thebestvibedev/tromcho.net
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix mark_partial_write for replicas (TODO: try to write an OSD unit test for it)

Browse Source
This commit is contained in:
Vitaliy Filippov
2026-05-18 01:17:56 +03:00
parent 4e2724b28f
commit 572b20fedc
5 changed files with 51 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/client/msgr_op.h
+1
View File
@@ -157,6 +157,7 @@ struct __attribute__((visibility("default"))) osd_op_t
timespec tv_begin = { 0 }, tv_end = { 0 };
uint64_t op_type = OSD_OP_IN;
uint64_t client_id = 0;
osd_num_t osd_num = 0;
osd_any_op_t req;
osd_any_reply_t reply;
blockstore_op_t *bs_op = NULL;
src/osd/osd.h
+1 -2
View File
@@ -352,8 +352,7 @@ class osd_t
std::function<int(pg_osd_set_t & new_set)> calc_set);
pg_osd_set_state_t *mark_object_corrupted(pg_t & pg, object_id oid, pg_osd_set_state_t *prev_object_state,
osd_rmw_stripe_t *stripes, bool ref);
pg_osd_set_state_t *mark_partial_write(pg_t & pg, object_id oid, pg_osd_set_state_t *prev_object_state,
osd_rmw_stripe_t *stripes, bool ref);
pg_osd_set_state_t *mark_partial_write(pg_t & pg, osd_op_t *cur_op);
void deref_object_state(pg_t & pg, pg_osd_set_state_t **object_state, bool deref);
bool remember_unstable_write(osd_op_t *cur_op, pg_t & pg, pg_osd_set_t & loc_set, int base_state);
void handle_primary_subop(osd_op_t *subop, osd_op_t *cur_op);
src/osd/osd_primary.cpp
+20 -11
View File
@@ -435,24 +435,33 @@ pg_osd_set_state_t *osd_t::mark_object_corrupted(pg_t & pg, object_id oid,
}
// Mark the object as partially updated (probably due to a ENOSPC)
pg_osd_set_state_t *osd_t::mark_partial_write(pg_t & pg, object_id oid, pg_osd_set_state_t *prev_object_state,
osd_rmw_stripe_t *stripes, bool ref)
pg_osd_set_state_t *osd_t::mark_partial_write(pg_t & pg, osd_op_t *cur_op)
{
return mark_object(pg, oid, prev_object_state, ref, [stripes](pg_osd_set_t & new_set)
osd_primary_op_data_t *op_data = cur_op->op_data;
return mark_object(pg, op_data->oid, op_data->object_state, true, [&](pg_osd_set_t & new_set)
{
// Mark object chunk(s) as outdated
int changes = 0;
for (auto chunk_it = new_set.begin(); chunk_it != new_set.end(); )
for (auto & chunk: new_set)
{
auto & chunk = *chunk_it;
if (stripes[chunk.role].osd_num == chunk.osd_num &&
stripes[chunk.role].read_error &&
chunk.loc_bad != LOC_OUTDATED)
if (chunk.loc_bad != LOC_OUTDATED)
{
changes++;
chunk.loc_bad = LOC_OUTDATED;
bool success = false;
for (int i = 0; i < op_data->n_subops; i++)
{
if (op_data->subops[i].osd_num == chunk.osd_num &&
op_data->subops[i].reply.hdr.retval == op_data->subops[i].req.sec_rw.len)
{
success = true;
break;
}
}
if (!success)
{
changes++;
chunk.loc_bad = LOC_OUTDATED;
}
}
chunk_it++;
}
return changes;
});
src/osd/osd_primary_subops.cpp
+23 -17
View File
@@ -276,6 +276,7 @@ void osd_t::submit_primary_subop(osd_op_t *cur_op, osd_op_t *subop,
bool osd_t::submit_to_osd(osd_op_t *subop, osd_num_t osd_num)
