A Backpressure Algorithm for Sender-Side Track Switching in MOQ Transport

Introduction Sender-Side Track Switching (SSTS) lets a subscriber group several encodings of the same content into a switching set and hands the choice of which encoding to forward to the publisher, typically a relay. The publisher forwards one member of the set at a time and dynamically switches between members as path conditions change. Which member it picks is not fixed by SSTS: the SWITCHING_SET_ASSIGNMENT parameter names an algorithm, and each algorithm defines its own fields, its own publisher behavior, and its own subscriber behavior. The default algorithm defined in is an allocation algorithm. It starts from B_total, an estimate of the downstream bandwidth available to the subscriber's connection, divides it between switching sets by rank and weight, and selects, in each set, the highest member whose declared throughput threshold fits the share the set received. That design assumes two inputs the publisher may not have:

A bandwidth estimate with a usable timebase. The estimate is obtained from the transport stack, and what a transport stack can offer is a congestion controller's view of the recent past: a congestion window, a pacing rate, a smoothed round-trip time . On a connection that is not sending at capacity -- which is the normal state of a relay -- that view is bounded by what was sent, not by what could have been sent, so the estimate tends to confirm the tier already in use rather than reveal the next one up. Measuring the headroom, rather than inferring it, requires sending data, which is a separate mechanism .
Sensitivity to absolute threshold calibration. Comparing a transport rate estimate directly against subscriber-declared throughput thresholds requires both numbers to share a well-calibrated absolute scale. If a track's actual bitrate fluctuates above its declared threshold (e.g., during complex video scenes), an estimate-driven selector may continue forwarding a track that is already building a queue at the transport layer.

This document defines an algorithm that needs neither. Rather than asking the transport stack what rate the path might support, the publisher counts how many forwarding streams carrying the currently selected tier remain open and unconsumed. An accumulating stream depth is direct evidence of overrun on the connection. The cost of using evidence instead of inference is that the evidence arrives late. A bandwidth estimate can suggest that a higher tier would fit before anything is sent at that tier; backpressure can only report that the tier currently in use does not fit, after a group has already been delayed. The algorithm in this document is therefore conservative by construction: it starts at the lowest tier, climbs only on a streak of healthy groups, and drops on the first sign of a queue. An earlier version of this SSTS algorithm has been evaluated in .

Scope This document defines one SSTS algorithm designed for a single active switching set per connection. Concurrent adaptation across multiple active switching sets on the same connection is not supported by this specification; subscribers with multiple switching sets SHOULD assign at most one switching set to this algorithm and use an allocation algorithm (such as the default algorithm of ) for any others. This document does not change the SSTS extension itself: negotiation, the SWITCHING_SET_ASSIGNMENT parameter, the rules for forming and modifying switching sets, and the default algorithm defined in are unaffected.

Conventions and Definitions The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in BCP 14 when, and only when, they appear in all capitals, as shown here. This document uses the terms Track, Group, Object, Subgroup, publisher, subscriber and relay as defined in , and the terms switching set, member and algorithm as defined in . In addition:

Ladder:: The members of one switching set, ordered by ascending throughput threshold. Position 0 is the lowest-quality member.
Tier:: An integer index into the switching set's ladder, in the range 0 to i_max.
Nominal Tier Rate (R[i]):: The declared throughput threshold of the track at tier i of the ladder.
Forwarding stream:: A unidirectional QUIC stream the publisher has opened toward the subscriber to carry Objects of a Subgroup of a member of a switching set, and that has neither been closed nor reset. A stream still draining its last Object is open.
Replacement stream:: A forwarding stream opened during a retroactive supersede () to re-send an in-flight Group at a lower tier after canceling the higher-tier stream.
Active stream depth (d):: The number of currently open forwarding streams carrying the track selected at the current tier i, excluding replacement streams ().

