mirror of
https://github.com/git-for-windows/git.git
synced 2026-03-16 11:02:37 -05:00
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 <jeffhost@microsoft.com>
447 lines
13 KiB
C
447 lines
13 KiB
C
#include "cache.h"
|
|
#include "config.h"
|
|
#include "dir.h"
|
|
#include "ewah/ewok.h"
|
|
#include "fsmonitor.h"
|
|
#include "run-command.h"
|
|
#include "strbuf.h"
|
|
|
|
#define INDEX_EXTENSION_VERSION1 (1)
|
|
#define INDEX_EXTENSION_VERSION2 (2)
|
|
#define HOOK_INTERFACE_VERSION1 (1)
|
|
#define HOOK_INTERFACE_VERSION2 (2)
|
|
|
|
struct trace_key trace_fsmonitor = TRACE_KEY_INIT(FSMONITOR);
|
|
|
|
static void assert_index_minimum(struct index_state *istate, size_t pos)
|
|
{
|
|
if (pos > istate->cache_nr)
|
|
BUG("fsmonitor_dirty has more entries than the index (%"PRIuMAX" > %u)",
|
|
(uintmax_t)pos, istate->cache_nr);
|
|
}
|
|
|
|
static void fsmonitor_ewah_callback(size_t pos, void *is)
|
|
{
|
|
struct index_state *istate = (struct index_state *)is;
|
|
struct cache_entry *ce;
|
|
|
|
assert_index_minimum(istate, pos + 1);
|
|
|
|
ce = istate->cache[pos];
|
|
ce->ce_flags &= ~CE_FSMONITOR_VALID;
|
|
}
|
|
|
|
static int fsmonitor_hook_version(void)
|
|
{
|
|
int hook_version;
|
|
|
|
if (git_config_get_int("core.fsmonitorhookversion", &hook_version))
|
|
return -1;
|
|
|
|
if (hook_version == HOOK_INTERFACE_VERSION1 ||
|
|
hook_version == HOOK_INTERFACE_VERSION2)
|
|
return hook_version;
|
|
|
|
warning("Invalid hook version '%i' in core.fsmonitorhookversion. "
|
|
"Must be 1 or 2.", hook_version);
|
|
return -1;
|
|
}
|
|
|
|
int read_fsmonitor_extension(struct index_state *istate, const void *data,
|
|
unsigned long sz)
|
|
{
|
|
const char *index = data;
|
|
uint32_t hdr_version;
|
|
uint32_t ewah_size;
|
|
struct ewah_bitmap *fsmonitor_dirty;
|
|
int ret;
|
|
uint64_t timestamp;
|
|
struct strbuf last_update = STRBUF_INIT;
|
|
|
|
if (sz < sizeof(uint32_t) + 1 + sizeof(uint32_t))
|
|
return error("corrupt fsmonitor extension (too short)");
|
|
|
|
hdr_version = get_be32(index);
|
|
index += sizeof(uint32_t);
|
|
if (hdr_version == INDEX_EXTENSION_VERSION1) {
|
|
timestamp = get_be64(index);
|
|
strbuf_addf(&last_update, "%"PRIu64"", timestamp);
|
|
index += sizeof(uint64_t);
|
|
} else if (hdr_version == INDEX_EXTENSION_VERSION2) {
|
|
strbuf_addstr(&last_update, index);
|
|
index += last_update.len + 1;
|
|
} else {
|
|
return error("bad fsmonitor version %d", hdr_version);
|
|
}
|
|
|
|
istate->fsmonitor_last_update = strbuf_detach(&last_update, NULL);
|
|
|
|
ewah_size = get_be32(index);
|
|
index += sizeof(uint32_t);
|
|
|
|
fsmonitor_dirty = ewah_new();
|
|
ret = ewah_read_mmap(fsmonitor_dirty, index, ewah_size);
|
|
if (ret != ewah_size) {
|
|
ewah_free(fsmonitor_dirty);
|
|
return error("failed to parse ewah bitmap reading fsmonitor index extension");
|
|
}
|
|
istate->fsmonitor_dirty = fsmonitor_dirty;
|
|
|
|
if (!istate->split_index)
|
|
assert_index_minimum(istate, istate->fsmonitor_dirty->bit_size);
|
|
|
|
trace2_data_string("index", NULL, "extension/fsmn/read/token",
|
|
istate->fsmonitor_last_update);
|
|
trace_printf_key(&trace_fsmonitor,
|
|
"read fsmonitor extension successful '%s'",
|
|
istate->fsmonitor_last_update);
|
|
return 0;
|
|
}
|
|
|
|
void fill_fsmonitor_bitmap(struct index_state *istate)
