data->client_ref_count > 0) + token_data->client_ref_count--; + + if (token_data->client_ref_count == 0) { + if (token_data != state->current_token_data) { + /* + * The listener thread did a token-reset while we were + * walking the batch list. Therefore, this token is + * stale and can be discarded completely. If we are + * the last reader thread using this token, we own + * that work. + */ + fsmonitor_free_token_data(token_data); + } + } + + pthread_mutex_unlock(&state->main_lock); + + trace2_data_intmax("fsmonitor", the_repository, "response/length", total_response_len); + trace2_data_intmax("fsmonitor", the_repository, "response/count/files", count); + trace2_data_intmax("fsmonitor", the_repository, "response/count/duplicates", duplicates); + + strbuf_release(&response_token); + strbuf_release(&requested_token_id); + strbuf_release(&payload); + + return 0; +} + static ipc_server_application_cb handle_client; static int handle_client(void *data, @@ -360,7 +666,7 @@ static int handle_client(void *data, ipc_server_reply_cb *reply, struct ipc_server_reply_data *reply_data) { - /* struct fsmonitor_daemon_state *state = data; */ + struct fsmonitor_daemon_state *state = data; int result; /* @@ -371,10 +677,12 @@ static int handle_client(void *data, if (command_len != strlen(command)) BUG("FSMonitor assumes text messages"); + trace_printf_key(&trace_fsmonitor, "requested token: %s", command); + trace2_region_enter("fsmonitor", "handle_client", the_repository); trace2_data_string("fsmonitor", the_repository, "request", command); - result = 0; /* TODO Do something here. */ + result = do_handle_client(state, command, reply, reply_data); trace2_region_leave("fsmonitor", "handle_client", the_repository); From af34de2067567b76ba71f70f58759753eb43722c Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Fri, 18 Dec 2020 11:46:06 -0500 Subject: [PATCH 21/30] fsmonitor--daemon: periodically truncate list of modified files Teach fsmonitor--daemon to periodically truncate the list of modified files to save some memory. Clients will ask for the set of changes relative to a token that they found in the FSMN index extension in the index. (This token is like a point in time, but different). Clients will then update the index to contain the response token (so that subsequent commands will be relative to this new token). Therefore, the daemon can gradually truncate the in-memory list of changed paths as they become obsolete (older than the previous token). Since we may have multiple clients making concurrent requests with a skew of tokens and clients may be racing to the talk to the daemon, we lazily truncate the list. We introduce a 5 minute delay and truncate batches 5 minutes after they are considered obsolete. Signed-off-by: Jeff Hostetler --- builtin/fsmonitor--daemon.c | 80 +++++++++++++++++++++++++++++++++++++ 1 file changed, 80 insertions(+) diff --git a/builtin/fsmonitor--daemon.c b/builtin/fsmonitor--daemon.c index 33b4f09c72..e807aa8f67 100644 --- a/builtin/fsmonitor--daemon.c +++ b/builtin/fsmonitor--daemon.c @@ -298,6 +298,77 @@ static void fsmonitor_batch__combine(struct fsmonitor_batch *batch_dest, batch_src->interned_paths[k]; } +/* + * To keep the batch list from growing unbounded in response to filesystem + * activity, we try to truncate old batches from the end of the list as + * they become irrelevant. + * + * We assume that the .git/index will be updated with the most recent token + * any time the index is updated. And future commands will only ask for + * recent changes *since* that new token. So as tokens advance into the + * future, older batch items will never be requested/needed. So we can + * truncate them without loss of functionality. + * + * However, multiple commands may be talking to the daemon concurrently + * or perform a slow command, so a little "token skew" is possible. + * Therefore, we want this to be a little bit lazy and have a generous + * delay. + * + * The current reader thread walked backwards in time from `token->batch_head` + * back to `batch_marker` somewhere in the middle of the batch list. + * + * Let's walk backwards in time from that marker an arbitrary delay + * and truncate the list there. Note that these timestamps are completely + * artificial (based on when we pinned the batch item) and not on any + * filesystem activity. + */ +#define MY_TIME_DELAY_SECONDS (5 * 60) /* seconds */ + +static void with_lock__truncate_old_batches( + struct fsmonitor_daemon_state *state, + const struct fsmonitor_batch *batch_marker) +{ + /* assert current thread holding state->main_lock */ + + const struct fsmonitor_batch *batch; + struct fsmonitor_batch *rest; + struct fsmonitor_batch *p; + + if (!batch_marker) + return; + + trace_printf_key(&trace_fsmonitor, "Truncate: mark (%"PRIu64",%"PRIu64")", + batch_marker->batch_seq_nr, + (uint64_t)batch_marker->pinned_time); + + for (batch = batch_marker; batch; batch = batch->next) { + time_t t; + + if (!batch->pinned_time) /* an overflow batch */ + continue; + + t = batch->pinned_time + MY_TIME_DELAY_SECONDS; + if (t > batch_marker->pinned_time) /* too close to marker */ + continue; + + goto truncate_past_here; + } + + return; + +truncate_past_here: + state->current_token_data->batch_tail = (struct fsmonitor_batch *)batch; + + rest = ((struct fsmonitor_batch *)batch)->next; + ((struct fsmonitor_batch *)batch)->next = NULL; + + for (p = rest; p; p = fsmonitor_batch__pop(p)) { + trace_printf_key(&trace_fsmonitor, + "Truncate: kill (%"PRIu64",%"PRIu64")", + p->batch_seq_nr, (uint64_t)p->pinned_time); + } +} + static void fsmonitor_free_token_data(struct fsmonitor_token_data *token) { struct fsmonitor_batch *p; @@ -643,6 +714,15 @@ static int do_handle_client(struct fsmonitor_daemon_state *state, * that work. */ fsmonitor_free_token_data(token_data); + } else if (batch) { + /* + * This batch is the first item in the list + * that is older than the requested sequence + * number and might be considered to be + * obsolete. See if we can truncate the list + * and save some memory. + */ + with_lock__truncate_old_batches(state, batch); } } From 