Algorithm Overview For a switching set assigned to this algorithm, the publisher orders the member tracks into a ladder of tiers 0 to i_max by ascending throughput threshold and maintains a current tier index i, initialized to 0. The adaptation controller evaluates the active stream depth d across two execution paths:

Group boundary evaluations: When the publisher begins forwarding a new Group (a Group ID greater than the largest Group ID previously evaluated), it checks whether the transport path is clear: the active stream depth is within target (d <= D_target, where D_target is 1 by default), no replacement stream from a previous supersede is still in flight, and the next tier up (i + 1) has no open forwarding stream still draining ().
- During Fast Start (exploring = true), each clear Group boundary immediately advances the tier by one (i = i + 1) so the session can discover available capacity rapidly. Fast start ends permanently as soon as congestion is detected (d >= D_down, where D_down is 2 by default) or when i reaches i_max.
- During Steady-State Regulation (exploring = false), the publisher advances from tier i to i + 1 only after observing U(i) consecutive clear Group boundaries. U(i) scales dynamically with the fractional bitrate increase (R[i+1] - R[i]) / R[i] and the subscriber's probing risk tolerance rho, bounded by U_min and U_max. If d >= D_down at a Group boundary, the publisher immediately steps down one tier (i = max(i - 1, 0)) and, when Retroactive supersede is enabled, triggers a retroactive supersede.
Intra-group monitoring: Waiting for the next Group boundary to react to a sudden bandwidth drop can stall playback. Whenever an Object is forwarded within an ongoing Group during steady state, the publisher checks d. A single reading of d >= D_down is tolerated to allow brief handoff overlap between consecutive Groups, but if d >= D_down persists for M consecutive Object transmissions, the publisher immediately steps down one tier mid-Group and, when Retroactive supersede is enabled, triggers a retroactive supersede.

Whenever a downshift occurs (i < i_prev) and Retroactive supersede is enabled, Retroactive Supersede () clears queued higher-bitrate bytes from the path by resetting the newest overtaken in-flight stream with the MOQT Cancelled error code and re-sending that Group on a new stream using the newly selected lower-tier track, prepending cached Objects from the start of the Subgroup and inheriting the remaining client latency budget.

Negotiation and Assignment

Negotiation Support for this algorithm is advertised in the SSTS_ALGORITHMS Setup Option of by including the algorithm identifier allocated in . An endpoint that does not advertise the identifier MUST NOT be sent a SWITCHING_SET_ASSIGNMENT naming it; a publisher that receives one for an algorithm it did not advertise follows the error handling of .

SWITCHING_SET_ASSIGNMENT Fields This algorithm extends the base SWITCHING_SET_ASSIGNMENT parameter of with the fields of the default algorithm (, Section 6.1) followed by five adaptation parameters: The fields are interpreted as follows:

Throughput threshold: The nominal bitrate of this track in kbps. Unlike the default algorithm of , this value is never compared against an estimated connection bandwidth B_total. Instead, it is used for two relative calculations:
1. Ordering the members within the switching set's ladder (R[0] <= R[1] <= ... <= R[i_max]); and
2. Computing the relative step ratio (R[i+1] - R[i]) / R[i] in the dynamic upshift streak formula (). If two members of a switching set declare the same throughput threshold, the publisher MUST break the tie deterministically (for example, by order of assignment arrival) and keep the order stable while both members remain in the set.
Set throughput weight: Expressed as an integer N in the range 1 to 10 as defined in . Because this algorithm operates on a single switching set per connection and does not divide a bandwidth budget across sets, the publisher parses this field for wire compatibility with Section 6.1 and ignores its value.
Activate switching: As defined in . When 0, switching is paused for the set. When N, the publisher activates switching for the set once at least N tracks in the set have active subscriptions.
Set rank: Expressed as an 8-bit unsigned integer (0-255) as defined in . The publisher parses this field for wire compatibility with Section 6.1 and ignores its value.
Latency budget (B): The subscriber's reorder/jitter buffer budget in milliseconds. Any in-flight forwarding stream that remains open for longer than B milliseconds without completing is reset by the publisher (Group discarded). When retroactive supersede replaces an overtaken stream of age t_age, the replacement stream inherits a remaining deadline of T_resend = max(1, B - t_age) ms. Setting B = 0 designates a latency-insensitive profile where delivery timeout resets are disabled and the publisher performs lossless forwarding without drop deadlines.
Probing risk factor (rho_pct): The probing risk tolerance rho (0 < rho <= 1), encoded as an integer percentage rho_pct. A value of 0 selects the publisher default (25, corresponding to rho = 0.25), 1..100 are explicit percentages, and values greater than 100 MUST be clamped to 100. Larger values climb more aggressively across large bitrate jumps; smaller values require longer observation streaks.
Upshift min streak (U_min): The minimum number of consecutive uncongested Group boundaries required before stepping up one tier in steady state. When set to 0 (unset) or set below 2, the publisher clamps U_min to a minimum of 2 to ensure stability, with a default U_default = 2.
Upshift max streak (U_max): The upper bound on the number of consecutive uncongested Group boundaries required before stepping up one tier in steady state. When set to 0 (unset), the publisher leaves U_max unbounded (no upper cap is enforced). If U_max > 0 and U_max < U_min, the publisher MUST set U_max = U_min. A subscriber can enforce a static upshift interval of K Groups (bypassing rho) by setting U_min = U_max = K.
Retroactive supersede: Controls whether the publisher performs retroactive supersede () upon a downshift. When set to 1, a downshift cancels the newest overtaken in-flight stream and re-sends the affected Subgroup from its beginning at the newly selected lower tier. Unlike rho_pct, U_min, and U_max, a value of 0 does not select a default; when set to 0, retroactive supersede is disabled: in-flight Groups are not canceled and continue to completion on the track they started on, while the lowered tier i takes effect at the next new Group boundary. Any non-zero value is treated as 1.