|
|
{
|
|
unsigned int i, skipped = 0;
|
|
istate->fsmonitor_dirty = ewah_new();
|
|
for (i = 0; i < istate->cache_nr; i++) {
|
|
if (istate->cache[i]->ce_flags & CE_REMOVE)
|
|
skipped++;
|
|
else if (!(istate->cache[i]->ce_flags & CE_FSMONITOR_VALID))
|
|
ewah_set(istate->fsmonitor_dirty, i - skipped);
|
|
}
|
|
}
|
|
|
|
void write_fsmonitor_extension(struct strbuf *sb, struct index_state *istate)
|
|
{
|
|
uint32_t hdr_version;
|
|
uint32_t ewah_start;
|
|
uint32_t ewah_size = 0;
|
|
int fixup = 0;
|
|
|
|
if (!istate->split_index)
|
|
assert_index_minimum(istate, istate->fsmonitor_dirty->bit_size);
|
|
|
|
put_be32(&hdr_version, INDEX_EXTENSION_VERSION2);
|
|
strbuf_add(sb, &hdr_version, sizeof(uint32_t));
|
|
|
|
strbuf_addstr(sb, istate->fsmonitor_last_update);
|
|
strbuf_addch(sb, 0); /* Want to keep a NUL */
|
|
|
|
fixup = sb->len;
|
|
strbuf_add(sb, &ewah_size, sizeof(uint32_t)); /* we'll fix this up later */
|
|
|
|
ewah_start = sb->len;
|
|
ewah_serialize_strbuf(istate->fsmonitor_dirty, sb);
|
|
ewah_free(istate->fsmonitor_dirty);
|
|
istate->fsmonitor_dirty = NULL;
|
|
|
|
/* fix up size field */
|
|
put_be32(&ewah_size, sb->len - ewah_start);
|
|
memcpy(sb->buf + fixup, &ewah_size, sizeof(uint32_t));
|
|
|
|
trace2_data_string("index", NULL, "extension/fsmn/write/token",
|
|
istate->fsmonitor_last_update);
|
|
trace_printf_key(&trace_fsmonitor,
|
|
"write fsmonitor extension successful '%s'",
|
|
istate->fsmonitor_last_update);
|
|
}
|
|
|
|
/*
|
|
* Call the query-fsmonitor hook passing the last update token of the saved results.
|
|
*/
|
|
static int query_fsmonitor(int version, const char *last_update, struct strbuf *query_result)
|
|
{
|
|
struct child_process cp = CHILD_PROCESS_INIT;
|
|
int result;
|
|
|
|
if (!core_fsmonitor)
|
|
return -1;
|
|
|
|
strvec_push(&cp.args, core_fsmonitor);
|
|
strvec_pushf(&cp.args, "%d", version);
|
|
strvec_pushf(&cp.args, "%s", last_update);
|
|
cp.use_shell = 1;
|
|
cp.dir = get_git_work_tree();
|
|
|
|
trace2_region_enter("fsm_hook", "query", NULL);
|
|
|
|
result = capture_command(&cp, query_result, 1024);
|
|
|
|
if (result)
|
|
trace2_data_intmax("fsm_hook", NULL, "query/failed", result);
|
|
else {
|
|
trace2_data_intmax("fsm_hook", NULL, "query/response-length",
|
|
query_result->len);
|
|
|
|
if (fsmonitor_is_trivial_response(query_result))
|
|
trace2_data_intmax("fsm_hook", NULL,
|
|
"query/trivial-response", 1);
|
|
}
|
|
|
|
trace2_region_leave("fsm_hook", "query", NULL);
|
|
|
|
return result;
|
|
}
|
|
|
|
int fsmonitor_is_trivial_response(const struct strbuf *query_result)
|
|
{
|
|
static char trivial_response[3] = { '\0', '/', '\0' };
|
|
|
|
return query_result->len >= 3 &&
|
|
!memcmp(trivial_response,
|
|
&query_result->buf[query_result->len - 3], 3);
|
|
}
|
|
|
|
static void fsmonitor_refresh_callback(struct index_state *istate, char *name)
|
|
{
|
|
int i, len = strlen(name);
|
|
if (name[len - 1] == '/') {
|
|
|
|
/*
|
|
* TODO We should binary search to find the first path with
|
|
* TODO this directory prefix. Then linearly update entries
|
|
* TODO while the prefix matches. Taking care to search without
|
|
* TODO the trailing slash -- because '/' sorts after a few
|
|
* TODO interesting special chars, like '.' and ' '.
