From 26b9f34ab32b66a6387dc5ab3c773d3d4cd86685 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Fri, 25 Mar 2022 18:03:12 +0000 Subject: [PATCH] fsmonitor: force update index after large responses Measure the time taken to apply the FSMonitor query result to the index and the untracked-cache. 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 Signed-off-by: Junio C Hamano --- fsmonitor.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 54 insertions(+), 1 deletion(-) diff --git a/fsmonitor.c b/fsmonitor.c index a38b5710eb..292a6742b4 100644 --- a/fsmonitor.c +++ b/fsmonitor.c @@ -219,6 +219,43 @@ 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. + */ +static int fsmonitor_force_update_threshold = 100; + void refresh_fsmonitor(struct index_state *istate) { struct strbuf query_result = STRBUF_INIT; @@ -362,25 +399,39 @@ apply_results: * information and that we should consider everything * invalid. We call this a trivial response. */ + trace2_region_enter("fsmonitor", "apply_results", istate->repo); + if (query_success && !is_trivial) { /* * Mark all pathnames returned by the monitor as dirty. * * 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; + + trace2_data_intmax("fsmonitor", istate->repo, "apply_count", + count); + } else { /* * We failed to get a response or received a trivial response, @@ -409,6 +460,8 @@ apply_results: if (istate->untracked) istate->untracked->use_fsmonitor = 0; } + trace2_region_leave("fsmonitor", "apply_results", istate->repo); + strbuf_release(&query_result); /* Now that we've updated istate, save the last_update_token */