When multiple subscriptions in the same switching set specify different values for any set-level field (Activate switching, Latency budget, Probing risk factor, Upshift min streak, Upshift max streak, or Retroactive supersede), the publisher MUST use the value from the most recently received message for that set.

Subscriber Behavior The subscriber follows the general rules of for establishing and modifying switching sets, adding or removing tracks, and pausing or resuming switching via Activate switching. A subscriber MUST NOT assign more than one active switching set per connection to this algorithm. If a subscriber uses multiple switching sets on the same connection, it SHOULD assign at most one switching set (typically video) to this algorithm and assign the remaining switching sets to an algorithm that allocates bandwidth across sets, such as the default algorithm of . In particular, constant-bitrate or low-bitrate media such as audio SHOULD be subscribed as ordinary MOQT tracks or assigned to another algorithm rather than occupying the single switching set governed by this algorithm. If a publisher nevertheless receives a SWITCHING_SET_ASSIGNMENT assigning an additional active switching set on the same connection to this algorithm, it SHOULD reject the assignment or leave the additional set inactive. When configuring the adaptation parameters in , it is RECOMMENDED that the subscriber leave Upshift min streak (U_min) and Upshift max streak (U_max) unset (0) and adjust upshift sensitivity solely using Probing risk factor (rho). A subscriber that requires a fixed upshift interval of K clear Groups (K >= 2) regardless of the relative bitrate step size MAY bypass rho by setting U_min = U_max = K. A subscriber whose media pipeline cannot discard partially buffered Groups and replace them with a re-sent Subgroup stream MUST set Retroactive supersede to 0 in SWITCHING_SET_ASSIGNMENT (). When Retroactive supersede is enabled (1), the publisher aborts the overtaken in-flight forwarding stream with a QUIC RESET_STREAM and opens a replacement stream for the same Group ID on the newly selected lower-tier track, starting from the beginning of the affected Subgroup. Upon receiving a RESET_STREAM carrying the MOQT Cancelled error code on a stream belonging to the switching set -- or upon receiving a new forwarding stream for the same Group ID on a different member track of the switching set -- the subscriber MUST discard any Objects already buffered from the canceled higher-tier stream that have not yet been passed to the decoder, and MUST instead buffer and decode the Objects arriving on the replacement stream from the beginning of the Subgroup so that inter-frame decoder state remains valid. For any Object position that has already been presented prior to the switch, the subscriber MUST decode the replacement Object without rendering it; it MUST NOT present the same Object position twice.

Publisher Behavior

Ladder Construction For the active switching set assigned to this algorithm, the publisher orders its member tracks into a ladder L = [m[0], m[1], ..., m[i_max]] sorted by ascending declared throughput threshold R[0] <= R[1] <= ... <= R[i_max]. Whenever a track is added to or removed from the switching set, the publisher recomputes the ladder and sets the current tier index i to the highest tier whose nominal rate R[i] does not exceed the nominal rate of the previously selected track (clamped to the range 0 to i_max).