94525b7fca6e7d2371e9f14ff5ff9a63e64fd6f1 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Fri, 18 Dec 2020 12:11:29 -0500 Subject: [PATCH 22/30] fsmonitor--daemon: use a cookie file to sync with file system Teach fsmonitor--daemon client threads to create a cookie file inside the .git directory and then wait until FS events for the cookie are observed by the FS listener thread. This helps address the racy nature of file system events by blocking the client response until the kernel has drained any event backlog. This is especially important on MacOS where kernel events are only issued with a limited frequency. See the `latency` argument of `FSeventStreamCreate()`. The kernel only signals every `latency` seconds, but does not guarantee that the kernel queue is completely drained, so we may have to wait more than one interval. If we increase the frequency, the system is more likely to drop events. We avoid these issues by having each client thread create a unique cookie file and then wait until it is seen in the event stream. Co-authored-by: Kevin Willford Co-authored-by: Johannes Schindelin Signed-off-by: Jeff Hostetler --- builtin/fsmonitor--daemon.c | 210 +++++++++++++++++++++++++++++++++++- fsmonitor--daemon.h | 5 + 2 files changed, 214 insertions(+), 1 deletion(-) diff --git a/builtin/fsmonitor--daemon.c b/builtin/fsmonitor--daemon.c index e807aa8f67..985a82cf39 100644 --- a/builtin/fsmonitor--daemon.c +++ b/builtin/fsmonitor--daemon.c @@ -92,6 +92,149 @@ static int do_as_client__status(void) } } +enum fsmonitor_cookie_item_result { + FCIR_ERROR = -1, /* could not create cookie file ? */ + FCIR_INIT = 0, + FCIR_SEEN, + FCIR_ABORT, +}; + +struct fsmonitor_cookie_item { + struct hashmap_entry entry; + const char *name; + enum fsmonitor_cookie_item_result result; +}; + +static int cookies_cmp(const void *data, const struct hashmap_entry *he1, + const struct hashmap_entry *he2, const void *keydata) +{ + const struct fsmonitor_cookie_item *a = + container_of(he1, const struct fsmonitor_cookie_item, entry); + const struct fsmonitor_cookie_item *b = + container_of(he2, const struct fsmonitor_cookie_item, entry); + + return strcmp(a->name, keydata ? keydata : b->name); +} + +static enum fsmonitor_cookie_item_result with_lock__wait_for_cookie( + struct fsmonitor_daemon_state *state) +{ + /* assert current thread holding state->main_lock */ + + int fd; + struct fsmonitor_cookie_item *cookie; + struct strbuf cookie_pathname = STRBUF_INIT; + struct strbuf cookie_filename = STRBUF_INIT; + enum fsmonitor_cookie_item_result result; + int my_cookie_seq; + + CALLOC_ARRAY(cookie, 1); + + my_cookie_seq = state->cookie_seq++; + + strbuf_addf(&cookie_filename, "%i-%i", getpid(), my_cookie_seq); + + strbuf_addbuf(&cookie_pathname, &state->path_cookie_prefix); + strbuf_addbuf(&cookie_pathname, &cookie_filename); + + cookie->name = strbuf_detach(&cookie_filename, NULL); + cookie->result = FCIR_INIT; + hashmap_entry_init(&cookie->entry, strhash(cookie->name)); + + hashmap_add(&state->cookies, &cookie->entry); + + trace_printf_key(&trace_fsmonitor, "cookie-wait: '%s' '%s'", + cookie->name, cookie_pathname.buf); + + /* + * Create the cookie file on disk and then wait for a notification + * that the listener thread has seen it. + */ + fd = open(cookie_pathname.buf, O_WRONLY | O_CREAT | O_EXCL, 0600); + if (fd >= 0) { + close(fd); + unlink(cookie_pathname.buf); + + /* + * NEEDSWORK: This is an infinite wait (well, unless another + * thread sends us an abort). I'd like to change this to + * use `pthread_cond_timedwait()` and return an error/timeout + * and let the caller do the trivial response thing. + */ + while (cookie->result == FCIR_INIT) + pthread_cond_wait(&state->cookies_cond, + &state->main_lock); + } else { + error_errno(_("could not create fsmonitor cookie '%s'"), + cookie->name); + + cookie->result = FCIR_ERROR; + } + + hashmap_remove(&state->cookies, &cookie->entry, NULL); + + result = cookie->result; + + free((char*)cookie->name); + free(cookie); + strbuf_release(&cookie_pathname); + + return result; +} + +/* + * Mark these cookies as _SEEN and wake up the corresponding client threads. + */ +static void with_lock__mark_cookies_seen(struct fsmonitor_daemon_state *state, + const struct string_list *cookie_names) +{ + /* assert current thread holding state->main_lock */ + + int k; + int nr_seen = 0; + + for (k = 0; k < cookie_names->nr; k++) { + struct fsmonitor_cookie_item key; + struct fsmonitor_cookie_item *cookie; + + key.name = cookie_names->items[k].string; + hashmap_entry_init(&key.entry, strhash(key.name)); + + cookie = hashmap_get_entry(&state->cookies, &key, entry, NULL); + if (cookie) { + trace_printf_key(&trace_fsmonitor, "cookie-seen: '%s'", + cookie->name); + cookie->result = FCIR_SEEN; + nr_seen++; + } + } + + if (nr_seen) + pthread_cond_broadcast(&state->cookies_cond); +} + +/* + * Set _ABORT on all pending cookies and wake up all client threads. + */ +static void with_lock__abort_all_cookies(struct fsmonitor_daemon_state *state) +{ + /* assert current thread holding state->main_lock */ + + struct hashmap_iter iter; + struct fsmonitor_cookie_item *cookie; + int nr_aborted = 0; + + hashmap_for_each_entry(&state->cookies, &iter, cookie, entry) { + trace_printf_key(&trace_fsmonitor, "cookie-abort: '%s'", + cookie->name); + cookie->result = FCIR_ABORT; + nr_aborted++; + } + + if (nr_aborted) + pthread_cond_broadcast(&state->cookies_cond); +} + /* * Requests to and from a FSMonitor Protocol V2 provider use an opaque * "token" as a virtual timestamp. Clients can request a summary of all @@ -395,6 +538,9 @@ static void fsmonitor_free_token_data(struct fsmonitor_token_data *token) * We should create a new token and start fresh (as if we just * booted up). * + * [2] Some of those lost events may have been for cookie files. We + * should assume the worst and abort them rather letting them starve. + * * If there are no concurrent threads readering the current token data * series, we can free it now. Otherwise, let the last reader free * it. @@ -416,6 +562,8 @@ static void