From a70231c78aaea436575d427a1386a64d1471b776 Mon Sep 17 00:00:00 2001 From: Pranith Kumar K Date: Fri, 27 Feb 2015 16:01:31 +0530 Subject: cluster/ec: Add self-heal-daemon command handlers This patch introduces the changes required in ec xlator to handle index/full heal. Index healer threads: Ec xlator start an index healer thread per local brick. This thread keeps waking up every minute to check if there are any files to be healed based on the indices kept in index directory. Whenever child_up event comes, then also this index healer thread wakes up and crawls the indices and triggers heal. When self-heal-daemon is disabled on this particular volume then the healer thread keeps waiting until it is enabled again to perform heals. Full healer threads: Ec xlator starts a full healer thread for the local subvolume provided by glusterd to perform full crawl on the directory hierarchy to perform heals. Once the crawl completes the thread exits if no more full heals are issued. Changed xl-op prefix GF_AFR_OP to GF_SHD_OP to make it more generic. Change-Id: Idf9b2735d779a6253717be064173dfde6f8f824b BUG: 1177601 Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.org/9787 Tested-by: Gluster Build System Reviewed-by: Ravishankar N Reviewed-by: Vijay Bellur --- xlators/cluster/afr/src/afr-self-heal-common.c | 4 ++-- xlators/cluster/afr/src/afr-self-heald.c | 20 ++++++++++---------- 2 files changed, 12 insertions(+), 12 deletions(-) (limited to 'xlators/cluster/afr/src') diff --git a/xlators/cluster/afr/src/afr-self-heal-common.c b/xlators/cluster/afr/src/afr-self-heal-common.c index 74d340bc808..fd450be0890 100644 --- a/xlators/cluster/afr/src/afr-self-heal-common.c +++ b/xlators/cluster/afr/src/afr-self-heal-common.c @@ -409,7 +409,7 @@ afr_mark_split_brain_source_sinks (call_frame_t *frame, xlator_t *this, xdata_rsp = local->xdata_rsp; switch (heal_op) { - case GF_AFR_OP_SBRAIN_HEAL_FROM_BIGGER_FILE: + case GF_SHD_OP_SBRAIN_HEAL_FROM_BIGGER_FILE: if (type == AFR_METADATA_TRANSACTION) { ret = dict_set_str (xdata_rsp, "sh-fail-msg", "Use source-brick option to" @@ -435,7 +435,7 @@ afr_mark_split_brain_source_sinks (call_frame_t *frame, xlator_t *this, sinks[source] = 0; healed_sinks[source] = 0; break; - case GF_AFR_OP_SBRAIN_HEAL_FROM_BRICK: + case GF_SHD_OP_SBRAIN_HEAL_FROM_BRICK: ret = dict_get_str (xdata_req, "child-name", &name); if (ret) goto out; diff --git a/xlators/cluster/afr/src/afr-self-heald.c b/xlators/cluster/afr/src/afr-self-heald.c index 707c12b7565..cb5bf6ce197 100644 --- a/xlators/cluster/afr/src/afr-self-heald.c +++ b/xlators/cluster/afr/src/afr-self-heald.c @@ -1006,7 +1006,7 @@ out: int afr_xl_op (xlator_t *this, dict_t *input, dict_t *output) { - gf_xl_afr_op_t op = GF_AFR_OP_INVALID; + gf_xl_afr_op_t op = GF_SHD_OP_INVALID; int ret = 0; int xl_id = 0; afr_private_t *priv = NULL; @@ -1034,7 +1034,7 @@ afr_xl_op (xlator_t *this, dict_t *input, dict_t *output) if (ret) goto out; switch (op) { - case GF_AFR_OP_HEAL_INDEX: + case GF_SHD_OP_HEAL_INDEX: op_ret = -1; for (i = 0; i < priv->child_count; i++) { @@ -1059,7 +1059,7 @@ afr_xl_op (xlator_t *this, dict_t *input, dict_t *output) } } break; - case GF_AFR_OP_HEAL_FULL: + case GF_SHD_OP_HEAL_FULL: op_ret = -1; for (i = 0; i < priv->child_count; i++) { @@ -1084,23 +1084,23 @@ afr_xl_op (xlator_t *this, dict_t *input, dict_t *output) } } break; - case GF_AFR_OP_INDEX_SUMMARY: + case GF_SHD_OP_INDEX_SUMMARY: for (i = 0; i < priv->child_count; i++) if (shd->index_healers[i].local) afr_shd_gather_index_entries (this, i, output); break; - case GF_AFR_OP_HEALED_FILES: - case GF_AFR_OP_HEAL_FAILED_FILES: + case GF_SHD_OP_HEALED_FILES: + case GF_SHD_OP_HEAL_FAILED_FILES: for (i = 0; i < priv->child_count; i++) { snprintf (key, sizeof (key), "%d-%d-status", xl_id, i); ret = dict_set_str (output, key, "Operation Not " "Supported"); } break; - case GF_AFR_OP_SPLIT_BRAIN_FILES: + case GF_SHD_OP_SPLIT_BRAIN_FILES: eh_dump (shd->split_brain, output, afr_add_shd_event); break; - case GF_AFR_OP_STATISTICS: + case GF_SHD_OP_STATISTICS: for (i = 0; i < priv->child_count; i++) { eh_dump (shd->statistics[i], output, afr_add_crawl_event); @@ -1110,8 +1110,8 @@ afr_xl_op (xlator_t *this, dict_t *input, dict_t *output) &shd->full_healers[i].crawl_event); } break; - case GF_AFR_OP_STATISTICS_HEAL_COUNT: - case GF_AFR_OP_STATISTICS_HEAL_COUNT_PER_REPLICA: + case GF_SHD_OP_STATISTICS_HEAL_COUNT: + case GF_SHD_OP_STATISTICS_HEAL_COUNT_PER_REPLICA: op_ret = -1; for (i = 0; i < priv->child_count; i++) { -- cgit