features/quota: Improvements to quota

Old implementation
* Client side implementation of quota
    - Not secure
    - Increased traffic in updating the ctx

New Implementation
* 2 stages of quota implementation is done: Soft and hard quota
    Upon reaching soft quota limit on the directory it logs/alerts in the quota
    daemon log (ie DEFAULT_LOG_DIR/quotad.log) and no more writes allowed after
    hard quota limit. After reaching the soft-limit the daemon alerts the
    user/admin repeatively for every 'alert-time', which is configurable.

* Quota is moved to server-side.

    There will be 2 quota xlators
    i. Quota Server
        It takes care of the enforcing the quota and maintains the context
        specific to the brick. Since this doesn't have the complete picture of
        the cluster, cluster wide usage is updated from the quota daemon. This
        updated context is saved and used for the enforcement.

        It updates its context by searching the QUOTA_UPDATE_KEY from the dict
        in the setxattr call, and is updated from nowhere else.

        The quota is always loaded in the server graph and is by passed if the
        feature is not enabled.

        Options specific to quota-server:
        server-quota    - Specifies whether the features is on/off. It is used
                          to by pass the quota if turned off.
        deem-statfs     - If set to on, it takes quota limits into
                          consideration while estimating fs size. (df command)

    ii. Quota Daemon
        This is the new xlator introduced with this patch. Its the
        *gluster client* process with no mount point, started upon enabling
        quota or restarting the volume. This is a single process for all the
        volumes in the cluster. Its volfile stored in
        GLUSTERD_DEFAULT_WORKI_DIR/quotad/quotad.vol.

        It queries for the sizes on all the bricks, aggregates the size and
        sends back the updated size, periodically. The timeout between
        successive updation is configurable and typically/by default more for
        below-soft-quota usage and less for above-soft-quota usage. It
        maintains the timeout inside the limit structure based on the usage;
        below soft limit and above soft limit.

        There will be thread running per volume which iterates through the list
        and decides whether the size to be queried in the current iteration
        based on its timeout. It takes the next iteration time taking the least
        of the timeouts in the list of entries.

        Maintains a separate inode table for each volume in the quotad. In the
        first iteration it builds the table for quota-dirs (dirs on which limit
        is set) and its components.

        Options specific to quotad:
        hard-timeout       - Timeout for updation of usage to the quota-server
                             when the usage is crosses the soft-limit.
        soft-timeout       - Timeout for the updation of usage to the
                             quota-server when the usage is below soft-limit.
        alert-time         - Frequency of logging after the usage reached
                             soft limit.
   Options common to both:
   default-soft-limit - This is used when individual paths are not
                        configured with soft-limit and default value of
                        this option is 90% of the hard-limit.
   limit-set          - String containing all the limits.

   Thus in the current implementation we'll have 2 quota xlators: one in server
   graph and one in trusted client (quota daemon) of which the sole
   purpose will be to aggregate the quota size xattrs from all the bricks and
   send the same to server quota xlator.

* Changes in glusterd and CLI

   A single volfile is created for all the volumes, similar to nfs volfile.
   All files related to quota client (volfile, pid etc) are stored in
   GLUSTERD_DEFAULT_WORK_DIR/quotad/.

   The new pattern of the quota limit stores in
   limit-set = <single-dir-limit>[,<single-dir-limit>]
   single-dir-limit = <abs-path>:<hard-limit>[:<soft-limit-in-percent>]

   It also introduces new options:
   volume quota <VOLNAME> {enable|disable|list [<path> ...]|remove <path>| default-soft-limit <percent>} |
   volume quota <VOLNAME> {limit-usage <path> <size> |soft-limit <path> <percent>} |
   volume quota <VOLNAME> {alert-time|soft-timeout|hard-timeout} {<time>}

Credit:
Raghavendra Bhat        <rabhat@redhat.com>
Varun Shastry           <vshastry@redhat.com>
Shishir Gowda           <sgowda@redhat.com>
Kruthika Dhananjay      <kdhananj@redhat.com>
Brian Foster            <bfoster@redhat.com>
Krishnan Parthasarathi  <kparthas@redhat.com>