Signals The publisher scopes its congestion signal strictly to the currently active tier i of the switching set controlled by this algorithm. For any tier j of the switching set, let ordinary_open_streams(j) be the number of currently open forwarding streams carrying track m[j] that were not opened as replacement streams by a retroactive supersede (). The counter is incremented when the publisher opens an ordinary forwarding stream for m[j] and decremented when that stream closes, is reset by the publisher, or is stopped by the subscriber (STOP_SENDING). Similarly, let open_replacement_streams be the number of currently open replacement streams for the switching set, incremented when a replacement stream is opened during a retroactive supersede and decremented when it closes, is reset, or is stopped. Streams belonging to tracks outside the switching set (such as an ordinary audio subscription) MUST NOT be counted in either counter. The active stream depth d evaluated by the state machine is: Isolating d to the active tier i and excluding replacement streams has two important properties:

No cooldown state required: When the publisher steps down from tier i_prev to a lower tier i, any streams still draining from i_prev (or older tiers) are not counted in d at tier i. The controller evaluates whether the new tier i is sustainable on its own merits without cascading downshifts from historical congestion.
No separate timeout counter required: Streams that expire due to the latency budget B are symptoms of queue accumulation that has already raised d to or above D_down. Filtering timeout events out of d avoids double-penalizing the tier after a downshift has already taken place.

Because d is scoped strictly to ordinary forwarding streams at the current tier i, d <= D_target alone does not guarantee that the pipeline is clear to step up to tier i + 1. The publisher therefore combines d <= D_target with two boolean climb guards when evaluating whether a Group boundary is clear:

Repair in flight (resent_in_flight): True when at least one replacement stream opened by a previous retroactive supersede () is still open for the switching set (open_replacement_streams > 0). Because replacement streams are excluded from d so a downshift cannot trigger a second downshift, an open replacement stream cannot be counted as a clear boundary either: until the repair finishes, the overtaken delivery has not resolved.
Target rung occupied (target_occupied): True when i < i_max and ordinary_open_streams(i + 1) > 0 (at least one ordinary forwarding stream is still open at the next tier up). An old stream draining at tier i + 1 is not congestion at tier i and MUST NOT trigger a downshift, but stepping up to tier i + 1 while that stream is still open would immediately combine the new Group's stream with the lingering one (d >= 2) and force an immediate downshift. At the top of the ladder (i = i_max), target_occupied is false.

A Group boundary is considered clear if and only if d <= D_target, resent_in_flight is false, and target_occupied is false. When d <= D_target but either guard is true, the boundary is neither clear nor congested: clear_streak and monitor_streak are reset to 0, and the current tier i and exploring state are held unchanged.

State Machine and Adaptation Logic In addition to the per-tier ordinary_open_streams(j) counters and the switching set's validated parameters (rho in (0, 1], U_min >= 2, U_max set to 0 or >= U_min, B, and retroactive_supersede from ), the publisher maintains the following state for the switching set: The internal threshold constants have the following default values: = D_down ; required to trigger a mid-group downshift ]]> The controller runs on two events: when the first Object of a new Group g is about to be forwarded (is_new_group is true when g_last == none or g > g_last), and when a subsequent Object of an active Group is about to be forwarded (is_new_group is false). 0) target_occupied = (i < i_max) and (ordinary_open_streams(i + 1) > 0) i_prev = i is_new_group = (g_last == none or g > g_last) if is_new_group: ; 1. Group boundary evaluation g_last = g is_clear = (d <= D_target) and (not resent_in_flight) and (not target_occupied) if is_clear: ; Clear: eligible to climb monitor_streak = 0 clear_streak = clear_streak + 1 if i < i_max: step_ratio = 1.0 if R[i] == 0 else (R[i + 1] - R[i]) / R[i] U_i = max( U_min, ceil( step_ratio / rho ) ) if U_max > 0: U_i = min( U_max, U_i ) else: U_i = 2 needed = 1 if exploring else U_i if clear_streak >= needed: i = min( i + 1, i_max ) clear_streak = 0 if exploring and i >= i_max: exploring = false else if d >= D_down: ; Congested: downshift clear_streak = 0 monitor_streak = 0 exploring = false i = max( i - 1, 0 ) else: ; Guarded (or D_target < d < D_down): clear_streak = 0 ; hold tier, reset streaks monitor_streak = 0 else: ; 2. Intra-group monitor if d >= D_down: monitor_streak = monitor_streak + 1 else: monitor_streak = 0 if (not exploring) and i > 0 and monitor_streak >= M: i = i - 1 monitor_streak = 0 clear_streak = 0 downshifted = (i < i_prev) if downshifted and retroactive_supersede == 1: ; 3. Retroactive supersede trigger_retroactive_supersede(i, i_prev) ; if s_last > i and cache exist, ; cancels s_last and opens a ; replacement stream at tier i ; with Subgroup Objects 0..N-1 if is_new_group: ; 4. Forward current Object open ordinary forwarding stream for Group g on track m[i] forward current Object on Group g's new stream else if a replacement stream is open for Group g: forward current Object on Group g's replacement stream else: forward current Object on Group g's existing stream ]]>