{
subop->osd_num = osd_num;
auto peer_it = msgr.osd_peers.find(osd_num);
if (peer_it != msgr.osd_peers.end())
{
@@ -489,8 +490,11 @@ void osd_t::handle_primary_subop(osd_op_t *subop, osd_op_t *cur_op)
}
if ((op_data->errors + op_data->done) >= op_data->n_subops)
{
delete[] op_data->subops;
op_data->subops = NULL;
if (!op_data->errors || !op_data->done || opcode != OSD_OP_SEC_WRITE && opcode != OSD_OP_SEC_WRITE_STABLE)
{
delete[] op_data->subops;
op_data->subops = NULL;
}
op_data->st++;
if (cur_op->req.hdr.opcode == OSD_OP_READ)
{
@@ -641,45 +645,47 @@ void osd_t::submit_primary_sync_subops(osd_op_t *cur_op)
osd_op_t *subops = new osd_op_t[n_osds];
op_data->subops = subops;
robin_hood::unordered_flat_map<uint64_t, osd_client_t*>::iterator peer_it;
int subop_idx = 0;
for (int i = 0; i < n_osds; i++)
{
osd_num_t sync_osd = op_data->dirty_osds[i];
osd_op_t *subop = &subops[subop_idx];
if (sync_osd == this->osd_num)
{
clock_gettime(CLOCK_REALTIME, &subops[i].tv_begin);
subops[i].op_type = (uint64_t)cur_op;
subops[i].bs_op = new blockstore_op_t({
clock_gettime(CLOCK_REALTIME, &subop->tv_begin);
subop->op_type = (uint64_t)cur_op;
subop->bs_op = new blockstore_op_t({
.opcode = BS_OP_SYNC,
.callback = [subop = &subops[i], this](blockstore_op_t *bs_subop)
.callback = [subop, this](blockstore_op_t *bs_subop)
{
handle_primary_bs_subop(subop);
},
});
bs->enqueue_op(subops[i].bs_op);
bs->enqueue_op(subop->bs_op);
subop_idx++;
}
else if ((peer_it = msgr.osd_peers.find(sync_osd)) != msgr.osd_peers.end())
{
subops[i].op_type = OSD_OP_OUT;
subops[i].client_id = peer_it->second->client_id;
subops[i].req = (osd_any_op_t){ .sec_sync = {
subop->op_type = OSD_OP_OUT;
subop->osd_num = sync_osd;
subop->client_id = peer_it->second->client_id;
subop->req = (osd_any_op_t){ .sec_sync = {
.header = {
.magic = SECONDARY_OSD_OP_MAGIC,
.opcode = OSD_OP_SEC_SYNC,
},
.flags = cur_op->client_id == SELF_CLIENT && cur_op->req.hdr.opcode != OSD_OP_SCRUB ? OSD_OP_RECOVERY_RELATED : 0,
} };
subops[i].callback = [cur_op, this](osd_op_t *subop)
subop->callback = [cur_op, this](osd_op_t *subop)
{
handle_primary_subop(subop, cur_op);
};
msgr.outbox_push(&subops[i]);
}
else
{
op_data->n_subops--;
msgr.outbox_push(subop);
subop_idx++;
}
}
if (op_data->n_subops <= 0)
op_data->n_subops = subop_idx;
if (subop_idx <= 0)
{
delete[] op_data->subops;
op_data->subops = NULL;
src/osd/osd_primary_write.cpp
+6 -1
View File
@@ -263,11 +263,16 @@ resume_12:
else
{
pg.ver_override.erase(op_data->oid);
mark_partial_write(pg, op_data->oid, op_data->object_state, op_data->stripes, true);
mark_partial_write(pg, cur_op);
pg_cancel_write_queue(pg, cur_op, op_data->oid, op_data->errcode);
return;
}
}
if (op_data->subops)
{
delete[] op_data->subops;
op_data->subops = NULL;
}
pg.ver_override.erase(op_data->oid);
deref_object_state(pg, &op_data->object_state, true);
pg_cancel_write_queue(pg, cur_op, op_data->oid, op_data->errcode);