with_lock__do_force_resync(struct fsmonitor_daemon_state *state) state->current_token_data = new_one; fsmonitor_free_token_data(free_me); + + with_lock__abort_all_cookies(state); } void fsmonitor_force_resync(struct fsmonitor_daemon_state *state) @@ -490,6 +638,8 @@ static int do_handle_client(struct fsmonitor_daemon_state *state, int hash_ret; int do_trivial = 0; int do_flush = 0; + int do_cookie = 0; + enum fsmonitor_cookie_item_result cookie_result; /* * We expect `command` to be of the form: @@ -522,6 +672,7 @@ static int do_handle_client(struct fsmonitor_daemon_state *state, */ do_flush = 1; do_trivial = 1; + do_cookie = 1; } else if (!skip_prefix(command, "builtin:", &p)) { /* assume V1 timestamp or garbage */ @@ -535,6 +686,7 @@ static int do_handle_client(struct fsmonitor_daemon_state *state, "fsmonitor: unsupported V1 protocol '%s'"), command); do_trivial = 1; + do_cookie = 1; } else { /* We have "builtin:*" */ @@ -544,12 +696,14 @@ static int do_handle_client(struct fsmonitor_daemon_state *state, "fsmonitor: invalid V2 protocol token '%s'", command); do_trivial = 1; + do_cookie = 1; } else { /* * We have a V2 valid token: * "builtin::" */ + do_cookie = 1; } } @@ -558,6 +712,30 @@ static int do_handle_client(struct fsmonitor_daemon_state *state, if (!state->current_token_data) BUG("fsmonitor state does not have a current token"); + /* + * Write a cookie file inside the directory being watched in + * an effort to flush out existing filesystem events that we + * actually care about. Suspend this client thread until we + * see the filesystem events for this cookie file. + * + * Creating the cookie lets us guarantee that our FS listener + * thread has drained the kernel queue and we are caught up + * with the kernel. + * + * If we cannot create the cookie (or otherwise guarantee that + * we are caught up), we send a trivial response. We have to + * assume that there might be some very, very recent activity + * on the FS still in flight. + */ + if (do_cookie) { + cookie_result = with_lock__wait_for_cookie(state); + if (cookie_result != FCIR_SEEN) { + error(_("fsmonitor: cookie_result '%d' != SEEN"), + cookie_result); + do_trivial = 1; + } + } + if (do_flush) with_lock__do_force_resync(state); @@ -769,7 +947,9 @@ static int handle_client(void *data, return result; } -#define FSMONITOR_COOKIE_PREFIX ".fsmonitor-daemon-" +#define FSMONITOR_DIR "fsmonitor--daemon" +#define FSMONITOR_COOKIE_DIR "cookies" +#define FSMONITOR_COOKIE_PREFIX (FSMONITOR_DIR "/" FSMONITOR_COOKIE_DIR "/") enum fsmonitor_path_type fsmonitor_classify_path_workdir_relative( const char *rel) @@ -922,6 +1102,9 @@ void fsmonitor_publish(struct fsmonitor_daemon_state *state, } } + if (cookie_names->nr) + with_lock__mark_cookies_seen(state, cookie_names); + pthread_mutex_unlock(&state->main_lock); } @@ -1011,7 +1194,9 @@ static int fsmonitor_run_daemon(void) memset(&state, 0, sizeof(state)); + hashmap_init(&state.cookies, cookies_cmp, NULL, 0); pthread_mutex_init(&state.main_lock, NULL); + pthread_cond_init(&state.cookies_cond, NULL); state.error_code = 0; state.current_token_data = fsmonitor_new_token_data(); @@ -1035,6 +1220,23 @@ static int fsmonitor_run_daemon(void) state.nr_paths_watching = 2; } + /* + * We will write filesystem syncing cookie files into + * ///-. + */ + strbuf_init(&state.path_cookie_prefix, 0); + strbuf_addbuf(&state.path_cookie_prefix, &state.path_gitdir_watch); + + strbuf_addch(&state.path_cookie_prefix, '/'); + strbuf_addstr(&state.path_cookie_prefix, FSMONITOR_DIR); + mkdir(state.path_cookie_prefix.buf, 0777); + + strbuf_addch(&state.path_cookie_prefix, '/'); + strbuf_addstr(&state.path_cookie_prefix, FSMONITOR_COOKIE_DIR); + mkdir(state.path_cookie_prefix.buf, 0777); + + strbuf_addch(&state.path_cookie_prefix, '/'); + /* * Confirm that we can create platform-specific resources for the * filesystem listener before we bother starting all the threads. @@ -1047,6 +1249,7 @@ static int fsmonitor_run_daemon(void) err = fsmonitor_run_daemon_1(&state); done: + pthread_cond_destroy(&state.cookies_cond); pthread_mutex_destroy(&state.main_lock); fsmonitor_fs_listen__dtor(&state); @@ -1054,6 +1257,11 @@ done: strbuf_release(&state.path_worktree_watch); strbuf_release(&state.path_gitdir_watch); + strbuf_release(&state.path_cookie_prefix); + + /* + * NEEDSWORK: Consider "rm -rf /" + */ return err; } diff --git a/fsmonitor--daemon.h b/fsmonitor--daemon.h index 89a9ef20b2..e9fc099bae 100644 --- a/fsmonitor--daemon.h +++ b/fsmonitor--daemon.h @@ -45,6 +45,11 @@ struct fsmonitor_daemon_state { struct fsmonitor_token_data *current_token_data; + struct strbuf path_cookie_prefix; + pthread_cond_t cookies_cond; + int cookie_seq; + struct hashmap cookies; + int error_code; struct fsmonitor_daemon_backend_data *backend_data; From cedb3ddaca1e06ec144f565a227fa2751992fbe0 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Wed, 19 May 2021 13:45:55 -0400 Subject: [PATCH 23/30] fsmonitor: enhance existing comments Signed-off-by: Jeff Hostetler --- fsmonitor.c | 37 ++++++++++++++++++++++++++++++------- 1 file changed, 30 insertions(+), 7 deletions(-) diff --git a/fsmonitor.c b/fsmonitor.c index c6d3c34ad7..29adf3e53e 100644 --- a/fsmonitor.c +++ b/fsmonitor.c @@ -344,9 +344,25 @@ void refresh_fsmonitor(struct index_state *istate) } apply_results: - /* a fsmonitor process can return '/' to indicate all entries are invalid */ + /* + * The response from FSMonitor (excluding the header token) is + * either: + * + * [a] a (possibly empty) list of NUL delimited relative + * pathnames of changed paths. This list can contain + * files and directories. Directories have a trailing + * slash. + * + * [b] a single '/' to indicate the provider had no + * information and that we should consider everything + * invalid. We call this a trivial response. + */ if (query_success && query_result.buf[bol] != '/') { - /* Mark all entries returned by the monitor as dirty */ + /* + * Mark all pathnames returned by the monitor as dirty. + * + * This updates both the cache-entries and the untracked-cache. + */ buf = query_result.buf; for (i = bol; i < query_result.len; i++) { if (buf[i] != '\0') @@ -361,11 +377,15 @@ apply_results: if (istate->untracked) istate->untracked->use_fsmonitor = 1; } else { - - /* We only want to run the post index changed hook if we've actually changed entries, so keep track - * if we actually changed entries or not */ + /* + * We received a trivial response, so invalidate everything. + * + * We only want to run the post index changed hook if + * we've actually changed entries, so keep track if we + * actually changed entries or not. + */ int is_cache_changed = 0; - /* Mark all entries invalid */ + for (i = 0; i < istate->cache_nr; i++) { if (istate->cache[i]->ce_flags & CE_FSMONITOR_VALID) { is_cache_changed = 1; @@ -373,7 +393,10 @@ apply_results: } } - /* If we're going to check every file, ensure we save the results */ + /* + * If we're going to check every file, ensure we save + * the results. + */ if (is_cache_changed) istate->cache_changed |= FSMONITOR_CHANGED; From 2f8b7fa9fee62ba108a7494a2878ec02f5b64835 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Wed, 19 May 2021 15:42:21 -0400 Subject: [PATCH 24/30] fsmonitor: force update index after large responses Set the `FSMONITOR_CHANGED` bit on `istate->cache_changed` when FSMonitor returns a very large repsonse to ensure that the index is written to disk. Normally, when the FSMonitor response includes a tracked file, the index is always updated. Similarly, the index might be updated when the response alters the untracked-cache (when enabled). However, in cases where neither of those cause the index to be considered changed, the FSMonitor response is wasted. Subsequent Git commands will make requests with the same token and receive the same response. If that response is very large, performance may suffer. It would be more efficient to force update the index now (and the token in the index extension) in order to reduce the size of the response received by future commands. This was observed on Windows after a large checkout. On Windows, the kernel emits events for the files that are changed as they are changed. However, it might delay events for the containing directories until the system is more idle (or someone scans the directory (so it seems)). The first status following a checkout would get the list of files. The subsequent status commands would get the list of directories as the events trickled out. But they would never catch up because the token was not advanced because the index wasn't updated. This list of directories caused `wt_status_collect_untracked()` to unnecessarily spend time actually scanning them during each command. Signed-off-by: Jeff Hostetler --- fsmonitor.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 49 insertions(+), 1 deletion(-) diff --git a/fsmonitor.c b/fsmonitor.c index 29adf3e53e..22623fd228 100644 --- a/fsmonitor.c +++ b/fsmonitor.c @@ -230,6 +230,45 @@ static void fsmonitor_refresh_callback(struct index_state *istate, char *name) untracked_cache_invalidate_path(istate, name, 0); } +/* + * The number of pathnames that we need to receive from FSMonitor + * before we force the index to be updated. + * + * Note that any pathname within the set of received paths MAY cause + * cache-entry or istate flag bits to be updated and thus cause the + * index to be updated on disk. + * + * However, the response may contain many paths (such as ignored + * paths) that will not update any flag bits. And thus not force the + * index to be updated. (This is fine and normal.) It also means + * that the token will not be updated in the FSMonitor index + * extension. So the next Git command will find the same token in the + * index, make the same token-relative request, and receive the same + * response (plus any newly changed paths). If this response is large + * (and continues to grow), performance could be impacted. + * + * For example, if the user runs a build and it writes 100K object + * files but doesn't modify any source files, the index would not need + * to be updated. The FSMonitor response (after the build and + * relative to a pre-build token) might be 5MB. Each subsequent Git + * command will receive that same 100K/5MB response until something + * causes the index to be updated. And `refresh_fsmonitor()` will + * have to iterate over those 100K paths each time. + * + * Performance could be improved if we optionally force update the + * index after a very large response and get an updated token into + * the FSMonitor index extension. This should allow subsequent + * commands to get smaller and more current responses. + * + * The value chosen here does not need to be precise. The index + * will be updated automatically the first time the user touches + * a tracked file and causes a command like `git status` to + * update an mtime to be updated and/or set a flag bit. + * + * NEEDSWORK: Does this need to be a config value? + */ +static int fsmonitor_force_update_threshold = 100; + void refresh_fsmonitor(struct index_state *istate) { struct repository *r = istate->repo ? istate->repo : the_repository; @@ -363,19 +402,28 @@ apply_results: * * This updates both the cache-entries and the untracked-cache. */ + int count = 0; + buf = query_result.buf; for (i = bol; i < query_result.len; i++) { if (buf[i] != '\0') continue; fsmonitor_refresh_callback(istate, buf + bol); bol = i + 1; + count++; } - if (bol < query_result.len) + if (bol < query_result.len) { fsmonitor_refresh_callback(istate, buf + bol); + count++; + } /* Now mark the untracked cache for fsmonitor usage */ if (istate->untracked) istate->untracked->use_fsmonitor = 1; + + if (count > fsmonitor_force_update_threshold) + istate->cache_changed |= FSMONITOR_CHANGED; + } else { /* * We received a trivial response, so invalidate everything. From ea6ec6d457bec0adf90fb76d174301368c27b11b Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Fri, 18 Dec 2020 12:31:37 -0500 Subject: [PATCH 25/30] t7527: create test for fsmonitor--daemon Signed-off-by: Jeff Hostetler --- t/t7527-builtin-fsmonitor.sh | 475 +++++++++++++++++++++++++++++++++++ 1 file changed, 475 insertions(+) create mode 100755 t/t7527-builtin-fsmonitor.sh diff --git a/t/t7527-builtin-fsmonitor.sh b/t/t7527-builtin-fsmonitor.sh new file mode 100755 index 0000000000..eaed44ebad --- /dev/null +++ b/t/t7527-builtin-fsmonitor.sh @@ -0,0 +1,475 @@ +#!