OPTIM: halog: keep a fast path for the lines-count only
Using "halog -c" is still something quite common to perform on logs,
but unfortunately since the recent added controls, it was sensibly
slowed down due to the parsing of the accept date field.
Now we use a specific loop for the case where nothing is needed from
the input, and this sped up the line counting by 2.5x. A 2.4 GHz Xeon
now counts lines at a rate of 2 GB of logs per second.
diff --git a/contrib/halog/halog.c b/contrib/halog/halog.c
index df224b1..40852ae 100644
--- a/contrib/halog/halog.c
+++ b/contrib/halog/halog.c
@@ -631,6 +631,16 @@
else if (filter & FILT_COUNT_ONLY)
line_filter = NULL;
+ if (!line_filter &&
+ !(filter & (FILT_HTTP_ONLY|FILT_TIME_RESP|FILT_ERRORS_ONLY|FILT_HTTP_STATUS|FILT_QUEUE_ONLY|FILT_QUEUE_SRV_ONLY|FILT_TERM_CODE_NAME))) {
+ /* read the whole file at once first */
+ if (!filter_invert)
+ while (fgets2(stdin) != NULL)
+ lines_out++;
+
+ goto skip_filters;
+ }
+
while ((line = fgets2(stdin)) != NULL) {
linenum++;
time_field = NULL; accept_field = NULL;
@@ -788,7 +798,7 @@
lines_out++; /* we're just counting lines */
}
-
+ skip_filters:
/*****************************************************
* Here we've finished reading all input. Depending on the
* filters, we may still have some analysis to run on the