|
|
*/
|
|
|
|
/* Mark all entries for the folder invalid */
|
|
for (i = 0; i < istate->cache_nr; i++) {
|
|
if (istate->cache[i]->ce_flags & CE_FSMONITOR_VALID &&
|
|
starts_with(istate->cache[i]->name, name))
|
|
istate->cache[i]->ce_flags &= ~CE_FSMONITOR_VALID;
|
|
}
|
|
/* Need to remove the / from the path for the untracked cache */
|
|
name[len - 1] = '\0';
|
|
} else {
|
|
int pos = index_name_pos(istate, name, strlen(name));
|
|
|
|
if (pos >= 0) {
|
|
struct cache_entry *ce = istate->cache[pos];
|
|
ce->ce_flags &= ~CE_FSMONITOR_VALID;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Mark the untracked cache dirty even if it wasn't found in the index
|
|
* as it could be a new untracked file.
|
|
*/
|
|
trace_printf_key(&trace_fsmonitor, "fsmonitor_refresh_callback '%s'", name);
|
|
untracked_cache_invalidate_path(istate, name, 0);
|
|
}
|
|
|
|
void refresh_fsmonitor(struct index_state *istate)
|
|
{
|
|
struct strbuf query_result = STRBUF_INIT;
|
|
int query_success = 0, hook_version = -1;
|
|
size_t bol = 0; /* beginning of line */
|
|
uint64_t last_update;
|
|
struct strbuf last_update_token = STRBUF_INIT;
|
|
char *buf;
|
|
unsigned int i;
|
|
|
|
if (!core_fsmonitor || istate->fsmonitor_has_run_once)
|
|
return;
|
|
|
|
hook_version = fsmonitor_hook_version();
|
|
|
|
istate->fsmonitor_has_run_once = 1;
|
|
|
|
trace_printf_key(&trace_fsmonitor, "refresh fsmonitor");
|
|
/*
|
|
* This could be racy so save the date/time now and query_fsmonitor
|
|
* should be inclusive to ensure we don't miss potential changes.
|
|
*/
|
|
last_update = getnanotime();
|
|
if (hook_version == HOOK_INTERFACE_VERSION1)
|
|
strbuf_addf(&last_update_token, "%"PRIu64"", last_update);
|
|
|
|
/*
|
|
* If we have a last update token, call query_fsmonitor for the set of
|
|
* changes since that token, else assume everything is possibly dirty
|
|
* and check it all.
|
|
*/
|
|
if (istate->fsmonitor_last_update) {
|
|
if (hook_version == -1 || hook_version == HOOK_INTERFACE_VERSION2) {
|
|
query_success = !query_fsmonitor(HOOK_INTERFACE_VERSION2,
|
|
istate->fsmonitor_last_update, &query_result);
|
|
|
|
if (query_success) {
|
|
if (hook_version < 0)
|
|
hook_version = HOOK_INTERFACE_VERSION2;
|
|
|
|
/*
|
|
* First entry will be the last update token
|
|
* Need to use a char * variable because static
|
|
* analysis was suggesting to use strbuf_addbuf
|
|
* but we don't want to copy the entire strbuf
|
|
* only the chars up to the first NUL
|
|
*/
|
|
buf = query_result.buf;
|
|
strbuf_addstr(&last_update_token, buf);
|
|
if (!last_update_token.len) {
|
|
warning("Empty last update token.");
|
|
query_success = 0;
|
|
} else {
|
|
bol = last_update_token.len + 1;
|
|
}
|
|
} else if (hook_version < 0) {
|
|
hook_version = HOOK_INTERFACE_VERSION1;
|
|
if (!last_update_token.len)
|
|
strbuf_addf(&last_update_token, "%"PRIu64"", last_update);
|
|
}
|
|
}
|
|
|
|
if (hook_version == HOOK_INTERFACE_VERSION1) {
|
|
query_success = !query_fsmonitor(HOOK_INTERFACE_VERSION1,
|
|
istate->fsmonitor_last_update, &query_result);
|
|
}
|
|
|
|
trace_performance_since(last_update, "fsmonitor process '%s'", core_fsmonitor);
|
|
trace_printf_key(&trace_fsmonitor, "fsmonitor process '%s' returned %s",
|
|
core_fsmonitor, query_success ? "success" : "failure");
|
|
}
|
|
|
|
/* 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 */
|
|
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;
|
|
}
|
|
if (bol < query_result.len)
|
|
fsmonitor_refresh_callback(istate, buf + bol);
|
|
|
|
/* Now mark the untracked cache for fsmonitor usage */
|
|
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 */
|
|
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;
|
|
istate->cache[i]->ce_flags &= ~CE_FSMONITOR_VALID;
|
|
}
|
|
}
|
|
|
|
/* If we're going to check every file, ensure we save the results */
|
|
if (is_cache_changed)
|
|
istate->cache_changed |= FSMONITOR_CHANGED;
|
|
|
|
if (istate->untracked)
|
|
istate->untracked->use_fsmonitor = 0;
|
|
}
|
|
strbuf_release(&query_result);
|
|
|
|
/* Now that we've updated istate, save the last_update_token */
|
|
FREE_AND_NULL(istate->fsmonitor_last_update);
|
|
istate->fsmonitor_last_update = strbuf_detach(&last_update_token, NULL);
|
|
}
|
|
|
|
/*
|
|
* The caller wants to turn on FSMonitor. And when the caller writes
|
|
* the index to disk, a FSMonitor extension should be included. This
|
|
* requires that `istate->fsmonitor_last_update` not be NULL. But we
|
|
* have not actually talked to a FSMonitor process yet, so we don't
|
|
* have an initial value for this field.