/bin/sh + +test_description='built-in file system watcher' + +. ./test-lib.sh + +git version --build-options | grep "feature:" | grep "fsmonitor--daemon" || { + skip_all="The built-in FSMonitor is not supported on this platform" + test_done +} + +kill_repo () { + r=$1 + git -C $r fsmonitor--daemon stop >/dev/null 2>/dev/null + rm -rf $1 + return 0 +} + +start_daemon () { + case "$#" in + 1) r="-C $1";; + *) r=""; + esac + + git $r fsmonitor--daemon start || return $? + git $r fsmonitor--daemon status || return $? + + return 0 +} + +test_expect_success 'explicit daemon start and stop' ' + test_when_finished "kill_repo test_explicit" && + + git init test_explicit && + start_daemon test_explicit && + + git -C test_explicit fsmonitor--daemon stop && + test_must_fail git -C test_explicit fsmonitor--daemon status +' + +test_expect_success 'implicit daemon start' ' + test_when_finished "kill_repo test_implicit" && + + git init test_implicit && + test_must_fail git -C test_implicit fsmonitor--daemon status && + + # query will implicitly start the daemon. + # + # for test-script simplicity, we send a V1 timestamp rather than + # a V2 token. either way, the daemon response to any query contains + # a new V2 token. (the daemon may complain that we sent a V1 request, + # but this test case is only concerned with whether the daemon was + # implicitly started.) + + GIT_TRACE2_EVENT="$PWD/.git/trace" \ + test-tool -C test_implicit fsmonitor-client query --token 0 >actual && + nul_to_q actual.filtered && + grep "builtin:" actual.filtered && + + # confirm that a daemon was started in the background. + # + # since the mechanism for starting the background daemon is platform + # dependent, just confirm that the foreground command received a + # response from the daemon. + + grep :\"query/response-length\" .git/trace && + + git -C test_implicit fsmonitor--daemon status && + git -C test_implicit fsmonitor--daemon stop && + test_must_fail git -C test_implicit fsmonitor--daemon status +' + +test_expect_success 'implicit daemon stop (delete .git)' ' + test_when_finished "kill_repo test_implicit_1" && + + git init test_implicit_1 && + + start_daemon test_implicit_1 && + + # deleting the .git directory will implicitly stop the daemon. + rm -rf test_implicit_1/.git && + + # Create an empty .git directory so that the following Git command + # will stay relative to the `-C` directory. Without this, the Git + # command will (override the requested -C argument) and crawl out + # to the containing Git source tree. This would make the test + # result dependent upon whether we were using fsmonitor on our + # development worktree. + + sleep 1 && + mkdir test_implicit_1/.git && + + test_must_fail git -C test_implicit_1 fsmonitor--daemon status +' + +test_expect_success 'implicit daemon stop (rename .git)' ' + test_when_finished "kill_repo test_implicit_2" && + + git init test_implicit_2 && + + start_daemon test_implicit_2 && + + # renaming the .git directory will implicitly stop the daemon. + mv test_implicit_2/.git test_implicit_2/.xxx && + + # Create an empty .git directory so that the following Git command + # will stay relative to the `-C` directory. Without this, the Git + # command will (override the requested -C argument) and crawl out + # to the containing Git source tree. This would make the test + # result dependent upon whether we were using fsmonitor on our + # development worktree. + + sleep 1 && + mkdir test_implicit_2/.git && + + test_must_fail git -C test_implicit_2 fsmonitor--daemon status +' + +test_expect_success 'cannot start multiple daemons' ' + test_when_finished "kill_repo test_multiple" && + + git init test_multiple && + + start_daemon test_multiple && + + test_must_fail git -C test_multiple fsmonitor--daemon start 2>actual && + grep "fsmonitor--daemon is already running" actual && + + git -C test_multiple fsmonitor--daemon stop && + test_must_fail git -C test_multiple fsmonitor--daemon status +' + +test_expect_success 'setup' ' + >tracked && + >modified && + >delete && + >rename && + mkdir dir1 && + >dir1/tracked && + >dir1/modified && + >dir1/delete && + >dir1/rename && + mkdir dir2 && + >dir2/tracked && + >dir2/modified && + >dir2/delete && + >dir2/rename && + mkdir dirtorename && + >dirtorename/a && + >dirtorename/b && + + cat >.gitignore <<-\EOF && + .gitignore + expect* + actual* + EOF + + git -c core.useBuiltinFSMonitor= add . && + test_tick && + git -c core.useBuiltinFSMonitor= commit -m initial && + + git config core.useBuiltinFSMonitor true +' + +test_expect_success 'update-index implicitly starts daemon' ' + test_must_fail git fsmonitor--daemon status && + + GIT_TRACE2_EVENT="$PWD/.git/trace_implicit_1" \ + git update-index --fsmonitor && + + git fsmonitor--daemon status && + test_might_fail git fsmonitor--daemon stop && + + grep \"event\":\"start\".*\"fsmonitor--daemon\" .git/trace_implicit_1 +' + +test_expect_success 'status implicitly starts daemon' ' + test_must_fail git fsmonitor--daemon status && + + GIT_TRACE2_EVENT="$PWD/.git/trace_implicit_2" \ + git status >actual && + + git fsmonitor--daemon status && + test_might_fail git fsmonitor--daemon stop && + + grep \"event\":\"start\".