Re-distribute PG primaries over OSDs that come up after a short downtime

pull/5/head
Vitaliy Filippov 2021-03-14 01:26:06 +03:00
parent 9ac7e75178
commit 9f59381bea
1 changed files with 39 additions and 27 deletions

View File

@ -641,27 +641,48 @@ class Mon
return !has_online;
}
reset_rng()
{
this.seed = 0x5f020e43;
}
rng()
{
this.seed ^= this.seed << 13;
this.seed ^= this.seed >> 17;
this.seed ^= this.seed << 5;
return this.seed + 2147483648;
}
pick_primary(pool_id, osd_set, up_osds)
{
let alive_set;
if (this.state.config.pools[pool_id].scheme === 'replicated')
alive_set = osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
else
{
// Prefer data OSDs for EC because they can actually read something without an additional network hop
const pg_data_size = (this.state.config.pools[pool_id].pg_size||0) -
(this.state.config.pools[pool_id].parity_chunks||0);
alive_set = osd_set.slice(0, pg_data_size).filter(osd_num => osd_num && up_osds[osd_num]);
if (!alive_set.length)
alive_set = osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
}
if (!alive_set.length)
return 0;
return alive_set[this.rng() % alive_set.length];
}
save_new_pgs_txn(request, pool_id, up_osds, prev_pgs, new_pgs, pg_history)
{
const replicated = new_pgs.length && this.state.config.pools[pool_id].scheme === 'replicated';
const pg_minsize = new_pgs.length && this.state.config.pools[pool_id].pg_minsize;
const pg_items = {};
this.reset_rng();
new_pgs.map((osd_set, i) =>
{
osd_set = osd_set.map(osd_num => osd_num === LPOptimizer.NO_OSD ? 0 : osd_num);
let alive_set;
if (replicated)
alive_set = osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
else
{
// Prefer data OSDs for EC because they can actually read something without an additional network hop
alive_set = osd_set.slice(0, pg_minsize).filter(osd_num => osd_num && up_osds[osd_num]);
if (!alive_set.length)
alive_set = osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
}
pg_items[i+1] = {
osd_set,
primary: alive_set.length ? alive_set[Math.floor(Math.random()*alive_set.length)] : 0,
primary: this.pick_primary(pool_id, osd_set, up_osds),
};
if (prev_pgs[i] && prev_pgs[i].join(' ') != osd_set.join(' ') &&
prev_pgs[i].filter(osd_num => osd_num).length > 0)
@ -944,7 +965,7 @@ class Mon
}
else
{
// Nothing changed, but we still want to check for down OSDs
// Nothing changed, but we still want to recheck the distribution of primaries
let changed = false;
for (const pool_id in this.state.config.pools)
{
@ -954,22 +975,13 @@ class Mon
continue;
}
const replicated = pool_cfg.scheme === 'replicated';
for (const pg_num in ((this.state.config.pgs.items||{})[pool_id]||{})||{})
this.reset_rng();
for (let pg_num = 1; pg_num <= pool_cfg.pg_count; pg_num++)
{
const pg_cfg = this.state.config.pgs.items[pool_id][pg_num];
if (!Number(pg_cfg.primary) || !up_osds[pg_cfg.primary])
if (pg_cfg)
{
let alive_set;
if (replicated)
alive_set = pg_cfg.osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
else
{
// Prefer data OSDs for EC because they can actually read something without an additional network hop
alive_set = pg_cfg.osd_set.slice(0, pool_cfg.pg_minsize).filter(osd_num => osd_num && up_osds[osd_num]);
if (!alive_set.length)
alive_set = pg_cfg.osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
}
const new_primary = alive_set.length ? alive_set[Math.floor(Math.random()*alive_set.length)] : 0;
const new_primary = this.pick_primary(pool_id, pg_cfg.osd_set, up_osds);
if (pg_cfg.primary != new_primary)
{
console.log(