commit 96f1e69f24ec5c056964b44cb8538004649c504d
parent 1d2c918dfdfc1356890775bc57358b3523830224
Author: Nick Mathewson <nickm@torproject.org>
Date: Tue, 9 Nov 2021 13:43:48 -0500
Implement proposal 275: don't put "published" times in md consensus
When a new consensus method is negotiated, these values will all get
replaced with "2038-01-01 00:00:00".
This change should be safe because:
* As of 0.2.9.11 / 0.3.0.7 / 0.3.1.1-alpha, Tor takes no action
about published_on times in the future.
* The only remaining parties relying on published_on values are (we
believe) relays running 0.3.5.x, which rely on the values in a NS
consensus to see whether their descriptors are out of date. But
this patch only changes microdesc consensuses.
* The latest Tor no longer looks at this field in consensuses.
Why make this change? In experiments, replacing these values with a
fixed value made the size of compressed consensus diffs much much
smaller. (Like, by over 50%!)
Implements proposal 275; Implements #40130.
Diffstat:
4 files changed, 35 insertions(+), 3 deletions(-)
diff --git a/changes/prop275 b/changes/prop275
@@ -0,0 +1,12 @@
+ o Minor features (directory authority):
+ - Add a new consensus method in which the "published" times on router
+ entries in a microdesc consensus are all set to a meaningless fixed
+ date. Doing this will make the download size for compressed microdesc
+ consensus diffs much smaller.
+ Part of ticket 40130; implements proposal 275.
+
+ o Minor features (network documents):
+ - Clients and relays no longer track the "published on" time declared
+ for relays in any consensus documents. When reporting this time on
+ the control port, they instead report a fixed date in the future.
+ Part of ticket 40130.
diff --git a/src/feature/dirauth/dirvote.c b/src/feature/dirauth/dirvote.c
@@ -2048,7 +2048,6 @@ networkstatus_compute_consensus(smartlist_t *votes,
memcpy(rs_out.descriptor_digest, rs->status.descriptor_digest,
DIGEST_LEN);
tor_addr_copy(&rs_out.ipv4_addr, &rs->status.ipv4_addr);
- time_t published_on = rs->published_on;
rs_out.ipv4_dirport = rs->status.ipv4_dirport;
rs_out.ipv4_orport = rs->status.ipv4_orport;
tor_addr_copy(&rs_out.ipv6_addr, &alt_orport.addr);
@@ -2056,6 +2055,21 @@ networkstatus_compute_consensus(smartlist_t *votes,
rs_out.has_bandwidth = 0;
rs_out.has_exitsummary = 0;
+ time_t published_on = rs->published_on;
+
+ /* Starting with this consensus method, we no longer include a
+ meaningful published_on time for microdescriptor consensuses. This
+ makes their diffs smaller and more compressible.
+
+ We need to keep including a meaningful published_on time for NS
+ consensuses, however, until 035 relays are all obsolete. (They use
+ it for a purpose similar to the current StaleDesc flag.)
+ */
+ if (consensus_method >= MIN_METHOD_TO_SUPPRESS_MD_PUBLISHED &&
+ flavor == FLAV_MICRODESC) {
+ published_on = -1;
+ }
+
if (chosen_name && !naming_conflict) {
strlcpy(rs_out.nickname, chosen_name, sizeof(rs_out.nickname));
} else {
diff --git a/src/feature/dirauth/dirvote.h b/src/feature/dirauth/dirvote.h
@@ -53,7 +53,7 @@
#define MIN_SUPPORTED_CONSENSUS_METHOD 28
/** The highest consensus method that we currently support. */
-#define MAX_SUPPORTED_CONSENSUS_METHOD 32
+#define MAX_SUPPORTED_CONSENSUS_METHOD 33
/**
* Lowest consensus method where microdescriptor lines are put in canonical
@@ -74,6 +74,12 @@
*/
#define MIN_METHOD_FOR_MIDDLEONLY 32
+/**
+ * Lowest consensus method for which we suppress the published time in
+ * microdescriptor consensuses.
+ */
+#define MIN_METHOD_TO_SUPPRESS_MD_PUBLISHED 33
+
/** Default bandwidth to clip unmeasured bandwidths to using method >=
* MIN_METHOD_TO_CLIP_UNMEASURED_BW. (This is not a consensus method; do not
* get confused with the above macros.) */
diff --git a/src/feature/nodelist/fmt_routerstatus.c b/src/feature/nodelist/fmt_routerstatus.c
@@ -58,7 +58,7 @@ routerstatus_format_entry(const routerstatus_t *rs, const char *version,
char digest64[BASE64_DIGEST_LEN+1];
smartlist_t *chunks = smartlist_new();
- if (declared_publish_time != -1) {
+ if (declared_publish_time >= 0) {
format_iso_time(published, declared_publish_time);
} else if (vrs) {
format_iso_time(published, vrs->published_on);
