scheduler: allow to configure userids for which the scheduler should

not scan the host table. This was previously hardcoded for
  Einstein@home to prevent some users with many (identical) hosts
  from flooding the DB with slow queries. Now add
  <dont_search_host_for_userid>userid</dont_search_host_for_userid>
  to the project config (in config.xml) for each such userid.

svn path=/trunk/boinc/; revision=25346

checkin_notes

@@ -2226,3 +2226,16 @@ Bernd  27 feb 2012
 
     sched/
         validator.cpp
+
+Bernd  27 feb 2012
+    - scheduler: allow to configure userids for which the scheduler should
+        not scan the host table. This was previously hardcoded for
+        Einstein@home to prevent some users with many (identical) hosts
+        from flooding the DB with slow queries. Now add
+        <dont_search_host_for_userid>userid</dont_search_host_for_userid>
+        to the project config (in config.xml) for each such userid.
+
+    sched/
+        sched_config.h
+        sched_config.cpp
+        handle_request.cpp

sched/handle_request.cpp

@@ -68,11 +68,11 @@ static bool find_host_by_other(DB_USER& user, HOST req_host, DB_HOST& host) {
     char buf[2048];
     char dn[512], ip[512], os[512], pm[512];
 
-#ifdef EINSTEIN_AT_HOME
-    // This is to prevent GRID hosts that manipulate their hostids from flooding E@H's DB with slow queries
-    if ((user.id == 282952) || (user.id == 243543))
+    // don't dig through hosts of these users
+    // prevents flooding the DB with slow queries from users with many hosts
+    for(unsigned int i=0; i < config.dont_search_host_for_userid.size(); i++)
+      if (user.id == config.dont_search_host_for_userid[i])
         return false;
-#endif
 
     // Only check if the fields are populated
     if (strlen(req_host.domain_name) && strlen(req_host.last_ip_addr) && strlen(req_host.os_name) && strlen(req_host.p_model)) {

sched/sched_config.cpp

@@ -199,6 +199,10 @@ int SCHED_CONFIG::parse(FILE* f) {
             }
             continue;
         }
+        if (xp.parse_int(tag, "dont_search_host_for_user", retval)) {
+            dont_search_host_for_userid.push_back(retval);
+            continue;
+        }
         if (xp.parse_int("daily_result_quota", daily_result_quota)) continue;
         if (xp.parse_double("default_disk_max_used_gb", default_disk_max_used_gb)) continue;
         if (xp.parse_double("default_disk_max_used_pct", default_disk_max_used_pct)) continue;

sched/sched_config.h

@@ -104,6 +104,7 @@ struct SCHED_CONFIG {
 
     vector<regex_t> *ban_cpu;
     vector<regex_t> *ban_os;
+    vector<int> dont_search_host_for_userid;
     int daily_result_quota;         // max results per day is this * mult
     double default_disk_max_used_gb;
     double default_disk_max_used_pct;