fix(ingress): retry a failed dns-01 issuance only after a new account

custom-domain/dstack-ingress/TESTING.md

@@ -313,7 +313,7 @@ operator's CNAME. Expect the reason quoted back, e.g. `issue allows
 Note also that the first pass on a fresh deployment necessarily runs before any
 CAA exists: the record names the ACME account, so the account has to exist
 first. `process_domain` issues, writes the CAA, and issues again only if the
-first attempt failed.
+first attempt failed and had to create the account.
 
 ## Traps
 

custom-domain/dstack-ingress/scripts/dns01.sh

@@ -267,7 +267,7 @@ set_caa_record() {
 }
 
 process_domain() {
-    local domain="$1" status
+    local domain="$1" status retry=false
 
     if [ -n "${DELEGATION_ZONE:-}" ]; then
         # Delegation: the operator created three CNAMEs once, before deploying.
@@ -303,20 +303,23 @@ process_domain() {
     fi
 
     # The CAA record names our ACME account, so the account has to exist first:
-    # try once, write CAA, try again. The first attempt is expected to fail when
-    # a CAA record from an earlier account is still in place. Retry only then:
-    # after a success (0) or "nothing to renew" (2) a second attempt would
-    # issue another certificate whenever renewal is due on every check.
+    # try once, write CAA, and try again if the first attempt failed while
+    # creating the account. That is the attempt a CAA record naming an earlier
+    # account refuses, and set_caa_record has just replaced it. Any other
+    # failure would only fail again, spending another of Let's Encrypt's five
+    # failed validations per hostname per hour on every pass.
+    if [ -n "${DELEGATION_ZONE:-}" ] || [ "$SET_CAA" = "true" ]; then
+        acme_account_file >/dev/null 2>&1 || retry=true
+    fi
     if issue_certificate "$domain"; then status=0; else status=$?; fi
 
     set_caa_record "$domain"
 
-    if [ "$status" -ne 0 ] && [ "$status" -ne 2 ]; then
-        echo "First certificate attempt failed for $domain, retrying after the CAA record is set"
+    # Never after a success (0) or "nothing to renew" (2): a second attempt
+    # would issue another certificate whenever renewal is due.
+    if [ "$retry" = true ] && [ "$status" -ne 0 ] && [ "$status" -ne 2 ]; then
+        echo "First certificate attempt failed for $domain, retrying now that the CAA record names the new account"
         if issue_certificate "$domain"; then status=0; else status=$?; fi
-        # The failed attempt may still have saved a certificate (e.g. killed by
-        # the timeout after writing it), so "nothing to renew" now is a change.
-        [ "$status" -ne 2 ] || status=0
     fi
     return "$status"
 }