*\"fsmonitor--daemon\" .git/trace_implicit_2 +' + +edit_files() { + echo 1 >modified + echo 2 >dir1/modified + echo 3 >dir2/modified + >dir1/untracked +} + +delete_files() { + rm -f delete + rm -f dir1/delete + rm -f dir2/delete +} + +create_files() { + echo 1 >new + echo 2 >dir1/new + echo 3 >dir2/new +} + +rename_files() { + mv rename renamed + mv dir1/rename dir1/renamed + mv dir2/rename dir2/renamed +} + +file_to_directory() { + rm -f delete + mkdir delete + echo 1 >delete/new +} + +directory_to_file() { + rm -rf dir1 + echo 1 >dir1 +} + +verify_status() { + git status >actual && + GIT_INDEX_FILE=.git/fresh-index git read-tree master && + GIT_INDEX_FILE=.git/fresh-index git -c core.useBuiltinFSMonitor= status >expect && + test_cmp expect actual && + echo HELLO AFTER && + cat .git/trace && + echo HELLO AFTER +} + +# The next few test cases confirm that our fsmonitor daemon sees each type +# of OS filesystem notification that we care about. At this layer we just +# ensure we are getting the OS notifications and do not try to confirm what +# is reported by `git status`. +# +# We run a simple query after modifying the filesystem just to introduce +# a bit of a delay so that the trace logging from the daemon has time to +# get flushed to disk. +# +# We `reset` and `clean` at the bottom of each test (and before stopping the +# daemon) because these commands might implicitly restart the daemon. + +clean_up_repo_and_stop_daemon () { + git reset --hard HEAD + git clean -fd + git fsmonitor--daemon stop + rm -f .git/trace +} + +test_expect_success 'edit some files' ' + test_when_finished "clean_up_repo_and_stop_daemon" && + + ( + GIT_TRACE_FSMONITOR="$PWD/.git/trace" && + export GIT_TRACE_FSMONITOR && + + start_daemon + ) && + + edit_files && + + test-tool fsmonitor-client query --token 0 >/dev/null 2>&1 && + + grep "^event: dir1/modified$" .git/trace && + grep "^event: dir2/modified$" .git/trace && + grep "^event: modified$" .git/trace && + grep "^event: dir1/untracked$" .git/trace +' + +test_expect_success 'create some files' ' + test_when_finished "clean_up_repo_and_stop_daemon" && + + ( + GIT_TRACE_FSMONITOR="$PWD/.git/trace" && + export GIT_TRACE_FSMONITOR && + + start_daemon + ) && + + create_files && + + test-tool fsmonitor-client query --token 0 >/dev/null 2>&1 && + + grep "^event: dir1/new$" .git/trace && + grep "^event: dir2/new$" .git/trace && + grep "^event: new$" .git/trace +' + +test_expect_success 'delete some files' ' + test_when_finished "clean_up_repo_and_stop_daemon" && + + ( + GIT_TRACE_FSMONITOR="$PWD/.git/trace" && + export GIT_TRACE_FSMONITOR && + + start_daemon + ) && + + delete_files && + + test-tool fsmonitor-client query --token 0 >/dev/null 2>&1 && + + grep "^event: dir1/delete$" .git/trace && + grep "^event: dir2/delete$" .git/trace && + grep "^event: delete$" .git/trace +' + +test_expect_success 'rename some files' ' + test_when_finished "clean_up_repo_and_stop_daemon" && + + ( + GIT_TRACE_FSMONITOR="$PWD/.git/trace" && + export GIT_TRACE_FSMONITOR && + + start_daemon + ) && + + rename_files && + + test-tool fsmonitor-client query --token 0 >/dev/null 2>&1 && + + grep "^event: dir1/rename$" .git/trace && + grep "^event: dir2/rename$" .git/trace && + grep "^event: rename$" .git/trace && + grep "^event: dir1/renamed$" .git/trace && + grep "^event: dir2/renamed$" .git/trace && + grep "^event: renamed$" .git/trace +' + +test_expect_success 'rename directory' ' + test_when_finished "clean_up_repo_and_stop_daemon" && + + ( + GIT_TRACE_FSMONITOR="$PWD/.git/trace" && + export GIT_TRACE_FSMONITOR && + + start_daemon + ) && + + mv dirtorename dirrenamed && + + test-tool fsmonitor-client query --token 0 >/dev/null 2>&1 && + + grep "^event: dirtorename/*$" .git/trace && + grep "^event: dirrenamed/*$" .git/trace +' + +test_expect_success 'file changes to directory' ' + test_when_finished "clean_up_repo_and_stop_daemon" && + + ( + GIT_TRACE_FSMONITOR="$PWD/.git/trace" && + export GIT_TRACE_FSMONITOR && + + start_daemon + ) && + + file_to_directory && + + test-tool fsmonitor-client query --token 0 >/dev/null 2>&1 && + + grep "^event: delete$" .git/trace && + grep "^event: delete/new$" .git/trace +' + +test_expect_success 'directory changes to a file' ' + test_when_finished "clean_up_repo_and_stop_daemon" && + + ( + GIT_TRACE_FSMONITOR="$PWD/.git/trace" && + export GIT_TRACE_FSMONITOR && + + start_daemon + ) && + + directory_to_file && + + test-tool fsmonitor-client query --token 0 >/dev/null 2>&1 && + + grep "^event: dir1$" .git/trace +' + +# The next few test cases exercise the token-resync code. When filesystem +# drops events (because of filesystem velocity or because the daemon isn't +# polling fast enough), we need to discard the cached data (relative to the +# current token) and start collecting events under a new token. +# +# the 'test-tool fsmonitor-client flush' command can be used to send a +# "flush" message to a running daemon and ask it to do a flush/resync. + +test_expect_success 'flush cached data' ' + test_when_finished "kill_repo test_flush" && + + git init test_flush && + + ( + GIT_TEST_FSMONITOR_TOKEN=true && + export GIT_TEST_FSMONITOR_TOKEN && + + GIT_TRACE_FSMONITOR="$PWD/.git/trace_daemon" && + export GIT_TRACE_FSMONITOR && + + start_daemon test_flush + ) && + + # The daemon should have an initial token with no events in _0 and + # then a few (probably platform-specific number of) events in _1. + # These should both have the same . + + test-tool -C test_flush fsmonitor-client query --token "builtin:test_00000001:0" >actual_0 && + nul_to_q actual_q0 && + + touch test_flush/file_1 && + touch test_flush/file_2 && + + test-tool -C test_flush fsmonitor-client query --token "builtin:test_00000001:0" >actual_1 && + nul_to_q actual_q1 && + + grep "file_1" actual_q1 && + + # Force a flush. This will change the , reset the , and + # flush the file data. Then create some events and ensure that the file + # again appears in the cache. It should have the new . + + test-tool -C test_flush fsmonitor-client flush >flush_0 && + nul_to_q flush_q0 && + grep "^builtin:test_00000002:0Q/Q$" flush_q0 && + + test-tool -C test_flush fsmonitor-client query --token "builtin:test_00000002:0" >actual_2 && + nul_to_q actual_q2 && + + grep "^builtin:test_00000002:0Q$" actual_q2 && + + touch test_flush/file_3 && + + test-tool -C test_flush fsmonitor-client query --token "builtin:test_00000002:0" >actual_3 && + nul_to_q actual_q3 && + + grep "file_3" actual_q3 +' + +# The next few test cases create repos where the .git directory is NOT +# inside the one of the working directory. That is, where .git is a file +# that points to a directory elsewhere. This happens for submodules and +# non-primary worktrees. + +test_expect_success 