diff --git a/ChangeLog b/ChangeLog index 3c778c8643..30a776c29e 100644 --- a/ChangeLog +++ b/ChangeLog @@ -16,8 +16,10 @@ Changes in version 0.2.2.1-alpha - 2009-??-?? to make sure nothing writes beyond the end of an area. This might help debug some conceivable causes of bug 930. - Directories that are configured with the --enable-geoip-stats flag - now write their GeoIP stats to disk exactly every 24 hours. Also, - unresolved requests are listed with country code '??'. + now write their GeoIP stats to disk exactly every 24 hours. + Estimated shares of v2 and v3 requests are determined as averages, + not at the end of a measurement period. Also, unresolved requests + are listed with country code '??'. - Exit nodes can write statistics on the number of exit streams and transferred bytes per port to disk every 24 hours. To enable this, run configure with the --enable-exit-stats option, and set diff --git a/src/or/geoip.c b/src/or/geoip.c index 039cef3667..6cfc1392bb 100644 --- a/src/or/geoip.c +++ b/src/or/geoip.c @@ -306,6 +306,67 @@ HT_PROTOTYPE(clientmap, clientmap_entry_t, node, clientmap_entry_hash, HT_GENERATE(clientmap, clientmap_entry_t, node, clientmap_entry_hash, clientmap_entries_eq, 0.6, malloc, realloc, free); +/** How often do we update our estimate which share of v2 and v3 directory + * requests is sent to us? We could as well trigger updates of shares from + * network status updates, but that means adding a lot of calls into code + * that is independent from geoip stats (and keeping them up-to-date). We + * are perfectly fine with an approximation of 15-minute granularity. */ +#define REQUEST_SHARE_INTERVAL (15 * 60) + +/** When did we last determine which share of v2 and v3 directory requests + * is sent to us? */ +static time_t last_time_determined_shares = 0; + +/** Sum of products of v2 shares times the number of seconds for which we + * consider these shares as valid. */ +static double v2_share_times_seconds; + +/** Sum of products of v3 shares times the number of seconds for which we + * consider these shares as valid. */ +static double v3_share_times_seconds; + +/** Number of seconds we are determining v2 and v3 shares. */ +static int share_seconds; + +/** Try to determine which fraction of v2 and v3 directory requests aimed at + * caches will be sent to us at time now and store that value in + * order to take a mean value later on. */ +static void +geoip_determine_shares(time_t now) +{ + double v2_share = 0.0, v3_share = 0.0; + if (router_get_my_share_of_directory_requests(&v2_share, &v3_share) < 0) + return; + if (last_time_determined_shares) { + v2_share_times_seconds += v2_share * + ((double) (now - last_time_determined_shares)); + v3_share_times_seconds += v3_share * + ((double) (now - last_time_determined_shares)); + share_seconds += now - last_time_determined_shares; + } + last_time_determined_shares = now; +} + +/** Calculate which fraction of v2 and v3 directory requests aimed at caches + * have been sent to us since the last call of this function up to time + * now. Set *v2_share_out and *v3_share_out to the + * fractions of v2 and v3 protocol shares we expect to have seen. Reset + * counters afterwards. Return 0 on success, -1 on failure (e.g. when zero + * seconds have passed since the last call).*/ +static int +geoip_get_mean_shares(time_t now, double *v2_share_out, + double *v3_share_out) +{ + geoip_determine_shares(now); + if (!share_seconds) + return -1; + *v2_share_out = v2_share_times_seconds / ((double) share_seconds); + *v3_share_out = v3_share_times_seconds / ((double) share_seconds); + v2_share_times_seconds = v3_share_times_seconds = 0.0; + share_seconds = 0; + return 0; +} + /** Note that we've seen a client connect from the IP addr (host order) * at time now. Ignored by all but bridges and directories if * configured accordingly. */ @@ -391,6 +452,10 @@ geoip_note_client_seen(geoip_client_action_t action, else ++country->n_v2_ns_requests[REQUEST_HIST_LEN-1]; } + + /* Periodically determine share of requests that we should see */ + if (last_time_determined_shares + REQUEST_SHARE_INTERVAL < now) + geoip_determine_shares(now); } if (!client_history_starts) { @@ -646,7 +711,7 @@ dump_geoip_stats(void) since, data_v3 ? data_v3 : "", data_v2 ? data_v2 : "") < 0) goto done; - if (!router_get_my_share_of_directory_requests(&v2_share, &v3_share)) { + if (!geoip_get_mean_shares(now, &v2_share, &v3_share)) { if (fprintf(out, "v2-ns-share %0.2lf%%\n", v2_share*100) < 0) goto done; if (fprintf(out, "v3-ns-share %0.2lf%%\n", v3_share*100) < 0)