Change-Id: I16ec5be0c2faaf42b14034b9ccaf17796adef082
BUG: 969461
Signed-off-by: Varun Shastry <vshastry@redhat.com>

1 files changed, 46 insertions, 10 deletions

diff --git a/xlators/features/quota/src/quota.h b/xlators/features/quota/src/quota.h
index 84ecbb30..de9f6f16 100644
--- a/xlators/features/quota/src/quota.h
+++ b/xlators/features/quota/src/quota.h
@@ -25,6 +25,14 @@
 #define CONTRIBUTION            "contri"
 #define VAL_LENGTH              8
 #define READDIR_BUF             4096
+#define QUOTA_UPDATE_USAGE_KEY  "quota-update-usage"
+
+#define WIND_IF_QUOTAOFF(is_quota_on, label)     \
+        if (!is_quota_on)                       \
+                goto label;
+
+#define DID_REACH_LIMIT(lim, prev_size, cur_size)               \
+        ((cur_size) >= (lim) && (prev_size) < (lim))
 
 #define QUOTA_SAFE_INCREMENT(lock, var)         \
         do {                                    \
@@ -46,7 +54,7 @@
                                  gf_quota_mt_##type);   \
                 if (!var) {                             \
                         gf_log ("", GF_LOG_ERROR,       \
-                                "out of memory :(");    \
+                                "out of memory");    \
                         ret = -1;                       \
                         goto label;                     \
                 }                                       \
@@ -96,6 +104,8 @@
                         goto label;                             \
         } while (0)
 
+
+
 struct quota_dentry {
         char            *name;
         uuid_t           par;
@@ -105,7 +115,8 @@ typedef struct quota_dentry quota_dentry_t;
 
 struct quota_inode_ctx {
         int64_t          size;
-        int64_t          limit;
+        int64_t          hard_lim;
+        int64_t          soft_lim;
         struct iatt      buf;
         struct list_head parents;
         struct timeval   tv;
@@ -125,27 +136,52 @@ struct quota_local {
         int32_t      op_ret;
         int32_t      op_errno;
         int64_t      size;
-        int64_t      limit;
+        int64_t      hard_lim;
+        int64_t      soft_lim;
         char         just_validated;
         inode_t     *inode;
         call_stub_t *stub;
 };
 typedef struct quota_local quota_local_t;
 
+
+struct qd_vols_conf {
+        char                    *name;
+        inode_table_t           *itable;
+        uint32_t                 log_timeout;
+        gf_boolean_t             threads_status;
+        double                   default_soft_lim;
+        gf_lock_t                lock;
+        loc_t                    root_loc;
+	uint32_t		soft_timeout;
+	uint32_t		hard_timeout;
+	struct list_head	limit_head;
+	call_frame_t		*frame;
+};
+typedef struct qd_vols_conf qd_vols_conf_t;
+
+
 struct quota_priv {
-        int64_t           timeout;
-        gf_boolean_t      consider_statfs;
-        struct list_head  limit_head;
-        gf_lock_t         lock;
+        int64_t                 timeout;
+        double                  default_soft_lim;
+        gf_boolean_t            is_quota_on;
+        gf_boolean_t            consider_statfs;
+        struct list_head        limit_head;
+        qd_vols_conf_t        **qd_vols_conf;
+        gf_lock_t               lock;
 };
 typedef struct quota_priv quota_priv_t;
 
+
 struct limits {
         struct list_head  limit_list;
         char             *path;
-        int64_t           value;
         uuid_t            gfid;
+        int64_t           prev_size;
+        struct timeval    prev_log_tv;
+        int64_t           hard_lim;
+        int64_t           soft_lim;
+	struct timeval	  expire;
+	uint32_t	  timeout;
 };
 typedef struct limits     limits_t;
-
-uint64_t cn = 1;