Fast Start (exploring = true) At the start of a session, exploring is true and i = 0. At each clear Group boundary (d <= D_target with both resent_in_flight and target_occupied false), the required streak is needed = 1, allowing the tier to climb by one rung per Group boundary without waiting for multi-Group observation windows. During fast start, the intra-group monitor is disarmed (not exploring is false) so that each newly probed tier is tested across at least one complete Group transmission. Fast start terminates permanently (exploring = false) as soon as d >= D_down is observed at a Group boundary or when i reaches i_max.

Steady-State Regulation (exploring = false) Once fast start ends, advancing from tier i to tier i + 1 requires U(i) consecutive clear Group boundaries (d <= D_target with both resent_in_flight and target_occupied false), where: When U_max is greater than 0, the computed value is reduced to U_max if it exceeds U_max. Here (R[i+1] - R[i]) / R[i] is the fractional increase in nominal bitrate required by the next ladder tier. A step that doubles the bitrate requires twice the observation window of a step that increases the bitrate by 50%. If R[i] = 0, the publisher treats the step ratio as 1.0. Conversely, if d >= D_down at any Group boundary, the publisher immediately steps down to max(i - 1, 0), resets clear_streak and monitor_streak to 0, and, when Retroactive supersede is enabled, initiates a retroactive supersede ().

Intra-Group Monitoring Waiting for the next Group boundary to adapt can leave a congested stream blocking the connection when path capacity drops mid-Group. During steady state (exploring = false), the publisher evaluates d prior to forwarding each Object within a Group. Because a brief overlap (d = 2) can occur naturally during the handoff between the last Object of Group g - 1 and the first Object of Group g, a single reading of d >= D_down is tolerated. If d >= D_down persists for M consecutive Object forwarding events while i > 0, the publisher immediately decrements i by 1, resets both streak counters, and, when Retroactive supersede is enabled, executes a retroactive supersede ().

Retroactive Supersede A purely forward-looking downshift that only takes effect on the next Group leaves the currently in-flight Group at the higher tier queued in the transport send buffer, prolonging congestion. To evacuate those queued bytes immediately, whenever a decision lowers the tier (i < i_prev) and Retroactive supersede is enabled (1, ), the publisher performs a retroactive supersede on the switching set:

Locate and cancel the overtaken stream: The publisher identifies the newest in-flight forwarding stream s_last for the switching set that is carrying a track from a tier higher than i and that still has unsent Objects or bytes remaining in the transport send buffer yet to be transmitted on the wire (a stream whose bytes have all left the send buffer and is merely awaiting acknowledgment or closure is left to finish). If no such stream s_last exists, or if the cached beginning of the affected Subgroup on track m[i] is unavailable, steps 2-4 are skipped. Otherwise, the publisher aborts s_last by sending a QUIC RESET_STREAM frame with the MOQT Cancelled error code.
Open a replacement stream at tier i: The publisher opens a new unidirectional QUIC stream for the same Group ID using the track newly selected at tier i, writes the Subgroup header, and prepends the affected Subgroup's initial Objects 0 to N - 1 of track m[i] from the relay's object cache (where N is the number of Objects already dispatched on s_last), followed by subsequent live Objects of that Subgroup as they arrive. If the relay has already received the remaining Objects of the Subgroup and no further live Objects will arrive, it replays those cached Objects as well.
Inherit the remaining latency budget: Let t_age be the elapsed time in milliseconds since s_last was originally opened. If the subscriber configured a non-zero latency budget B > 0 (), the publisher assigns the replacement stream a delivery timeout of T_resend = max(1, B - t_age). If B = 0, no delivery timeout deadline is applied to the replacement stream.
Mark as replacement and exclude from d: The replacement stream is marked as a re-sent stream: it increments open_replacement_streams while open (setting resent_in_flight) and MUST NOT be counted in ordinary_open_streams(j) for any tier j (), ensuring that replacing an overtaken Group does not artificially inflate d or target_occupied.

When Retroactive supersede is disabled (0), the publisher skips steps 1-4 above: any Group already in flight continues to be forwarded on the track selected when that Group started, and the newly lowered tier i is applied starting with the next new Group. Because the still-draining stream at the higher tier sets target_occupied (), the state machine is automatically prevented from stepping back up into that tier until the in-flight Group finishes draining.