'setup worktree base' ' + git init wt-base && + echo 1 >wt-base/file1 && + git -C wt-base add file1 && + git -C wt-base commit -m "c1" +' + +test_expect_success 'worktree with .git file' ' + git -C wt-base worktree add ../wt-secondary && + + ( + GIT_TRACE2_PERF="$PWD/trace2_wt_secondary" && + export GIT_TRACE2_PERF && + + GIT_TRACE_FSMONITOR="$PWD/trace_wt_secondary" && + export GIT_TRACE_FSMONITOR && + + start_daemon wt-secondary + ) && + + git -C wt-secondary fsmonitor--daemon stop && + test_must_fail git -C wt-secondary fsmonitor--daemon status +' + +test_done From 2ec1d4de78c60ae6e520618e948f10eba35fbe10 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Fri, 15 Jan 2021 15:38:42 -0500 Subject: [PATCH 26/30] p7519: add fsmonitor--daemon Repeat all of the fsmonitor perf tests using `git fsmonitor--daemon` and the "Simple IPC" interface. Signed-off-by: Jeff Hostetler --- t/perf/p7519-fsmonitor.sh | 42 ++++++++++++++++++++++++++++++++++++--- 1 file changed, 39 insertions(+), 3 deletions(-) diff --git a/t/perf/p7519-fsmonitor.sh b/t/perf/p7519-fsmonitor.sh index 5eb5044a10..542ae61c99 100755 --- a/t/perf/p7519-fsmonitor.sh +++ b/t/perf/p7519-fsmonitor.sh @@ -24,7 +24,8 @@ test_description="Test core.fsmonitor" # GIT_PERF_7519_SPLIT_INDEX: used to configure core.splitIndex # GIT_PERF_7519_FSMONITOR: used to configure core.fsMonitor. May be an # absolute path to an integration. May be a space delimited list of -# absolute paths to integrations. +# absolute paths to integrations. (This hook or list of hooks does not +# include the built-in fsmonitor--daemon.) # # The big win for using fsmonitor is the elimination of the need to scan the # working directory looking for changed and untracked files. If the file @@ -135,10 +136,16 @@ test_expect_success "one time repo setup" ' setup_for_fsmonitor() { # set INTEGRATION_SCRIPT depending on the environment - if test -n "$INTEGRATION_PATH" + if test -n "$USE_FSMONITOR_DAEMON" then + git config core.useBuiltinFSMonitor true && + INTEGRATION_SCRIPT=false + elif test -n "$INTEGRATION_PATH" + then + git config core.useBuiltinFSMonitor false && INTEGRATION_SCRIPT="$INTEGRATION_PATH" else + git config core.useBuiltinFSMonitor false && # # Choose integration script based on existence of Watchman. # Fall back to an empty integration script. @@ -174,7 +181,10 @@ test_perf_w_drop_caches () { } test_fsmonitor_suite() { - if test -n "$INTEGRATION_SCRIPT"; then + if test -n "$USE_FSMONITOR_DAEMON" + then + DESC="builtin fsmonitor--daemon" + elif test -n "$INTEGRATION_SCRIPT"; then DESC="fsmonitor=$(basename $INTEGRATION_SCRIPT)" else DESC="fsmonitor=disabled" @@ -285,4 +295,30 @@ test_expect_success "setup without fsmonitor" ' test_fsmonitor_suite trace_stop +# +# Run a full set of perf tests using the built-in fsmonitor--daemon. +# It does not use the Hook API, so it has a different setup. +# Explicitly start the daemon here and before we start client commands +# so that we can later add custom tracing. +# + +test_lazy_prereq HAVE_FSMONITOR_DAEMON ' + git version --build-options | grep "feature:" | grep "fsmonitor--daemon" +' + +if test_have_prereq HAVE_FSMONITOR_DAEMON +then + USE_FSMONITOR_DAEMON=t + + trace_start fsmonitor--daemon--server + git fsmonitor--daemon start + + trace_start fsmonitor--daemon--client + test_expect_success "setup for fsmonitor--daemon" 'setup_for_fsmonitor' + test_fsmonitor_suite + + git fsmonitor--daemon stop + trace_stop +fi + test_done From 02515c9be4bc64221091b4da98ecfa5c3c601a58 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Mon, 1 Mar 2021 17:48:39 -0500 Subject: [PATCH 27/30] t7527: test status with untracked-cache and fsmonitor--daemon Create 2x2 test matrix with the untracked-cache and fsmonitor--daemon features and a series of edits and verify that status output is identical. Signed-off-by: Jeff Hostetler --- t/t7527-builtin-fsmonitor.sh | 97 ++++++++++++++++++++++++++++++++++++ 1 file changed, 97 insertions(+) diff --git a/t/t7527-builtin-fsmonitor.sh b/t/t7527-builtin-fsmonitor.sh index eaed44ebad..106adc2a7e 100755 --- a/t/t7527-builtin-fsmonitor.sh +++ b/t/t7527-builtin-fsmonitor.sh @@ -153,6 +153,8 @@ test_expect_success 'setup' ' .gitignore expect* actual* + flush* + trace* EOF git -c core.useBuiltinFSMonitor= add . && @@ -472,4 +474,99 @@ test_expect_success 'worktree with .git file' ' test_must_fail git -C wt-secondary fsmonitor--daemon status ' +# TODO Repeat one of the "edit" tests on wt-secondary and confirm that +# TODO we get the same events and behavior -- that is, that fsmonitor--daemon +# TODO correctly listens to events on both the working directory and to the +# TODO referenced GITDIR. + +test_expect_success 'cleanup worktrees' ' + kill_repo wt-secondary && + kill_repo wt-base +' + +# The next few tests perform arbitrary/contrived file operations and +# confirm that status is correct. That is, that the data (or lack of +# data) from fsmonitor doesn't cause incorrect results. And doesn't +# cause incorrect results when the untracked-cache is enabled. + +test_lazy_prereq UNTRACKED_CACHE ' + { git update-index --test-untracked-cache; ret=$?; } && + test $ret -ne 1 +' + +test_expect_success 'Matrix: setup for untracked-cache,fsmonitor matrix' ' + test_might_fail git config --unset core.useBuiltinFSMonitor && + git update-index --no-fsmonitor && + test_might_fail git fsmonitor--daemon stop +' + +matrix_clean_up_repo () { + git reset --hard HEAD + git clean -fd +} + +matrix_try () { + uc=$1 + fsm=$2 + fn=$3 + + test_expect_success "Matrix[uc:$uc][fsm:$fsm] $fn" ' + matrix_clean_up_repo && + $fn && + if test $uc = false -a $fsm = false + then + git status --porcelain=v1 >.git/expect.$fn + else + git status --porcelain=v1 >.git/actual.$fn + test_cmp .git/expect.$fn .git/actual.