|
|
*
|
|
* For a protocol V1 FSMonitor process, this field is a formatted
|
|
* "nanoseconds since epoch" field. However, for a protocol V2
|
|
* FSMonitor process, this field is an opaque token.
|
|
*
|
|
* Historically, `add_fsmonitor()` has initialized this field to the
|
|
* current time for protocol V1 processes. There are lots of race
|
|
* conditions here, but that code has shipped...
|
|
*
|
|
* The only true solution is to use a V2 FSMonitor and get a current
|
|
* or default token value (that it understands), but we cannot do that
|
|
* until we have actually talked to an instance of the FSMonitor process
|
|
* (but the protocol requires that we send a token first...).
|
|
*
|
|
* For simplicity, just initialize like we have a V1 process and require
|
|
* that V2 processes adapt.
|
|
*/
|
|
static void initialize_fsmonitor_last_update(struct index_state *istate)
|
|
{
|
|
struct strbuf last_update = STRBUF_INIT;
|
|
|
|
strbuf_addf(&last_update, "%"PRIu64"", getnanotime());
|
|
istate->fsmonitor_last_update = strbuf_detach(&last_update, NULL);
|
|
}
|
|
|
|
void add_fsmonitor(struct index_state *istate)
|
|
{
|
|
unsigned int i;
|
|
|
|
if (!istate->fsmonitor_last_update) {
|
|
trace_printf_key(&trace_fsmonitor, "add fsmonitor");
|
|
istate->cache_changed |= FSMONITOR_CHANGED;
|
|
initialize_fsmonitor_last_update(istate);
|
|
|
|
/* reset the fsmonitor state */
|
|
for (i = 0; i < istate->cache_nr; i++)
|
|
istate->cache[i]->ce_flags &= ~CE_FSMONITOR_VALID;
|
|
|
|
/* reset the untracked cache */
|
|
if (istate->untracked) {
|
|
add_untracked_cache(istate);
|
|
istate->untracked->use_fsmonitor = 1;
|
|
}
|
|
|
|
/* Update the fsmonitor state */
|
|
refresh_fsmonitor(istate);
|
|
}
|
|
}
|
|
|
|
void remove_fsmonitor(struct index_state *istate)
|
|
{
|
|
if (istate->fsmonitor_last_update) {
|
|
trace_printf_key(&trace_fsmonitor, "remove fsmonitor");
|
|
istate->cache_changed |= FSMONITOR_CHANGED;
|
|
FREE_AND_NULL(istate->fsmonitor_last_update);
|
|
}
|
|
}
|
|
|
|
void tweak_fsmonitor(struct index_state *istate)
|
|
{
|
|
unsigned int i;
|
|
int fsmonitor_enabled = git_config_get_fsmonitor();
|
|
|
|
if (istate->fsmonitor_dirty) {
|
|
if (fsmonitor_enabled) {
|
|
/* Mark all entries valid */
|
|
for (i = 0; i < istate->cache_nr; i++) {
|
|
istate->cache[i]->ce_flags |= CE_FSMONITOR_VALID;
|
|
}
|
|
|
|
/* Mark all previously saved entries as dirty */
|
|
assert_index_minimum(istate, istate->fsmonitor_dirty->bit_size);
|
|
ewah_each_bit(istate->fsmonitor_dirty, fsmonitor_ewah_callback, istate);
|
|
|
|
refresh_fsmonitor(istate);
|
|
}
|
|
|
|
ewah_free(istate->fsmonitor_dirty);
|
|
istate->fsmonitor_dirty = NULL;
|
|
}
|
|
|
|
switch (fsmonitor_enabled) {
|
|
case -1: /* keep: do nothing */
|
|
break;
|
|
case 0: /* false */
|
|
remove_fsmonitor(istate);
|
|
break;
|
|
case 1: /* true */
|
|
add_fsmonitor(istate);
|
|
break;
|
|
default: /* unknown value: do nothing */
|
|
break;
|
|
}
|
|
}
|