Properties and Trade-Offs

Reactive Congestion Detection Because active stream depth measures unconsumed streams rather than estimating path capacity in advance, congestion is detected only after a Group has begun to overlap with the next Group (d >= D_down). Retroactive supersede () mitigates the latency penalty of late detection by aborting the stalled high-bitrate stream and replacing it with a lower-bitrate encoding within the remaining latency budget B, provided the relay holds the earlier Objects of that Group in its cache.

No Absolute Bitrate Floor The algorithm never falls below tier 0. If the path cannot sustain even the lowest-bitrate member (tier 0) of the ladder, streams at tier 0 will exceed the latency budget B and be reset on delivery timeout, while the publisher continues attempting to forward tier 0. Deciding to terminate a subscription entirely when tier 0 is unsustainable is a publisher policy decision outside the scope of this algorithm.

Single Switching Set Scope This algorithm adapts a single switching set per connection. Because backpressure is observed as open forwarding streams rather than an explicit bandwidth rate B_total, the signal reports whether the currently selected track fits the path, but does not produce a divisible bitrate figure that can be partitioned across multiple independent switching sets by rank and weight. Subscribers that require concurrent adaptation across multiple switching sets on the same connection SHOULD use an allocation algorithm such as the default algorithm of .

Implementation Status This section is to be removed before publishing as an RFC, per . An experimental implementation of the algorithm described in this document has been developed for the MOQtail relay . It covers , , , and for a single switching set, including cached object replay and the inherited re-send deadline. The prototype currently differs from this specification in two respects. First, rather than exposing a single algorithm identifier whose supersede behavior is toggled by the Retroactive supersede field in SWITCHING_SET_ASSIGNMENT (), it registers the supersede and non-supersede modes as two separate provisional algorithm identifiers from the private-use range pending the allocation requested in ; consequently, the Retroactive supersede field value is not yet acted on even though the wire codec parses the trailing extension fields. Second, it does not yet reject a second active switching set. An earlier version of this SSTS algorithm has been evaluated in , and the current prototype has also been evaluated against the MOQtail publisher and subscriber; interoperability with other SSTS implementations has not yet been tested.

Security Considerations This document defines an algorithm for an existing MOQT extension and inherits the security considerations of and , including the asymmetric resource exhaustion that switching set fan-out makes easier. The considerations below are those that differ from the default algorithm.

Inaccurate Throughput Thresholds Cannot Starve a Track In the default algorithm of , a track whose declared throughput threshold exceeds the publisher's bandwidth estimate B_total is never selected. Under the algorithm defined in this document, throughput thresholds are used only for ladder ordering and relative step size calculation (R[i+1] - R[i]) / R[i]. A miscalibrated absolute threshold cannot permanently prevent the algorithm from probing a higher tier once the transport queue is clear, and if the probed tier exceeds actual path capacity, stream depth d rises and forces a downshift regardless of what bitrate was declared.

Subscriber Manipulation of Flow Control or Parameters A subscriber that intentionally withholds QUIC flow control credit or stops reading from forwarding streams causes d to rise, forcing the publisher down to tier 0. Because tier state is isolated per connection, a slow subscriber only degrades its own quality and causes the publisher to send it fewer bytes. Conversely, a subscriber that signals an aggressive probing risk factor (rho_pct = 100, U_min = 2) can cause the publisher to probe upward more frequently, triggering more frequent retroactive supersedes. Each retroactive supersede cancels an existing stream and re-sends cached Objects at a lower bitrate. Publishers SHOULD bound the rate of retroactive supersedes (for example, at most one supersede per Group ID per switching set) so that repeated downshifts within a single Group do not cause excessive cache reads or stream churn.

Resource Cost of the Signals The state and stream counter the publisher keeps (, ) are bounded and freed with the connection. There are no process-wide tables keyed by subscriber identity, and no state that outlives a subscription, so a subscriber cannot cause unbounded memory growth at the publisher by repeatedly creating and destroying switching sets. Publishers SHOULD nevertheless bound the number of switching sets and members per connection, as recommended by .

IANA Considerations

SSTS Algorithm Registration IANA is requested to add the following entry to the "SSTS-Algorithms" registry established by :

Type	Name	Specification
TBD	Backpressure	This document