$fn + fi + ' + + return $? +} + +uc_values="false" +test_have_prereq UNTRACKED_CACHE && uc_values="false true" +for uc_val in $uc_values +do + if test $uc_val = false + then + test_expect_success "Matrix[uc:$uc_val] disable untracked cache" ' + git config core.untrackedcache false && + git update-index --no-untracked-cache + ' + else + test_expect_success "Matrix[uc:$uc_val] enable untracked cache" ' + git config core.untrackedcache true && + git update-index --untracked-cache + ' + fi + + fsm_values="false true" + for fsm_val in $fsm_values + do + if test $fsm_val = false + then + test_expect_success "Matrix[uc:$uc_val][fsm:$fsm_val] disable fsmonitor" ' + test_might_fail git config --unset core.useBuiltinFSMonitor && + git update-index --no-fsmonitor && + test_might_fail git fsmonitor--daemon stop 2>/dev/null + ' + else + test_expect_success "Matrix[uc:$uc_val][fsm:$fsm_val] enable fsmonitor" ' + git config core.useBuiltinFSMonitor true && + git fsmonitor--daemon start && + git update-index --fsmonitor + ' + fi + + matrix_try $uc_val $fsm_val edit_files + matrix_try $uc_val $fsm_val delete_files + matrix_try $uc_val $fsm_val create_files + matrix_try $uc_val $fsm_val rename_files + matrix_try $uc_val $fsm_val file_to_directory + matrix_try $uc_val $fsm_val directory_to_file + done +done + test_done From cabdf94b7deb6659c1bebdb10d96355391ced9a2 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Wed, 21 Apr 2021 09:03:24 -0400 Subject: [PATCH 28/30] t/perf: avoid copying builtin fsmonitor files into test repo Do not try to copy a fsmonitor--daemon socket from the current development directory into the test trash directory. When we run the perf suite without an explicit source repo set, we copy of the current $GIT_DIR into the test trash directory. Unix domain sockets cannot be copied in that manner, so the test setup fails. Additionally, omit any other fsmonitor--daemon temp files inside the $GIT_DIR directory. Signed-off-by: Jeff Hostetler --- t/perf/perf-lib.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/t/perf/perf-lib.sh b/t/perf/perf-lib.sh index 601d9f67dd..3b97e3fc0f 100644 --- a/t/perf/perf-lib.sh +++ b/t/perf/perf-lib.sh @@ -74,7 +74,7 @@ test_perf_copy_repo_contents () { for stuff in "$1"/* do case "$stuff" in - */objects|*/hooks|*/config|*/commondir|*/gitdir|*/worktrees) + */objects|*/hooks|*/config|*/commondir|*/gitdir|*/worktrees|*/fsmonitor--daemon*) ;; *) cp -R "$stuff" "$repo/.git/" || exit 1 From 7261cb98db2cdabd9e348af9ecf6c63a0ee4ee11 Mon Sep 17 00:00:00 2001 From: Johannes Schindelin Date: Fri, 5 Mar 2021 23:07:26 +0100 Subject: [PATCH 29/30] fsmonitor: mark the built-in FSMonitor as experimental Signed-off-by: Johannes Schindelin --- Documentation/config/core.txt | 4 ++-- Documentation/git-fsmonitor--daemon.txt | 5 ++++- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/Documentation/config/core.txt b/Documentation/config/core.txt index 4f6e519bc0..0210f330d7 100644 --- a/Documentation/config/core.txt +++ b/Documentation/config/core.txt @@ -71,7 +71,7 @@ git by avoiding unnecessary scanning of files that have not changed. + See the "fsmonitor-watchman" section of linkgit:githooks[5]. + -Note: The value of this config setting is ignored if the +Note: The value of this config setting is ignored if the (experimental) built-in file system monitor is enabled (see `core.useBuiltinFSMonitor`). core.fsmonitorHookVersion:: @@ -91,7 +91,7 @@ Note: The value of this config setting is ignored if the built-in file system monitor is enabled (see `core.useBuiltinFSMonitor`). core.useBuiltinFSMonitor:: - If set to true, enable the built-in file system monitor + (EXPERIMENTAL) If set to true, enable the built-in file system monitor daemon for this working directory (linkgit:git-fsmonitor--daemon[1]). + Like hook-based file system monitors, the built-in file system monitor diff --git a/Documentation/git-fsmonitor--daemon.txt b/Documentation/git-fsmonitor--daemon.txt index 154e7684da..cf1d4556a5 100644 --- a/Documentation/git-fsmonitor--daemon.txt +++ b/Documentation/git-fsmonitor--daemon.txt @@ -3,7 +3,7 @@ git-fsmonitor--daemon(1) NAME ---- -git-fsmonitor--daemon - A Built-in File System Monitor +git-fsmonitor--daemon - (EXPERIMENTAL) A Built-in File System Monitor SYNOPSIS -------- @@ -16,6 +16,9 @@ SYNOPSIS DESCRIPTION ----------- +NOTE! This command is still only an experiment, subject to change dramatically +(or even to be abandoned). + A daemon to watch the working directory for file and directory changes using platform-specific file system notification facilities. From 58fca5ee466bd2aa8175f32e6fb98a7d6d001d83 Mon Sep 17 00:00:00 2001 From: Johannes Schindelin Date: Fri, 5 Mar 2021 23:12:11 +0100 Subject: [PATCH 30/30] Enable the built-in FSMonitor as an experimental feature If `feature.experimental` and `feature.manyFiles` are set, we now start the built-in FSMonitor by default. Signed-off-by: Johannes Schindelin --- repo-settings.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/repo-settings.c b/repo-settings.c index bbcf71461b..237dbfe61d 100644 --- a/repo-settings.c +++ b/repo-settings.c @@ -2,12 +2,13 @@ #include "config.h" #include "repository.h" #include "midx.h" +#include "fsmonitor-ipc.h" #define UPDATE_DEFAULT_BOOL(s,v) do { if (s == -1) { s = v; } } while(0) void prepare_repo_settings(struct repository *r) { - int value; + int value, feature_many_files = 0; char *strval; if (r->settings.initialized) @@ -62,6 +63,7 @@ void prepare_repo_settings(struct repository *r) r->settings.use_builtin_fsmonitor = 1; if (!repo_config_get_bool(r, "feature.manyfiles", &value) && value) { + feature_many_files = 1; UPDATE_DEFAULT_BOOL(r->settings.index_version, 4); UPDATE_DEFAULT_BOOL(r->settings.core_untracked_cache, UNTRACKED_CACHE_WRITE); } @@ -70,8 +72,12 @@ void prepare_repo_settings(struct repository *r) r->settings.fetch_write_commit_graph = value; UPDATE_DEFAULT_BOOL(r->settings.fetch_write_commit_graph, 0); - if (!repo_config_get_bool(r, "feature.experimental", &value) && value) + if (!repo_config_get_bool(r, "feature.experimental", &value) && value) { UPDATE_DEFAULT_BOOL(r->settings.fetch_negotiation_algorithm, FETCH_NEGOTIATION_SKIPPING); + if (feature_many_files && fsmonitor_ipc__is_supported()) + UPDATE_DEFAULT_BOOL(r->settings.use_builtin_fsmonitor, + 1); + } /* Hack for test programs like test-dump-untracked-cache */ if (ignore_untracked_cache_config)